This AI startup lets you build an entire 3D universe from a single image

San Francisco-based startup World Labs has unveiled a new platform focused on what it calls Large World Models (LWMs). The company is developing these LWMs to create 3D worlds we can enter and interact with, but with a difference. These worlds are completely built up from a single image.They are already available to play with on the World Labs website with more to come in the future. Companies like Netflix are exploring how to deploy this type of AI gaming, and Midjourney is actively looking to create a Holodeck system.World Labs is headed up by Meta and Google alumni, including Fei Fei Li, one of the pioneers behind AI development research at Stanford University. By modeling 3D worlds, using 'spatial intelligence' AI, the team hopes to become a key player in the future of robotics, AI video and the Metaverse.

Creating 3D worlds with AI is not a new concept

Creating 3D worlds with AI is not a new concept. We’ve reported in the past on several attempts to transition away from flat 2D universes. However, this is the first time we’ve seen AI which comes with the kind of motion-focused interactivity which is going to be vital for future AI applications.The company’s launch demos offer a provocative look at the type of rich, colorful environments that an LWM can create on demand. Suddenly it’s much easier to see a potential Holodeck future for us all.