Roblox Unveils Cube 3D: Open-Source AI Model for Generating 3D Objects

Roblox releases its open-source model that can create 3D objects using AI | TechCrunch

Roblox announced Monday that it's launching the first iteration of its 3D model, dubbed "Cube," to allow creators to create 3D objects using generative AI. The company also launched an open-source version so anyone off the platform can build on it. Announced last year at Roblox's annual developer conference, the company is demoing Cube at the Game Developers Conference (GDC) later this afternoon. Creators will have access to Cube later this week, which includes its first tool: mesh generation. Cube's 3D mesh generation, currently available in beta, enables creators to "meshes," or 3D representations of objects, using a single prompt. For instance, "generate an orange racing car with black stripes." Creators can further adjust the in-game item within Roblox Studio. The open-source version of Cube 3D allows anyone to customize, create plug-ins, or train the model with their own datasets to fit their needs. Roblox also announced three additional AI tools- text generation, text-to-speech, and speech-to-text. These capabilities will launch in the coming months. The text generation tool lets developers add text-based AI features to their games. This includes giving players the option of having conversations with interactive non-player characters (NPCs). Text-to-speech, meanwhile, lets developers add narration, have NPCs speak, or include spoken captions in their games. Speech-to-text allows players to use voice commands, like directing characters to move forward. Other future plans the company has include launching mesh generation for more "complex" objects and scene generation, Roblox explains. The scene generation tool, for instance, will allow creators to prompt the AI to make a full forest scene and change the green leaves on trees to fall colors to show the season changing. As Roblox previously stated last year, the long-term goal is to have the 3D objects and scenes fully functional, which it calls "4D creation." "Where the fourth dimension is interaction between objects, environments, and people," Nick Tornow, vice president of engineering at Roblox, told TechCrunch. As with any company exploring generative AI tools, Roblox believes Cube will help creators work faster, allowing indie developers to take on bigger projects. The company has already released several AI tools, including for texture generation and avatar creation. AI tools in gaming are a hot topic, with several companies making advancements in the space. Most recently, Tencent launched its open-source 3D generation model, designed to generate 3D models through text prompts or 2D images. However, the use of AI continues to raise concerns within the industry. As indicated in GDC's recent report, 30% of game developers feel that generative AI is negatively affecting the gaming space. According to a CVL Economics study, it's projected that 13.4% of gaming jobs could be impacted or replaced by AI by 2026.

Roblox's new AI model can generate 3D objects

Jay Peters is a news editor covering technology, gaming, and more. He joined The Verge in 2019 after nearly two years at Techmeme. Roblox is launching and open-sourcing Cube 3D, the first version of its foundational AI model for generating 3D objects. "With Cube, we intend to make 3D creation more efficient," Roblox says in a press release. "With 3D mesh generation, developers can quickly explore new creative directions and increase their productivity by deciding rapidly which to move forward with." The model is trained on 3D objects, as Roblox explains in its press release: To achieve this, we've 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. We've 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. The actual data used to train the model includes "a combination of licensed and publicly available datasets, as well as experience data from the Roblox ecosystem," spokesperson Samantha Spielman tells The Verge. Down the line, Cube 3D will be able to generate objects using images as inputs, too. "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," according to Roblox.

Roblox's new AI can generate 3D objects from text

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. 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. 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.

GDC 2025: Roblox says its new AI generator will allow groundbreaking '4D creation'

With the 2025 Game Developers Conference underway in San Francisco, the online game platform and creation system Roblox has launched its Roblox Cube 3D generative AI model for building 3D objects and scenes. The open-source foundational model can generate 3D models and environments from text prompts for now, but there are plans to add support for reference images. Ultimately, Roblox plans to expand the model to allow what it calls '4D creation' compatible with the best game development software. Anyone can use Cube 3D, and it's not necessary to use the the Roblox platform. Since it's being made open source, anyone can fine-tune, develop plug-ins for, or train Cube 3D on their own data. Roblox says the AI allows developers to model props or design their space much faster, with no need to spend hours modeling simple objects. In the announcement, Roblox notes that current state-of-the-art 3D generation uses images and a reconstruction approach to build 3D objects, which it says is a good option when there isn't sufficient 3D training data. But Roblox trains on native 3D data. The generated object is fully compatible with game engines today and can be extended to make objects functional, it says. It compares the difference 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, you'd 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, we've 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. We've 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." Roblox said the core technical breakthrough was 3D tokenization, which allows it to represent 3D objects as tokens in the same way that text can be represented as tokens. This gives us the ability to predict the next shape just as language models predict the next word in a sentence. To achieve 3D generation, Roblox designed a unified architecture for autoregressive generation of single object, shape completion, and multiobject/scene layout generation. This architecture provides scalability and multimodal compatibility so that as Roblox expands the model, it will work with different kinds of input. Roblox says Cube will underpin more AI tools in the years to come, including highly complex scene-generation tools. The plan is to make it a multimodal model, trained on text, images, video and other types of input, integrating with the company's existing AI creation tools through its AI-powered assistant in Roblox Studio. Ultimately, the objective is for the 3D objects and scenes generated to be fully functional. Roblox calls this '4D creation', the fourth dimension being the interaction between objects, environments and people. Achieving this requires the AI's ability to to understand the contexts and relationships between those objects. The news provides another example of how AI is changing game design. Next week, Nvidia ACE-powered AI-generated characters will make their debuts in two games: Naraka: Bladepoint Mobile and the Sims-like inZOI. However, the latest Unity Gaming Report suggests that AI isn't the 'creative cure-all' that some hoped.