modify readme

README.md

@@ -1,3 +1,57 @@
 ---
 license: mit
+language:
+- en
+base_model:
+- black-forest-labs/FLUX.1-Kontext-dev
+pipeline_tag: image-to-image
+library_name: diffusers
+tags:
+- art
 ---
+
+<h1 align="center">
+ContextGen: Contextual Layout Anchoring </br> for Identity-Consistent Multi-Instance Generation
+</h1>
+
+<p align="center">
+<a href="https://scholar.google.com/citations?user=5ZDU6wwAAAAJ">Ruihang Xu</a>,
+<a href="https://scholar.google.com/citations?user=4C_OwWMAAAAJ">Dewei Zhou</a>,
+<a href="https://scholar.google.com/citations?user=FyglsaAAAAAJ">Fan Ma</a>,
+<a href="https://scholar.google.com/citations?user=RMSuNFwAAAAJ">Yi Yang</a><sup>&#8224;</sup> <br>
+<span>ReLER, CCAI, Zhejiang University</span>
+</p>
+
+<p align="center">
+<a href="https://github.com/nenhang/ContextGen"><img src="https://img.shields.io/badge/GitHub-Code-black" alt="GitHub Code"></a>
+<a href="https://nenhang.github.io/ContextGen"><img src="https://img.shields.io/badge/Project-Page-brightgreen" alt="Project Page"></a>
+<a href="https://arxiv.org/abs/2510.11000"><img src="https://img.shields.io/badge/arXiv-2510.11000-b31b1b" alt="Paper"></a>
+<a href="https://github.com/nenhang/IMIG-Source"><img src="https://img.shields.io/badge/Dataset-Code-blue" alt="Dataset Code"></a>
+</p>
+
+<div align="center">
+<img src="docs/teaser.webp" alt="Teaser Image" style="max-width: 80%;">
+<p style="text-align: left;">
+<b>ContextGen</b> is a novel framework that uses <b>user-provided reference images</b> to generate image with multiple instances, offering <b>layout control</b> over their positions while guaranteeing <b>identity preservation</b>.
+</p>
+</div>
+
+## 🚀 Usage
+
+Please refer to our [GitHub Repository](https://github.com/nenhang/ContextGen) for detailed instructions on how to use ContextGen.
+
+## 📭 Citation
+
+If you find ContextGen helpful to your research, please consider citing our paper:
+
+```bibtex
+@article{xu2025contextgencontextuallayoutanchoring,
+      title={ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation},
+      author={Ruihang Xu and Dewei Zhou and Fan Ma and Yi Yang},
+      year={2025},
+      eprint={2510.11000},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2510.11000},
+}
+```