Chen Sun (@jesu9)

2025-05-28 | โค๏ธ 52 | ๐Ÿ” 5


Can you inject causal control to models trained solely on video data? How about eliciting their understanding of physical forces when animating a photo? Nateโ€™s latest project shows that both are promising directions to explore! I tried it on my favorite photo, and you should too! https://github.com/brown-palm/force-prompting

๋ฏธ๋””์–ด

video


์ธ์šฉ ํŠธ์œ—

Nate Gillman (@GillmanLab)

Ever wish you could turn your video generator into a controllable physics simulator?

Weโ€™re thrilled to introduce Force Prompting! Animate any image with physical forces and get fine-grained control, without needing any physics simulator or 3D assets at inference. ๐Ÿงต(1/n)

์›๋ณธ ํŠธ์œ—

๐ŸŽฌ ์˜์ƒ

Tags

domain-ai-ml