World Labs has announced a new AI feature that turns 2D images into miniature worlds. The tool, the first from Fei-Fei Li's highly touted startup, takes a prompt or 2D reference image and spits out a fully navigable 3D environment.
By producing in 3D, World Labs can avoid some of the control and consistency issues with other image and video production devices. GenAI tools create scenes with persistent visual aspects, real-time control, and consistent geometry, allowing creators to create precise camera movements within the generated environment. However, the scene boundaries are still quite close.
This kind of rapid generation could have a huge impact on how movies, video games, and simulators are created, especially when incorporated into workflows that use other AI video tools. Animation studios have already begun experimenting with this technology to create consistent AI-generated backgrounds to easily stage characters in different scenes.
This tool is not available to the public, but you can explore some examples of what you can create on the website.