| --- |
| base_model: Qwen/Qwen-Image-Edit-2511 |
| library_name: peft |
| license: apache-2.0 |
| tags: |
| - lora |
| - diffusion |
| - image-editing |
| - product-consistency |
| - grpo |
| - reinforcement-learning |
| --- |
| |
| # ReCoEdit — RL LoRA Adapter (Epoch 24) |
|
|
| LoRA adapter for **Qwen-Image-Edit-2511**, trained with Flow-GRPO and a product consistency reward. |
| Plug this into `Qwen/Qwen-Image-Edit-2511` to get a model that better preserves product identity (color, shape, logo) during image editing. |
|
|
| - **Base model**: `Qwen/Qwen-Image-Edit-2511` |
| - **Training**: GRPO (Group Relative Policy Optimization) on e-commerce product editing data |
| - **Reward**: Qwen3-VL-30B-A3B-Instruct as VLM judge, 1-5 product consistency score |
| - **Result**: Reward improved from 0.022 → 0.480 (21.8× over SFT baseline) |
| - **LoRA rank / alpha**: 64 / 128 |
| - **Checkpoint**: Epoch 24 (peak performance) |
|
|
| ## Usage |
|
|
| ```python |
| from peft import PeftModel |
| from huggingface_hub import snapshot_download |
| |
| # Load base model (via DiffSynth-Studio) |
| # See https://github.com/Matteoooo46/ReCoEdit for full inference script |
| lora_path = snapshot_download("Matteoooo46/ReCoEdit-RL") |
| pipe.load_lora(pipe.dit, lora_path + "/adapter_model.safetensors") |
| ``` |
|
|
| See the [ReCoEdit repository](https://github.com/Matteoooo46/ReCoEdit) for the complete inference pipeline including APG guidance and prompt rewriter. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @misc{recoedit2025, |
| title={ReCoEdit: Rewriter-Guided Consistency Alignment for Product Image Editing}, |
| author={}, |
| year={2025}, |
| howpublished={\url{https://github.com/Matteoooo46/ReCoEdit}}, |
| } |
| ``` |
|
|
