--- base_model: Qwen/Qwen2.5-VL-7B-Instruct library_name: peft pipeline_tag: text-generation tags: - base_model:adapter:Qwen/Qwen2.5-VL-7B-Instruct - lora - transformers ---

project page arxiv model dataset

News | Quick Start | Benchmark Usage | Citation

**EditScore** is a series of state-of-the-art open-source reward models (7Bโ€“72B) designed to evaluate and enhance instruction-guided image editing. ## โœจ Highlights - **State-of-the-Art Performance**: Effectively matches the performance of leading proprietary VLMs. With a self-ensembling strategy, **our largest model surpasses even GPT-5** on our comprehensive benchmark, **EditReward-Bench**. - **A Reliable Evaluation Standard**: We introduce **EditReward-Bench**, the first public benchmark specifically designed for evaluating reward models in image editing, featuring 13 subtasks, 11 state-of-the-art editing models (*including proprietary models*) and expert human annotations. - **Simple and Easy-to-Use**: Get an accurate quality score for your image edits with just a few lines of code. - **Versatile Applications**: Ready to use as a best-in-class reranker to improve editing outputs, or as a high-fidelity reward signal for **stable and effective Reinforcement Learning (RL) fine-tuning**. ## ๐Ÿ”ฅ News - **2025-09-30**: We release **OmniGen2-EditScore7B**, unlocking online RL For Image Editing via high-fidelity EditScore. LoRA weights are available at [Hugging Face](https://huggingface.co/OmniGen2/OmniGen2-EditScore7B) and [ModelScope](https://www.modelscope.cn/models/OmniGen2/OmniGen2-EditScore7B). - **2025-09-30**: We are excited to release **EditScore** and **EditReward-Bench**! Model weights and the benchmark dataset are now publicly available. You can access them on Hugging Face: [Models Collection](https://huggingface.co/collections/EditScore/editscore-68d8e27ee676981221db3cfe) and [Benchmark Dataset](https://huggingface.co/datasets/EditScore/EditReward-Bench), and on ModelScope: [Models Collection](https://www.modelscope.cn/collections/EditScore-8b0d53aa945d4e) and [Benchmark Dataset](https://www.modelscope.cn/datasets/EditScore/EditReward-Bench). ## ๐Ÿ“– Introduction While Reinforcement Learning (RL) holds immense potential for this domain, its progress has been severely hindered by the absence of a high-fidelity, efficient reward signal. To overcome this barrier, we provide a systematic, two-part solution: - **A Rigorous Evaluation Standard**: We first introduce **EditReward-Bench**, a new public benchmark for the direct and reliable evaluation of reward models. It features 13 diverse subtasks and expert human annotations, establishing a gold standard for measuring reward signal quality. - **A Powerful & Versatile Tool**: Guided by our benchmark, we developed the **EditScore** model series. Through meticulous data curation and an effective self-ensembling strategy, EditScore sets a new state of the art for open-source reward models, even surpassing the accuracy of leading proprietary VLMs.


Benchmark results on EditReward-Bench.

We demonstrate the practical utility of EditScore through two key applications: - **As a State-of-the-Art Reranker**: Use EditScore to perform Best-of-*N* selection and instantly improve the output quality of diverse editing models. - **As a High-Fidelity Reward for RL**: Use EditScore as a robust reward signal to fine-tune models via RL, enabling stable training and unlocking significant performance gains where general-purpose VLMs fail. This repository releases both the **EditScore** models and the **EditReward-Bench** dataset to facilitate future research in reward modeling, policy optimization, and AI-driven model improvement.


EditScore as a superior reward signal for image editing.

## ๐Ÿ“Œ TODO We are actively working on improving EditScore and expanding its capabilities. Here's what's next: - [ ] Release RL training code applying EditScore to OmniGen2. - [ ] Provide Best-of-N inference scripts for OmniGen2, Flux-dev-Kontext, and Qwen-Image-Edit. ## ๐Ÿš€ Quick Start ### ๐Ÿ› ๏ธ Environment Setup #### โœ… Recommended Setup ```bash # 1. Clone the repo git clone git@github.com:VectorSpaceLab/EditScore.git cd EditScore # 2. (Optional) Create a clean Python environment conda create -n editscore python=3.12 conda activate editscore # 3. Install dependencies # 3.1 Install PyTorch (choose correct CUDA version) pip install torch==2.7.1 torchvision --extra-index-url https://download.pytorch.org/whl/cu126 # 3.2 Install other required packages pip install -r requirements.txt # EditScore runs even without vllm, though we recommend install it for best performance. pip install vllm ``` #### ๐ŸŒ For users in Mainland China ```bash # Install PyTorch from a domestic mirror pip install torch==2.7.1 torchvision --index-url https://mirror.sjtu.edu.cn/pytorch-wheels/cu126 # Install other dependencies from Tsinghua mirror pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple # EditScore runs even without vllm, though we recommend install it for best performance. pip install vllm -i https://pypi.tuna.tsinghua.edu.cn/simple ``` --- ### ๐Ÿงช Usage Example Using EditScore is straightforward. The model will be automatically downloaded from the Hugging Face Hub on its first run. ```python from PIL import Image from editscore import EditScore # Load the EditScore model. It will be downloaded automatically. # Replace with the specific model version you want to use. model_path = "Qwen/Qwen2.5-VL-7B-Instruct" lora_path = "EditScore/EditScore-7B" scorer = EditScore( backbone="qwen25vl", # set to "qwen25vl_vllm" for faster inference model_name_or_path=model_path, enable_lora=True, lora_path=lora_path, score_range=25, num_pass=1, # Increase for better performance via self-ensembling ) input_image = Image.open("example_images/input.png") output_image = Image.open("example_images/output.png") instruction = "Adjust the background to a glass wall." result = scorer.evaluate([input_image, output_image], instruction) print(f"Edit Score: {result['final_score']}") # Expected output: A dictionary containing the final score and other details. ``` --- ## ๐Ÿ“Š Benchmark Your Image-Editing Reward Model We provide an evaluation script to benchmark reward models on **EditReward-Bench**. To evaluate your own custom reward model, simply create a scorer class with a similar interface and update the script. ```bash # This script will evaluate the default EditScore model on the benchmark bash evaluate.sh # Or speed up inference with VLLM bash evaluate_vllm.sh ``` ## โค๏ธ Citing Us If you find this repository or our work useful, please consider giving a star โญ and citation ๐Ÿฆ–, which would be greatly appreciated: ```bibtex @article{luo2025editscore, title={EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling}, author={Xin Luo and Jiahao Wang and Chenyuan Wu and Shitao Xiao and Xiyan Jiang and Defu Lian and Jiajun Zhang and Dong Liu and Zheng Liu}, journal={arXiv preprint arXiv:2509.23909}, year={2025} } ```