Meta’s Movie Gen: ‘AI models designed to create & manipulate 🎥, 🔊, & 🖼️, incl creating realistic video from a single photo of a person…models outperform other video-synthesis models when evaluated by ppl, pushing us closer to a future where anyone can synthesize a full vid of any subject on demand.’
The use cases will all be as wholesome as making women from photos drink pumpkin spice lattes.
https://arstechnica.com/ai/2024/10/metas-new-movie-gen-ai-system-can-deepfake-video-from-a-single-photo
https://arstechnica.com/ai/2024/10/metas-new-movie-gen-ai-system-can-deepfake-video-from-a-single-photo/
Renee DiResta /
npub1w3…53ufe
2024-10-05 04:42:08
Author Public Key
npub1w3psc006v30xfvpsjxssh07ju23rrjp2j67xzpl73emc85lp0rus253ufeSeen on
wss://relay.mostr.pubPublished at
2024-10-05 04:42:08Event JSON
{
"id": "d88e36d04064f2be81eb08bb0aabd9dc188ffa27f1fae225d7facd3b41734c48",
"pubkey": "74430c3dfa645e64b03091a10bbfd2e2a231c82a96bc6107fe8e7783d3e178f9",
"created_at": 1728103328,
"kind": 1,
"tags": [
[
"p",
"d01c4853a58122cf9a378760453a3acfa0c4f9c5c7adb8bc97bb48a364d4a578",
"wss://relay.mostr.pub"
],
[
"proxy",
"https://threads.net/ap/users/17841460782220944/post/17933669978928781/",
"activitypub"
]
],
"content": "Meta’s Movie Gen: ‘AI models designed to create \u0026 manipulate 🎥, 🔊, \u0026 🖼️, incl creating realistic video from a single photo of a person…models outperform other video-synthesis models when evaluated by ppl, pushing us closer to a future where anyone can synthesize a full vid of any subject on demand.’\n\nThe use cases will all be as wholesome as making women from photos drink pumpkin spice lattes.\n\nhttps://arstechnica.com/ai/2024/10/metas-new-movie-gen-ai-system-can-deepfake-video-from-a-single-photo\n\nhttps://arstechnica.com/ai/2024/10/metas-new-movie-gen-ai-system-can-deepfake-video-from-a-single-photo/",
"sig": "d638aa29b14d774bfc6ac345fb0860f6703d074a1789debdfec78635d79165ecdd220d8a004f0bcac3c3ad3e4582267268d3ca686b3035369789fb5d2c089e30"
}