Genie 4: A new generation of world simulation

Google DeepMind has announced Genie 4, the next generation of its world model, which generates explorable environments in real time with keyboard controls and more realism than Genie 3. It now produces sound (music, ambient noise, dialogue) together with the visuals. Users can change a running simulation with a text prompt (weather, camera, adding a person or object), with Gemini models helping keep the world consistent. For now Genie 4 is a research preview for trusted testers; Google plans to open it next to Google AI Ultra subscribers in Project Genie and to early-access partners of the Gemini API and Google AI Studio. A waitlist is open.

See original publication↗Google DeepMind (blog officiel) · deepmind.google