"This past summer, Google DeepMind debuted Genie 3. It's what's known as a world world, an AI system capable of generating images and reacting as the user moves through the environment the software is simulating. At the time, DeepMind positioned Genie 3 as a tool for training AI agents. Now, it's making the model available to people outside of Google to try with Project Genie."
"To start, you'll need Google's $250 per month AI Ultra plan to check out Project Genie. You'll also need to live in the US and be 18 years or older. At launch, Project Genie offers three different modes of interaction: World Sketching, exploration and remixing. The first sees Google's Nano Banana Pro model generating the source image Genie 3 will use to create the world you will later explore."
Google DeepMind released Genie 3, a world model that generates images and reacts to user movement within simulated environments. Project Genie opens access to Genie 3 for external users but requires Google's $250-per-month AI Ultra subscription, U.S. residency and a minimum age of 18. Project Genie offers World Sketching, exploration, and remixing modes. Nano Banana Pro generates a source image and provides a sketch for user tweaks while letting users specify characters and camera perspectives such as first-person, third-person or isometric. Genie 3 is not a game engine; outputs can be game-like, generations are limited to 60 seconds, and presentation is capped at 24 fps and 720p.
Read at Engadget
Unable to calculate read time
Collection
[
|
...
]