World Labs, a Unicorn AI startup valued at over $1 billion, unveiled a brand new AI on Monday that may turn any image right into a 3D world.
World Labs wrote in a thread about X that the brand new AI system takes a picture, approximates the 3D geometry and fills the scene so more could be seen. The AI adapts to different art styles and scenes.
The output is fully interactive, allowing the viewer to view the 3D scenes as in the event that they were inside with a moving camera. You can zoom out and in and move across the room.
Related: Testers leak OpenAI’s latest AI video generator, claiming it was used as “unpaid labor.”
“Most GenAI tools create 2D content such as images or videos,” World Labs wrote in a blog post. “Instead, generating in 3D improves control and consistency. This will change the way we create films, games, simulators and other digital manifestations of our physical world.”
We were busy constructing an AI system to generate 3D worlds from a single image. Check out some early results on our website, where you may interact with our scenes right within the browser!https://t.co/ASD6ZHMwxI
1/n pic.twitter.com/tuvGXHmepP
— World Labs (@theworldlabs) December 2, 2024
During World Labs will not be The First To explore this area, it’s the primary company to make its 3D worlds explorable TechCrunch. Viewers can interact with the AI-created scenes on the World Labs website via an internet browser.
In one demonstrationWorld Labs takes the viewer contained in the 1942 painting night owls by Edward Hopper. With just just a few clicks, the viewer can move freely on the earth created by the painting.
We also had a good time peeking into the worlds behind some creative masterpieces, just 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
The painting Nighthawks by Edward Hopper. Photo by VCG Wilson/Corbis via Getty Images
In one other demo, content creator and animator Eric Solorio shows how he uses the technology to quickly create 3D environments and scenes.
“The process was very quick and easy,” Solorio explained. “Something previously impossible with this precision.”
@8bit_e shows how our models fill a niche in his creative workflow, making it easier to direct characters inside scenes and control precise camera movements.
8/n pic.twitter.com/AIbhFtXU1B
— World Labs (@theworldlabs) December 2, 2024
World Labs says that AI-generated images could be used as a basis also for 3D spaces and the complete means of making a 3D world, from the image to the world itself, could be AI-generated.
Although these demos are a “first early preview” of what the technology can do, the corporate says the team is working to make the worlds generated larger and more true to form. The company hopes so first product finished sometime next 12 months.
Related: I attempted 3 AI headshot generators and there was a transparent winner
