World Labs’ AI system can generate a 3D world from an image

World Labs, the AI ​​startup co-founded by AI pioneer Fei-Fei Li, has released a first look at what they’re building: an AI system that can create fully interactive 3D scenes from just a single image. Imagine uploading a photo and then being able to step into that world and move through it like a scene from your favorite video game. That’s what World Labs makes possible.

Why it’s important: Unlike AI image/video generators that produce static content, World Labs’ system creates persistent 3D environments that maintain consistency as users explore them from different angles. This is a big deal, so let’s unpack it a bit.

Zoom in: First, once a world is created, it continues to exist – no sudden changes if you look away for a moment and then look back again. And in addition to visual fidelity, World Labs technology brings the physics of real life to virtual space. Users can also apply real-time camera effects such as depth of field adjustments and dolly zooms, similar to traditional filmmaking techniques. The technology also enables interactive features such as dynamic lighting changes and scene adjustments, all directly in a web browser.

The big picture: The application of 3D generative AI extends to video games, films, architecture and even virtual education. As co-founder Justin Johnson noted, creating interactive, immersive worlds today takes years of development time and huge budgets. With AI-generated world models, they hope to make this process faster and more accessible, democratizing creativity in the process.

What they say: Early makers who tested the technology are finding practical applications in their workflows. Digital artist Eric Solorio has used the system to stage characters in generated environments and orchestrate precise camera movements, demonstrating its potential for visual storytelling and content creation.

The numbers: The technology comes at a time when creative professionals are seeking greater control over AI-generated content. Earlier this year, World Labs secured $230 million in funding from investors including Andreessen Horowitz, Intel Capital, AMD Ventures, Ashton Kutcher and Eric Schmidt. The company, now valued at more than $1 billion, plans to launch its first product in 2025.

The end result: The company has shared some examples of what we can expect on their site. You can interact with scenes directly in the browser, experience effects such as depth of field or experiment with lighting. There are limitations, of course: for now you can only move within a certain area, and the occasional rendering error reminds you that this is still a work in progress.

The company hopes to make the technology generally available by 2025. If you want to follow along or be one of the first to try it out, sign up at worldlabs.ai/waitlist.