Last year, Roblox launched an open-source artificial intelligence model that could generate 3D objects on the platform, helping users quickly design digital objects such as furniture, vehicles and accessories. The company claims that the tool, called Cube 3D, has so far helped users create more than 1.8 million 3D objects since its launch in March last year.
On Tuesday, the company launched an open beta for its long-awaited 4D creation feature, which allows creators to create not only static 3D models, but fully functional and interactive objects. This feature has been in early access since November.
Roblox says 4D creation adds an important new layer: interactivity. Using this technology, users can design objects that can move and react to players in the game.
At launch, there are two types of object templates (called schemas) that developers can try.
The first is the “Car-5” scheme, which is used to create a car composed of five separate parts: the main body and four wheels. Previously, cars were the only fixed 3D object that could not move. The new system divides objects into parts and assigns behavior to each so that they function independently in the virtual world. So AI can generate cars with spinning wheels, making them more realistic and interactive.
The other is called “Body-1”, which can create any object made from one piece, such as a simple box or a statue.
The first experience with 4D generation is a game called Wish Master, where players can generate cars that can drive, planes that can fly, and even kites.
Techcrunch event
Boston, MA
|
June 23, 2026
In the future, Roblox plans to let creators create their own schemas, so they’ll have more freedom to define how objects behave. The company says it’s also developing new technology that could use a reference image to create a detailed 3D model that matches the style of the image (example below).

The company says it’s developing other ways to help people create games and experiences with AI, including a project it calls “dreaming in real time.” Roblox CEO David Baszucki explained last month that the project will allow creators to build new worlds using “keyboard navigation and real-time sharing of text prompts.”
The open beta follows Roblox’s recent implementation of mandatory facial verification for users to access in-game chat features, following child safety-related lawsuits and investigations.