Google Genie 2

AI model that can create an endless variety of playable 3D worlds - all from a single image.

Google Genie 2 is a cutting-edge AI model designed to generate a limitless variety of interactive, playable 3D worlds from a single image prompt. It serves as a foundation world model, enabling the creation of diverse environments for training and evaluating AI agents. With capabilities like simulating object interactions, complex animations, and realistic physics, Genie 2 supports rapid prototyping of interactive experiences. It can generate consistent, detailed worlds for up to a minute, responding intelligently to user inputs. This model not only accelerates AI research by providing rich training environments but also opens new creative possibilities for designers and researchers, paving the way for advancements in general AI systems.