🚀 Code Release: Now you can visit the new X-Dub code repository, download the pretrained weights, and try X-Dub! If you find our work helpful, please consider giving the code repo a ⭐ star.

Xu He^1,*, Haoxian Zhang^2,†, Hejia Chen³, Changyuan Zheng¹, Liyang Chen¹, Songlin Tang², Jiehui Huang⁴, Xiaoqiang Liu², Pengfei Wan², Zhiyong Wu^1,5,✉

¹Tsinghua University, ²Kling Team, Kuaishou Technology, ³Beihang University, ⁴HKUST, ⁵CUHK
*: Work done at Kling Team, Kuaishou Technology, †: Project Leader, ✉: Corresponding Author

• [2026.03.19] 🔥 Release inference code and pretrained weights: code | weights.
• [2025.12.31] Release Arxiv paper.

🔥 The public X-Dub release is now available: GitHub repository.

@misc{he2025inpaintingeditingselfbootstrappingframework,
      title={From Inpainting to Editing: A Self-Bootstrapping Framework for Context-Rich Visual Dubbing}, 
      author={Xu He and Haoxian Zhang and Hejia Chen and Changyuan Zheng and Liyang Chen and Songlin Tang and Jiehui Huang and Xiaoqiang Liu and Pengfei Wan and Zhiyong Wu},
      year={2025},
      eprint={2512.25066},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.25066}, 
}