San Mateo, California-based game developer Roblox has released a 3D object generator called Cube 3D, the first of several models the company plans to make available. Cube currently generates 3D models and environments from text, and in the future the company plans to add image inputs. Roblox says it is open-sourcing the tool, making it available to users on and off the platform. Cube will serve as the core generative AI system for Roblox’s 3D and 4D plans, the latter referring to interactive responsiveness. The launch coincides with the Game Developers Conference, running through Friday in San Francisco.

The platform trains on native 3D data, generating objects and environs that are “fully compatible with game engines today and can be extended to make objects functional,” Roblox VP of Engineering Anupam Singh and VP of Creator Engineering Nick Tornow write in a blog post.

As an example, the write-up introduces an auto racetrack to describe “building a truly immersive 3D world” that has “complete, functional structures, with garages you can drive into, stands you can sit in, and a victory lane with a functional podium,” as opposed to visual facades.

Cube 3D takes its cue from “state-of-the-art models trained on text tokens (or sets of characters) so they can predict the next token to form a sentence,” innovating on that core idea by adding “the ability to tokenize 3D objects and understand shapes as tokens and trained Cube 3D to predict the next shape token to build a complete 3D object.”

Extended to scene generation, Cube 3D “predicts the layout and recursively predicts the shape to complete that layout,” the post explains.

“Cube will underpin many of the AI tools Roblox will develop in the years to come, including highly complex scene-generation tools,” VentureBeat reports, adding that “it will ultimately be a multimodal model, trained on text, images, video, and other types of input — and will integrate with our existing AI creation tools.”

This first tool is essentially mesh generation. With Cube 3D, the 19-year-old UGC game platform “is making a major bet on generative AI for game development,” says Maginative, pointing out that because it is open source, developers can customize and extend it, creating plug-ins or training the model using proprietary data.

The idea is “to speed up the asset creation process, making it easier for indie developers to build rich, detailed worlds without spending hours modeling objects from scratch,” Maginative writes.

Once an asset is generated, “creators can further adjust the in-game item within Roblox Studio,” the company’s Integrated Development Environment (IDE), notes TechCrunch.