For the best experience, it's better to use a desktop computer to view this website.

VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches
via In-Context Conditioning

Minghong Cai1†, Qiulin Wang2*, Zongli Ye1, Wenze Liu1, Quande Liu2, Weicai Ye2, Xintao Wang2, Pengfei Wan2, Kun Gai2, Xiangyu Yue1*

1 MMLab, The Chinese University of Hong Kong, 2 Kling Team, Kuaishou Technology

†Work done at Kling Team, Kuaishou Technology, *Corresponding Authors

Please stay tuned for all video loading...

















Contact Us

Feel free to contact Minghong Cai at minghongcai@link.cuhk.edu.hk for any question,cooperation, and communication.

If you find this work useful, please consider citing:

                @article{cai2025videocanvas,
                    title={VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning},
                    author={Minghong Cai, Qiulin Wang, Zongli Ye, Wenze Liu, Quande Liu, Weicai Ye, Xintao Wang, Pengfei Wan, Kun Gai, Xiangyu Yue},
                    journal={arXiv preprint},
                    year={2025}
                    }
                    

Thank Jenga, UltraPixel and ControlNeXt to provide us the project page's template!