Skip Navigation

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

arstechnica.com 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.

Microsoft’s VASA-1 can deepfake a person with one photo and one audio track
55
55 comments
You've viewed 55 comments.