New Delhi: Google DeepMind has introduced a new AI model called Genie 3, which can generate 3D worlds while being interactive. The users just need to enter a text prompt describing the environment that the model will then simulate in real time at 24 frames per second, maintaining consistency at 720p for a few minutes. Google last year, Google released their first world models, Genie 1 and Genie 3. Additionally, advanced AI video generation models like Veo 2 and Veo 3 also demonstrate an understanding of the physical world.
What if you could not only watch a generated video, but explore it too? 🌐
Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt.
From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵 pic.twitter.com/P0cwFvf5d2
— Google DeepMind (@GoogleDeepMind) August 5, 2025
A blog post with the release stated that world models, which are able to understand environments and then re-create them, help agents to predict the environment changes and how their actions can affect it. World models are also a key stepping stone on the path to AGI, since they make it possible to train AI agents in an unlimited curriculum of rich simulation environments.
The team has stated that compared to Genie 2’s interactive window, which lasts between 10 and 20 seconds, Genie 3 offers a few minutes of interaction. The AI model is also able to be more consistent with the visuals, so if a user moves away from a location and returns to it later, the spot looks the same. However, the Genie 3 isn’t available for the public preview yet and will be rolled out to a select group of creators for testing.
