DeepMind Genie
Creates interactive 2D platformer environments from images or text prompts, enabling exploration and character control in AI-generated worlds learned from public video datasets, designed for advancing research in generalizable AI and world models.
Features
- First person view
- AI-Powered
Tags
- interactive-simulation
- terrain-generator
- Generative AI
- world-model
- physics-simulation
- ai-model
- artificial-general-intelligence
- real-time-interactivity
- real-time-simulation
DeepMind Genie News & Activities
Recent News
- Danilo_Venom published news article about DeepMind Genie
Google DeepMind unveils Genie 3, an AI creating interactive Worlds from promptsGoogle DeepMind has introduced Genie 3, an advanced world model capable of generating interactive 3...
Recent activities
- kaekazeh liked DeepMind Genie
- Danilo_Venom updated DeepMind Genie
Danilo_Venom added DeepMind Genie as alternative to Google Veo, Wan, Dream Machine and Runway- Danilo_Venom added DeepMind Genie
DeepMind Genie information
Developed by
Google Licensing
Proprietary and Commercial product.Alternatives
4 alternatives listedSupported Languages
- English
What is DeepMind Genie?
DeepMind Genie is a generative interactive environment that creates new, playable worlds from an image or text prompt. It's trained on a large dataset of public internet videos, learning to infer actions and understand game mechanics without explicit instructions. Users can prompt Genie with an image or text, and it will generate a unique, playable 2D platformer world. Users can then interact with this world, controlling a character and exploring the AI-generated environment. This is a significant step towards creating AI agents that can be trained in various simulated worlds. Genie serves as a prototype for future world models, setting the stage for AI that can learn and act in diverse digital realities.