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

Training-Free Efficient Video Generation via Dynamic Token Carving

Please stay tuned for all video loading...

Yuechen Zhang1, Jinbo Xing1, Bin Xia1, Shaoteng Liu1, Bohao Peng1, Xin Tao4, Pengfei Wan4, Eric Lo1, Jiaya Jia2,3

1 CUHK, 2 HKUST, 3 SmartMore, 4 Kuaishou Technology

Contact Us

Feel free to contact Yuechen Zhang at zhangyc@link.cuhk.edu.hk for any question,cooperation, and communication.

If you find this work useful, please consider citing:

@article{zhang2025trainingfreeefficientvideogeneration,
    title={Training-Free Efficient Video Generation via Dynamic Token Carving},
    author={Yuechen Zhang and Jinbo Xing and Bin Xia and Shaoteng Liu and Bohao Peng and Xin Tao and Pengfei Wan and Eric Lo and Jiaya Jia},
    journal={arXiv preprint arXiv:2505.16864},
    year={2025}
}

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