See Fei-Fei Li’s World Labs generate 3D environments from a single picture | TechCrunch

World Labs has announced a new AI feature that turns 2D images into tiny worlds. This tool, the first from Fei-Fei Li’s highly hyped startup, takes a prompt or 2D reference image and spits out a fully navigable 3D environment. 

By generating in 3D, World Labs can avoid some of the control and consistency issues in other image and video generators. The GenAI tool creates scenes with persistent visual aspects, real-time control, and consistent geometry, allowing creators to create precise camera movements within the generated environment — though the boundaries of the scene are still pretty close.

This kind of quick generation could have a huge impact on the way people create movies, video games, and simulators — especially when incorporated with a workflow that uses other AI video tools. Animation studios have already begun experimenting with using this tech to create consistent AI generated backgrounds to easily stage characters in various scenes.

The tool isn’t live for general use but you can explore some examples of what will be possible to create on their website.

TechCrunch has an AI-focused newsletter! Sign up here to get it in your inbox every Wednesday.