Microsoft dropped VASA-1.
This AI can make single image sing and talk from audio reference expressively. Here are some examples.
https://v.nostr.build/kZD7A.mp4
https://v.nostr.build/5G5ng.mp4
https://v.nostr.build/DjG6a.mp4
Why all women?
Please Login to reply.
We need more diversity!
In all seriousness they did have couple male examples I just forgot to download and add here.
