Add files using upload-large-folder tool

.gitattributes

@@ -19,6 +19,7 @@
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pickle filter=lfs diff=lfs merge=lfs -text
 *.pkl filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
@@ -28,8 +29,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mov filter=lfs diff=lfs merge=lfs -text

FL2VA/model_index.json

@@ -0,0 +1,42 @@
+{
+  "_class_name": "MiniMaxH3Pipeline",
+  "_diffusers_version": "0.32.2",
+  "text_encoder": [
+    "transformers",
+    "MiniMaxH3Qwen3VLHFEncoder"
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2TokenizerFast"
+  ],
+  "video_vae": [
+    "diffusers",
+    "MiniMaxH3VideoVAE"
+  ],
+  "audio_vae": [
+    "diffusers",
+    "MiniMaxH3AudioVAE"
+  ],
+  "scheduler": null,
+  "transformer": [
+    "diffusers",
+    "MiniMaxH3DiTModel"
+  ],
+  "processor": [
+    "transformers",
+    "Qwen3VLProcessor"
+  ],
+  "_minimax_h3": {
+    "schema_version": 1,
+    "partition": "fl2va",
+    "tasks": [
+      "t2va",
+      "fl2va"
+    ],
+    "task_aliases": {},
+    "sigma_shift_scales": {
+      "video": 12.0,
+      "audio": 3.0
+    }
+  }
+}

LICENSE

@@ -0,0 +1,84 @@
+MiniMax H3 COMMUNITY LICENSE AGREEMENT
+MiniMax H3 release date/License date: August 2, 2026.
+The scope of this License Agreement (this “Agreement”) is expressly limited to the “Applicable Territory” as defined below.
+By clicking to accept, or by using, reproducing, modifying, distributing, running, or displaying any portion or element of the MiniMax H3 Works (including through any Hosted Services) in any manner, you acknowledge and accept the terms of this Agreement, and this Agreement shall take immediate effect upon the occurrence of such act.
+I.  Definitions
+1. “Acceptable Use Policy” means the policy published by MiniMax in Exhibit A.
+2. “Agreement” means the terms and conditions set forth herein that govern the use, reproduction, distribution, modification, running, and display of the MiniMax H3 Works or any portion or element thereof.
+3. “Applicable Territory” means worldwide, excluding the Excluded Territories.
+4. “Documentation” means the specifications, manuals, and documentation concerning MiniMax H3 that are publicly released by MiniMax.
+5. “Excluded Territories” means the European Union, the United Kingdom, the Republic of Korea and the United States of America.  
+6. “MiniMax H3” means the video generation model, together with its software and algorithms, including trained model weights, parameters (including optimizer states), machine-learning model code, inference-supporting code, and other elements thereof made publicly available by Us, as released at https://huggingface.co/MiniMaxAI/MiniMax-H3.
+7. “MiniMax H3 Works” means (i) the Materials, (ii) the Model Derivatives, and (iii) all derivatives thereof.
+8. “Hosted Services” means hosted services provided via application programming interfaces (APIs), web access, or any other electronic or remote means.
+9. “Licensee,” “you,” or “your” means the natural or legal person exercising rights and/or using the MiniMax H3 Works for any purpose in any field of use under this Agreement.
+10. “Materials” means, collectively, MiniMax H3 and the Documentation (and any portion thereof), in each case as made available by MiniMax under this Agreement and proprietary to MiniMax.
+11. “Model Derivatives” means all of the following: (i) any modification of MiniMax H3 or any Model Derivative thereof; (ii) any work based on MiniMax H3 or any Model Derivative thereof; or (iii) any other machine learning model created by transferring the patterns of the weights, parameters, operational patterns, or Outputs of MiniMax H3 or any Model Derivative thereof to another model, such that the latter model exhibits behavior similar to MiniMax H3 or its Model Derivatives, including by distillation methods, methods using intermediate data representations, or methods based on training using synthetic-data Outputs generated by MiniMax H3 or its Model Derivatives. For the avoidance of doubt, Outputs are not deemed Model Derivatives.
+12. “Output” means any result of operating or otherwise using MiniMax H3 or any Model Derivatives (including through Hosted Services).
+13. “Third Party” means any natural or legal person that is not under common control with us or with you.
+14. “Including” means “including but not limited to.”
+15. “We,” “Us”  or  “MiniMax” means Nanonoble Pte. Ltd..
+II.  Grant of Rights
+Solely within the Applicable Territory, we grant you a non-exclusive, non-transferable, royalty-free, limited license to use, reproduce, distribute, create derivative works (including Model Derivatives), and modify the Materials in accordance with the terms of this Agreement and the Acceptable Use Policy, based on the intellectual property and other rights owned by MiniMax that are embodied in or used by the Materials. You shall not violate (or encourage or permit any person to violate) any term of this Agreement or the Acceptable Use Policy.
+We will continuously evaluate the applicable laws, regulations and compliance requirements for the Excluded Territories. In the meantime, should any person in such Excluded Territories be interested in deploying our models, you are welcome to contact us about obtaining a license, which will be granted based on robust controls and guardrails for purposes of complying with the laws, regulations and compliance requirements of the Excluded Territories.
+III.  Distribution and Redistribution
+Subject to and conditioned on your continuing compliance with this Agreement, including its territorial restrictions and the Acceptable Use Policy, and solely within the Applicable Territory, you may distribute or make available the MiniMax H3 Works to Third Parties within the Applicable Territory; provided, that all of the following conditions are met:
+1. You must provide a copy of this Agreement to all such Third Parties who receive the MiniMax H3 Works or use your products or services related thereto;
+2. You must cause any modified files to carry prominent notices stating that you have modified such files;
+3. You are encouraged to:
+  a. display a notice on any product or service developed using MiniMax H3 indicating that the product or service is “Powered by MiniMax H3”; 
+  b. add an AI-generation identifier to files produced using generative AI models including MiniMax H3; and
+  c. publish at least one technical blog post or a public statement describing your experience using MiniMax H3 Works;
+4. All distributions to Third Parties (other than through Hosted Services) must be accompanied by a “NOTICE” text file containing the following notice:
+  “MiniMax H3 is licensed under the MiniMax H3 Community License Agreement, Copyright © 2026 MiniMax. All Rights Reserved.”
+You may add your own copyright notices on your modifications; except as provided in this Section and in Section V, however, you may not impose additional or different terms and conditions on the use, reproduction, or distribution of your modifications or of any aggregate Model Derivatives, and your use, reproduction, modification, distribution, running, and display of the work must otherwise comply with the terms and conditions of this Agreement (including the provisions concerning the Applicable Territory). If you receive the MiniMax H3 Works from a Licensee as part of an integrated end-user product, the provisions of Section III of this Agreement do not apply to you, but Section V and Exhibit A remain applicable.
+IV.  Additional Commercial Terms
+1. You shall obtain a separate, prior written authorization from MiniMax by contacting api@minimax.io with the subject line “MiniMax H3 licensing - authorization request”, if your commercial products and services generate more than 20 million US dollars (or equivalent in other currencies) in yearly revenue.
+2. You shall prominently display “MiniMax H3”on the user interface of commercial product or service that uses MiniMax H3 or MiniMax H3 Works.
+V. Use Restrictions
+1. Your use of the MiniMax H3 Works must comply with applicable laws and regulations (including trade-compliance laws and regulations) and must comply with the Acceptable Use Policy for the MiniMax H3 Works, which is incorporated into this Agreement by reference. 
+2. Before providing access to the MiniMax H3 Works or any product, service, or Hosted Service incorporating them, you must bind each recipient or user to enforceable terms at least as protective as the use restrictions in this Section V and Exhibit A, and you must notify each recipient or user that those restrictions apply.
+3. You may not use the MiniMax H3 Works or any of their Outputs or results to improve any other artificial intelligence model (other than MiniMax H3 or its Model Derivatives).
+4. You may not use, reproduce, modify, distribute, or display the MiniMax H3 Works or any of their Outputs or results outside the Applicable Territory. Any such use outside the Applicable Territory is not authorized by this Agreement.
+5. If you provide or make available to any Third Party a product, service, or Hosted Service that permits the generation of Outputs using MiniMax H3 or any Model Derivative, you must, before making that product or service available and throughout its operation, implement, maintain, test, and periodically review reasonable and proportionate technical and organizational safeguards designed to prevent and mitigate access, uses, and Outputs that violate this Section V or Exhibit A, including uses or Outputs that infringe, misappropriate, or otherwise violate any Third Party’s intellectual-property or other rights. You must not knowingly disable, materially weaken, or permit the circumvention of those safeguards. You must maintain a reasonably accessible mechanism for reporting suspected violations. Upon receiving a good-faith report or otherwise obtaining actual knowledge of a violation, you must promptly investigate and take reasonable steps within your control to stop or mitigate the violation, including removing or disabling access to offending content or services and suspending or terminating repeat violators where appropriate. You are responsible for implementing and enforcing these requirements with respect to your products, services, systems, users, and downstream recipients.
+VI.  Intellectual Property
+1. Subject to MiniMax’s rights in the MiniMax H3 Works (and the intellectual property therein), and to your compliance with the terms and conditions of this Agreement, as between you and MiniMax, you will own the derivative works and modifications of the Materials that you have created or had created, as well as any Model Derivatives.
+2. Except for the limited license expressly granted in this paragraph, no trademark license is granted under this Agreement; with respect to MiniMax H3 Works, the Licensee may not use any name or mark owned by or associated with MiniMax or any of its affiliates, except as reasonably and customarily necessary to describe and distribute the MiniMax H3 Works. MiniMax hereby grants you a license to use the “MiniMax H3” mark (the “Mark”) within the Applicable Territory solely for the purpose of complying with Section III.3; provided, that you comply with all applicable trademark-protection laws. All goodwill arising from your use of the Mark shall inure to the benefit of MiniMax.
+3. If you bring or assert any suit or other legal proceeding (including a cross-claim or counterclaim in any action) against us or any other natural or legal person alleging that the Materials, any Output, or any portion of the foregoing infringes any intellectual property right or other right owned by you or for which you can obtain a license, all licenses granted to you under this Agreement will terminate as of the date such suit or proceeding is filed. You shall defend, indemnify, and hold us harmless against any Third-Party claim arising out of or related to the use or distribution of the MiniMax H3 Works by you or by any Third Party.
+4. MiniMax claims no rights over the Outputs you generate. You and your users are entirely responsible for the Outputs and any subsequent use thereof.
+VII.  Disclaimers and Limitations of Liability
+1. We have no obligation to support, update, provide training for, or develop any further version of the MiniMax H3 Works, or to grant any license with respect thereto.
+2. UNLESS AND ONLY TO THE EXTENT REQUIRED BY APPLICABLE LAW, THE MINIMAX H3 WORKS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED “AS IS” WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES OF ANY KIND INCLUDING ANY WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, COURSE OF DEALING, USAGE OF TRADE, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING, REPRODUCING, MODIFYING, PERFORMING, DISPLAYING OR DISTRIBUTING ANY OF THE MINIMAX H3 WORKS OR OUTPUTS AND ASSUME ANY AND ALL RISKS ASSOCIATED WITH YOUR OR A THIRD PARTY’S USE OR DISTRIBUTION OF ANY OF THE MINIMAX H3 WORKS OR OUTPUTS AND YOUR EXERCISE OF RIGHTS AND PERMISSIONS UNDER THIS AGREEMENT.
+3. TO THE FULLEST EXTENT PERMITTED BY APPLICABLE LAW, IN NO EVENT SHALL MINIMAX OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, FOR ANY DAMAGES, INCLUDING ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, EXEMPLARY, CONSEQUENTIAL OR PUNITIVE DAMAGES, OR LOST PROFITS OF ANY KIND ARISING FROM THIS AGREEMENT OR RELATED TO ANY OF THE MINIMAX H3 WORKS OR OUTPUTS, EVEN IF MINIMAX OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+VIII.  Term and Termination
+1. This Agreement is effective from the moment you accept this Agreement or begin accessing the Materials, and, subject to your compliance with its terms and conditions, will remain in effect until terminated as provided herein.
+2. If you breach any term or condition of this Agreement, we have the right to terminate this Agreement. Upon termination, you must immediately cease accessing, using, and distributing the MiniMax H3 Works; delete or destroy all copies within your possession or control; and notify each downstream recipient that your authorization has ended. The obligations in the preceding sentence and Sections VI.1, VI.3, VII, and IX survive termination.
+IX.  Governing Law and Jurisdiction
+1. This Agreement, and any dispute arising out of or related to this Agreement, shall be governed by the laws of the Hong Kong Special Administrative Region of the People’s Republic of China, without regard to its conflict-of-laws rules. The United Nations Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
+2. Any dispute arising out of or related to this Agreement shall be subject to the exclusive jurisdiction of the courts of the Hong Kong Special Administrative Region of the People’s Republic of China with competent jurisdiction. Both MiniMax and the Licensee hereby consent to the exclusive jurisdiction of such courts for any such dispute.
+Additional Note: Please note that the encoder of MiniMax H3 uses Qwen3-VL-32B, which is licensed under Apache 2.0 License: https://github.com/QwenLM/Qwen3-VL/blob/main/LICENSE.
+
+Exhibit A — Acceptable Use Policy
+MiniMax reserves the right to update this Acceptable Use Policy from time to time. 
+Last revised: August 2, 2026.
+MiniMax is committed to promoting the safe and fair use of its tools and features, including MiniMax H3. You agree not to use MiniMax H3, any Model Derivatives, or any Output in any of the following ways:
+1. Use outside the Applicable Territory;
+2. Use in any manner that violates any applicable national, federal, state, local, or international law, regulation, or other legal requirement, or that infringes, misappropriates, or otherwise violates any Third Party’s intellectual-property or other proprietary rights, including through unauthorized reproduction, distribution, public display, public performance, or creation of derivative works;
+3. Use in any manner that may harm yourself or others;
+4. Use to repurpose or distribute the Outputs of MiniMax H3 or any Model Derivatives in order to harm yourself or others;
+5. Use to circumvent or bypass any safety guardrails or safeguards we have implemented;
+6. Use in any manner that exploits or harms, or intends to exploit or harm, minors;
+7. Use to generate or disseminate verifiably false information and/or content for the purpose of harming others or influencing elections;
+8. Use to manufacture or facilitate false online engagement, including fake reviews and other means of false online engagement;
+9. Use to intentionally defame, disparage, or otherwise harass others;
+10. Use to generate and/or disseminate malware (including ransomware) or any other content intended to damage electronic systems;
+11. Use to generate or disseminate personally identifiable information for the purpose of harming others;
+12. Use to generate or disseminate information (including images, code, posts, or articles) in or to any public environment (including via bot tweets or similar means) without clearly and prominently disclosing that such information and/or content is machine-generated;
+13. Use to impersonate another person without that person’s consent, authorization, or lawful right to do so;
+14. Use to make high-risk automated decisions in critical domains that affect individual safety, rights, or well-being (such as law enforcement, immigration, healthcare or medical services, critical-infrastructure management, product-safety components, essential services, credit, employment, housing, education, social scoring, or insurance);
+15. Use in any manner that violates or disregards the social, ethical, or moral standards of other countries or regions;
+16. Use to carry out, assist, threaten, incite, plan, advocate for, or encourage violent extremism or terrorism;
+17. Use for any purpose intended to discriminate against, or harm, individuals or groups based on protected characteristics or categories, online or offline social behavior, or known or predicted personality traits;
+18. Use to intentionally exploit the vulnerabilities of specific populations based on age, social, physical, or psychological characteristics, so as to materially distort the behavior of a member of that group in a manner that causes, or is likely to cause, physical or psychological harm to that person or to others;
+19. Use for military purposes;
+20. Use to engage in any unauthorized or unlicensed professional activity, including but not limited to financial, legal, medical or healthcare, or other professional practice.

README.md

@@ -0,0 +1,420 @@
+---
+pipeline_tag: image-text-to-video
+license: other
+license_name: minimax-h3-community-license-agreement
+license_link: LICENSE
+library_name: diffusers
+tags:
+  - text-to-video
+  - image-to-video
+  - image-text-to-video
+  - video-to-video
+  - text-to-audio-video
+  - image-to-audio-video
+  - image-text-to-audio-video
+  - video-to-audio-video
+  - audio-to-audio-video
+  - audio-video-generation
+  - multimodal
+  - synchronized-audio-video
+  - reference-to-audio-video
+---
+
+<div align="center">
+  <img width="100%" src="assets/minimax-h3.png" alt="MiniMax">
+</div>
+
+<p align="center">
+  <a href="https://hailuoai.video" target="_blank"><img src="https://img.shields.io/badge/Hailuo%20AI-FF6C37?logo=minimax&logoColor=white" alt="Hailuo AI"></a>
+  <a href="https://platform.minimax.io/docs/guides/text-generation" target="_blank"><img src="https://img.shields.io/badge/API-FF6C37?logo=minimax&logoColor=white" alt="API"></a>
+  <a href="https://www.minimax.io" target="_blank"><img src="https://img.shields.io/badge/MiniMax%20Website-FF6C37?logo=minimax&logoColor=white" alt="MiniMax Website"></a>
+  <a href="https://github.com/MiniMax-AI/MiniMax-H3" target="_blank"><img src="https://img.shields.io/badge/GitHub-181717?logo=github&logoColor=white" alt="GitHub"></a>
+  <a href="https://huggingface.co/MiniMaxAI/MiniMax-H3" target="_blank"><img src="https://img.shields.io/badge/Hugging%20Face-FFD21E?logo=huggingface&logoColor=black" alt="Hugging Face"></a>
+  <br>
+  <a href="https://modelscope.cn/organization/minimax" target="_blank" rel="noopener noreferrer"><img alt="ModelScope MiniMax AI" src="https://img.shields.io/badge/ModelScope-MiniMax%20AI-white?labelColor=%23EF3D5D"></a>
+  <a href="https://platform.minimaxi.com/docs/faq/contact-us" target="_blank"><img src="https://img.shields.io/badge/WeChat-07C160?logo=wechat&logoColor=white" alt="WeChat"></a>
+  <a href="https://discord.com/invite/dbMxutw7tP" target="_blank"><img src="https://img.shields.io/badge/Discord-5865F2?logo=discord&logoColor=white" alt="Discord"></a>
+  <a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE"><img src="https://img.shields.io/badge/LICENSE-4CAF50?logo=creativecommons&logoColor=white" alt="LICENSE"></a>
+</p>
+
+
+# MiniMax H3
+
+## Online API
+Use MiniMax\-H3 directly via API\. 
+- Global: [platform\.minimax\.io](https://platform.minimax.io/docs/api-reference/video-generation-v2-create) \| CN: [platform\.minimaxi\.com](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-create)
+
+## Online App
+Use MiniMax\-H3 directly via App\.
+- WebApp Global: [hailuoai\.video](https://hailuoai.video/tools/minimax-h3) \| CN: [hailuoai\.com](https://hailuoai.com/)
+- Desktop Global: [hub\.minimax\.io](https://hub.minimax.io/) \| CN: [hub\.minimaxi\.com](https://hub.minimaxi.com/)
+
+## System Overview
+MiniMax H3 is a general-purpose, omni-modal generative system. It supports unified understanding of multimodal contexts composed of text, images, video, and audio, and can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. Thanks to its task-generalization-oriented system design, H3 already possesses broad multimodal context understanding and generation capabilities at the pre-training stage, enabling outstanding performance in following complex multimodal instructions.
+
+H3 supports the following input and output specifications:
+
+| Category | Specification |
+|---|---|
+| Output duration | 4–15 seconds |
+| Output aspect ratio | Supports a wide range of aspect ratios, including but not limited to 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16 |
+| Output resolution | Supports various resolution dimensions. The shorter side is set to 768 pixels by default. 2K \| generation can be achieved with H3-Regenerate-2K |
+| Output frame rate | 24 FPS |
+| Output audio | 32 kHz stereo |
+| Supported dialogue languages | Stable support for 11 languages: Arabic, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, and Spanish. Additional languages are also supported to varying degrees |
+
+### Model Variants and Input Specifications
+
+| Model Variant | Input Mode | Specifications |
+|---|---|---|
+| H3-Base-FL2VA | First-and-last-frame mode | Supports zero, one, or two input images. <br><br>- No image input: Text-to-video mode <br>- One image input: First-frame-to-video or last-frame-to-video generation <br>- Two image inputs: First-and-last-frame-to-video generation |
+| H3-Base-Ref2VA | Omni-reference mode | Supports multi-modal reference inputs: <br><br>- **Images:** ≤ 9 images <br>- **Videos:** ≤ 3 clips; each clip must be 2–15 seconds long; total duration ≤ 15 seconds <br>- **Audio:** ≤ 3 clips; audio must be accompanied by image or video input and cannot be used as the sole input; each clip must be 2–15 seconds long; total duration ≤ 15 seconds <br>- **Mixed inputs:** Maximum number of files across all input types is 12 |
+
+![Image](assets/overview.png)
+
+The complete H3 system consists of the following three modules:
+- H3-Context-IR: As inputs become increasingly complex, we build a dedicated system to deeply understand and refine the input multimodal instructions, then convert them into a form that H3 can readily understand—the Context Intermediate Representation—for generation. **H3-Context-IR is critical to the quality of the final output, so we strongly recommend incorporating it into your generation pipeline or following the “Prompting Guidance” to build your own context-processing system.**
+- H3-Base: Generates audio and video based on the H3-Context-IR output, producing results at 768p resolution.
+- H3-Regenerate-2K: Feeds the 768p result together with the original context back into H3 to regenerate the output at 2K resolution. This process leverages both H3’s powerful generative capabilities and the rich information contained in the original context, enabling it to produce high-resolution outputs with more accurate details and greater visual fidelity.
+
+## Model Architecture
+
+### H3\-Context\-IR
+
+H3\-Context\-IR is a hosted preprocessing and orchestration system designed for free\-form multimodal inputs\.
+
+It interprets the relationships among text, images, audio, and reference videos, as well as how these materials relate to the intended generation output\. Its internal workflow includes instruction parsing, cross\-modal association, temporal understanding, and complex logical reasoning\.
+
+H3\-Context\-IR serializes its understanding of the context into a structured representation accepted by H3\-Base\. Without deviating from the user’s original intent, it may also supplement missing or underspecified semantic details where appropriate\.
+
+Because H3\-Context\-IR relies on a multi\-stage workflow and multiple hosted models and services, it is not included in this open\-source release\. We provide an API that enables users to reproduce the behavior of the official workflow\. We also provide detailed tutorials, and developers can follow the **Prompting Guidance** to build their own preprocessing systems\.
+
+For detailed usage instructions, see **Recommended Workflow — Full 2K Workflow**\.
+
+**Safety Guardrails**
+
+User\-submitted text, images and videos, as well as enhanced prompts, are subject to automated moderation\. Content suspected of being unlawful, pornographic, or infringing third\-party rights may be blocked\. We use industry\-standard filtering measures but cannot eliminate false positives or false negatives\. These guardrails do not affect the Licensee’s obligations under the MiniMax H3 Community License, especially those relating to lawful use and use restrictions\.
+
+### H3\-Base
+
+![Image](assets/full-arch.png)
+
+#### Architecture Overview
+
+- H3\-Base encodes different modalities using their corresponding encoders or VAEs and organizes the encoded representations into a unified packed multimodal sequence\. RoPE is used to capture the necessary spatial and temporal relationships among tokens before the entire sequence is passed to the H3\-Omni\-Transformer\.
+
+- Specifically, text is encoded by the H3\-Encoder; visual inputs are encoded by both the H3\-Encoder and the H3\-VisualVAE; and audio is encoded solely by the H3\-AudioVAE\.
+
+- The H3\-Omni\-Transformer jointly predicts video and audio latents, which are then decoded into video and stereo audio, respectively\.
+
+- To reduce the computational cost of long multimodal sequences, H3 natively supports sparse\-attention training and inference\. The initial open\-source release provides inference with full attention only\. Our sparse\-attention implementation will be released in a future update\.
+
+#### H3\-Encoder
+
+- The H3\-Encoder uses the full pretrained weights of Qwen3\-VL\-32B and provides the hidden states from its 50th layer to the H3\-Omni\-Transformer\.
+
+- We add several special tokens, such as `<d>`, to the tokenizer configuration\. When using H3, the tokenizer and associated configuration files provided in the H3 repository are required\.
+
+#### H3\-VAE
+
+H3 uses separate visual and audio latents to represent their respective modalities\.
+
+##### H3\-VisualVAE
+
+- H3\-VisualVAE is a temporally causal video autoencoder with a spatial compression factor of 16×, a temporal compression factor of 4×, and 24 latent channels, denoted as f16t4d24\. We apply several latent\-space optimization techniques to jointly improve reconstruction quality and latent learnability\.
+
+- Before being passed to the H3\-Omni\-Transformer, the visual latents are further patchified with a patch size of `1 × 2 × 2` along the `(time, height, width)` dimensions\. As a result, the visual tokens entering the Transformer have an effective spatial downsampling factor of 32×, while the temporal downsampling factor remains 4×\.
+
+- The latent space of H3\-VisualVAE is optimized for both reconstruction quality and ease of learning by the generative model\. After training its encoder, we additionally train a ViT\-based decoder to reduce decoding costs and further improve reconstruction quality\.
+
+##### H3\-AudioVAE
+
+- H3-AudioVAE uses the same encoder and decoder for both the left and right audio channels while processing each channel independently. The decoded channels are then recombined, enabling stereo audio input and output.
+- For each channel, H3-AudioVAE compresses 32 kHz audio into a sequence of latent tokens with a temporal rate of 40 Hz.
+- Inspired by VA-VAE, we optimize the latent space to preserve audio reconstruction quality while making it easier for the generative model to learn.
+
+#### H3\-Omni\-Transformer
+
+- For scalability and generalization, we adopt a relatively simple Transformer block design\. H3\-Omni\-Transformer is a 33B\-parameter dense, single\-stream Transformer, with approximately 13B parameters residing in AdaLN\-related branches\. Because the AdaLN modulation outputs can be precomputed and cached, these parameters do not need to be loaded for inference\-only deployment\. We release the complete model weights to support further development, including fine\-tuning\.
+
+- Neither the attention layers nor the FFN layers contain modality\-specific structures\. Modality\-specific parameters are confined to the input/output layers and the AdaLN branches\. In particular, modality\-specific AdaLN improves generation quality with relatively low additional training and inference costs\.
+
+- The model uses three\-dimensional Multimodal Rotary Position Embeddings \(MM\-RoPE\) to represent positional relationships across the temporal and two spatial dimensions, `(t, h, w)`\.
+
+- During the final stage of training, we introduce native sparse attention to reduce the computational cost of long sequences\. The sparse\-attention implementation is not included in the initial open\-source release and will be published separately in a future update\.
+
+    
+
+### H3-Regenerate-2K
+
+- For H3's 2K\-resolution output, instead of using a conventional dedicated super\-resolution module, we use the H3 base model to regenerate its own low\-resolution result through an in\-context manner\.
+
+- This approach provides two advantages: \(1\) the regeneration process can reuse the generative capabilities of H3 base model to the greatest extent possible; and \(2\) the in\-context format can reuse the original multimodal context when producing high\-resolution output, allowing it to recover information that conventional super\-resolution methods would otherwise have to “guess,” such as small text and fine details\.
+
+- In\-context regeneration is also an example of task generalization\.
+
+- **Due to the complexity of the system, this module is not yet open\-sourced\. We will release it once it is ready\.** We provide an API for validating the official results; see "Full 2K Workflow" below\.
+
+
+
+## Recommended Workflow
+
+To help the community deploy MiniMax H3 correctly, we provide two validation methods\.
+
+Since the complete H3 system consists of three modules—H3\-Context\-IR, H3\-Base, and H3\-Regenerate\-2K—the “Full 2K Workflow” provides an end\-to\-end validation pipeline for 2K output, combining the Open Platform API with a locally deployed H3\-Base\. The “Local Deployment of H3\-Base” section provides a method for validating 768p output using only a locally deployed H3\-Base\.
+
+In addition, the “Prompting Guidance” section provides a detailed tutorial to help the community develop their own prompting systems\.
+
+### Local Deployment of H3\-Base
+
+MiniMax H3 is released as two task\-specific checkpoints\. Each checkpoint contains a specialized Omni Transformer Model together with the required processor, tokenizer, text encoder, Visual VAE, and standalone Audio VAE components\.
+
+|Checkpoint|Supported Tasks|Input Conditions|Output|Precision|
+|---|---|---|---|---|
+|MiniMax\-H3 Base FL2VA|Text\-to\-Audio\-Video \(`t2va`\), First/Last\-Frame\-to\-Audio\-Video \(`fl2va`\)|Text; optional first frame, last frame, or both|Video and audio|BF16|
+|MiniMax\-H3 Base Ref2VA|Reference\-to\-Audio\-Video \(`ref2va`\)|Text with reference images, videos, and/or audio|Video and audio|BF16|
+
+The released checkpoints are CFG-distilled Omni Transformer model weights. 
+
+Each checkpoint is distributed as a self\-contained Hugging Face\-style repository with the following components:
+
+```text
+<TASK>/
+├── model_index.json
+├── processor/
+├── tokenizer/
+├── text_encoder/
+├── transformer/
+├── visual_vae/
+└── audio_vae/
+```
+
+Download the model. The repository hosts the original checkpoint (`FL2VA/`, `Ref2VA/`) and the diffusers format side by side, so scope the download to what your framework needs:
+
+`model_index.json` is the repository-level public entry. The task-family-specific diffusers indexes remain under `FL2VA/model_index.json` and `Ref2VA/model_index.json`.
+
+```bash
+# Original checkpoint, both task families (SGLang, vLLM):
+hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "FL2VA/*" "Ref2VA/*" --local-dir MiniMax-H3
+
+# Or a single task family:
+hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "FL2VA/*" --local-dir MiniMax-H3
+```
+
+diffusers users do not need a manual download: `ModularPipeline.from_pretrained("MiniMaxAI/MiniMax-H3")` fetches exactly the components it needs. See the [diffusers documentation](https://huggingface.co/docs/diffusers/main/en/api/pipelines/minimax_h3) for loading recipes.
+
+We recommend the following inference frameworks to serve the model:
+
+- [SGLang](https://docs.sglang.io/) \- see [cookbook](https://docs.sglang.io/cookbook/diffusion/MiniMax/MiniMax-H3) 
+
+- [vLLM](https://github.com/vllm-project/vllm) \- see [vllm recipes](https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3)
+
+- [diffusers](https://github.com/huggingface/diffusers) \- see [diffusers docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/minimax_h3)
+
+- [ComfyUI](https://github.com/Comfy-Org/ComfyUI) \- see  [Comfy tutorial](https://docs.comfy.org/tutorials/video/minimax/minimax-h3); use [R2V template](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_minimax_h3_r2v.json) / [T2V template](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_minimax_h3_t2v.json)
+
+#### Sglang Deployment
+
+Here we use sglang as a deployment example\. See the [MiniMax\-H3 deployment guide](https://docs.sglang.io/cookbook/diffusion/MiniMax/MiniMax-H3#3-serve-minimax-h3) for additional deployment configurations\.
+
+FL2VA:
+
+```bash
+sglang serve \
+  --model-path MiniMaxAI/MiniMax-H3 \
+  --num-gpus 4 \
+  --ulysses-degree 4 \
+  --performance-mode speed \
+  --host 0.0.0.0 \
+  --port 30010 \
+  --model-variant fl2va
+```
+
+Ref2VA:
+
+```bash
+sglang serve \
+  --model-path MiniMaxAI/MiniMax-H3 \
+  --num-gpus 4 \
+  --ulysses-degree 4 \
+  --performance-mode speed \
+  --host 0.0.0.0 \
+  --port 30011 \
+  --model-variant ref2va
+```
+
+#### Reproducible 768p cases
+
+The following three use cases T2VA, FL2VA, and Ref2VA demonstrate how to reproduce MiniMax\-H3 video\-audio generation\.
+
+| Use case | Request | Result |
+|---|---|---|
+| T2VA | [View script](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/reproducible-768p-t2va-request.sh) | [t2va.mp4](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/t2va.mp4) |
+| FL2VA | [View script](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/reproducible-768p-fl2va-request.sh) | [fl2va.mp4](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/fl2va.mp4) |
+| Ref2VA | [View script](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/reproducible-768p-ref2va-request.sh) | [ref2va.mp4](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/ref2va.mp4) |
+
+### Full 2K\-Workflow
+
+This section explains how to combine a locally deployed SGLang service with the official **H3\-Context\-IR** and **H3\-Regenerate\-2K** APIs to reproduce the quality of 2K videos generated directly by the MiniMax API\.
+Before you begin, configure the SGLang endpoint and your MiniMax API credentials:
+
+```bash
+# URL of your SGLang deployment
+SGLANG_DEPLOYMENT_URL="<sglang-deployment-url>"
+
+# MiniMax API endpoint (choose one)
+# CN
+MINIMAX_API_BASE="https://api.minimaxi.com"
+# Global
+# MINIMAX_API_BASE="https://api.minimax.io"
+
+# API token obtained from the MiniMax platform
+TOKEN="<token>"
+```
+
+MiniMax platform:
+
+API docs:
+- Create H3-2K: use /video-generation-v2-create [EN-docs](https://platform.minimax.io/docs/api-reference/video-generation-v2-create), [CN-docs](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-create)
+- H3-Context-IR：use /video-generation-v2-h3-context-ir [EN-docs](https://platform.minimax.io/docs/api-reference/video-generation-v2-h3-context-ir), [CN-docs](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-h3-context-ir)
+- H3-Regenerate-2K：use /video-generation-v2-regeneration [EN-docs](https://platform.minimax.io/docs/api-reference/video-generation-v2-regeneration), [CN-docs](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-regeneration)
+
+
+The examples below encode local H3\-Base output files as Base64 Data URLs\. For production use, uploading the video to a publicly accessible URL and passing that URL as `base_video` is recommended\.
+
+For each case below, we provide reference outputs at both 2K and 768p generated directly through the Open Platform API, making it easier to validate the results\.
+
+#### case\-T2VA
+
+- Type: Text-to-video
+- Duration: 10 seconds
+- Aspect ratio: 16:9
+
+<table>
+  <thead>
+    <tr><th>stage</th><th>request</th><th>result</th></tr>
+  </thead>
+  <tbody>
+    <tr><td>H3-Context-IR</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-t2va-h3-context-ir.sh">View script</a></td><td><pre><code class="language-json">{
+  &quot;task&quot;: {
+    &quot;id&quot;: &quot;&lt;task_id&gt;&quot;,
+    &quot;model&quot;: &quot;MiniMax-H3&quot;,
+    &quot;status&quot;: &quot;succeeded&quot;,
+    &quot;created_at&quot;: &quot;&lt;created_at&gt;&quot;,
+    &quot;updated_at&quot;: &quot;&lt;updated_at&gt;&quot;,
+    &quot;content&quot;: {
+      &quot;prompt&quot;: &quot;integrated_multimodal_description: [Shot 1] Cinematic, medium wide shot, pushing in slowly. In the cavernous, dimly lit bridge of a starship, sleek metallic consoles with glowing amber displays flank a massive, curved observation window. A female captain, in her late 40s with an athletic build and short silver-streaked black hair, stands in the center midground. She wears a structured, high-collared dark navy military tunic with silver chest insignias. Her back is to the camera, silhouetted against the cool, ambient starlight pouring through the thick glass. She stands perfectly still with her hands clasped tightly behind her back. Outside the window, a massive armada of jagged, dark grey dreadnoughts hovers in tight formation against a deep purple space nebula. The fleet&#39;s massive rear thrusters begin to glow with an intense, escalating bright blue light. [Shot 2] At 00:04.500, the camera cuts to a close-up of the captain&#39;s face and shakes strongly. The brilliant blue-white light from the fleet&#39;s gathering energy reflects vividly in her dark eyes. Suddenly, a blinding white flash floods through the window, completely washing out the background as the fleet jumps to hyperspace. The sheer spatial force violently jolts the bridge, causing the captain from Shot 1 to stagger slightly forward, her shoulders tensing as she visibly braces herself against the physical tremors. As the intense white light fades abruptly, leaving only the dim, empty expanse of the purple nebula reflected on her starkly lit skin, her jaw clenches, and she slowly closes her eyes in the newly emptied space.\noverall_soundscape: A low, resonant hum of the ship&#39;s ambient life support systems serves as the baseline, soon drowned out by an audible, escalating, high-pitched electronic whine as the fleet outside charges its hyperdrives. A massive, deafening, bass-heavy boom and sharp crackle erupts during the blinding flash, accompanied by the loud metallic creaking, rattling, and deep thuds of the bridge&#39;s bulkheads vibrating under immense physical stress. The intense roaring impact then cuts abruptly back to a hollow, echoing room tone, leaving only the faint, steady hum of the isolated bridge.\nnon_diegetic_music: Cinematic space-opera orchestral score, slow tempo, featuring a solitary, mournful French horn melody over deep, sustained string dissonances that build rapidly in volume and intensity, swelling to a massive orchestral peak before snapping immediately into silence right after the jump.&quot;
+    },
+    &quot;duration&quot;: 10,
+    &quot;usage&quot;: {
+      &quot;total_tokens&quot;: 8565,
+      &quot;prompt_tokens&quot;: 5650,
+      &quot;completion_tokens&quot;: 2915
+    },
+    &quot;ratio&quot;: &quot;16:9&quot;,
+    &quot;task_type&quot;: &quot;h3_context_ir&quot;,
+    &quot;modality&quot;: &quot;text&quot;
+  }
+}</code></pre></td></tr>
+    <tr><td>H3-Base</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-t2va-h3-base.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/t2va.mp4">t2va.mp4</a></td></tr>
+    <tr><td>H3-Regenerate-2K</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-t2va-h3-regenerate-2k.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/t2va_2k.mp4">t2va_2k.mp4</a></td></tr>
+    <tr><td>Reference 2K result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-t2va-reference-2k-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/h3_direct_2k.mp4">h3_direct_2k.mp4</a></td></tr>
+    <tr><td>Reference 768P result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-t2va-reference-768p-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/h3_direct_768p.mp4">h3_direct_768p.mp4</a><br></td></tr>
+  </tbody>
+</table>
+
+#### case\-I2VA
+
+- Type: First-frame image-to-video
+- Duration: 8 seconds
+- Aspect ratio: adaptive
+
+<table>
+  <thead>
+    <tr><th>stage</th><th>request</th><th>result</th></tr>
+  </thead>
+  <tbody>
+    <tr><td>H3-Context-IR</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-i2va-h3-context-ir.sh">View script</a></td><td><pre><code class="language-json">{
+  &quot;task&quot;: {
+    &quot;id&quot;: &quot;&lt;task_id&gt;&quot;,
+    &quot;model&quot;: &quot;MiniMax-H3&quot;,
+    &quot;status&quot;: &quot;succeeded&quot;,
+    &quot;created_at&quot;: &quot;&lt;created_at&gt;&quot;,
+    &quot;updated_at&quot;: &quot;&lt;updated_at&gt;&quot;,
+    &quot;content&quot;: {
+      &quot;prompt&quot;: &quot;For the target video, at 0.00 seconds into the target video, &lt;Picture 1&gt; (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] This is a live-action, cinematic shot with a shallow depth of field. The camera holds a perfectly static shot throughout the entire eight-second duration, capturing a cozy family gathering in a traditional Japanese dining room. The scene opens with a large, intricately patterned blue and white ceramic bowl of ramen in the immediate foreground, rendered in crisp, sharp focus. The bowl sits on a smooth, polished long wooden table. Inside the bowl, a rich, oily golden-brown broth surrounds yellow wavy noodles, topped with two thick, round slices of chashu pork featuring visible fat marbling and a distinct spiral meat pattern. A generous mound of freshly chopped, bright green scallions rests in the center, and a crisp, dark green rectangular sheet of nori seaweed is tucked into the right edge. To the left of the bowl, a pair of light brown wooden chopsticks rests horizontally on a small, dark rectangular chopstick rest, near a small cylindrical ceramic teacup with blue painted patterns. On the right side of the table, a spherical paper lantern with a ribbed bamboo frame sits on a black wooden base. In the background, a large family of seven is gathered around the table, initially appearing as a soft, blurred presence. Behind them, traditional Japanese sliding shoji screens with wooden lattice frames are open, revealing a bright outdoor scene with lush green trees. Early in the clip, the thick, white steam rising from the hot ramen broth immediately intensifies, billowing upwards in thick, swirling clouds that dance continuously above the bowl. As the clip progresses into the middle seconds, the camera maintains its static position while the focus begins a deliberate, smooth shift deeper into the room. The foreground ramen bowl, its vibrant ingredients, and the rising steam gradually soften into a hazy, out-of-focus blur. Simultaneously, the family members in the background come into sharp, detailed clarity. The heavy steam continues to rise from the foreground, creating a dynamic, translucent veil between the camera and the family. With the focus now firmly locked on the background, the vibrant family dinner comes alive. The man in the dark navy blue long-sleeved shirt on the left leans forward, his mouth moving animatedly in a silent exchange. The young girl in the crisp white short-sleeved t-shirt beside him smiles brightly, looking toward the center of the table. The woman on the far left, wearing a soft light blue long-sleeved blouse, turns her head slightly, smiling gently. Across the table, the woman in the light grey button-down shirt smiles broadly, her eyes crinkling, as she rests her hands near her plate. The woman in the dark grey top further back uses her wooden chopsticks to pick up a small piece of food from a central ceramic dish filled with bright red pickled vegetables. The woman in the center back in the light grey sweater smiles gently, her hands clasped softly in front of her, observing the interaction. Throughout the remainder of the clip, the family continues their lively physical interaction, their mouths moving in continuous, silent cadences of conversation, while the thick, white steam from the blurred ramen bowl in the foreground never stops rising, adding a comforting atmosphere to the warm gathering.\n\noverall_soundscape: The soundscape begins with a quiet room tone mixed with the faint, airy rustle of the thick steam billowing from the hot ramen bowl in the foreground, accompanied by the subtle, continuous hissing and bubbling of the rich broth. As the visual focus shifts deeper into the room, the physical sounds of the bustling family dinner become dominant in the foreground. The clear, sharp clinking of ceramic bowls and wooden chopsticks touching plates is clearly heard as the family members reach for food. This is followed by the faint, muffled thud of a cup being set down on the smooth wooden table, and the subtle, rhythmic rustle of cotton and wool clothing as the family members lean forward and gesture, perfectly capturing the lively, physical atmosphere of the shared meal.\n\nnon_diegetic_music: A gentle, heartwarming acoustic guitar melody plays softly in the background, accompanied by the subtle, resonant notes of a traditional Japanese koto. The music maintains a slow, comforting tempo that enhances the cozy, nostalgic, and joyful atmosphere of the family gathering.&quot;
+    },
+    &quot;duration&quot;: 8,
+    &quot;usage&quot;: {
+      &quot;total_tokens&quot;: 22822,
+      &quot;prompt_tokens&quot;: 12800,
+      &quot;completion_tokens&quot;: 10022
+    },
+    &quot;ratio&quot;: &quot;16:9&quot;,
+    &quot;task_type&quot;: &quot;h3_context_ir&quot;,
+    &quot;modality&quot;: &quot;text&quot;
+  }
+}</code></pre></td></tr>
+    <tr><td>H3-Base</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-i2va-h3-base.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/i2va.mp4">i2va.mp4</a></td></tr>
+    <tr><td>H3-Regenerate-2K</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-i2va-h3-regenerate-2k.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/i2va_2k.mp4">i2va_2k.mp4</a><br></td></tr>
+    <tr><td>Reference 2K result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-i2va-reference-2k-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/i2va_direct_2k.mp4">i2va_direct_2k.mp4</a></td></tr>
+    <tr><td>Reference 768P result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-i2va-reference-768p-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/i2va_direct_768p.mp4">i2va_direct_768p.mp4</a></td></tr>
+  </tbody>
+</table>
+
+#### case\-Ref2VA
+
+- Type: Multimodal reference-to-video (video + audio)
+- Duration: 5 seconds
+- Aspect ratio: adaptive
+
+<table>
+  <thead>
+    <tr><th>stage</th><th>request</th><th>result</th></tr>
+  </thead>
+  <tbody>
+    <tr><td>H3-Context-IR</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-ref2va-h3-context-ir.sh">View script</a></td><td><pre><code class="language-json">{
+  &quot;task&quot;: {
+    &quot;id&quot;: &quot;&lt;task_id&gt;&quot;,
+    &quot;model&quot;: &quot;MiniMax-H3&quot;,
+    &quot;status&quot;: &quot;succeeded&quot;,
+    &quot;created_at&quot;: &quot;&lt;created_at&gt;&quot;,
+    &quot;updated_at&quot;: &quot;&lt;updated_at&gt;&quot;,
+    &quot;content&quot;: {
+      &quot;prompt&quot;: &quot;subject_definitions:\n&lt;Subject 1&gt; is the young man with short wavy blonde hair, wearing a bright pink suit jacket, matching pink trousers, an unbuttoned white shirt, and silver rings, holding a small black lamb in his arms in &lt;Video 1&gt;.\n&lt;Video 1&gt; is the source video for the editing task.\n&lt;Audio 1&gt; is the synchronized audio track of &lt;Video 1&gt;, providing the background music.\n&lt;Audio 2&gt; is the voice timbre reference for &lt;Subject 1&gt;&#39;s voice, containing a spoken male voiceover.\n\nsummary:\n[video editing + audio reference + audio reuse] The target video is an edited version of &lt;Video 1&gt;. &lt;Subject 1&gt;, wearing a bright pink suit and holding a black lamb, stands in a grassy field with other white lambs in the background. The edit animates &lt;Subject 1&gt;&#39;s face to speak the user-provided dialogue. &lt;Audio 1&gt; is partially reused as the continuous background music, while the target references the calm male voice timbre of &lt;Audio 2&gt; for &lt;Subject 1&gt;&#39;s spoken lines.\n\nretention_analysis:\n&lt;Subject 1&gt; (appears in [Shot 1]): fully_preserved - the man retains his identity, wavy blonde hair, pink suit, white shirt, accessories, and the black lamb he holds, with his mouth newly animated to speak.\n&lt;Video 1&gt; (source video editing): fully_preserved - the original camera framing, warm golden hour lighting, grassy hill setting, and background white lambs are maintained while the central character is edited.\n&lt;Audio 1&gt;: partially_copy - the atmospheric background music from &lt;Audio 1&gt; is reused in the target video, mixed beneath the newly added spoken dialogue.\n&lt;Audio 2&gt;: reference - the target audio references the male voice timbre from &lt;Audio 2&gt; to generate &lt;Subject 1&gt;&#39;s spoken dialogue.\n\ndetailed_description:\nThe target video is in realistic photographic style.\n[Shot 1] The shot begins from the source &lt;Video 1&gt;, showing &lt;Subject 1&gt;, a young man with short wavy blonde hair, wearing a bright pink suit jacket, matching pink trousers, and a casually unbuttoned white shirt. He stands confidently in a sunlit green pasture, gently holding a small black lamb securely in his arms. The warm, golden hour lighting casts soft shadows across his face and the bright pink fabric of his suit. Behind him, several white lambs stand and graze on the rolling grassy hill against a clear, pale blue sky. The atmospheric background music from &lt;Audio 1&gt; plays continuously throughout the scene. &lt;Subject 1&gt; physically speaks, his mouth movements naturally syncing to the new dialogue, with his voice timbre referencing the calm male delivery from &lt;Audio 2&gt;. Looking thoughtfully forward, &lt;Subject 1&gt; (S1) speaks softly, &lt;d&gt;[English] Follow the wind, live free.&lt;/d&gt; As he delivers the line, he subtly shifts his weight, cradling the resting black lamb while the camera slowly pushes in. &lt;Subject 1&gt; (S1) continues his thought, &lt;d&gt;[English] Leave worries behind, enjoy the moment.&lt;/d&gt; Exactly as his voice stops, his lips meet in a relaxed, peaceful smile, and his jaw ceases speaking motion. He then turns his gaze slightly away toward the horizon, gently stroking the black lamb&#39;s fleece with his fingers as the camera holds on this tranquil, sunlit state through the end of the video.\n\noverall_soundscape:\nThe soundscape consists of the continuous, atmospheric background music from &lt;Audio 1&gt;, overlaid with the clear, calm male dialogue spoken by the main character, referencing the voice timbre of &lt;Audio 2&gt;.\n\nnon_diegetic_music:\nThe atmospheric, sustained background music from &lt;Audio 1&gt; is reused as the continuous score, playing quietly beneath the spoken dialogue.&quot;
+    },
+    &quot;duration&quot;: 5,
+    &quot;usage&quot;: {
+      &quot;total_tokens&quot;: 39299,
+      &quot;prompt_tokens&quot;: 33323,
+      &quot;completion_tokens&quot;: 5976
+    },
+    &quot;ratio&quot;: &quot;16:9&quot;,
+    &quot;task_type&quot;: &quot;h3_context_ir&quot;,
+    &quot;modality&quot;: &quot;text&quot;
+  }
+}</code></pre></td></tr>
+    <tr><td>H3-Base</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-ref2va-h3-base.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/r2va.mp4">r2va.mp4</a><br></td></tr>
+    <tr><td>Reference 2K result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-ref2va-reference-2k-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/r2va_2k.mp4">r2va_2k.mp4</a></td></tr>
+    <tr><td>H3 API 2K in Open Platform for reference</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-ref2va-h3-api-2k-in-open-platform-for-reference.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/r2va_direct_2k.mp4">r2va_direct_2k.mp4</a><br></td></tr>
+    <tr><td>Reference 768P result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-ref2va-reference-768p-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/r2va_direct_768p.mp4">r2va_direct_768p.mp4</a><br></td></tr>
+  </tbody>
+</table>
+
+### Prompting Guidance
+
+[VIDEO\_PROMPT\_WRITING\_GUIDE\_base\_en\.md](docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md)
+
+[VIDEO\_PROMPT\_WRITING\_GUIDE\_ref\_en\.md](docs/VIDEO_PROMPT_WRITING_GUIDE_ref_en.md)
+
+skills to improve prompt: https://github.com/MiniMax-AI/MiniMax-H3/tree/main/skills
+
+## License
+
+- MiniMax H3 is released under the [MiniMax H3 Community License Agreement](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE).
+- [Q&A about the License](docs/QA-about-License.md)
+- [Application form(only for USA/EU/UK/South Korea)](https://platform.minimax.io/h3-license)
+
+## Contact Us
+
+Contact us at [model@minimax.io](mailto:model@minimax.io).

Ref2VA/model_index.json

@@ -0,0 +1,41 @@
+{
+  "_class_name": "MiniMaxH3Pipeline",
+  "_diffusers_version": "0.32.2",
+  "text_encoder": [
+    "transformers",
+    "MiniMaxH3Qwen3VLHFEncoder"
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2TokenizerFast"
+  ],
+  "video_vae": [
+    "diffusers",
+    "MiniMaxH3VideoVAE"
+  ],
+  "audio_vae": [
+    "diffusers",
+    "MiniMaxH3AudioVAE"
+  ],
+  "scheduler": null,
+  "transformer": [
+    "diffusers",
+    "MiniMaxH3DiTModel"
+  ],
+  "processor": [
+    "transformers",
+    "Qwen3VLProcessor"
+  ],
+  "_minimax_h3": {
+    "schema_version": 1,
+    "partition": "ref2va",
+    "tasks": [
+      "ref2va"
+    ],
+    "task_aliases": {},
+    "sigma_shift_scales": {
+      "video": 12.0,
+      "audio": 3.0
+    }
+  }
+}

audio_scheduler/scheduler_config.json

@@ -0,0 +1,5 @@
+{
+  "_class_name": "MiniMaxH3Scheduler",
+  "_diffusers_version": "0.36.0.dev0",
+  "shift": 3.0
+}

audio_vae/config.json

@@ -0,0 +1,125 @@
+{
+  "_class_name": "AutoencoderKLMiniMaxH3Audio",
+  "_diffusers_version": "0.36.0.dev0",
+  "encoder_dim": 64,
+  "encoder_rates": [
+    2,
+    4,
+    4,
+    5,
+    5
+  ],
+  "latent_dim": 2048,
+  "latent_channels": 32,
+  "decoder_dim": 1024,
+  "decoder_rates": [
+    5,
+    5,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "decoder_kernel_sizes": [
+    9,
+    9,
+    4,
+    4,
+    4,
+    4,
+    4
+  ],
+  "num_attention_heads": 8,
+  "resblock_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "resblock_dilation_sizes": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "sampling_rate": 32000,
+  "latents_mean": [
+    -0.020211687488382354,
+    0.3876466479950502,
+    -0.04398279799186767,
+    -0.28591514936373,
+    0.08179686214561671,
+    -0.35782641352446604,
+    0.040623809960919084,
+    -0.01552534501956604,
+    -0.223362481667332,
+    0.1821006842509091,
+    0.2941778783780663,
+    -0.07901167601970885,
+    -0.056815072777201,
+    -0.3699028221860095,
+    -0.31616315591624855,
+    0.5905951377425391,
+    -0.052139568068853864,
+    0.013673160263486295,
+    -0.03691647864630577,
+    0.09732660653298163,
+    -0.3394662328788498,
+    -0.30685677538541667,
+    -0.24504598907458763,
+    -0.034698524462007344,
+    0.02868032184767538,
+    -0.21217779266454084,
+    -0.1678263169941987,
+    0.3221287889040614,
+    -0.1223055851554907,
+    0.4356604928128464,
+    -0.0502599202236253,
+    0.3979258376211797
+  ],
+  "latents_std": [
+    1.6895524230479284,
+    2.76263727217653,
+    1.7945344281264435,
+    1.6801681847309828,
+    1.6390226546605453,
+    2.7788298348882177,
+    1.7659090095747236,
+    1.6199757612137327,
+    2.6336525640336896,
+    1.8539356672817833,
+    2.5056497896915633,
+    1.811019237886178,
+    1.9579657790720237,
+    1.6685498243529284,
+    1.4922469314453364,
+    3.298670198067373,
+    1.9491804496832168,
+    1.8720003270431442,
+    1.8334080103291832,
+    1.6488070416529093,
+    1.6176957696319716,
+    1.9131449234774398,
+    1.5695245398428617,
+    1.6943659940415912,
+    1.8318420762504692,
+    1.5540637421583379,
+    1.9344930328968526,
+    1.599198216109855,
+    1.718045989838149,
+    1.6307219190837705,
+    1.8661226051202384,
+    1.5613768203168363
+  ]
+}

docs/QA-about-License.md

@@ -0,0 +1,65 @@
+# Q&A About License
+
+## Why is MiniMax-H3's open-weight license currently limited to the EU, UK, South Korea, and US?
+
+MiniMax-H3 was built with the goal of global availability. The current territory scope is not about excluding specific countries or regions, but about recognizing that video generation models are facing a more complex and rapidly evolving regulatory environment compared with text or code models.
+
+Regions such as the EU, UK, South Korea, and the US are currently developing or enforcing AI-related regulations that may have specific implications for generative video models, especially around areas such as likeness generation, copyright, content safety, and responsible deployment.
+
+- The EU AI Act has started enforcement, while practical requirements for models capable of generating video and likeness-related content are still evolving.
+- Similar regulatory uncertainties exist in the UK and South Korea regarding AI-generated content and video generation.
+- In the US, AI regulation remains a rapidly changing landscape, and MiniMax is also involved in ongoing copyright-related legal proceedings specifically concerning generative video AI.
+
+For open-weight models, once the weights are released, developers can deploy and modify them independently. This creates different compliance challenges compared with hosted services.
+
+We had two options:
+
+1. Wait until every jurisdiction reaches complete regulatory clarity before releasing open weights, which could take a long time while AI technology continues to evolve.
+2. Release the model now with a transparent license scope, while continuing to evaluate and expand availability.
+
+We chose the second approach. The current limitation means "not yet", not "not ever."
+
+## Why can MiniMax-H3 API be used globally if open weights are restricted in some regions?
+
+The difference is the distribution model.
+
+The main concern is not the existence of MiniMax-H3 itself, but the ability to control compliance after open weights leave our infrastructure.
+
+For API access, MiniMax operates the serving infrastructure and can enforce appropriate safeguards, including:
+
+- Protection against misuse involving minors.
+- Copyright-related compliance measures.
+- Content safety controls.
+- Compliance with applicable laws and regulations.
+
+With open weights, users can independently deploy, modify, and distribute the model, which makes it much harder to ensure the same level of compliance.
+
+Therefore, the API and open-weight release follow different approaches:
+
+- API: Globally available with built-in safeguards and responsible-use controls.
+- Open weights: Temporarily limited in certain regions until the regulatory and compliance framework becomes clearer.
+
+## Can organizations in restricted regions still use MiniMax-H3?
+
+Yes.
+
+Organizations in these regions can apply for a formal license. After reviewing the deployment scenario and confirming that appropriate compliance controls and safeguards are implemented, MiniMax may authorize usage.
+
+[Application form](https://platform.minimax.io/h3-license)
+
+Through authorized deployments, MiniMax can ensure that MiniMax-H3 is used responsibly while meeting local legal and regulatory requirements.
+
+## Will MiniMax expand open-weight availability in the future?
+
+Yes. We will continue monitoring legal developments and reassessing the territory scope.
+
+Our commitments:
+
+- Continuously review regulations and compliance requirements across regions.
+- Keep MiniMax-H3 API available globally, so users can continue accessing the model.
+- Clearly communicate any future license changes instead of making silent updates.
+- Listen to feedback from developers, researchers, and organizations affected by these restrictions.
+
+Our goal remains the same: bringing intelligence to everyone with responsible AI use.
+
+The current license scope reflects today's regulatory reality, not our long-term vision.

docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md

@@ -0,0 +1,222 @@
+# Video Prompt Writing Guide (T2VA / I2VA / FL2VA / L2VA)
+
+## 1. Task Overview
+
+- **T2VA**: Builds a complete audiovisual timeline from text.
+- **I2VA**: T2VA body + first-frame instruction + a visual path that develops forward from the first frame.
+- **FL2VA**: T2VA body + first-and-last-frame instruction + a continuous path from the first frame to the last frame.
+- **L2VA**: T2VA body + last-frame instruction + a path that converges from a plausible preceding state to the last frame.
+
+## 2. Final Prompt Structure
+
+### 2.1 Part One Is the Instruction
+
+**T2VA** has no image-alignment instruction and begins directly with the three core fields.
+
+**I2VA** always uses:
+
+```text
+For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
+```
+
+**FL2VA** always uses:
+
+```text
+How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot N) aligns with the S.SS-second mark of the target video.
+```
+
+**L2VA** always uses:
+
+```text
+How the reference pictures align with the target video — <Picture 1> (from [Shot N]) aligns with the S.SS-second mark of the target video.
+```
+
+Here, `N` is the index of the actual final shot, and `S.SS` is the effective video duration formatted to exactly two decimal places. The instruction must be the first line of the final prompt, followed by one blank line before the core fields.
+
+### 2.2 Part Two Contains the Three Core Fields
+
+```text
+integrated_multimodal_description: [Shot 1] ...
+
+overall_soundscape: ...
+
+non_diegetic_music: ...
+```
+
+- **integrated_multimodal_description**: Describes visuals, actions, shots, speakers, dialogue, singing, and diegetic audio along the timeline.
+- **overall_soundscape**: Summarizes ambient sound, physical action sounds, and non-verbal human sounds across the entire video.
+- **non_diegetic_music**: Describes background music that the characters cannot hear and only the audience can hear.
+
+## 3. How to Incorporate Keyframes into the Multimodal Description
+
+### 3.1 I2VA: Begin from the Image and Develop Forward
+
+`<Picture 1>` is the actual first frame of the video at 0.00 seconds and belongs to `[Shot 1]`. The description should first establish the style, subjects, composition, and scene anchors in the image, then describe the next action. Character identity, clothing, colors, key objects, and spatial relationships should remain consistent.
+
+Recommended structure: **first-frame anchor → action onset → continuous development → result or reaction**.
+
+### 3.2 FL2VA: Describe the Path Between the First and Last Frames
+
+Picture 1 is the opening, and Picture 2 is the ending. Focus on how the subject moves, how poses change, how objects are manipulated, how the composition evolves, and how the scene or lighting transitions.
+
+FL2VA generally favors a single shot so the model can interpolate continuously from the first frame to the last frame. Use multiple shots only when they are explicitly specified. The last frame must be reached by the final `[Shot N]` at the end of the video.
+
+Recommended structure: **first-frame state → observable intermediate changes → progressively narrowing differences → last-frame state**.
+
+### 3.3 L2VA: Infer the Opening and Land on the Image at the End
+
+`<Picture 1>` is the final frame of the video and belongs to the last `[Shot N]`; it does not inherently belong to Shot 1. Infer a plausible earlier state from the user's intent and the last frame, then describe how the characters, objects, camera, and scene gradually approach the reference image.
+
+Recommended structure: **plausible preceding state → explicit action and transition path → gradual convergence in the final shot → last-frame landing**.
+
+## 4. How to Write the Three Shared Core Sections
+
+### 4.1 Develop the Multimodal Description Along the Timeline
+
+`integrated_multimodal_description` is the main body of the rewritten prompt. Every detail should correspond to something visible or audible: visual style, initial composition, subject appearance and position, scene and key props, actions and reactions, shot changes, spoken language, and synchronized diegetic sound.
+
+At the beginning of `[Shot 1]`, state the overall style and initial composition. Common styles include `Cinematic`, `live-action`, `2D-animated`, `3D CG`, `claymation`, `watercolor`, and `vintage film`. For keyframe tasks, derive the style from the reference image; for T2VA, select it from the user's text.
+
+```text
+[Shot 1] Live-action, cinematic, a medium-wide shot frames...
+```
+
+### 4.2 Shots and Cuts
+
+Do not add a timestamp to the first shot. Use sequential shot numbers for later shots, and begin each one with a strictly increasing cut time that falls within the video duration:
+
+```text
+[Shot 2] At 00:03.500, the camera cuts to...
+```
+
+For ordinary cuts, use `the camera cuts to`, `the shot cuts to`, `the shot transitions to`, `the shot changes to`, or `the shot switches to`. When explicitly requested by the user, cross-dissolve, fade, or wipe may also be used. A cut should introduce new information about the subject, space, state, viewpoint, or time. If only the distance or a slight angle needs to change, prefer camera motion.
+
+### 4.3 Camera Motion: Motion Type + Amplitude + Speed
+
+A complete camera-motion expression has three dimensions: the **motion type** defines how the camera moves, **amplitude** defines the range of compositional change, and **speed** defines the pacing of that change. Add amplitude and speed only when they are meaningful; medium amplitude and normal speed are usually omitted.
+
+| Dimension | Available Expression | Description |
+|-|-|-|
+| Motion type | `Zoom In / Zoom Out` | The focal length changes while the camera body remains stationary |
+| Motion type | `Push In / Pull Out` | The camera moves forward / backward |
+| Motion type | `Pan Left / Pan Right` | The camera remains in place while the lens pivots horizontally |
+| Motion type | `Truck Left / Truck Right` | The camera translates horizontally |
+| Motion type | `Tilt Up / Tilt Down` | The camera remains in place while the lens pivots vertically |
+| Motion type | `Pedestal Up / Pedestal Down` | The entire camera moves upward / downward |
+| Motion type | `Arc Shot` | The camera moves in an arc around the subject |
+| Motion type | `Tracking Shot` | The camera follows a moving subject |
+| Motion type | `Static Shot` | The camera position and lens remain still |
+| Motion type | `Shake Slightly / Shake Strongly` | Slight / strong camera shake |
+| Motion type | `POV` | The subject's point of view |
+| Motion type | `Roll Clockwise / Roll Counterclockwise` | The camera rolls clockwise / counterclockwise around the lens axis |
+| Amplitude | `with small amplitude` | Small-range change |
+| Amplitude | `with large amplitude` | Large-range change |
+| Speed | `at slow speed` | Slow movement |
+| Speed | `at fast speed` | Fast movement |
+
+Camera motion should be written as a natural English action within the shot, rather than stacked as separate labels at the end of a sentence:
+
+```text
+The camera pushes in with small amplitude at slow speed toward the folded letter in her hands.
+The camera pans right with large amplitude at fast speed, revealing the open doorway.
+The camera holds a static shot as the runner exits the frame.
+```
+
+### 4.4 Speakers, Dialogue, and Singing
+
+Subjects who speak, sing, or produce an off-screen human voice use stable IDs such as `(S1)` and `(S2)`. When multiple already-numbered speakers speak or sing together, use a compound ID such as `(S1,S2)`. A speaker keeps the same ID across shots; characters who never vocalize receive no speaker ID.
+
+When a speaker first appears, provide enough information from the visual and audio context to establish a stable identity, such as character type, age, gender, whether the person is on-screen, pitch, timbre, speaking rate, or accent. Place the speaker's identifying phrase, ID, action, and delivery outside `<d>`. Inside `<d>`, include only the language tag and the actual user-provided spoken content. Preserve every original word and punctuation mark verbatim; do not translate or rewrite them.
+
+```text
+The young woman with a quiet, breathy voice (S1) says: <d>[English] I get off at the next station.</d>
+The two children (S1,S2) shout together, <d>[English] Wait for us!</d>
+```
+
+For voiceover, use the exact phrase `says in an off-screen voiceover`. Immediately after every voiceover `<d>` block, state that the corresponding on-screen character's lips remain closed:
+
+```text
+The man (S1) says in an off-screen voiceover: <d>[English] I still remember that road.</d> while his lips remain completely closed.
+```
+
+When the same line of dialogue or lyrics crosses a cut, use `<scenetrans>` at the connecting points in both parts and explicitly state that the audio continues across the cut. Use `<cutoff>` when speech is truncated by the end of the video. Continuity may be expressed with `continues seamlessly across the cut`, `continues uninterrupted into the next shot`, `carries over from the previous shot`, or `remains audible across the transition`.
+
+### 4.5 On-Screen Text
+
+Place any banner, sign, label, subtitle, or neon text that is actually visible on screen in English double quotation marks. Preserve the original text and punctuation verbatim, without translation.
+
+```text
+A red neon sign reading "营业中" glows above the doorway.
+```
+
+### 4.6 overall_soundscape
+
+Use 1–4 English sentences in one continuous paragraph to summarize the ambient sound, physical action sounds, and non-verbal human sounds across the full video, such as wind, rain, traffic, footsteps, fabric movement, impacts, breathing, laughter, or panting. Dialogue, singing, and diegetic music already belong in the multimodal description and should not be repeated here. Use `N/A` only when the user explicitly requests complete silence throughout the video.
+
+```text
+overall_soundscape: Steady rain taps against the café windows while low room ambience continues underneath. The entrance bell rings once, followed by wet footsteps and the soft scrape of a chair.
+```
+
+### 4.7 non_diegetic_music
+
+Use 1–3 English sentences to describe background music that the characters cannot hear and only the audience can hear. Focus on instrumentation, speed, rhythm, and dynamic changes; do not use abstract mood words or explain the emotional function of the score. Singing, instruments, radio, television, or phone music audible to the characters are diegetic events and should appear in the multimodal description. Use `N/A` when there is no non-diegetic music.
+
+```text
+non_diegetic_music: Sparse piano notes at a slow tempo, joined by sustained low strings that gradually increase in volume before fading out.
+```
+
+## 5. Cases
+
+### Case 1: T2VA
+
+With no reference image, construct the complete timeline directly from the text. You may add scene, character, action, and sound details that remain consistent with the user's intent.
+
+```text
+integrated_multimodal_description: [Shot 1] Live-action, cinematic, a medium-wide shot frames a baker opening the shutters of a small street bakery before sunrise. The camera pushes in with small amplitude at slow speed as the middle-aged baker with a calm, slightly raspy voice (S1) places a fresh loaf on the wooden counter and says: <d>[English] First batch of the morning.</d> [Shot 2] At 00:05.000, the camera cuts to a close-up of steam rising from the sliced bread while the baker's final words carry over from the previous shot.
+
+overall_soundscape: Wooden shutters scrape open over a quiet street as trays clink softly inside the bakery. The doorbell rings once, followed by light footsteps and the crisp sound of bread being sliced.
+
+non_diegetic_music: A soft acoustic-guitar pattern at a moderate tempo, joined by sparse upright-bass notes and a gentle fade at the end.
+```
+
+### Case 2: I2VA
+
+Write the first-frame instruction first, then use the subject, composition, and scene in Picture 1 as the starting point of Shot 1 before describing how the scene continues to develop.
+
+```text
+For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
+
+integrated_multimodal_description: [Shot 1] Live-action, cinematic, the young woman shown in <Picture 1> remains beside the rain-covered train window, preserving her appearance, clothing, seat position, and the carriage layout. The camera trucks right with small amplitude at slow speed as she lifts her gaze from the folded letter toward the passing city lights. Her reflection moves across the glass while the quiet, breathy young woman (S1) says: <d>[English] I get off at the next station.</d> She folds the letter along its existing crease.
+
+overall_soundscape: The train wheels produce a steady metallic rhythm beneath a low ventilation hum. Rain ticks against the window while paper rustles softly in her hands.
+
+non_diegetic_music: Sustained cello notes at a slow tempo with widely spaced piano tones, gradually decreasing in volume.
+```
+
+### Case 3: FL2VA
+
+The two images anchor the opening and ending respectively. The body should not repeat two static image descriptions; instead, it should supply the motion path that connects them. The following example is an eight-second single shot.
+
+```text
+How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 1) aligns with the 8.00-second mark of the target video.
+
+integrated_multimodal_description: [Shot 1] Live-action, cinematic, a rain-soaked cyclist begins in the position and framing established by Picture 1, holding a closed black umbrella beside a silver bicycle. The camera pulls out with small amplitude at slow speed as she releases the bicycle handle, raises the umbrella above her shoulder, and presses the runner upward until the canopy opens. Water rolls from the expanding fabric while she steps beneath it, rotates the handle into the final angle, and settles into the pose, spacing, and composition established by Picture 2 at the end of the shot.
+
+overall_soundscape: Rain falls steadily on the pavement, followed by the metallic click of the umbrella runner and the soft snap of the canopy opening. Water drips from the bicycle frame as distant traffic passes.
+
+non_diegetic_music: N/A
+```
+
+### Case 4: L2VA
+
+The image anchors only the final moment. First establish a compatible earlier state, then let the actions, object states, and composition gradually land on Picture 1 in the final shot. The following example is a six-second single shot.
+
+```text
+How the reference pictures align with the target video — <Picture 1> (from [Shot 1]) aligns with the 6.00-second mark of the target video.
+
+integrated_multimodal_description: [Shot 1] Live-action, cinematic, a close shot begins with an intact drinking glass near the edge of a dark wooden table, while the same hand and sleeve visible in <Picture 1> approach from the right. The camera pushes in with small amplitude at slow speed as the fingertips strike the rim. The glass tips, falls, and hits the floor with a sharp impact; cracks spread through it as fragments slide outward. Toward the end, the moving pieces lose momentum and settle into the exact broken arrangement, hand position, camera angle, lighting, and final composition established by <Picture 1>.
+
+overall_soundscape: Fingertips tap the glass before it scrapes across the tabletop, falls, and breaks with a sharp crash. Small fragments scatter and gradually stop sliding across the floor.
+
+non_diegetic_music: A low electronic pulse at a slow tempo, ending immediately after the glass breaks.
+```

docs/VIDEO_PROMPT_WRITING_GUIDE_ref_en.md

@@ -0,0 +1,341 @@
+# Full-Reference Mode Rewrite Output Format Guide
+
+This guide explains how rewrite outputs are organized and written in full-reference mode.
+
+Write all six rewrite sections in English. Preserve the original language only for dialogue and lyrics inside `<d>` and for text visibly present in the scene.
+
+**Description detail:** Make `detailed_description` as detailed and explicit as possible. For each shot, clearly establish the current composition, subject appearance and position, environment and lighting, actions and state changes, camera movement, current sound, and the points where referenced content actually appears or takes effect. Avoid reducing the description to a plot summary or a list of reference relationships.
+
+> The basic formats for shots, camera movement, speakers, dialogue, and ordinary sound are shared with the Video Prompt Writing Guide (T2VA / I2VA / FL2VA / L2VA). This guide focuses on the reference labels, analysis sections, and format differences specific to full-reference mode.
+
+## 1. Overall Structure
+
+A complete rewrite output consists of six sections in the following order:
+
+| Section | Purpose |
+| --- | --- |
+| `subject_definitions` | Defines referenced content and its reference labels |
+| `summary` | Summarizes the task type, target video, and main reference relationships |
+| `retention_analysis` | Describes how referenced content is preserved, transferred, or reused |
+| `detailed_description` | Describes visuals, actions, shots, sound, and dialogue in playback order |
+| `overall_soundscape` | Summarizes ambience and physical sounds |
+| `non_diegetic_music` | Describes background music audible only to the audience |
+
+## 2. Reference Labels and Definitions (`subject_definitions`)
+
+Full-reference rewrites use four types of labels to identify the source and role of referenced content:
+
+| Label | Meaning |
+| --- | --- |
+| `<Subject N>` | Visible content abstracted from reference assets that can be reused or modified in the target video |
+| `<Picture N>` | A reference image used as a concrete target frame or shot-planning anchor |
+| `<Video N>` | A reference video that provides an editing source, continuation starting point, or whole-video temporal structure |
+| `<Audio N>` | An audio signal that is copied or referenced |
+
+> Once a reference label is assigned to a piece of content, it keeps the same meaning across `subject_definitions`, `summary`, `retention_analysis`, `detailed_description`, and the audio sections.
+
+`subject_definitions` defines each piece of referenced content that must be tracked separately later, such as a person, an environment, a source video's structure, or an audio track. Give each item its own line and explain what its label denotes, its reference role, and the main features to follow; name the corresponding source asset when its provenance needs to be made explicit. If `<Picture N>` or `<Video N>` only identifies the source of another referenced item and will not be analyzed or used separately later, cite it inside that item's definition without adding a separate line. `retention_analysis` records where each referenced item appears and whether it is fully preserved, partially preserved, transferred, or reused.
+
+### 2.1 `<Subject N>`
+
+`<Subject N>` is used for reusable visible content, including:
+
+- People, animals, or objects
+- Scenes, backgrounds, or environments
+- Clothing, props, interfaces, or visual effects
+- Styles, actions, expressions, or poses
+
+It represents a content unit that will actually be used in the target video, rather than the source file itself. One subject may be defined by multiple reference assets, and one reference asset may provide multiple subjects.
+
+```text
+<Subject 1> is the young woman in <Picture 1>, with long dark hair, a blue cardigan, and a thin silver necklace.
+```
+
+When the same subject comes from multiple assets, combine the sources and state what each asset provides:
+
+```text
+<Subject 1> is the woman whose appearance comes from <Picture 1> and whose walking motion comes from <Video 1>.
+```
+
+### 2.2 `<Picture N>`
+
+Use a standalone `<Picture N>` when the reference image itself serves as a shot's first frame, keyframe, last frame, edited keyframe, or composition anchor:
+
+```text
+<Picture 2> is the first frame of [Shot 1], showing a woman seated beside a café window.
+```
+
+If an image is used only to define a character, scene, costume, or style, do not create a standalone picture entry. Instead, cite the image source inside the corresponding `<Subject N>` definition.
+
+When an image acts as a storyboard or shot-planning reference, state which shots it maps to and what planning information it provides:
+
+```text
+<Picture 3> is a storyboard reference for [Shot 1] and [Shot 2], defining their viewpoint, subject placement, and shot order.
+```
+
+### 2.3 `<Video N>`
+
+`<Video N>` is reserved for whole-video relationships, such as:
+
+- Editing an original video
+- Continuing from the end of an original video
+- Referencing the original video's camera movement, cuts, rhythm, or temporal structure
+
+```text
+<Video 1> is the source video for the target video edit.
+```
+
+If a person, object, scene, action, or effect from a reference video is reused as visible content, it still belongs under `<Subject N>`. `<Video N>` identifies the asset or structural source and does not replace subject labels.
+
+### 2.4 `<Audio N>`
+
+`<Audio N>` represents a standalone audio asset or an enabled synchronized audio track from a reference video. Common uses include:
+
+- Copying all or part of an audio signal
+- Referencing a background-music style
+- Referencing a speaker's voice timbre and delivery
+- Using dialogue, lyrics, or sound effects from the original audio
+- Referencing beat, rhythm, or audio continuity
+
+When an `<Audio N>` explicitly corresponds to a target speaker, reuse that speaker's global ID in the definition: write `<Subject N> (Sx)` when the speaker maps to a defined subject, or use a stable voice description followed by `(Sx)` otherwise. The ID comes from the target video's global speaker order and is not independently assigned or renumbered in the audio definition. See Section 5.4 for the speaker-numbering rules:
+
+```text
+<Audio 1> is the voice-timbre reference for <Subject 1> (S1).
+```
+
+When one audio asset serves multiple roles, describe those roles in one natural sentence rather than creating additional subsections.
+
+### 2.5 Visual and Audio Tracks from the Same Reference Video
+
+`<Video N>` and `<Audio N>` are numbered independently. Each index indicates only the label's order within its own category and does not encode a pairing between the two categories. The same reference video may therefore correspond to `<Video 1>` and `<Audio 2>`; different indices do not prevent them from coming from the same source asset.
+
+An ordinary reference video does not create `<Audio N>` merely because the file contains sound.
+
+An `<Audio N>` definition primarily states the audio's role and does not have to name the `<Video N>` it comes from. State the shared source only when needed to remove provenance ambiguity, for example:
+
+```text
+<Video 1> is the source video for the target video edit.
+<Audio 2> is the synchronized audio track of <Video 1> and is reused in the target video.
+```
+
+## 3. `summary`
+
+This section uses one short English paragraph to summarize the target video and its reference relationships. It begins with a square-bracketed task-type prefix:
+
+```text
+[reference generation] ...
+[video editing + reference generation + audio reuse] ...
+```
+
+Choose task types according to the actual role each reference asset plays in the target video:
+
+| Task type | When to use it |
+| --- | --- |
+| `keyframe completion` | An image serves as the target video's first frame, keyframe, last frame, edited keyframe, or another concrete frame anchor |
+| `reference generation` | An image, video, or audio asset provides generation guidance for a character, scene, style, action, camera movement, storyboard, and so on, without serving as a concrete frame or as the source video being edited or continued |
+| `video editing` | An existing source video is directly modified; editing an image or generating between still keyframes does not belong to this type |
+| `video continuation` | New content continues, extends, resumes, or transitions from an existing source video |
+| `audio reuse` | The same audio signal is reused in full or in part |
+| `audio reference` | The audio signal is not copied directly; only its music style, timbre, dialogue or lyric content, sound-effect texture, beat, or continuity is referenced |
+
+When a task satisfies multiple relationships, combine the task types with ` + ` and do not repeat a type. For example, continuing from a source video while using an image as the last frame is written as `[video continuation + keyframe completion]`. Editing a source video while retaining its original audio may be written as `[video editing + audio reuse]`.
+
+The mere presence of video or audio does not automatically create a corresponding task type. If a reference video provides only camera movement, cuts, or rhythm, it normally belongs to `reference generation`. Use `video editing` or `video continuation` only when that video is directly edited or continued.
+
+When editing a source video, use `audio reuse` as well if its original audio remains audible. When continuing a source video without directly copying the audio signal, use `audio reference` if the new audio only continues the original track's audible characteristics.
+
+The summary uses the previously defined `<Subject N>`, `<Picture N>`, `<Video N>`, and `<Audio N>` labels to describe the main subjects, shot flow, and roles of the reference assets. Do not introduce new reference labels in this section.
+
+For video-editing tasks, begin the summary after the task-type prefix with:
+
+```text
+The target video is an edited version of <Video 1>.
+```
+
+## 4. `retention_analysis`
+
+This section describes how each piece of referenced content is preserved, transferred, copied, or referenced in the target video. Use one line for each reference label and preserve the meaning established in `subject_definitions`.
+
+### 4.1 Visible Content
+
+`<Subject N>`, `<Picture N>`, and `<Video N>` use the following relationship markers. These markers are fixed English values in the output format:
+
+| Relationship marker | Meaning |
+| --- | --- |
+| `fully_preserved` | The defined role of the referenced content is fully preserved |
+| `partially_preserved` | The referenced content is still used, but some defined characteristics are changed or only partially retained |
+| `attribute_transfer` | Referenced characteristics are transferred to a different identifiable target subject |
+| `weak_reference` | Only broad similarity in style, category, composition, or atmosphere is retained |
+
+Subject entry:
+
+```text
+<Subject 1> (appears in [Shot 1], [Shot 3]): fully_preserved - ...
+```
+
+Picture entry:
+
+```text
+<Picture 2> ([Shot 1] first frame): fully_preserved - ...
+```
+
+Video-structure entry:
+
+```text
+<Video 1> (cut and pacing structure): weak_reference - ...
+```
+
+### 4.2 Audio
+
+`<Audio N>` uses the following relationship markers:
+
+| Relationship marker | Meaning |
+| --- | --- |
+| `fully_copy` | The complete source audio serves as the target video's complete final audio track |
+| `partially_copy` | Only part of the timeline or selected audio layers are copied, or other sounds are added, removed, or replaced after copying |
+| `reference` | The signal is not copied directly; only timbre, rhythm, music style, dialogue content, or sound texture is referenced |
+| `weak_reference` | Only broad similarity in category or atmosphere is retained |
+
+```text
+<Audio 1>: fully_copy - <Audio 1> is reused 1:1 as the target video's complete final audio track.
+```
+
+```text
+<Audio 2>: reference - the target speaker follows <Audio 2>'s voice timbre and measured delivery without copying the original signal.
+```
+
+Choose each relationship marker only within the reference role already defined for that label in `subject_definitions`. Do not treat newly added actions, backgrounds, or plot events in the target video as losses of reference fidelity.
+
+## 5. `detailed_description`
+
+This is the main body of a full-reference rewrite. It describes visuals, actions, sound, and dialogue shot by shot in target-video playback order and inserts reference labels where they apply.
+
+### 5.1 Basic Format
+
+The basic format follows the Video Prompt Writing Guide (T2VA / I2VA / FL2VA / L2VA):
+
+- Write the body in English. Preserve the original language of dialogue, lyrics, and visible text.
+- `[Shot 1]` marks the opening shot and has no timestamp. Later shots use `[Shot N] At MM:SS.mmm, ...` to mark cut times.
+- Write camera movement as natural English within the current shot, including movement type, amplitude, and speed when they need to be expressed.
+- Give vocal sources stable `(S1)`, `(S2)`, and subsequent IDs. Write dialogue and lyrics as `<d>[Language] ...</d>`.
+- Use `<scenetrans>`, `<cutoff>`, and the corresponding continuity descriptions for dialogue crossing a cut, speech truncated by the video ending, and continuous audio across shots.
+
+For complete rules and examples covering camera vocabulary, group speech, voice-over, dialogue across cuts, and visible text, see the Video Prompt Writing Guide (T2VA / I2VA / FL2VA / L2VA).
+
+### 5.2 Full-Reference Mode Differences
+
+| Dimension | T2VA | Full-reference mode |
+| --- | --- | --- |
+| Main field | `integrated_multimodal_description` | `detailed_description` |
+| Style opening | Written after `[Shot 1]` | Established in one or two English sentences before `[Shot 1]` |
+| Reference information | Does not use full-reference labels | Inserts `<Subject N>`, `<Picture N>`, `<Video N>`, and `<Audio N>` at their first appearance and where their roles apply |
+| Audio relationships | Describes the target video's own sound | Cites `<Audio N>` in the corresponding shot or audio phase and states whether the signal is copied or referenced |
+
+Opening example:
+
+```text
+The target video is in a cinematic, literary music-video style with soft lighting and a slightly desaturated color palette.
+[Shot 1] The scene opens in a crowded urban street...
+[Shot 2] At 00:09.000, the shot cuts to an extreme close-up...
+```
+
+For generation tasks, `detailed_description` is normally 350-500 English words. Dialogue-dense content prioritizes fitting the complete spoken timeline rather than mechanically reaching a word count. Video-editing descriptions scale with the complexity of the source video and do not have to follow the generation-task range. A single shot does not automatically justify a shorter description; distribute detail across multiple shots according to their information load.
+
+### 5.3 Using Reference Labels in Shots
+
+At the first clear appearance of an important `<Subject N>`, describe its referenced characteristics, position in the frame, and current action within what is actually visible in the shot. Continue using the same label in later shots without redefining what the label represents.
+
+Use natural phrasing for concrete frame anchors:
+
+```text
+the shot begins from <Picture 1>
+the shot's keyframe corresponds to <Picture 2>
+the shot ends on <Picture 3>
+```
+
+When editing or continuing an original video, cite `<Video N>` naturally where its source state, structure, or continuation relationship applies. Cite `<Audio N>` in the shot or semantic phase where the audio relationship is active.
+
+### 5.4 Speakers, Audio Sources, and Dialogue
+
+The basic speaker-ID and `<d>` formats follow T2VA. When a referenced subject physically speaks, retain both the visual reference label and the speaker ID:
+
+```text
+<Subject 2> (S1) turns toward the woman and says, <d>[English] Last summer, I went to my grandfather's house. He talked about you.</d>
+```
+
+`<Subject N>` identifies the referenced subject, while `(Sx)` identifies the actual speaker. When the subject speaks, write `<Subject N> (Sx)`. If the same subject speaks off-screen, keep the same form and mark it as `off-screen`. When the speaker does not correspond to a defined subject, use a stable voice description followed by `(Sx)`.
+
+When verbal content is only a cue within a directly reused BGM or complete soundtrack, and no person, character, narrator, or other independent vocal source physically produces it, use `<Audio N>` as the audible source and do not invent an additional `(Sx)`. If a concrete person, character, narrator, or other independent vocal source produces the voice, assign and reuse `(Sx)` for that source:
+
+```text
+When <Audio 1> reaches the phrase <d>[English] I'm lonely lonely lonely lonely lonely I'm lonely</d>, <Subject 1> performs the corresponding hand gesture without becoming a separate speaker source.
+```
+
+When dialogue, narration, or lyrics from reference audio are directly reused, or when the input prompt explicitly requests their reperformance, preserve the exact source words and original language inside `<d>`. Write `[unclear]` for unintelligible spans instead of guessing or paraphrasing them. Standardize punctuation to the basic written marks needed to express the sentence, such as `,`, `.`, `?`, and `!`; remove repeated tildes, emoji, bullets, and repeated or decorative punctuation. End complete statements, questions, and exclamations with `.`, `?`, or `!` respectively before `</d>`.
+
+When only timbre, rhythm, emotion, or delivery is referenced, do not carry the original dialogue from the reference audio into the target video.
+
+Assign `(Sx)` once according to the order of actual vocal events in the target video. Reuse the corresponding ID at every actual vocal event in `detailed_description`; an `<Audio N>` definition bound to a target speaker in `subject_definitions` also reuses the same `(Sx)` but never assigns a new one independently. Do not write `(Sx)` in `retention_analysis`. Verbal cues that exist only within a directly reused BGM or complete soundtrack use `<Audio N>`; voices physically produced by a concrete person, character, narrator, or other independent vocal source use `(Sx)`.
+
+## 6. `overall_soundscape` and `non_diegetic_music`
+
+The definitions of these two sound categories follow the Video Prompt Writing Guide (T2VA / I2VA / FL2VA / L2VA).
+
+`overall_soundscape` summarizes ambience and physical sounds across the full video. Dialogue, singing, and sound events synchronized to a particular shot remain in `detailed_description`:
+
+```text
+overall_soundscape: Quiet indoor room tone and a low ventilation hum continue throughout the video.
+```
+
+`non_diegetic_music` describes background music that the characters cannot hear and that is audible only to the audience. When music is present, state its instrumentation, tempo, and dynamic development:
+
+```text
+non_diegetic_music: A restrained solo-piano score at a slow tempo, with sustained low cello underneath and no swell.
+```
+
+When reference audio is used, state its copy or reference relationship only in the section that matches the audible layer: ambience and sound effects belong in `overall_soundscape`, while audience-only score belongs in `non_diegetic_music`. If the same audio provides both kinds of content, describe the corresponding relationship in each section:
+
+```text
+overall_soundscape: The copied ambience layer from <Audio 1> continues throughout the target video.
+non_diegetic_music: <Audio 2> is directly reused as the complete audience-only score.
+```
+
+Write complete dialogue and lyrics only inside `<d>` in `detailed_description`; do not repeat them in these two sections.
+
+## 7. Complete Example
+
+<details>
+<summary>Show the complete example</summary>
+
+```text
+subject_definitions:
+<Subject 1> is the coffee-shop environment in <Picture 1>, featuring an exposed brick wall, an orange tufted sofa with patterned pillows, a neon sign, and a wooden coffee table.
+<Subject 2> is the fluffy white Samoyed in <Picture 2>, <Picture 3>, and <Picture 4>, with thick white fur, pointed ears, a dark nose, and a curved tail.
+<Subject 3> is the young blonde woman in <Video 1>, with long blonde hair and a light-pink button-down shirt with rolled-up sleeves.
+<Subject 4> is the young man in <Video 2>, with short wavy brown hair and a dark-grey hoodie with drawstrings.
+<Audio 1> is the voice-timbre reference for <Subject 3> (S1), containing a spoken English vocal layer.
+
+summary:
+[reference generation + audio reference] The target video shows <Subject 3> eating a cookie in <Subject 1>. <Subject 4> enters with <Subject 2>, which lunges toward the cookie. The three-shot exchange uses <Audio 1> as the voice-timbre reference for <Subject 3> and ends with a canned audience laugh.
+
+retention_analysis:
+<Subject 1> (appears in [Shot 1], [Shot 2], [Shot 3]): fully_preserved - the exposed brick wall, orange tufted sofa, patterned pillows, neon sign, and wooden coffee table are retained.
+<Subject 2> (appears in [Shot 1], [Shot 2]): fully_preserved - the Samoyed's thick white fur, pointed ears, dark nose, and curved tail are retained.
+<Subject 3> (appears in [Shot 1], [Shot 2], [Shot 3]): fully_preserved - the blonde woman's identity, long hair, and light-pink shirt are retained.
+<Subject 4> (appears in [Shot 1], [Shot 2]): fully_preserved - the young man's short wavy brown hair and dark-grey hoodie are retained.
+<Audio 1>: reference - its vocal timbre guides the dialogue delivery of <Subject 3> without copying the original signal.
+
+detailed_description:
+The target video uses a realistic multi-camera sitcom style with warm indoor lighting.
+[Shot 1] A medium shot establishes <Subject 1>, the coffee shop with its exposed brick wall, orange tufted sofa, patterned pillows, neon sign, and wooden coffee table. <Subject 3> (S1), the young woman with long blonde hair and a light-pink button-down shirt with rolled-up sleeves, sits on the sofa holding a chocolate-chip cookie. From the left, <Subject 4>, the young man with short wavy brown hair and a dark-grey hoodie with drawstrings, enters holding the leash of <Subject 2>, the thick-furred white Samoyed with pointed ears, a dark nose, and a curved tail. The dog lunges toward the cookie and pulls the leash taut. <Subject 3> (S1) jerks her hand back and, using the clear youthful voice timbre referenced from <Audio 1>, exclaims with light annoyance, <d>[English] Hey! Watch your dog!</d> She closes her lips and guards the cookie while <Subject 4> pulls the dog back.
+[Shot 2] At 00:03.000, the shot cuts to a close-up of <Subject 4> (S2), the young man in the dark-grey hoodie from Shot 1, sitting beside <Subject 3> on the sofa and holding <Subject 2> securely in his arms. <Subject 4> (S2) says in a casual young male voice with a playful tone and an easy conversational pace, <d>[English] He just likes cookies more than me.</d> He closes his mouth into an apologetic smile and strokes the dog's thick white fur.
+[Shot 3] At 00:05.000, the shot cuts to a close-up of <Subject 3> (S1), the blonde woman in the light-pink shirt from Shot 1. Her annoyance softens as she looks toward the Samoyed. <Subject 3> (S1) replies in the same clear youthful voice referenced from <Audio 1> with an amused cadence, <d>[English] Well, he has good taste at least.</d> She smiles and raises the cookie in a small toast-like gesture. A classic canned audience laugh begins immediately after the line and continues through the final frame.
+
+overall_soundscape:
+Soft indoor coffee-shop room tone continues throughout the scene.
+
+non_diegetic_music:
+N/A
+```
+
+</details>

model_index.json

@@ -0,0 +1,131 @@
+{
+  "_class_name": "MiniMaxH3ModularPipeline",
+  "_diffusers_version": "0.36.0.dev0",
+  "_blocks_class_name": "MiniMaxH3Blocks",
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLForConditionalGeneration",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen3VLForConditionalGeneration"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "text_encoder",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2TokenizerFast",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen2TokenizerFast"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "tokenizer",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "processor": [
+    "transformers",
+    "Qwen3VLProcessor",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen3VLProcessor"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "processor",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLMiniMaxH3",
+    {
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLMiniMaxH3"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "vae",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "audio_vae": [
+    "diffusers",
+    "AutoencoderKLMiniMaxH3Audio",
+    {
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLMiniMaxH3Audio"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "audio_vae",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "transformer": [
+    "diffusers",
+    "MiniMaxH3Transformer3DModel",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Transformer3DModel"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "transformer",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "transformer_ref": [
+    "diffusers",
+    "MiniMaxH3Transformer3DModel",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Transformer3DModel"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "transformer_ref",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "scheduler": [
+    "diffusers",
+    "MiniMaxH3Scheduler",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Scheduler"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "scheduler",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "audio_scheduler": [
+    "diffusers",
+    "MiniMaxH3Scheduler",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Scheduler"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "audio_scheduler",
+      "variant": null,
+      "revision": null
+    }
+  ]
+}

modular_model_index.json

@@ -0,0 +1,131 @@
+{
+  "_class_name": "MiniMaxH3ModularPipeline",
+  "_diffusers_version": "0.36.0.dev0",
+  "_blocks_class_name": "MiniMaxH3Blocks",
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLForConditionalGeneration",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen3VLForConditionalGeneration"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "text_encoder",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2TokenizerFast",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen2TokenizerFast"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "tokenizer",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "processor": [
+    "transformers",
+    "Qwen3VLProcessor",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen3VLProcessor"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "processor",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLMiniMaxH3",
+    {
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLMiniMaxH3"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "vae",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "audio_vae": [
+    "diffusers",
+    "AutoencoderKLMiniMaxH3Audio",
+    {
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLMiniMaxH3Audio"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "audio_vae",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "transformer": [
+    "diffusers",
+    "MiniMaxH3Transformer3DModel",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Transformer3DModel"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "transformer",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "transformer_ref": [
+    "diffusers",
+    "MiniMaxH3Transformer3DModel",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Transformer3DModel"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "transformer_ref",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "scheduler": [
+    "diffusers",
+    "MiniMaxH3Scheduler",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Scheduler"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "scheduler",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "audio_scheduler": [
+    "diffusers",
+    "MiniMaxH3Scheduler",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Scheduler"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "audio_scheduler",
+      "variant": null,
+      "revision": null
+    }
+  ]
+}

processor/chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}

processor/preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

processor/tokenizer_config.json

@@ -0,0 +1,246 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<d>",
+    "</d>",
+    "<|cutoff|>",
+    "<|lyrics_start|>",
+    "<|lyrics_end|>",
+    "<|caption_start|>",
+    "<|caption_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

processor/video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}

scheduler/scheduler_config.json

@@ -0,0 +1,5 @@
+{
+  "_class_name": "MiniMaxH3Scheduler",
+  "_diffusers_version": "0.36.0.dev0",
+  "shift": 12.0
+}

scripts/readme/full-2k-i2va-h3-base.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Create the H3-Base request with the expanded prompt and capture the video ID.
+video_id=$(
+  jq -n \
+    --arg prompt "$EXPANDED_PROMPT" \
+    '{
+  "task": "fl2va",
+  "prompt": $prompt,
+  "conditions": [
+    {
+      "type": "image",
+      "uri": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/H3_AA_I2VA/gallery/sr_v17_variants_seed42_43_20260724/inputs/4a3a90bf9100_KDmcbkhzYo5sjjxr9FqcVmWVnzb.png",
+      "role": "keyframe",
+      "frame_index": 0
+    }
+  ],
+  "target": {
+    "short_edge": 768,
+    "aspect_ratio": "auto",
+    "duration_seconds": 8
+  },
+  "seed": 0
+}' |
+    curl --silent --show-error \
+      --request POST \
+      --url "$SGLANG_DEPLOYMENT_URL/v1/videos" \
+      --header 'Content-Type: application/json' \
+      --data-binary @- |
+    jq -er '.id'
+)
+# Query the generation status.
+curl --silent --show-error \
+  --request GET \
+  --url "$SGLANG_DEPLOYMENT_URL/v1/videos/$video_id" |
+  jq '{status}'
+# Download the local H3-Base MP4 after its status becomes completed.
+curl --silent --show-error \
+  --request GET \
+  --url "$SGLANG_DEPLOYMENT_URL/v1/videos/$video_id/content" \
+  --output i2va.mp4

scripts/readme/full-2k-i2va-h3-context-ir.sh

@@ -0,0 +1,40 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Create the prompt-expansion task and capture its runtime ID.
+task_id=$(
+  curl --silent --show-error \
+    --request POST \
+    --url "$MINIMAX_API_BASE/v2/h3_context_ir" \
+    --header "Authorization: Bearer $TOKEN" \
+    --header 'Content-Type: application/json' \
+    --data '{
+  "model": "MiniMax-H3",
+  "content": [
+    {
+      "type": "text",
+      "text": "Pull focus to the people in the background and add more steam to the ramen bowl."
+    },
+    {
+      "type": "image_url",
+      "image_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/H3_AA_I2VA/gallery/sr_v17_variants_seed42_43_20260724/inputs/4a3a90bf9100_KDmcbkhzYo5sjjxr9FqcVmWVnzb.png"
+      },
+      "role": "first_frame"
+    }
+  ],
+  "duration": 8,
+  "ratio": "adaptive"
+}' |
+    jq -er '.task_id'
+)
+# Query again while the task is queued or running.
+context_ir_result=$(
+  curl --silent --show-error \
+    --request GET \
+    --url "$MINIMAX_API_BASE/v2/query/video_generation/$task_id" \
+    --header "Authorization: Bearer $TOKEN"
+)
+echo "$context_ir_result" | jq .
+# Export the complete expanded prompt for H3-Base and regeneration.
+EXPANDED_PROMPT=$(echo "$context_ir_result" | jq -er '.task.content.prompt')

scripts/readme/full-2k-i2va-h3-regenerate-2k.sh

@@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+H3_BASE_VIDEO='./i2va.mp4'
+# Encode the local H3-Base video as a Data URL and create the regeneration task.
+task_id=$(
+  jq -n \
+    --arg prompt "$EXPANDED_PROMPT" \
+    --rawfile base_video <(
+      printf 'data:video/mp4;base64,'
+      base64 -w0 "$H3_BASE_VIDEO"
+    ) \
+    '{
+  "model": "MiniMax-H3",
+  "content": [
+    {
+      "type": "text",
+      "text": $prompt
+    },
+    {
+      "type": "image_url",
+      "image_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/H3_AA_I2VA/gallery/sr_v17_variants_seed42_43_20260724/inputs/4a3a90bf9100_KDmcbkhzYo5sjjxr9FqcVmWVnzb.png"
+      },
+      "role": "first_frame"
+    },
+    {
+      "type": "video_url",
+      "video_url": {
+        "url": $base_video
+      },
+      "role": "base_video"
+    }
+  ],
+  "resolution": "2K"
+}' |
+    curl --silent --show-error \
+      --request POST \
+      --url "$MINIMAX_API_BASE/v2/video_regeneration" \
+      --header "Authorization: Bearer $TOKEN" \
+      --header 'Content-Type: application/json' \
+      --data-binary @- |
+    jq -er '.task_id'
+)
+# Query again while the task is queued or running.
+regeneration_result=$(
+  curl --silent --show-error \
+    --request GET \
+    --url "$MINIMAX_API_BASE/v2/query/video_generation/$task_id" \
+    --header "Authorization: Bearer $TOKEN"
+)
+echo "$regeneration_result" | jq '{status: .task.status}'
+# Download the 2K MP4 after the task succeeds.
+video_url=$(echo "$regeneration_result" | jq -er '.task.content.url')
+curl --location "$video_url" --output i2va_2k.mp4

scripts/readme/full-2k-i2va-reference-2k-result-by-directly-calling-open-platform-api.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Create an 8-second 2K FL2VA video directly and capture its runtime task ID.
+task_id=$(
+  curl --silent --show-error \
+    --request POST \
+    --url "$MINIMAX_API_BASE/v2/video_generation" \
+    --header "Authorization: Bearer $TOKEN" \
+    --header 'Content-Type: application/json' \
+    --data '{
+  "model": "MiniMax-H3",
+  "content": [
+    {
+      "type": "text",
+      "text": "Pull focus to the people in the background and add more steam to the ramen bowl."
+    },
+    {
+      "type": "image_url",
+      "image_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/H3_AA_I2VA/gallery/sr_v17_variants_seed42_43_20260724/inputs/4a3a90bf9100_KDmcbkhzYo5sjjxr9FqcVmWVnzb.png"
+      },
+      "role": "first_frame"
+    }
+  ],
+  "resolution": "2K",
+  "duration": 8,
+  "ratio": "adaptive"
+}' |
+    jq -er '.task_id'
+)
+# Query again while the task is queued or running.
+generation_result=$(
+  curl --silent --show-error \
+    --request GET \
+    --url "$MINIMAX_API_BASE/v2/query/video_generation/$task_id" \
+    --header "Authorization: Bearer $TOKEN"
+)
+echo "$generation_result" | jq '{status: .task.status}'
+# Download the 2K MP4 after the task succeeds.
+video_url=$(echo "$generation_result" | jq -er '.task.content.url')
+curl --location "$video_url" --output i2va_direct_2k.mp4

scripts/readme/full-2k-i2va-reference-768p-result-by-directly-calling-open-platform-api.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Create an 8-second 768P FL2VA video directly and capture its runtime task ID.
+task_id=$(
+  curl --silent --show-error \
+    --request POST \
+    --url "$MINIMAX_API_BASE/v2/video_generation" \
+    --header "Authorization: Bearer $TOKEN" \
+    --header 'Content-Type: application/json' \
+    --data '{
+  "model": "MiniMax-H3",
+  "content": [
+    {
+      "type": "text",
+      "text": "Pull focus to the people in the background and add more steam to the ramen bowl."
+    },
+    {
+      "type": "image_url",
+      "image_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/H3_AA_I2VA/gallery/sr_v17_variants_seed42_43_20260724/inputs/4a3a90bf9100_KDmcbkhzYo5sjjxr9FqcVmWVnzb.png"
+      },
+      "role": "first_frame"
+    }
+  ],
+  "resolution": "768P",
+  "duration": 8,
+  "ratio": "adaptive"
+}' |
+    jq -er '.task_id'
+)
+# Query again while the task is queued or running.
+generation_result=$(
+  curl --silent --show-error \
+    --request GET \
+    --url "$MINIMAX_API_BASE/v2/query/video_generation/$task_id" \
+    --header "Authorization: Bearer $TOKEN"
+)
+echo "$generation_result" | jq '{status: .task.status}'
+# Download the 768P MP4 after the task succeeds.
+video_url=$(echo "$generation_result" | jq -er '.task.content.url')
+curl --location "$video_url" --output i2va_direct_768p.mp4

scripts/readme/full-2k-ref2va-h3-api-2k-in-open-platform-for-reference.sh

@@ -0,0 +1,49 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Create a 5-second 2K Ref2VA video directly and capture its runtime task ID.
+task_id=$(
+  curl --silent --show-error \
+    --request POST \
+    --url "$MINIMAX_API_BASE/v2/video_generation" \
+    --header "Authorization: Bearer $TOKEN" \
+    --header 'Content-Type: application/json' \
+    --data '{
+  "model": "MiniMax-H3",
+  "content": [
+    {
+      "type": "text",
+      "text": "Character speaks: Follow the wind, live free. Leave worries behind, enjoy the moment. Voice timbre follows reference audio 1."
+    },
+    {
+      "type": "video_url",
+      "video_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/297573323635_00_%E8%A7%86%E9%A2%911_YnyRbxEwio_video_20260525_163755_1927e9d3.mp4"
+      },
+      "role": "reference_video"
+    },
+    {
+      "type": "audio_url",
+      "audio_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/f463d523c5ce_01_%E9%9F%B3%E9%A2%911_RSLcbpzJPo_6%E6%9C%885%E6%97%A5(1).mp3"
+      },
+      "role": "reference_audio"
+    }
+  ],
+  "resolution": "2K",
+  "duration": 5,
+  "ratio": "adaptive"
+}' |
+    jq -er '.task_id'
+)
+# Query again while the task is queued or running.
+generation_result=$(
+  curl --silent --show-error \
+    --request GET \
+    --url "$MINIMAX_API_BASE/v2/query/video_generation/$task_id" \
+    --header "Authorization: Bearer $TOKEN"
+)
+echo "$generation_result" | jq '{status: .task.status}'
+# Download the 2K MP4 after the task succeeds.
+video_url=$(echo "$generation_result" | jq -er '.task.content.url')
+curl --location "$video_url" --output r2va_direct_2k.mp4

scripts/readme/full-2k-ref2va-h3-base.sh

@@ -0,0 +1,46 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Create the H3-Base request with the expanded prompt and capture the video ID.
+video_id=$(
+  jq -n \
+    --arg prompt "$EXPANDED_PROMPT" \
+    '{
+  "task": "ref2va",
+  "prompt": $prompt,
+  "conditions": [
+    {
+      "type": "video",
+      "uri": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/297573323635_00_%E8%A7%86%E9%A2%911_YnyRbxEwio_video_20260525_163755_1927e9d3.mp4",
+      "role": "reference"
+    },
+    {
+      "type": "audio",
+      "uri": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/f463d523c5ce_01_%E9%9F%B3%E9%A2%911_RSLcbpzJPo_6%E6%9C%885%E6%97%A5(1).mp3",
+      "role": "reference"
+    }
+  ],
+  "target": {
+    "short_edge": 768,
+    "aspect_ratio": "auto",
+    "duration_seconds": 5
+  },
+  "seed": 0
+}' |
+    curl --silent --show-error \
+      --request POST \
+      --url "$SGLANG_DEPLOYMENT_URL/v1/videos" \
+      --header 'Content-Type: application/json' \
+      --data-binary @- |
+    jq -er '.id'
+)
+# Query the generation status.
+curl --silent --show-error \
+  --request GET \
+  --url "$SGLANG_DEPLOYMENT_URL/v1/videos/$video_id" |
+  jq '{status}'
+# Download the local H3-Base MP4 after its status becomes completed.
+curl --silent --show-error \
+  --request GET \
+  --url "$SGLANG_DEPLOYMENT_URL/v1/videos/$video_id/content" \
+  --output r2va.mp4

scripts/readme/full-2k-ref2va-h3-context-ir.sh

@@ -0,0 +1,47 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Create the prompt-expansion task and capture its runtime ID.
+task_id=$(
+  curl --silent --show-error \
+    --request POST \
+    --url "$MINIMAX_API_BASE/v2/h3_context_ir" \
+    --header "Authorization: Bearer $TOKEN" \
+    --header 'Content-Type: application/json' \
+    --data '{
+  "model": "MiniMax-H3",
+  "content": [
+    {
+      "type": "text",
+      "text": "Character speaks: Follow the wind, live free. Leave worries behind, enjoy the moment. Voice timbre follows reference audio 1."
+    },
+    {
+      "type": "video_url",
+      "video_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/297573323635_00_%E8%A7%86%E9%A2%911_YnyRbxEwio_video_20260525_163755_1927e9d3.mp4"
+      },
+      "role": "reference_video"
+    },
+    {
+      "type": "audio_url",
+      "audio_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/f463d523c5ce_01_%E9%9F%B3%E9%A2%911_RSLcbpzJPo_6%E6%9C%885%E6%97%A5(1).mp3"
+      },
+      "role": "reference_audio"
+    }
+  ],
+  "duration": 5,
+  "ratio": "adaptive"
+}' |
+    jq -er '.task_id'
+)
+# Query again while the task is queued or running.
+context_ir_result=$(
+  curl --silent --show-error \
+    --request GET \
+    --url "$MINIMAX_API_BASE/v2/query/video_generation/$task_id" \
+    --header "Authorization: Bearer $TOKEN"
+)
+echo "$context_ir_result" | jq .
+# Export the complete expanded prompt for H3-Base and regeneration.
+EXPANDED_PROMPT=$(echo "$context_ir_result" | jq -er '.task.content.prompt')

scripts/readme/full-2k-ref2va-reference-2k-result-by-directly-calling-open-platform-api.sh

@@ -0,0 +1,62 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+H3_BASE_VIDEO='./r2va.mp4'
+# Encode the local H3-Base video as a Data URL and create the regeneration task.
+task_id=$(
+  jq -n \
+    --arg prompt "$EXPANDED_PROMPT" \
+    --rawfile base_video <(
+      printf 'data:video/mp4;base64,'
+      base64 -w0 "$H3_BASE_VIDEO"
+    ) \
+    '{
+  "model": "MiniMax-H3",
+  "content": [
+    {
+      "type": "text",
+      "text": $prompt
+    },
+    {
+      "type": "video_url",
+      "video_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/297573323635_00_%E8%A7%86%E9%A2%911_YnyRbxEwio_video_20260525_163755_1927e9d3.mp4"
+      },
+      "role": "reference_video"
+    },
+    {
+      "type": "audio_url",
+      "audio_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/f463d523c5ce_01_%E9%9F%B3%E9%A2%911_RSLcbpzJPo_6%E6%9C%885%E6%97%A5(1).mp3"
+      },
+      "role": "reference_audio"
+    },
+    {
+      "type": "video_url",
+      "video_url": {
+        "url": $base_video
+      },
+      "role": "base_video"
+    }
+  ],
+  "resolution": "2K"
+}' |
+    curl --silent --show-error \
+      --request POST \
+      --url "$MINIMAX_API_BASE/v2/video_regeneration" \
+      --header "Authorization: Bearer $TOKEN" \
+      --header 'Content-Type: application/json' \
+      --data-binary @- |
+    jq -er '.task_id'
+)
+# Query again while the task is queued or running.
+regeneration_result=$(
+  curl --silent --show-error \
+    --request GET \
+    --url "$MINIMAX_API_BASE/v2/query/video_generation/$task_id" \
+    --header "Authorization: Bearer $TOKEN"
+)
+echo "$regeneration_result" | jq '{status: .task.status}'
+# Download the 2K MP4 after the task succeeds.
+video_url=$(echo "$regeneration_result" | jq -er '.task.content.url')
+curl --location "$video_url" --output r2va_2k.mp4

scripts/readme/full-2k-ref2va-reference-768p-result-by-directly-calling-open-platform-api.sh

@@ -0,0 +1,49 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Create a 5-second 768P Ref2VA video directly and capture its runtime task ID.
+task_id=$(
+  curl --silent --show-error \
+    --request POST \
+    --url "$MINIMAX_API_BASE/v2/video_generation" \
+    --header "Authorization: Bearer $TOKEN" \
+    --header 'Content-Type: application/json' \
+    --data '{
+  "model": "MiniMax-H3",
+  "content": [
+    {
+      "type": "text",
+      "text": "Character speaks: Follow the wind, live free. Leave worries behind, enjoy the moment. Voice timbre follows reference audio 1."
+    },
+    {
+      "type": "video_url",
+      "video_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/297573323635_00_%E8%A7%86%E9%A2%911_YnyRbxEwio_video_20260525_163755_1927e9d3.mp4"
+      },
+      "role": "reference_video"
+    },
+    {
+      "type": "audio_url",
+      "audio_url": {
+        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/h3_promo_eval_ref2va/gallery/sr_v2p26_trio_seed42_20260724/inputs/f463d523c5ce_01_%E9%9F%B3%E9%A2%911_RSLcbpzJPo_6%E6%9C%885%E6%97%A5(1).mp3"
+      },
+      "role": "reference_audio"
+    }
+  ],
+  "resolution": "768P",
+  "duration": 5,
+  "ratio": "adaptive"
+}' |
+    jq -er '.task_id'
+)
+# Query again while the task is queued or running.
+generation_result=$(
+  curl --silent --show-error \
+    --request GET \
+    --url "$MINIMAX_API_BASE/v2/query/video_generation/$task_id" \
+    --header "Authorization: Bearer $TOKEN"
+)
+echo "$generation_result" | jq '{status: .task.status}'
+# Download the 768P MP4 after the task succeeds.
+video_url=$(echo "$generation_result" | jq -er '.task.content.url')
+curl --location "$video_url" --output r2va_direct_768p.mp4

scripts/readme/full-2k-t2va-h3-base.sh

@@ -0,0 +1,35 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Create the H3-Base request with the expanded prompt and capture the video ID.
+video_id=$(
+  jq -n \
+    --arg prompt "$EXPANDED_PROMPT" \
+    '{
+  "task": "t2va",
+  "prompt": $prompt,
+  "conditions": [],
+  "target": {
+    "short_edge": 768,
+    "aspect_ratio": "16:9",
+    "duration_seconds": 10
+  },
+  "seed": 0
+}' |
+    curl --silent --show-error \
+      --request POST \
+      --url "$SGLANG_DEPLOYMENT_URL/v1/videos" \
+      --header 'Content-Type: application/json' \
+      --data-binary @- |
+    jq -er '.id'
+)
+# Query the generation status.
+curl --silent --show-error \
+  --request GET \
+  --url "$SGLANG_DEPLOYMENT_URL/v1/videos/$video_id" |
+  jq '{status}'
+# Download the local H3-Base MP4 after its status becomes completed.
+curl --silent --show-error \
+  --request GET \
+  --url "$SGLANG_DEPLOYMENT_URL/v1/videos/$video_id/content" \
+  --output t2va.mp4

text_encoder/chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}

text_encoder/config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 25600,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

text_encoder/model.safetensors.index.json

@@ -0,0 +1,1065 @@
+{
+  "metadata": {
+    "total_size": 66714780128
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.38.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.43.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.48.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.53.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.58.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.language_model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.language_model.layers.63.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.merger.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.merger.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.pos_embed.weight": "model-00014-of-00014.safetensors"
+  }
+}

text_encoder/preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

text_encoder/tokenizer_config.json

@@ -0,0 +1,246 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<d>",
+    "</d>",
+    "<|cutoff|>",
+    "<|lyrics_start|>",
+    "<|lyrics_end|>",
+    "<|caption_start|>",
+    "<|caption_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

text_encoder/video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,246 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<d>",
+    "</d>",
+    "<|cutoff|>",
+    "<|lyrics_start|>",
+    "<|lyrics_end|>",
+    "<|caption_start|>",
+    "<|caption_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,26 @@
+{
+  "_class_name": "MiniMaxH3Transformer3DModel",
+  "_diffusers_version": "0.36.0.dev0",
+  "num_attention_heads": 56,
+  "attention_head_dim": 128,
+  "hidden_size": 5376,
+  "num_layers": 50,
+  "num_refiner_layers": 2,
+  "ffn_dim": 14336,
+  "in_channels": 24,
+  "audio_in_channels": 32,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "text_dim": 5120,
+  "freq_dim": 256,
+  "time_embed_hidden_dim": 5376,
+  "time_embed_dim": 2688,
+  "rope_freq_dim": 16,
+  "rope_theta": 10000.0,
+  "norm_eps": 1e-05,
+  "qk_norm_eps": 1e-05,
+  "final_norm_eps": 1e-05
+}

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,645 @@
+{
+  "metadata": {
+    "total_size": 66280430080
+  },
+  "weight_map": {
+    "proj_in.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "proj_in.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "audio_proj_in.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "audio_proj_in.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "context_embedder.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "context_embedder.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.final_norm.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "norm_out.norm.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "norm_out.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "norm_out.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "proj_out.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "audio_proj_out.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "audio_proj_out.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.3.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.7.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.7.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.11.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.11.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.norm1.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.norm2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.norm1.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.norm2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.norm1.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.norm2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.14.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.norm1.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.norm2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.norm1.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.norm2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.norm1.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.norm2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.norm1.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.norm2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.18.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.18.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.18.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.22.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.22.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.ff.net.2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.adaln_proj.linear.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.adaln_proj.linear.bias": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.norm1.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.norm2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.ff.net.2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.adaln_proj.linear.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.adaln_proj.linear.bias": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.norm1.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.norm2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.ff.net.0.proj.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.ff.net.2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.adaln_proj.linear.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.adaln_proj.linear.bias": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.norm1.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.norm2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.ff.net.0.proj.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.ff.net.2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.25.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.ff.net.0.proj.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.ff.net.2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_out.0.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_out.0.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.ff.net.0.proj.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.ff.net.2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_out.0.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.ff.net.0.proj.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.ff.net.2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_out.0.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.ff.net.0.proj.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.29.ff.net.2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.29.adaln_proj.linear.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.29.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.ff.net.0.proj.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.ff.net.2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.adaln_proj.linear.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_out.0.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_out.0.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.ff.net.0.proj.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.ff.net.2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.adaln_proj.linear.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_out.0.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.ff.net.0.proj.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.ff.net.2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.adaln_proj.linear.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.33.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.33.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.ff.net.0.proj.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.ff.net.2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.adaln_proj.linear.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.adaln_proj.linear.bias": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.norm1.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.norm2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.ff.net.0.proj.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.ff.net.2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.adaln_proj.linear.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.adaln_proj.linear.bias": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.norm1.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.norm2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.ff.net.0.proj.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.ff.net.2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.adaln_proj.linear.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.adaln_proj.linear.bias": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.norm1.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.norm2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.ff.net.0.proj.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.ff.net.2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.36.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.ff.net.0.proj.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.ff.net.2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.ff.net.0.proj.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.ff.net.2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.ff.net.0.proj.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.ff.net.2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.ff.net.0.proj.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.40.ff.net.2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.40.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.40.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_out.0.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.ff.net.0.proj.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.ff.net.2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.ff.net.0.proj.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.ff.net.2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_out.0.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_out.0.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.ff.net.0.proj.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.ff.net.2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.44.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.44.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_out.0.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.ff.net.0.proj.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.ff.net.2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.adaln_proj.linear.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.adaln_proj.linear.bias": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.norm1.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.norm2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_out.0.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.ff.net.0.proj.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.ff.net.2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.adaln_proj.linear.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.adaln_proj.linear.bias": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.norm1.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.norm2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.ff.net.0.proj.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.ff.net.2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.adaln_proj.linear.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.adaln_proj.linear.bias": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_out.0.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.norm1.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.norm2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_out.0.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.ff.net.0.proj.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.ff.net.2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.norm1.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.norm2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.norm1.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.norm2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.47.adaln_proj.linear.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.47.adaln_proj.linear.bias": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.norm1.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.norm2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_v.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.norm_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.norm_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_out.0.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.ff.net.0.proj.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.ff.net.2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.adaln_proj.linear.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.adaln_proj.linear.bias": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.norm1.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.norm2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_v.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.norm_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.norm_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_out.0.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.ff.net.0.proj.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.ff.net.2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.adaln_proj.linear.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.adaln_proj.linear.bias": "diffusion_pytorch_model-00014-of-00014.safetensors"
+  }
+}

transformer_ref/config.json

@@ -0,0 +1,26 @@
+{
+  "_class_name": "MiniMaxH3Transformer3DModel",
+  "_diffusers_version": "0.36.0.dev0",
+  "num_attention_heads": 56,
+  "attention_head_dim": 128,
+  "hidden_size": 5376,
+  "num_layers": 50,
+  "num_refiner_layers": 2,
+  "ffn_dim": 14336,
+  "in_channels": 24,
+  "audio_in_channels": 32,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "text_dim": 5120,
+  "freq_dim": 256,
+  "time_embed_hidden_dim": 5376,
+  "time_embed_dim": 2688,
+  "rope_freq_dim": 16,
+  "rope_theta": 10000.0,
+  "norm_eps": 1e-05,
+  "qk_norm_eps": 1e-05,
+  "final_norm_eps": 1e-05
+}

transformer_ref/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,645 @@
+{
+  "metadata": {
+    "total_size": 66280430080
+  },
+  "weight_map": {
+    "proj_in.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "proj_in.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "audio_proj_in.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "audio_proj_in.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "context_embedder.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "context_embedder.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "time_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "token_refiner.final_norm.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.0.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.1.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.adaln_proj.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.norm1.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.norm2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "norm_out.norm.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "norm_out.linear.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "norm_out.linear.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "proj_out.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "audio_proj_out.weight": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "audio_proj_out.bias": "diffusion_pytorch_model-00001-of-00014.safetensors",
+    "transformer_blocks.3.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.3.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.4.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.5.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.adaln_proj.linear.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.norm1.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.norm2.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00014.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.7.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.7.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.8.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.9.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.adaln_proj.linear.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.11.norm1.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.11.norm2.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.11.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.norm1.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.norm2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.12.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.norm1.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.norm2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.adaln_proj.linear.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.13.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.norm1.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.norm2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model-00004-of-00014.safetensors",
+    "transformer_blocks.14.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.14.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.norm1.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.norm2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.15.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.norm1.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.norm2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.16.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.norm1.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.norm2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.adaln_proj.linear.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.17.adaln_proj.linear.bias": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.norm1.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.norm2.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model-00005-of-00014.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.18.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.18.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.18.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.19.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.20.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.adaln_proj.linear.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.21.adaln_proj.linear.bias": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.22.norm1.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.22.norm2.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00006-of-00014.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.ff.net.2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.adaln_proj.linear.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.adaln_proj.linear.bias": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.norm1.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.norm2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.ff.net.2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.adaln_proj.linear.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.23.adaln_proj.linear.bias": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.norm1.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.norm2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.ff.net.0.proj.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.ff.net.2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.adaln_proj.linear.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.24.adaln_proj.linear.bias": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.norm1.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.norm2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_v.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.attn.to_out.0.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.ff.net.0.proj.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.ff.net.2.weight": "diffusion_pytorch_model-00007-of-00014.safetensors",
+    "transformer_blocks.25.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.25.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.ff.net.0.proj.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.ff.net.2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.26.attn.to_out.0.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.attn.to_out.0.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.ff.net.0.proj.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.ff.net.2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.27.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.attn.to_out.0.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.ff.net.0.proj.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.ff.net.2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.adaln_proj.linear.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.28.adaln_proj.linear.bias": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.norm1.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.norm2.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_v.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.attn.to_out.0.weight": "diffusion_pytorch_model-00008-of-00014.safetensors",
+    "transformer_blocks.29.ff.net.0.proj.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.29.ff.net.2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.29.adaln_proj.linear.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.29.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.ff.net.0.proj.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.ff.net.2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.adaln_proj.linear.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.30.attn.to_out.0.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.attn.to_out.0.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.ff.net.0.proj.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.ff.net.2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.adaln_proj.linear.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.31.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_v.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.norm_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.norm_k.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.attn.to_out.0.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.ff.net.0.proj.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.ff.net.2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.adaln_proj.linear.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.32.adaln_proj.linear.bias": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.33.norm1.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.33.norm2.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_q.weight": "diffusion_pytorch_model-00009-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.ff.net.0.proj.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.ff.net.2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.adaln_proj.linear.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.33.adaln_proj.linear.bias": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.norm1.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.norm2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.ff.net.0.proj.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.ff.net.2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.adaln_proj.linear.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.adaln_proj.linear.bias": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.34.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.norm1.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.norm2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.ff.net.0.proj.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.ff.net.2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.adaln_proj.linear.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.35.adaln_proj.linear.bias": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.norm1.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.norm2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_v.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.norm_q.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.norm_k.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.attn.to_out.0.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.ff.net.0.proj.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.ff.net.2.weight": "diffusion_pytorch_model-00010-of-00014.safetensors",
+    "transformer_blocks.36.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.36.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.ff.net.0.proj.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.ff.net.2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.37.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.ff.net.0.proj.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.ff.net.2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.38.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.ff.net.0.proj.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.ff.net.2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.adaln_proj.linear.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.39.adaln_proj.linear.bias": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.norm1.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.norm2.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_v.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.norm_q.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.norm_k.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.attn.to_out.0.weight": "diffusion_pytorch_model-00011-of-00014.safetensors",
+    "transformer_blocks.40.ff.net.0.proj.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.40.ff.net.2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.40.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.40.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.attn.to_out.0.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.ff.net.0.proj.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.ff.net.2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.41.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.ff.net.0.proj.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.ff.net.2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.42.attn.to_out.0.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_v.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.norm_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.norm_k.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.attn.to_out.0.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.ff.net.0.proj.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.ff.net.2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.adaln_proj.linear.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.43.adaln_proj.linear.bias": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.44.norm1.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.44.norm2.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_q.weight": "diffusion_pytorch_model-00012-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.attn.to_out.0.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.ff.net.0.proj.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.ff.net.2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.adaln_proj.linear.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.44.adaln_proj.linear.bias": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.norm1.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.norm2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.attn.to_out.0.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.ff.net.0.proj.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.ff.net.2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.adaln_proj.linear.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.45.adaln_proj.linear.bias": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.norm1.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.norm2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.ff.net.0.proj.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.ff.net.2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.adaln_proj.linear.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.adaln_proj.linear.bias": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.46.attn.to_out.0.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.norm1.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.norm2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_v.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.norm_q.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.norm_k.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.attn.to_out.0.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.ff.net.0.proj.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "transformer_blocks.47.ff.net.2.weight": "diffusion_pytorch_model-00013-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.norm1.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.norm2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.norm1.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.norm2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "token_refiner.refiner_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.47.adaln_proj.linear.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.47.adaln_proj.linear.bias": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.norm1.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.norm2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_v.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.norm_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.norm_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.attn.to_out.0.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.ff.net.0.proj.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.ff.net.2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.adaln_proj.linear.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.48.adaln_proj.linear.bias": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.norm1.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.norm2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_v.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.norm_q.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.norm_k.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.attn.to_out.0.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.ff.net.0.proj.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.ff.net.2.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.adaln_proj.linear.weight": "diffusion_pytorch_model-00014-of-00014.safetensors",
+    "transformer_blocks.49.adaln_proj.linear.bias": "diffusion_pytorch_model-00014-of-00014.safetensors"
+  }
+}

vae/config.json

@@ -0,0 +1,97 @@
+{
+  "_class_name": "AutoencoderKLMiniMaxH3",
+  "_diffusers_version": "0.36.0.dev0",
+  "in_channels": 3,
+  "out_channels": 3,
+  "latent_channels": 24,
+  "block_out_channels": [
+    128,
+    256,
+    256,
+    512,
+    512,
+    1024
+  ],
+  "layers_per_block": 2,
+  "spatial_downsample_factors": [
+    2,
+    2,
+    2,
+    2,
+    1,
+    1
+  ],
+  "temporal_downsample_factors": [
+    1,
+    2,
+    2,
+    1,
+    1,
+    1
+  ],
+  "norm_num_groups": 32,
+  "norm_eps": 1e-06,
+  "spatial_padding_mode": "reflect",
+  "decoder_num_layers": 36,
+  "decoder_num_attention_heads": 32,
+  "decoder_attention_head_dim": 64,
+  "decoder_num_register_tokens": 4,
+  "decoder_ffn_mult": 4,
+  "decoder_rope_theta": 100.0,
+  "decoder_rope_dim_ratio": 0.75,
+  "decoder_norm_eps": 1e-05,
+  "clip_length": 17,
+  "token_drop": 3,
+  "latents_mean": [
+    0.858090341091156,
+    -0.9606591463088989,
+    1.0661640167236328,
+    -0.5090325474739075,
+    -0.2727581858634949,
+    -1.3675414323806763,
+    -0.2553254961967468,
+    -0.26907554268836975,
+    -0.5376840829849243,
+    -0.0464097298681736,
+    0.6657370328903198,
+    0.19690127670764923,
+    -0.5460608005523682,
+    -0.4035342037677765,
+    -0.23683024942874908,
+    0.25928452610969543,
+    -0.30133944749832153,
+    0.211341992020607,
+    -1.1206848621368408,
+    0.3581933379173279,
+    -0.04225143790245056,
+    0.2604829967021942,
+    0.22864092886447906,
+    0.7056031823158264
+  ],
+  "latents_std": [
+    1.2223774194717407,
+    1.2767263650894165,
+    1.6831774711608887,
+    1.7549455165863037,
+    1.5636216402053833,
+    2.194143533706665,
+    0.9653137922286987,
+    1.0569885969161987,
+    0.841948926448822,
+    0.7729952931404114,
+    1.8955937623977661,
+    0.946841835975647,
+    0.7996809482574463,
+    0.44988900423049927,
+    0.7197399735450745,
+    0.6936293244361877,
+    2.961095094680786,
+    2.7694199085235596,
+    3.0496184825897217,
+    2.1088054180145264,
+    3.276226282119751,
+    3.1627357006073,
+    2.2816812992095947,
+    2.6127843856811523
+  ]
+}

vae/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,710 @@
+{
+  "metadata": {
+    "total_size": 10415475936
+  },
+  "weight_map": {
+    "decoder.norm_out.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.norm_out.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.proj_in.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.proj_in.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.proj_out.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.proj_out.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.register_tokens": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.0.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.1.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.10.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.11.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.12.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.13.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.14.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.15.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.16.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.17.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.18.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.19.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.2.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.20.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.21.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.22.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.23.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.scale1": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.24.scale2": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "decoder.transformer_blocks.25.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.25.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.25.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.25.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.25.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.25.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.26.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.27.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.28.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.29.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.3.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.30.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.31.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.32.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.33.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.34.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.35.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.4.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.5.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.6.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.7.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.8.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.scale1": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "decoder.transformer_blocks.9.scale2": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.conv_in.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.conv_in.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.conv_out.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.conv_out.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.downsamplers.0.conv.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.downsamplers.0.conv.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.downsamplers.0.conv.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.downsamplers.0.conv.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv_shortcut.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv_shortcut.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.downsamplers.0.conv.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.downsamplers.0.conv.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.downsamplers.0.conv.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.downsamplers.0.conv.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv_shortcut.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv_shortcut.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.norm1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.norm2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.0.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.conv1.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.conv1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.conv2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.conv2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.norm1.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.norm2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.4.resnets.1.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv1.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv_shortcut.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.conv_shortcut.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.norm1.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.norm2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.0.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.conv1.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.conv1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.conv2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.conv2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.norm1.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.norm2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.down_blocks.5.resnets.1.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.norm_out.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "encoder.norm_out.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "post_quant_conv.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "post_quant_conv.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "quant_conv.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "quant_conv.weight": "diffusion_pytorch_model-00003-of-00003.safetensors"
+  }
+}