Google DeepMind Launches Genie 4 World Model and Project Genie for Real-Time Interactive Worlds
Google DeepMind · youtube · 2026-11-19
Genie 4 and Project Genie Launch
Google DeepMind has released Genie 4, its most realistic and interactive world model yet, along with Project Genie—an experience that turns ideas into explorable, shareable worlds right in the browser.
Key capabilities:
- Shape worlds in real time with Genie 4: trigger dynamic events via natural language—shift the weather, introduce new characters, or change the action mid-session—with simulated physics, natural lighting, scene-matched audio, and character dialogue.
- Agent-assisted building: describe the story or simulation you want; the Project Genie agent generates starting visuals and custom background music, while Gemini observes the session to suggest or trigger live events.
- Explore & remix the community gallery: jump into curated and community-built worlds, remix their environments, rules, and audio; upgraded Genie 3 (up to 3-minute sessions, 360-degree panorama grounding) remains available in the model picker.
Availability: rolling out to eligible Google AI Ultra subscribers (18+); Google AI Pro members can join the waitlist.
More from Multimodal
- NVIDIA to demo Cosmos Data Factory pipeline for training-ready synthetic datasets with Voxel51 and Encord — NVIDIAAI · 2026-11-19
- Gradium designed 16,000+ voices — here are the five parts of a good voice prompt — rdesh26 · 2026-11-19
- AI video recasts The Weeknd as Michael Jackson in striking demo — TMcFly · 2026-11-19
- AI film Gods Don't Give Gifts lands worldwide theatrical release on January 22 — DavidmComfort · 2026-11-19
- Same-seed image model shootout: Minimax H3 edges out Z-Image Turbo and Krea2 — Engine_Hungry · 2026-11-19
- Suno MCP launches for all, bringing song generation into ChatGPT and Claude — suno · 2026-11-19