Technology @lemmy.world fart_pickle @lemmy.world 2mo ago

VASA-1: Lifelike Audio-Driven Talking Faces

www.microsoft.com VASA-1 - Microsoft Research

Opens in a new tab

Single portrait photo + speech audio = hyper-realistic talking face video with precise lip-audio sync, lifelike facial behavior, and naturalistic head movements, generated in real time.

Hacker News @lemmy.smeargle.fans bot @lemmy.smeargle.fans

BOT

3mo ago

VASA-1: Lifelike audio-driven talking faces generated in real time

www.microsoft.com /en-us/research/project/vasa-1/

0 comments