Genie (AI model)

Last updated

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 page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.