Video-Painter

VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control

Yuxuan Bian 1, 2, Zhaoyang Zhang 2, Xuan Ju 2, Mingdeng Cao 3, Liangbin Xie 4, Ying Shan 1, Qiang Xu 2
1 ARC Lab, Tencent PCG    2 The Chinese University of Hong Kong    3 The University of Tokyo    4 University of Macau

SIGGRAPH 2025

Introduction Video
Click to Play

Method

VideoPainter enables plug-and-play text-guided video inpainting and editing for any video length and pre-trained Diffusion Transformer with masked video and video caption (user editing instruction). VideoPainter contains 1) an efficient and plug-and-play dual-branch framework featuring a lightweight background context encoder, and 2) a ID resampling technique for inpainted region ID preservation.


Gallery-Inpaint

Gallery-Edit

Results-Inpaint

Results-Inpaint (Any Length)

Results-Edit

Results-Edit (Any Length)

VPData and VPBench Visualization

More...

Code
View on Github

HF Collection
View on HF

Preprint Paper
View on ArXiv

⭐ Star our github repo if you find our work helpful in your research.

Limitation

As a generative model, VideoPainter may occasionally produce unexpected outputs due to several limitations: (1) Generation quality is limited by the base model, which may struggle with complex physical and motion modeling, and (2) performance is suboptimal with low-quality masks or misaligned video captions. We're actively working on an improved version with enhanced datasets and a more powerful foundation model.

Citation

😊 Consider citing this paper if you find our work helpful in your research. 

@misc{bian2025videopainteranylengthvideoinpainting,
      title={VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control}, 
      author={Yuxuan Bian and Zhaoyang Zhang and Xuan Ju and Mingdeng Cao and Liangbin Xie and Ying Shan and Qiang Xu},
      year={2025},
      eprint={2503.05639},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2503.05639}, 
}