---
base_model: Qwen/Qwen3-VL-8B-Instruct
library_name: peft
license: apache-2.0
tags:
- lora
- vision-language
- prompt-rewriting
- image-editing
- ecommerce
---

# ReCoEdit — Prompt Rewriter LoRA

LoRA adapter for **Qwen3-VL-8B-Instruct**, trained to rewrite raw e-commerce product prompts into structured editing instructions for Qwen-Image-Edit.

- **Base model**: `Qwen/Qwen3-VL-8B-Instruct`
- **Training**: SFT via LLaMA-Factory on paired (product image, raw prompt → structured prompt) data
- **Input**: Product reference image + raw editing prompt (Chinese)
- **Output**: Structured editing prompt optimized for Qwen-Image-Edit (120-150 chars, Chinese)
- **LoRA rank**: 64, trained for 10,000 steps

## Usage

```python
from transformers import AutoProcessor
from qwen_vl_utils import process_vision_info
from peft import PeftModel
from transformers import Qwen3VLForConditionalGeneration
from huggingface_hub import snapshot_download

base_model = "Qwen/Qwen3-VL-8B-Instruct"
lora_path = snapshot_download("Matteoooo46/ReCoEdit-rewriter")

model = Qwen3VLForConditionalGeneration.from_pretrained(
    base_model, torch_dtype="auto", device_map="auto"
)
model = PeftModel.from_pretrained(model, lora_path)
processor = AutoProcessor.from_pretrained(base_model, trust_remote_code=True)
```

See the [ReCoEdit repository](https://github.com/Matteoooo46/ReCoEdit) for the complete inference pipeline.

## Citation

```bibtex
@misc{recoedit2025,
  title={ReCoEdit: Rewriter-Guided Consistency Alignment for Product Image Editing},
  author={},
  year={2025},
  howpublished={\url{https://github.com/Matteoooo46/ReCoEdit}},
}
```