Artificial Intelligence

197 readers

74 users here now

Chat about and share AI stuff

founded 2 years ago

MODERATORS

Stability AI releases Stable Virtual Camera, an AI model with a non-commercial use license that can create “immersive” 3D videos using up to 32 2D images. (stability.ai)

submitted 3 days ago* (last edited 3 days ago) by [email protected] to c/[email protected]

1 comments fedilink hide all child comments

Introducing Stable Virtual Camera, currently in research preview. This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization.

The model generates 3D videos from a single input image or up to 32, following user-defined camera trajectories as well as 14 other dynamic camera paths, including 360°, Lemniscate, Spiral, Dolly Zoom, Move, Pan, and Roll.

Stable Virtual Camera is available for research use under a Non-Commercial License. You can read the paper here, download the weights on Hugging Face, and access the code on GitHub.

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 1 points 1 day ago* (last edited 1 day ago)

Interesting. How fast is it? I keep waiting for AI videogame rendering, which I expect would blow conventional algorithms out of the water. (Obviously that's a bit different, because you can't predict future frames perfectly, but still)