"Like many of Google's other experimental efforts, Project Genie is rolling out through Google Labs, where users can generate and explore short interactive environments from text or image prompts. Built on DeepMind's Genie 3 world-model research, the prototype lets users move through AI-generated scenes in real time and regenerate variations using revised prompts, rather than serving as a full game engine or production tool."
"Demos shown on Google's Project Genie website show various examples, like a cat exploring a living room from the back of a Roomba, a car exploring the surface of a rocky moon, and a person in a wingsuit flying down the side of a mountain. All of the worlds can be navigated in real time, and while they're generated as characters move through them, the worlds are consistent, so backtracking won't result in new areas being generated on top of old ones."
Project Genie is an experimental AI world-model prototype that generates explorable 3D environments from text or image prompts. The prototype is available to Google AI Ultra subscribers in the US via Google Labs. Built on DeepMind's Genie 3 research, the system creates environments autoregressively, producing frames based on the world description and user actions. Users can move through AI-generated scenes in real time and regenerate variations with revised prompts. Worlds remain largely consistent for several minutes, with memory recalling changes for up to a minute. Generation is currently limited to 60 seconds and the prototype is not a full game engine or production tool.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]