At GDC 2025, Roblox have just announced the upcoming release of Roblox Cube, a genAI model for generating 3D meshes. In addition to be integrated into Roblox Studio, it is also available as Cube 3D Foundational Model, an open source implementation.Details of Roblox Cube 3D:We are releasing our Cube 3D foundational model for generative AI.We are also open-sourcing a version of the Cube 3D foundational model.The beta version of Cube 3D mesh generationin Roblox Studio and as an in-experience Lua APIwill be available this week.Last fall, weannouncedan ambitious project to build an open-source 3D foundational model to create 3D objects and scenes on Roblox. This week, we are open-sourcing the first release for this model to make it available for use by anyone on or off the Roblox platform. Weve named this model Cube 3D. We are also launching the first of its capabilities, with the beta launch of our mesh generation API. Cube will underpin many of the AI tools well develop in the years to come, including highly complex scene-generation tools. It will ultimately be a multimodal model, trained on text, images, video, and other types of inputand will integrate with our existing AI creation tools.Cube 3D generates 3D models and environments directly from text and, in the future, image inputs. Today, state-of-the-art 3D generation uses images and a reconstruction approach to build 3D objects. This is a good option when there isnt sufficient 3D training data. However, thanks to the nature of our platform, we train on native 3D data. The generated object is fully compatible with game engines today and can be extended to make objects functional.The difference here is similar to a racetrack movie set. On TV, you might see what looks like a fully functional racetrack, with stands, garages, and a victory lane. But if you were to walk around on that set, youd quickly realize that the structures were actually flat. Building a truly immersive 3D world requires complete, functional structures, with garages you can drive into, stands you can sit in, and a victory lane with a functional podium.To achieve this, weve taken inspiration 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. Our innovation builds on the same core idea. Weve built 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. When we extend this to full scene generation, Cube 3D then predicts the layout and recursively predicts the shape to complete that layout.Anyone can fine-tune, develop plug-ins for, or train Cube 3D on their own data to suit their needs. We believe that AI tools should be built on openness and transparency, which is why we are a committed partner in the open-source AI community. We released one of ourAI safety modelsbecause we feel strongly that sharing advancements in AI safety helps the entire industry accelerate innovation and technical advancements. For this reason, we also helped foundROOST, a new nonprofit dedicated to tackling important areas in digital safety with open-source safety tools. In open-sourcing Cube 3D, our goal is to enable researchers, developers, and the broader AI community to learn, augment, and advance 3D generation industry-wide.Key LinksRoblox Cube AnnouncementWhile not available yet, it should become available in the coming days as the release is described as available later this week. You can learn more about Roblox 3D GenAI Cube in the video below.