JavisDiT:

Joint Audio-Video Diffusion Transformer with
Hierarchical Spatio-Temporal Prior Synchronization

Kai Liu1,2, Wei Li3, Lai Chen1, Shengqiong Wu2, Yanhao Zheng1, Jiayi Ji2,
Fan Zhou1, Rongxin Jiang1, Jiebo Luo4, Hao Fei2*, Tat-Seng Chua2,
1 Zhejiang University, 2 National University of Singapore,
3 University of Science and Technology of China, 4 University of Rochester
Work in progress (*Correspondence)
ArXiv Paper HF Paper Code Model Data Video

JavisDiT has been moved to this URL under the JavisVerse project. Click to see the updates!