Improve model card: Add metadata, links, and usage example

README.md

@@ -1,5 +1,74 @@
 ---
 license: apache-2.0
+pipeline_tag: image-to-image
+library_name: transformers
 ---
 
-[UniREditBench: A Unified Reasoning-based Image Editing Benchmark](https://arxiv.org/abs/2511.01295)
+# UniREdit-Bagel
+
+This repository contains **UniREdit-Bagel**, a model developed for **UniREditBench: A Unified Reasoning-based Image Editing Benchmark**. The paper introduces UniREditBench as a unified benchmark for reasoning-based image editing evaluation and UniREdit-Bagel as a model fine-tuned on the UniREdit-Data-100K dataset, demonstrating substantial improvements in both in-domain and out-of-distribution settings.
+
+*   [**Paper on arXiv**](https://arxiv.org/abs/2511.01295)
+*   [**Project Page**](https://maplebb.github.io/UniREditBench/)
+*   [**GitHub Repository**](https://github.com/Maplebb/UniREditBench)
+
+## Introduction
+
+We propose **UniREditBench**, a unified benchmark for reasoning-based image editing assessment with broader evaluation dimension coverage and robust evaluation pipeline. We also design an automated multi-scenario data synthesis pipeline and construct **UniREdit-Data-100K**, a large-scale synthetic dataset with high-quality chain-of-thought (CoT) reasoning annotations. We fine-tune Bagel on this dataset and develop **UniREdit-Bagel**, demonstrating substantial improvements in both in-domain and out-of-distribution settings.
+
+<img alt="image" src="https://github.com/Maplebb/UniREditBench/raw/main/docs/static/images/teaser.png" />
+
+<img alt="image" src="https://github.com/Maplebb/UniREditBench/raw/main/docs/static/images/radar.png" />
+
+### ✨ Highlights:
+
+-   **Broader Scenario and Reasoning Dimension Coverage**: It contains 2,700 high-quality samples organized into 8 primary reasoning dimensions and 18 sub-categories, spanning both real-world and game-world image editing tasks.
+-   **Reliable Dual-Reference Evaluation**: For each sample assessment, we design both the textual reference and ground-truth (GT) image reference. This multi-modal reference enables vision-language model (VLM) evaluators to perform direct and fine-grained comparisons at both the textual and visual levels with the generated images, leading to more reliable evaluation.
+
+<img alt="image" src="https://github.com/Maplebb/UniREditBench/raw/main/docs/static/images/motivation_tab.png" />
+<img alt="image" src="https://github.com/Maplebb/UniREditBench/raw/main/docs/static/images/motivation_fig.png" />
+
+<img alt="image" src="https://github.com/Maplebb/UniREditBench/raw/main/docs/static/images/testpoint_cases.png" />
+
+## 🚀 Sample Usage (Inference)
+
+Here's an example of how to run inference with UniREdit-Bagel. Please refer to the [GitHub repository](https://github.com/Maplebb/UniREditBench) for detailed environment setup and checkpoint preparation steps.
+
+```bash
+GPUS=8
+model_path=./ckpt
+input_path=./UniREditBench
+output_path=./output_images
+
+# Image Editing with Reasoning
+torchrun \
+    --nnodes=1 \
+    --nproc_per_node=$GPUS \
+    gen_images_mp_uniredit.py \
+    --input_dir $input_path \
+    --output_dir $output_path \
+    --metadata_file ./UniREditBench/data.json \
+    --max_latent_size 64 \
+    --model-path $model_path \
+    --think
+```
+
+## 📧 Contact
+
+If you have any comments or questions, please open a new issue on the [GitHub repository](https://github.com/Maplebb/UniREditBench) or feel free to contact [Feng Han](fhan25@m.fudan.edu.cn) and [Yibin Wang](https://codegoat24.github.io).
+
+## ⭐ Citation
+
+If you find UniREditBench or UniREdit-Bagel useful, please cite our paper:
+
+```bibtex
+@misc{han2025unireditbench,
+      title={UniREditBench: A Unified Reasoning-based Image Editing Benchmark},
+      author={Feng Han and Yibin Wang and Chenglin Li and Zheming Liang and Dianyi Wang and Yang Jiao and Zhipeng Wei and Chao Gong and Cheng Jin and Jingjing Chen and Jiaqi Wang},
+      year={2025},
+      eprint={2511.01295},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2511.01295},
+}
+```