README.md

<h1 align="center">From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping</h1>

<div align='center'>
  <p>
    <a href="https://scholar.google.com/citations?user=KMrFk2MAAAAJ&hl=en&oi=sra">Xu He</a><sup>1,*</sup>
    <a href="">Haoxian Zhang</a><sup>2,†</sup>
    <a href="">Hejia Chen</a><sup>3</sup>
    <a href="">Changyuan Zheng</a><sup>1</sup>
    <a href="">Liyang Chen</a><sup>1</sup>
    <br>
    <a href="">Songlin Tang</a><sup>2</sup>
    <a href="">Jiehui Huang</a><sup>4</sup>
    <a href="">Xiaoqiang Liu</a><sup>2</sup>
    <a href="">Pengfei Wan</a><sup>2</sup>
    <a href="">Zhiyong Wu</a><sup>1,5,✉</sup>
  </p>
  <p>
    <sup>1</sup>Tsinghua University &nbsp;&nbsp;
    <sup>2</sup>Kling Team, Kuaishou Technology &nbsp;&nbsp;
    <sup>3</sup>Beihang University &nbsp;&nbsp;
    <sup>4</sup>HKUST &nbsp;&nbsp;
    <sup>5</sup>CUHK
    <br>
    <sup>*</sup>Work done at Kling Team, Kuaishou Technology &nbsp;&nbsp;
    <sup>†</sup>Project leader &nbsp;&nbsp;
    <sup>✉</sup>Corresponding author
  </p>
  

</div>

<p align="center">
  <a href="https://hjrphoebus.github.io/X-Dub/"><img src="https://img.shields.io/badge/Project-Homepage-green"></a>
  &nbsp;
  <a href="https://arxiv.org/abs/2512.25066"><img src="https://img.shields.io/static/v1?label=ArXiv&message=X-Dub&color=red&logo=arxiv"></a>
  &nbsp;
  <a href="https://github.com/KlingAIResearch/X-Dub"><img src="https://img.shields.io/badge/GitHub-X--Dub-black?logo=github"></a>
</p>

Please refer to the [GitHub README](https://github.com/KlingAIResearch/X-Dub) for usage.

* Paper: [https://arxiv.org/abs/2512.25066](https://arxiv.org/abs/2512.25066)
* Project Page: [https://hjrphoebus.github.io/X-Dub/](https://hjrphoebus.github.io/X-Dub/)
* Code: [https://github.com/KlingAIResearch/X-Dub](https://github.com/KlingAIResearch/X-Dub)


## 📌 TL;DR
X-Dub is a visual dubbing system that synchronizes a character's lip movements in a video to match arbitrary input audio. This repository hosts the public Wan-based X-Dub release and its pretrained weights.


## 🌟 Citation
Please cite our paper if you find our work helpful.

```bibtex
@article{he2025from,
  title={From Inpainting to Editing: A Self-Bootstrapping Framework for Context-Rich Visual Dubbing},
  author={He, Xu and Zhang, Haoxian and Chen, Hejia and Zheng, Changyuan and Chen, Liyang and Tang, Songlin and Huang, Jiehui and Liu, Xiaoqiang and Wan, Pengfei and Wu, Zhiyong},
  journal={arXiv preprint arXiv:2512.25066},
  year={2025}
}
```