Google DeepMind releases Genie 4 world model in research preview

The new model generates photorealistic, interactive worlds with real-time audio and improved physics.

Google DeepMind released its newest world model, Genie 4, in research preview on Tuesday. The model generates photorealistic and interactive worlds that allow users to type prompts mid-simulation to change the scene. It can maintain a consistent scene for up to two minutes, which is double the limit of Genie 3.

Genie 4 includes native real-time audio that matches the simulated world, such as ambient noises, music, and interactive dialogue. Users can perform free-form edits in real time, including changing the weather, camera angles, or adding new objects and people. The model offers improved physics, such as better aerodynamics and collisions, and features more humanlike characters.

Google's Gemini model is integrated with Genie 4 to act 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. This provides a way to test robot scenarios in simulation before they occur in the real world.

Tejas Kulkarni, a research director at Google, said that future hybrid world models will combine Gemini writing code and text with Genie simulating reality in real time. While commercial use cases include gaming, interactive learning, and robotics, trusted testers have pointed to prototyping films as a possible new use.

Diego Rivas, a Google DeepMind engineer, said the real time aspect is valuable for rapid ideation in the storyboarding and ideation phases.

Google plans to roll out Genie 4 for developers via the Gemini API and AI Studio, though pricing is not yet available. Consumers will access the model in phases through Google's AI Ultra plans, which start at $100 per month.

Key facts

  • Genie 4 can maintain a consistent scene for up to two minutes.
  • The model features native real-time audio, including music and interactive dialogue.
  • Google plans to offer Genie 4 to consumers via AI Ultra plans starting at $100 per month.

Three perspectives

Neutral

Google DeepMind has released Genie 4, a world model capable of generating interactive, photorealistic simulations with real-time audio.

Positive

The model offers improved physics, more humanlike characters, and the ability to simulate robot scenarios before they happen in the real world.

Negative

Genie 4 still faces challenges with object drift during long simulations and ensuring the accuracy of audio and in-world text.

Your week in news, every Wednesday

The biggest stories of the week for your edition, in your inbox every Wednesday morning, your time. Free, and you can unsubscribe at any time.

Choose your news coverage

Please choose and confirm your coverage.

All sections

Edition