Roblox releases its AI-powered 3D image generator
Add Axios as your preferred source to
see more of our stories on Google.
Image: Roblox
Roblox on Monday announced an early version of a 3D object generator, the first of several AI models the company plans to release.
Why it matters: The tool could help creators develop new Roblox experiences faster, a key part of Roblox's push to capture 10% of the $180 billion global gaming market.
Driving the news: The tool, called Mesh Generator API, is powered by CUBE 3D, a 1.8 billion-parameter model that Roblox will release this week as open source.
- Developers and players using the tool can generate a 3D image by entering a text prompt, such as "draw a car with racing stripes and a spoiler."
- Roblox also plans to let users create 3D objects from a still image and is working on additional large language models that can convert speech-to-text and text-to-speech, as well as another for real-time language translation.
- The company's long-term goal is to offer tools that create entire scenes on demand.
What they're saying: "Beyond this first use case of mesh generation, we plan to extend to scene generation and understanding," Roblox said in a blog post.
- "For example, in an experience with a forest scene, a developer could ask [the API] to replace all the lush green leaves on the trees with fall foliage to indicate the change of season."
Between the lines: Roblox hopes that making it easier to create 3D content will attract new types of developers and content beyond traditional game design.
Yes, but: While the generative AI tools are free for both developers and creators, there will be caps on usage. "We do have limits, for obvious reasons," Roblox VP of engineering Nick Tornow told Axios.
