Roblox Unveils Open-Source AI Model for 3D Object Creation
Roblox has launched its open-source AI model, Cube, designed to create 3D objects using generative AI. Announced on their website, Cube allows creators to generate 3D meshes from simple text prompts, such as 'generate an orange racing car with black stripes.' This tool is available in beta and will be accessible to creators later this week.
The open-source version of Cube enables developers to customize, create plug-ins, or train the model with their own datasets. Roblox also plans to introduce additional AI tools, including text generation, text-to-speech, and speech-to-text, in the coming months.
Cube's capabilities extend beyond simple object creation. Future updates aim to support more complex objects and scene generation, allowing creators to prompt the AI to generate entire environments, such as a forest scene with seasonal changes. This initiative is part of Roblox's broader vision to enhance 3D and 4D creation, where interaction between objects, environments, and users is key.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Daily AI Brief.
Also, consider following us on social media:
More from AI in Game Development
Oct 13 Epic Games Reportedly Orders AI-First Development for Disney Shooter Oct 7 Google Labs Launches Playground for AI Game Creation Sep 22 Meshy Details Mora Architecture and Releases Meshy 7.1 Sep 19 Generative AI Use Reaches 85.8% Among Surveyed Japanese Game Developers Aug 27 Tencent Games Motus Shows AI Animation Pipeline at GamescomDaily AI Brief
Daily report covering major AI developments and industry news, with both top stories and complete market updates
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
ugee launches AI 3D printing platform for families
Configure One Launches AI Modeling and Quoting Platform
Google Labs Launches Playground for AI Game Creation
Overmind Open Sources Platform for Specialized AI Models
Blueprints AI releases expanded building blueprint generator
Daily AI Brief: the AI news that matters, in your inbox.