World Labs, a unicorn AI startup with a valuation of more than $1 billion, unveiled on Monday a new artificial intelligence that can transform any image into a 3D world.
World Labs writes at a thread in X that its new AI system works by taking an image, approximating the 3D geometry and filling in the scene so there's more to see. AI adapts to different art styles and scenes.
The output is fully interactive, so viewers can see the 3D scenes as if they were inside them with a portable camera. They can zoom in and out and move around the space.
Related: Testers reveal OpenAI's new AI video generator, claiming they were used as 'unpaid work'
“Most GenAI tools render 2D content like images or videos,” World Labs has written in a blog post. “Generating in 3D improves control and consistency. This will change the way we make movies, games, simulators and other digital manifestations of our physical world.”
We have been busy building an AI system to generate 3D worlds from a single image. Check out some early results on our site, where you can interact with our scenes right in the browser!https://t.co/ASD6ZHMwxI
1/n pic.twitter.com/tuvGXHmepP
— World Labs (@theworldlabs) December 2, 2024
While World Labs it is not THE first to explore this area, it is the first to make its 3D worlds explorable, per TechCrunch. Viewers can interact with the AI-generated scenes on the World Labs website from a web browser.
In one demonstrationWorld Labs brings viewers to the 1942 painting Nighthawks by Edward Hopper. With a few clicks, viewers can move freely within the world created by the painting.
We also had fun seeing the world behind some creative masterpieces, like the neighborhood surrounding the restaurant in Edward Hopper's iconic painting Nighthawks.
6/n pic.twitter.com/QSTDnZfkwb
— World Labs (@theworldlabs) December 2, 2024
Painting Nighthawks by Edward Hopper. Photo by VCG Wilson/Corbis via Getty Images
In another demo, the content creator and animator Eric Solorio shows how he uses the technology to rapidly generate 3D environments and scenes.
“The process was very quick and easy,” Solorio said. “Something impossible before, with this level of precision.”
@8bit_e shows how our models fill a gap in his creative workflow, making it easy to stage characters within scenes and direct precise camera movements.
8/n pic.twitter.com/AIbhFtXU1B
— World Labs (@theworldlabs) December 2, 2024
World Labs says AI-generated images can be used as the foundation for 3D spaces, too, and the entire process of creating a 3D world, from the image to the world itself, can be generated by AI.
Although these demos are a “first early preview” of what its technology can do, according to the company, the team is working to make the created worlds bigger and more true to form. The company hopes to have its own the first product ready sometime next year.
Related: I tested 3 AI Headshot generators and a clear winner emerged