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

4
crossposts
You're viewing a single thread.
All comments
57
comments
These vids are just off enough that I think doing a bunch of mushrooms and watching them would be a deeply haunting experience
27 0 ReplySo essentially the music video for Drugs by Ratatat.
5 0 ReplyHere is an alternative Piped link(s):
music video for Drugs by Ratatat
Piped is a privacy-respecting open-source alternative frontend to YouTube.
I'm open-source; check me out at GitHub.
1 0 Reply
The first video her bottom teeth shift around.
2 0 Reply
57
comments
Scroll to top