Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,75 @@
+---
+library_name: diffusers
+tags:
+- modular-diffusers
+- diffusers
+- krea2
+- text-to-image
+---
+This is a modular diffusion pipeline built with 🧨 Diffusers' modular pipeline framework.
+
+**Pipeline Type**: Krea2AutoBlocks
+
+**Description**: Auto Modular pipeline for text-to-image generation using Krea 2: encode text -> core denoise (symmetric CFG) -> decode.
+
+This pipeline uses a 3-block architecture that can be customized and extended.
+
+## Example Usage
+
+[TODO]
+
+## Pipeline Architecture
+
+This modular pipeline is composed of the following blocks:
+
+1. **text_encoder** (`Krea2TextEncoderStep`)
+   - Text encoder step that tokenizes the prompt(s) with the Krea 2 chat template, runs the Qwen3-VL text encoder, and stacks a fixed set of decoder-layer hidden states per token as the transformer's text conditioning. When `guidance_scale > 0` the negative prompt is encoded the same way for CFG.
+2. **denoise** (`Krea2CoreDenoiseStep`)
+   - Core denoising workflow for Krea 2 text-to-image: prepares the batch/latents/timesteps and the shared position ids, then runs the symmetric-CFG denoising loop, producing the denoised packed latents for the decoder.
+3. **decode** (`Krea2DecodeStep`)
+   - Step that unpacks the denoised packed latents back to the spatial grid, de-normalizes them with the VAE's per-channel statistics, and decodes them through the Qwen-Image VAE into images. 
+
+## Model Components
+
+1. text_encoder (`Qwen3VLModel`): The Qwen3-VL text encoder.
+2. tokenizer (`AutoTokenizer`): The tokenizer paired with the text encoder.
+3. transformer (`Krea2Transformer2DModel`)
+4. scheduler (`FlowMatchEulerDiscreteScheduler`)
+5. vae (`AutoencoderKLQwenImage`)
+6. image_processor (`VaeImageProcessor`) 
+
+## Configuration Parameters
+
+is_distilled (default: False)
+
+## Workflow Input Specification
+
+<details>
+<summary><strong>text2image</strong></summary>
+
+- `prompt` (`str`): The prompt or prompts to guide image generation.
+
+</details>
+
+
+## Input/Output Specification
+
+**Inputs:**
+
+- `prompt` (`str`): The prompt or prompts to guide image generation.
+- `negative_prompt` (`str`, *optional*): The negative prompt(s) for CFG.
+- `guidance_scale` (`float`, *optional*, defaults to `4.5`): CFG scale; the negative prompt is only encoded when this is > 0.
+- `max_sequence_length` (`int`, *optional*, defaults to `512`): Maximum sequence length for prompt encoding.
+- `num_images_per_prompt` (`int`, *optional*, defaults to `1`): The number of images to generate per prompt.
+- `latents` (`Tensor`, *optional*): Pre-generated noisy latents for image generation.
+- `height` (`int`): The height in pixels of the generated image.
+- `width` (`int`): The width in pixels of the generated image.
+- `generator` (`Generator`, *optional*): Torch generator for deterministic generation.
+- `num_inference_steps` (`int`, *optional*, defaults to `28`): The number of denoising steps.
+- `sigmas` (`list`, *optional*): Custom sigma schedule (defaults to a linear ramp).
+- `attention_kwargs` (`dict`, *optional*): Additional kwargs for attention processors.
+- `output_type` (`str`, *optional*, defaults to `pil`): Output format: 'pil', 'np', 'pt'.
+
+**Outputs:**
+
+- `images` (`list`): Generated images.

modular_model_index.json

@@ -0,0 +1,76 @@
+{
+  "_blocks_class_name": "Krea2AutoBlocks",
+  "_class_name": "Krea2ModularPipeline",
+  "_diffusers_version": "0.39.0.dev0",
+  "is_distilled": false,
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler",
+    {
+      "pretrained_model_name_or_path": "CedricPerauer/tiny-krea2-modular-pipe",
+      "revision": null,
+      "subfolder": "scheduler",
+      "type_hint": [
+        "diffusers",
+        "FlowMatchEulerDiscreteScheduler"
+      ],
+      "variant": null
+    }
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLModel",
+    {
+      "pretrained_model_name_or_path": "CedricPerauer/tiny-krea2-modular-pipe",
+      "revision": null,
+      "subfolder": "text_encoder",
+      "type_hint": [
+        "transformers",
+        "Qwen3VLModel"
+      ],
+      "variant": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2Tokenizer",
+    {
+      "pretrained_model_name_or_path": "CedricPerauer/tiny-krea2-modular-pipe",
+      "revision": null,
+      "subfolder": "tokenizer",
+      "type_hint": [
+        "transformers",
+        "Qwen2Tokenizer"
+      ],
+      "variant": null
+    }
+  ],
+  "transformer": [
+    "diffusers",
+    "Krea2Transformer2DModel",
+    {
+      "pretrained_model_name_or_path": "CedricPerauer/tiny-krea2-modular-pipe",
+      "revision": null,
+      "subfolder": "transformer",
+      "type_hint": [
+        "diffusers",
+        "Krea2Transformer2DModel"
+      ],
+      "variant": null
+    }
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLQwenImage",
+    {
+      "pretrained_model_name_or_path": "CedricPerauer/tiny-krea2-modular-pipe",
+      "revision": null,
+      "subfolder": "vae",
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLQwenImage"
+      ],
+      "variant": null
+    }
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.39.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 6400,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,56 @@
+{
+  "architectures": [
+    "Qwen3VLModel"
+  ],
+  "dtype": "float32",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 8,
+    "hidden_act": "silu",
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 16,
+    "max_position_embeddings": 128000,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 2,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 500000.0,
+      "rope_type": "default"
+    },
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.12.1",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 2,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 16,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 16,
+    "model_type": "qwen3_vl_vision",
+    "num_heads": 2,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 16,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vocab_size": 152064
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c4589ff68c9c9b316c25a680f345990c3b65f3ebba045f5f7ec2b8bd24656a
+size 10383856

tokenizer/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312c03cb421e18f41c20c3e35f3302479a3a8f8b1f06779fd900326a0d32c22f
+size 11420534

tokenizer/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "max_length": null,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "Krea2Transformer2DModel",
+  "_diffusers_version": "0.39.0.dev0",
+  "attention_head_dim": 8,
+  "axes_dims_rope": [
+    4,
+    2,
+    2
+  ],
+  "in_channels": 16,
+  "intermediate_size": 32,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "num_layers": 2,
+  "num_layerwise_text_blocks": 1,
+  "num_refiner_text_blocks": 1,
+  "num_text_layers": 12,
+  "rope_theta": 1000.0,
+  "text_hidden_dim": 16,
+  "text_intermediate_size": 16,
+  "text_num_attention_heads": 2,
+  "text_num_key_value_heads": 1,
+  "timestep_embed_dim": 8
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea582bcdc2017d7955e81b8d799fa2a1824cdb80fa0019e4fa701398e0658795
+size 122872

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKLQwenImage",
+  "_diffusers_version": "0.39.0.dev0",
+  "attn_scales": [],
+  "base_dim": 24,
+  "dim_mult": [
+    1,
+    2,
+    4
+  ],
+  "dropout": 0.0,
+  "input_channels": 3,
+  "latents_mean": [
+    0.0,
+    0.0,
+    0.0,
+    0.0
+  ],
+  "latents_std": [
+    1.0,
+    1.0,
+    1.0,
+    1.0
+  ],
+  "num_res_blocks": 1,
+  "temperal_downsample": [
+    false,
+    true
+  ],
+  "z_dim": 4
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d82f6ac6ca2e5767a17a5efc504e0470705b3b3318bab132dd218ff0ff342d29
+size 16230492