Microsoft's VASA-1 can deepfake a person with one photo and one audio track

YouTube videos of 6K celebrities helped train AI model to animate photos in real time.

Related Keywords

Chong Li ,Jiaolong Yang ,Baining Guo ,Xin Tong ,Mona Lisa ,Sicheng Xu ,Yu Xiao Guo ,Conan Obrien ,Yizhong Zhang ,Zhenyu Zang ,Guojun Chen ,Anne Hathaway ,Microsoft Research Asia ,Youtube ,Alibaba Institute For Intelligent Computing ,Microsoft ,University Of Oxford ,Lifelike Audio Driven Talking Faces ,Real Time ,Lifelike Audio Driven Talking Faces Generated ,Affective Skills ,Emote Portrait Alive ,Intelligent Computing ,