Google DeepMind opens Genie 4 to AI Ultra subscribers
The story so far
Google DeepMind introduces a new version of Project Genie, opening up Genie 4's world model for the first time, currently only available to eligible Google AI Ultra subscribers; Google AI Pro members can join the waiting list on the same page. According to Google DeepMind, Genie 4 supports users inputting new prompts during exploration, modifying scene content such as weather, characters, or plots in real-time, and for the first time, pairing with real-time native audio that changes with the visuals. Genie 3 remains in the model selector for use when longer duration or panoramic starting scenes are needed, and has been upgraded to single-generation longest 3 minutes, supporting world continuity and 360-degree panoramic image generation. Google DeepMind states that all videos and audio generated by Project Genie are watermarked with SynthID, and both model input and output undergo security screening.
AI-written from the reports · Updated 27 minutes ago
Coverage timeline
Follow the coverage to see every side of the story.
- The DecoderGoogle Deepmind's Project Genie update brings Genie 4, chainable worlds, and a community gallery for remixing
Google Deepmind releases Genie 4, its most advanced interactive 3D world model, now open to Google AI Ultra subscribers, supporting real-time world reshaping through text.
- Google DeepMindFeaturedGenie 4 is now available
Google DeepMind has launched a new version of Project Genie for eligible Google AI Ultra subscribers, opening up Genie 4's world model for the first time. Genie 4 supports real-time scene modification by inputting new prompts during exploration and, for the first time, pairs with dynamic native audio that changes with the visuals. Genie 3 has also been upgraded to generate single images up to 3 minutes long, supporting world continuity and 360-degree panoramic image generation.
Heat over time
Not enough data yet to draw a trend.