VideoCrafter2 : Overcoming Data Limitations
for High-Quality Video Diffusion Models


Haoxin Chen, Yong Zhang*, Xiaodong Cun, Menghan Xia, Xintao Wang, Chao Weng, Ying Shan
Tencent AI Lab

Paper Code Demo Discord

VideoCrafter2 Improves: Visual Quality, Motion, Concept Composition

Exquisite film, produced by VideoCrafter2, directed by Human

Try VideoCrafter2 now !

Notes

- Citation: If you are using the code, models, and data in your research or are inspired by our work, please cite.

- License: Our code, models and data are distributed under Apache 2.0 License.

Acknowledgements

The website template was borrowed from Open X-Embodiment.