The brief
Genie 4 incorporates capabilities from the Gemini family, including Gemini Omni, which anchors simulations in real-world appearance and behavior. The model also builds on other Gemini models that provide complex reasoning to maintain a simulation's coherence and continuity. With Genie 4, users can set an event in motion and steer scenes in real time using natural language, allowing for actions like moving the camera, changing the weather, or introducing new characters.
Every world generated by Genie 4 produces native audio on the fly, including ambient sounds, music, and interactive dialogue. This capability is part of the model's ability to bring unprecedented realism to real-time interactive simulation. Simulating the world with Genie 4 is seen as a crucial step toward achieving Artificial General Intelligence (AGI), enabling safe training environments for robots and agents.
