From the source
Google DeepMind released Genie 4, its newest world model, in research preview on Tuesday, generating photorealistic interactive worlds with real-time audio and mid-simulation prompt edits.
- The model can maintain a consistent scene for up to two minutes, double Genie 3's limit, and adds better physics and more human-like characters, according to the company.
- Gemini is more closely integrated with Genie 4, acting as a director that plans steps and checks frames while Genie creates the visuals.
- In a research experiment tied to Gemini Robotics, a Gemini 4 Argon model broke down tasks into steps that Genie 4 simulated in real time, showing a possible way to test robot scenarios in simulation before they happen in the real world.
- Google's Tejas Kulkarni said the future will bring hybrid world models combining Gemini writing code and text with Genie simulating reality at different levels of abstraction.
- Trusted testers are pointing to film prototyping as a new use, with Google DeepMind engineer Diego Rivas saying the real-time aspect is most valuable during ideation and storyboarding.
- Rivas stressed it is still early days and the team acknowledged gaps: details and objects can drift the longer a simulation runs, and audio accuracy and in-world text legibility are unsolved.
- Genie 4 is available now as a research preview for trusted testers, and will roll out in the coming weeks to Google AI Ultra subscribers in Project Genie and to early access partners of the Gemini API and Google AI Studio.