Context: 

Recently, Google DeepMind has introduced Genie, a new AI model

Background:

Genie is currently not available to the public and only exists as a research model for now.

About GENIE AI MODEL: 

1. The Foundation: Genie is a foundational world model trained on videos sourced from the Internet.
2. Generative Capabilities: It can generate an endless variety of playable (action-controllable) worlds from synthetic images, photographs, and even sketches.
3. Training: It is the first generative interactive environment that has been trained in an unsupervised manner from unlabelled internet videos.
4. Functionality: These technical specifications let Genie act in generated environments on a frame-by-frame basis even in the absence of training, labels, or any other domain-specific requirements.
5. Diversity: Genie can be prompted to generate a diverse set of interactive and controllable environments although it is trained on video-only data.
6. Interactivity: It makes playable environments from a single image prompt. It can be prompted with images it has never seen. This includes real-world photographs, and sketches, allowing people to interact with their imagined virtual worlds.
7. This revolutionary generative AI allows anyone, including children, to immerse themselves in generated worlds resembling human-designed environments.
8. The standout aspect of Genie is its ability to learn and reproduce controls for in-game characters exclusively from internet videos.
9. This is noteworthy because internet videos do not have labels about the action that is performed in the video, or even which part of the image should be controlled.