项目页 https://causvid.github.io/ 🔥 多图警告！

Abstract

Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence, including the future. We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly. To further reduce latency, we extend distribution matching distillation (DMD) to videos, distilling 50-step diffusion model into a 4-step generator. To enable stable and high-quality distillation, we introduce a student initialization scheme based on teacher's ODE trajectories, as well as an asymmetric distillation strategy that supervises a causal student model with a bidirectional teacher. This approach effectively mitigates error accumulation in autoregressive generation, allowing long-duration video synthesis despite training on short clips. Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models. It enables fast streaming generation of high-quality videos at 9.4 FPS on a single GPU thanks to KV caching. Our approach also enables streaming video-to-video translation, image-to-video, and dynamic prompting in a zero-shot manner.

⚠️ This repo is a work in progress. Expect frequent updates in the coming weeks.

@inproceedings{yin2025causvid,

title={From Slow Bidirectional to Fast Autoregressive Video Diffusion Models},

author={Yin, Tianwei and Zhang, Qiang and Zhang, Richard and Freeman, William T and Durand, Fredo and Shechtman, Eli and Huang, Xun},

booktitle={CVPR},

year={2025}

}

@inproceedings{yin2024improved,

title={Improved Distribution Matching Distillation for Fast Image Synthesis},

author={Yin, Tianwei and Gharbi, Micha{\"e}l and Park, Taesung and Zhang, Richard and Shechtman, Eli and Durand, Fredo and Freeman, William T},

booktitle={NeurIPS},

year={2024}

}

@inproceedings{yin2024onestep,

title={One-step Diffusion with Distribution Matching Distillation},

author={Yin, Tianwei and Gharbi, Micha{\"e}l and Zhang, Richard and Shechtman, Eli and Durand, Fr{\'e}do and Freeman, William T and Park, Taesung},

booktitle={CVPR},

year={2024}

}

Acknowledgments

CausVid implementation is largely based on the Wan model suite.