Genie 3
Real-time interactive world model that generates explorable 3D environments.
Genie 3 is Google DeepMind’s general-purpose world model: it turns a text description into a photorealistic environment you can explore in real time at 720p and 20–24 fps, with “promptable world events” that change weather or add objects mid-session. Worlds stay consistent for a few minutes. Available through the experimental Project Genie prototype.
- Provider
- Type
- World model
- Released
- Aug 5, 2025
- Input
- text
- Output
- video
- Open weights
- No
Best for
- Multimodal
- Research
- Agents
Strengths
- Interactive in real time
- Promptable world events
- Minutes-long consistency
More from Google
- Gemini 4 Argon — Google. Google’s next-generation frontier model, currently restricted to vetted cyber defenders.
- Gemini 3.8 Flash — Google. Google’s most intelligent Flash model — fully multimodal, fast and affordable.
- Gemini 3.5 Flash Lite — Google. High-efficiency multimodal model for focused subagent tasks.
- Nano Banana 2.1 — Google. Google’s latest image generation and editing model.
- Gemma 4 31B — Google. Open-weight dense multimodal model from Google DeepMind.
- Gemma 4 26B A4B — Google. Open MoE Gemma: ~31B-class quality with only 3.8B active parameters.
- Gemini Embedding 2 — Google. Google’s first multimodal embedding model.
- Gemini Omni Flash 1.1 — Google. Google’s fast, low-cost video generation model.