World Labs has unveiled Atlas, a multimodal AI model designed to generate, reconstruct, and simulate scenes in three dimensions. The World Labs Team announces Atlas in an official blog post, describing it as a system that works with text, images, video, camera positions, and depth data in a shared spatial context. The company says Atlas …
Google has released Project Genie, an experimental research prototype that allows users to create and explore interactive virtual worlds. The tool is now available to Google AI Ultra subscribers in the United States who are 18 or older. Project Genie is powered by Genie 3, a world model that generates interactive environments in real time. …
World Labs, the AI startup founded by researcher Fei-Fei Li, has released Marble, its first commercial product. Marble is a world model that generates editable 3D environments from various inputs including text prompts, images, videos, 3D layouts, and panoramas. The product is now publicly available through freemium and paid subscription tiers. The launch positions World …
The artificial intelligence industry faces a critical shortage of high-quality data needed to train more powerful models. A new startup, Moonlake AI, aims to solve this problem by creating data from interactive 3D worlds. Rashi Shrivastava reports for Forbes. The company was cofounded by former Stanford PhD students Sharon Lee and Fan-Yun Sun. They are …
The gaming platform Roblox is launching several new AI tools to simplify development. Aisha Malik reports for TechCrunch that these updates were announced at the Roblox Developers Conference. One tool allows creators to generate fully functional 3D objects, like drivable cars, from a simple text prompt. The company is also introducing real-time voice chat translation …
Chinese tech giant Tencent has launched HunyuanWorld-Voyager, an AI model that transforms static images into navigable 3D-like video sequences. Benj Edwards reports about the announcement for Ars Technica. The system generates 49-frame video clips lasting roughly two seconds from a single photograph. Users can define camera movements such as forward, backward, and turning motions to …
Google Deepmind has announced Genie 3, a new AI “world model” capable of generating interactive, three-dimensional environments from text prompts. According to the company’s official post, users can navigate these dynamic worlds in real time. The model generates environments at a resolution of 720p and runs at 24 frames per second. Google Deepmind states that …
Stability AI has released Stable Virtual Camera, a new multi-view diffusion model that transforms 2D images into videos. According to Ana Guillen, the research preview enables users to generate immersive videos with realistic depth and perspective without complex reconstruction or scene-specific optimization. The model can create videos from a single image or up to 32 …
Infinite Realms is developing technology to transform fantasy books into interactive game worlds using artificial intelligence. According to Dean Takahashi of VentureBeat, the company plans to license IPs from bestselling fantasy authors and convert them into living game environments. CEO Irena Pereira explained that their AI-driven engine can process book manuscripts to create worlds that …
Tencent has launched Hunyuan3D 2.0, an artificial intelligence system that generates detailed 3D models from single images or text descriptions. As Michael Nuñez reports, the system can complete tasks in seconds that typically take artists days or weeks. The technology combines two main components: Hunyuan3D-DiT for basic shapes and Hunyuan3D-Paint for surface details. According to …