Google's Genie 2 creates small 3D game worlds from just an AI prompt, complete with physics, reflections, and even NPCs.

DeepMind, Google's AI research org, has unveiled a model that can generate an 'endless' variety of playable 3D worlds.

Genie 2 is a new foundation model capable of generating an "endless" amount of 3D environments that can be controlled by the ...

Creating realistic 3D models for applications like virtual reality, filmmaking, and engineering design can be a cumbersome ...

This licensed-digital-content company created an AI tool to generate images using its photo library. It's now pursuing new ...

Led by AI scientist Fei-Fei Li, World Labs says it is building Large World Models (LWMs) and wants to generate in 3D for use ...

DeepMind's Genie 2, an AI transforming single images into interactive 3D environments and playable games from text prompts.

An AI method enables the generation of sharp, high-quality 3D shapes that are closer to the quality of the best 2D image models. Previous approaches typically generated blurry or cartoonish 3D shapes.

DeepMind has unveiled its Genie 2, an advanced AI model that creates immersive 3D worlds from text prompts or images, ...

While no one outside of Google can yet play around with Genie 2's output, the company is eager to tout its potential use ...