Sync to ComfyUI-repackaged layout (bf16)

README.md

@@ -1,56 +1,62 @@
 ---
 license: apache-2.0
-library_name: diffusers
+library_name: ComfyUI
 pipeline_tag: image-to-image
 tags:
   - comfyui
   - image-editing
-  - diffusers
   - joyai
+base_model: jdopensource/JoyAI-Image-Edit-Diffusers
 ---
 
-# JoyAI-Image-Edit (ComfyUI weights)
+# JoyAI-Image-Edit (ComfyUI)
 
-Single-file `.safetensors` checkpoints of [JoyAI-Image-Edit](https://github.com/jd-opensource/JoyAI-Image), repackaged for the standard ComfyUI model folder layout.
-
-Use these with the `joyai_image_comfyui` custom node from the [JoyAI-Image GitHub repo](https://github.com/jd-opensource/JoyAI-Image/tree/main/joyai_image_comfyui).
+Repackaged single-file weights of [`jdopensource/JoyAI-Image-Edit-Diffusers`](https://huggingface.co/jdopensource/JoyAI-Image-Edit-Diffusers) for ComfyUI's standard model-folder layout. Keys, filenames and directory layout follow the [Comfy-Org](https://huggingface.co/Comfy-Org) packaging convention used by `Qwen-Image-Edit_ComfyUI` and `Wan_2.1_ComfyUI_repackaged` — drop the files into `ComfyUI/models/` and they load natively.
 
 ## Files
 
 | File | Size | Goes into | Component |
 |------|------|-----------|-----------|
-| `diffusion_models/joy_image_edit_bf16.safetensors` | ~32 GB | `ComfyUI/models/diffusion_models/` | `JoyImageEditTransformer3DModel` (bf16) |
-| `text_encoders/qwen3vl_joyimage_bf16.safetensors` | ~17 GB | `ComfyUI/models/text_encoders/` | Qwen3VL text encoder (bf16) |
-| `vae/joy_image_edit_vae.safetensors` | ~254 MB | `ComfyUI/models/vae/` | `AutoencoderKLWan` |
+| `split_files/diffusion_models/joyai_image_edit_bf16.safetensors` | ~32 GB | `ComfyUI/models/diffusion_models/` | `JoyImageEditTransformer3DModel` (bf16) |
+| `split_files/text_encoders/qwen_3vl_8b_joyimage_bf16.safetensors` | ~17 GB | `ComfyUI/models/text_encoders/` | Qwen3-VL-8B text encoder, JoyImage-finetuned (bf16) |
+| `split_files/vae/wan_2.1_vae.safetensors` | ~250 MB | `ComfyUI/models/vae/` | Wan 2.1 VAE (shared with Wan / Qwen-Image; bf16) |
 
-The repo's directory layout already matches `ComfyUI/models/`, so a single `hf download` into your models root drops every file where it needs to go.
+The VAE is the standard Wan 2.1 VAE — bit-identical to [`Comfy-Org/Wan_2.1_ComfyUI_repackaged/split_files/vae/wan_2.1_vae.safetensors`](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors). If you already have it from Wan or Qwen-Image, you can skip the VAE here.
 
 ## Quick start
 
 ```bash
-# 1) Install the custom node
-cd ComfyUI/custom_nodes
-git clone https://github.com/jd-opensource/JoyAI-Image.git
-cp -r JoyAI-Image/joyai_image_comfyui ./
-rm -rf JoyAI-Image
-
-# 2) Download the weights straight into ComfyUI/models/
+# Download into ComfyUI/models/ (skips split_files/ wrapper):
 hf download jdopensource/JoyAI-Image-Edit-ComfyUI \
-  --local-dir /path/to/ComfyUI/models
+  --include "split_files/*" \
+  --local-dir /path/to/ComfyUI/models \
+  --local-dir-use-symlinks False
 
-# 3) Restart ComfyUI — new nodes appear under `loaders/joyai` and `image/joyai`.
+# Or fetch each file individually into the matching model folder.
 ```
 
 ## Requirements
 
-- `diffusers >= 0.39.0.dev0` (install from source: `pip install git+https://github.com/huggingface/diffusers.git`)
-- `transformers >= 4.57.0`
+Native JoyImageEdit support is in flight upstream against [Comfy-Org/ComfyUI](https://github.com/comfyanonymous/ComfyUI). Until the PR lands, install ComfyUI from the JoyAI fork's branch:
+
+```bash
+git clone https://github.com/jd-opensource/JoyAI-Image.git
+# follow the ComfyUI branch instructions in JoyAI-Image/README.md
+```
+
+When the upstream PR merges, plain `comfyanonymous/ComfyUI` will detect and load these files with no extra setup.
+
+## Key namespaces
 
-## GGUF quantizations
+For developers / quantizers — the top-level state-dict prefixes in each file:
 
-Lower-bit GGUF quants of the transformer and text encoder are available at [huangfeice/JoyAI-Image-Edit-Diffusers-GGUF](https://huggingface.co/huangfeice/JoyAI-Image-Edit-Diffusers-GGUF) (community contribution). The VAE here is the only VAE you need — GGUF doesn't quantize VAE.
+- **diffusion_models**: raw transformer keys (`double_blocks.*`, `condition_embedder.*`, `img_in.*`, `proj_out.*`, `norm_out.*`). No `model.diffusion_model.` wrapper. Auto-detected by ComfyUI's `model_detection.py`.
+- **text_encoders**: HF Qwen3-VL keys (`model.language_model.*`, `model.visual.*`, `lm_head.*`). ComfyUI strips the `model.` wrappers internally.
+- **vae**: standard Comfy-Org Wan 2.1 VAE keys (`encoder.{conv1,downsamples,middle}.*`, `decoder.{conv1,upsamples,middle,head}.*`, plus top-level `conv1.*`/`conv2.*` for the post-quant projections).
 
 ## Links
 
-- Source code, node implementation, and full documentation: [github.com/jd-opensource/JoyAI-Image](https://github.com/jd-opensource/JoyAI-Image)
-- Original Diffusers-format weights: [jdopensource/JoyAI-Image-Edit-Diffusers](https://huggingface.co/jdopensource/JoyAI-Image-Edit-Diffusers)
+- Source code & nodes: [github.com/jd-opensource/JoyAI-Image](https://github.com/jd-opensource/JoyAI-Image)
+- Diffusers weights: [jdopensource/JoyAI-Image-Edit-Diffusers](https://huggingface.co/jdopensource/JoyAI-Image-Edit-Diffusers)
+- GGUF quantizations (community): [huangfeice/JoyAI-Image-Edit-Diffusers-GGUF](https://huggingface.co/huangfeice/JoyAI-Image-Edit-Diffusers-GGUF)
+- License: Apache 2.0

vae/joy_image_edit_vae.safetensors → split_files/vae/wan_2.1_vae.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ffe6326a57bbc7c8a704d862e482588e3affc858bdbfc123a91b5ac3a3a42a
-size 253806966
+oid sha256:2fc39d31359a4b0a64f55876d8ff7fa8d780956ae2cb13463b0223e15148976b
+size 253815318