Pinned Tweet
Colibrì : l'IA géante sur ton portable, à quelle vitesse ? - Pendant la ... youtu.be/ZRq3vMOUK9c?si=AN-q… via @YouTube
28
Vincent Binet | Formateur IA retweeted
Part 2 of our $102,725 episode is here, and it's the GREATEST thing we've ever made.
Steal our 50,000-character Claude skill that makes every frame look like a $100M film.
Save this thread for later 👇🏼🧵
China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time.
one camera. no LiDAR. 10,000+ frames without breaking down.
just walk around with your camera and see the whole world rebuilt in 3D at 20 fps.
→ ~20 FPS on a single GPU
→ Stays stable across 10,000+ frames
→ Outperforms optimization-based methods on benchmarks
→ Handles driving footage, outdoor scenes and indoor walkthroughs
100% open source.
Vincent Binet | Formateur IA retweeted
Stop using image models to make images.
Our animators used a video model to make a movie poster.
In our test, GPT Image 2.6 and Nano Banana Pro changed the character’s look in all 20 takes. Seedance 2.5 kept it in 10/10.
Here’s how we did it 🧵
🤖 Made with AI
Dans les années 1930, chez Disney, aucune fiche de personnage n'était validée sans un tampon : « O.K., J.G. » (Thomas et Johnston, 1981).
1
24
L'outil se loue. L'univers, il faut l'avoir écrit.
Et toi, si tu devais entraîner une IA sur ta marque, quels documents lui donnerais-tu à lire en premier ?
1
1





