Ars Technica on Nostr: Microsoft’s VASA-1 can deepfake a person with one photo and one audio track YouTube ...
Published at
2024-04-19 13:07:11Event JSON
{
"id": "a897ed235100890fc8d20fdb339962385b9b0fcb9c93e57694d7666a26d6b373",
"pubkey": "509c345f0518ca1421ba9f26a98ac6b0b6f884b1874ed9c20320fd41158313e4",
"created_at": 1713532031,
"kind": 1,
"tags": [
[
"proxy",
"https://mastodon.social/users/arstechnica/statuses/112298035216149518",
"activitypub"
]
],
"content": "Microsoft’s VASA-1 can deepfake a person with one photo and one audio track\n\nYouTube videos of 6K celebrities helped train AI model to animate photos in real time.\n\nhttps://arstechnica.com/information-technology/2024/04/microsofts-vasa-1-can-deepfake-a-person-with-one-photo-and-one-audio-track/?utm_brand=arstechnica\u0026utm_social-type=owned\u0026utm_source=mastodon\u0026utm_medium=social\n\nhttps://files.mastodon.social/media_attachments/files/112/298/035/156/079/383/original/d5163fbe9460d250.jpg",
"sig": "ebad81367bc9dc20469e6b7c4f71ffa9e07d39a1dafdb8a3220e216af8df9556412d7bf9d292f142bd95baaac0858ed26cca67b7cfb0b550f78eacc41716fca0"
}
