Google's DeepMind department has just announced its latest AI model, which it calls Genie 2. Genie 2 is able to generate playable 3D worlds on demand.

Google’s Genie 2 builds on this legacy, representing a natural evolution of procedural generation. There’s no announced launch date, but you can play with Genie 2 online soon.

For Genie 2, Google only says that "the samples in this blog post are generated by an undistilled base model, to show what is possible. We can play a distilled version in real-time with a ...

Google DeepMind, a leader in AI innovation , has unveiled Genie 2, a groundbreaking tool capable of creating limitless, diverse 3D environments for training and evaluating AI agents.

Google’s Genie 2 redefines gaming with AI-generated 3D environments, realistic physics, and adaptive gameplay. Explore the future of gaming ...

Google DeepMind CEO Demis Hassabis showed 60 Minutes Genie 2, an AI model that generates 3D interactive environments, which could be used to train robots in the not-so-distant future.

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future ...

DeepMind, Google’s AI research org, has unveiled a model that can generate an “endless” variety of playable 3D worlds.. Called Genie 2, the model — the successor to DeepMind’s Genie ...

According to Google, Genie 2 represents a massive improvement over Genie 1, which could generate 2D worlds. Simulating a 3D world also includes actions such as jumping and swimming.

While Genie 1 could create a diverse array of 2D worlds, Google Genie 2 represents a significant leap forward in generality, as it can generate a vast diversity of rich 3D worlds.

Last week, Google DeepMind announced Genie 2, a new video model that generates plausible, consistent, playable 3D environments based on a prompt image.

How Genie 2 Works. The process begins with an image prompt, often created through Google’s text-to-image AI tool Imagen 3, though real-world images are also supported.