Google DeepMind Launches Genie 4 and Project Genie for Interactive Worlds
kristianpaul · hn · 2026-11-19
Google DeepMind launched Project Genie, powered by Genie 4, its most realistic and interactive world model yet, combined with Gemini — turning ideas into explorable, shareable worlds in the browser.
- Real-time world shaping with Genie 4: trigger dynamic events with natural language (shifting weather, new characters, mid-session action changes), with simulated physics, natural lighting, and scene-matched native audio and character dialogue.
- Project Genie agent: describe a story or simulation and the agent generates starting visuals and custom background music, while Gemini observes in-session to suggest or trigger live events.
- Community gallery & remixing: jump into curated and community-built worlds, remix environments, rules, and audio; upgraded Genie 3 capabilities remain in the model picker (up to 3-minute sessions, 360° panorama grounding).
Rolling out to eligible Google AI Ultra subscribers (18+); Google AI Pro members can join the waitlist.
More from Multimodal
- Photographer crafts AI-generated digital muse Nous Girl on faux magazine cover — alexcovo_eth · 2026-11-22
- Turn any Google Maps location into a cinematic drone shot with AI — aziz4ai · 2026-11-22
- Open-source world model PAN 2 wows with GTA-like physics in driving demos — LinusEkenstam · 2026-11-22
- pi-H3 open-sourced: 768p video in under 40s on one RTX 3090 — linoy_tsaban · 2026-11-22
- 2D-to-3D character experiment: hand-drawn illustration becomes consistent 3D render — azed_ai · 2026-11-22
- "River Clash": AI-generated rural action short film with prompts included — propmt07 · 2026-11-22