Paper PDF Project Page

Yutong Wang ¹, Haiyu Zhang ^3,2, Tianfan Xue ^4,2, Yu Qiao ², Yaohui Wang ², Chang Xu ^1*, Xinyuan Chen ^2*

¹USYD, ²Shanghai AI Laboratory, ³BUAA, ⁴CUHK

VDOT is an efficient, unified video creation model that achieves high-quality results in just 4 denoising steps. By employing Computational Optimal Transport (OT) within the distillation process, VDOT ensures training stability and enhances both training and inference efficiency. VDOT unifies a wide range of capabilities, such as Reference-to-Video (R2V), Video-to-Video (V2V), Masked Video Editing (MV2V), and arbitrary composite tasks, matching the versatility of VACE with significantly reduced inference costs.

The codebase was tested with Python 3.10.13, CUDA version 12.4, and PyTorch >= 2.5.1.

We are grateful for the following awesome projects, including VACE, Wan, and Self-Forcing.