Steve Troughton-Smith on Nostr: Here’s your AI astonishment/nightmare fuel for today: "TL;DR: single portrait photo ...
Here’s your AI astonishment/nightmare fuel for today:
"TL;DR: single portrait photo + speech audio = hyper-realistic talking face video with precise lip-audio sync, lifelike facial behavior, and naturalistic head movements, generated in real time.”
{
"id":"84344450c3395e205a2c728d0f0170bc447fb0b022ec505c17cbad8ca6742432",
"pubkey":"d24206613793725d8e4745561d07a56cfeb9dbe534fc46e0a9b2d159b0bc9ad0",
"created_at":1713413152,
"kind":1,
"tags": [
[
"proxy",
"https://mastodon.social/users/stroughtonsmith/statuses/112290244383840103",
"activitypub"
]
],
"content":"Here’s your AI astonishment/nightmare fuel for today:\n\n\"TL;DR: single portrait photo + speech audio = hyper-realistic talking face video with precise lip-audio sync, lifelike facial behavior, and naturalistic head movements, generated in real time.”\n\nhttps://www.microsoft.com/en-us/research/project/vasa-1/\n\nhttps://files.mastodon.social/media_attachments/files/112/290/244/118/322/877/original/07e5c5cb354f2fef.mp4",
"sig":"29e5354f6be56768423038b6b9e5bcb53017a4591e7d1031f85562df595af5ab206dd45c42ddec204f651a0410e56b009e3a43d47df87b1ed3f5e5e27b1634d0"
}