Genie (AI model)

Genie, Genie 2 and Genie 3 (short for Generative Interactive Environments) are artificial intelligence models developed by DeepMind that can generate game-like, action-controllable virtual worlds based on textual descriptions, images, or sketches. Built as autoregressive latent diffusion models, they frame-by-frame interactivity without requiring labeled action data for training.

The first version of Genie was introduced in March 2024.[1] Its successor, Genie 2, released in December of that year, expanded these capabilities to generate diverse and interactive 3D environments.[2] Genie 3 was released in August 2025, with higher-resolution world generations and multiple minutes of visual consistency.[3][4] On January 29, 2026, DeepMind released Project Genie to AI Ultra subscribers.[5]

References

  1. ^ Orland, Kyle (2024-03-05). "Google's Genie game maker is what happens when AI watches 30K hrs of video games". Ars Technica. Archived from the original on 2024-12-08.
  2. ^ Orland, Kyle (2024-12-06). "Google's Genie 2 "world model" reveal leaves more questions than answers". Ars Technica. Archived from the original on 13 December 2024.
  3. ^ Whitwam, Ryan (2025-08-05). "DeepMind reveals Genie 3 "world model" that creates real-time interactive simulations". Ars Technica.
  4. ^ Bellan, Rebecca (2025-08-05). "DeepMind thinks its new Genie 3 world model presents a stepping stone toward AGI". TechCrunch. Archived from the original on 2025-08-05.
  5. ^ Whitwam, Ryan (2026-01-29). "Google Project Genie lets you create interactive worlds from a photo or prompt". Ars Technica.
This article is issued from Wikipedia. The text is available under Creative Commons Attribution-Share Alike 4.0 unless otherwise noted. Additional terms may apply for the media files.