MuseV

MuseV is an AI-based video generation system that is unique in that it can generate high-definition virtual character videos of any length. Previous AI video generation technologies were often limited to short videos, because the longer the generation time, the more likely the picture will be distorted and errors will accumulate. MuseV breaks through this limitation by using a new method called "visual conditional parallel denoising". Simply put, it divides the entire long video into multiple short clips, generates them in parallel, and then splices them together. In this way, even "endlessly long"...

Tencent's Tianqin Lab has just open-sourced the AI digital human MuseV project, the full name of which is: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising. MuseV and its later released MuseTalk video lip sync...