Google DeepMind rumored to launch Genie 4, a real-time photorealistic interactive world model
abhishek__AI · x · 2026-10-28
A third-party account claims Google DeepMind has released Genie 4, billed as its most realistic and interactive world model yet — generating photorealistic worlds you can explore and interact with in real time.
Highlights:
- Lifelike visuals with realistic physics
- Natively generated audio
- Prompt-driven scene changes
- Characters that react and speak
Note: unconfirmed by DeepMind officially; details remain to be verified.
Related event: Rumors: DeepMind to launch Genie 4 real-time world model(3 posts)→
More from Multimodal
- VEED launches dubbing API with built-in lip sync that preserves emotion and accent — hey_abusiddik · 2026-10-28
- Indie dev vibe-codes Try2Create, a one-click ComfyUI frontend for image, video and audio generation — ItsBalanse · 2026-10-28
- MiniMax H3 demo generates a continuous music video with seamless audio-video sync — EinhornArt · 2026-10-28
- Mundo turns photos of real places into explorable, editable interactive worlds — Scobleizer · 2026-10-28
- Google's new AI world model reportedly simulates entire worlds in real time — heykahn · 2026-10-28
- NVIDIA open-sources Nemotron 3.5 Transcribe 30B ASR model; fine-tuning cuts word error rate 45.8% — NVIDIAAI · 2026-10-28