How to try Google Project Genie, a powerful new ‘world model’

Google has launched a new AI experiment called Project Genie, a tool that allows users to create their own interactive virtual worlds. Project Genie comes from Google DeepMind research lab and is now available to Google AI Ultra subscribers in the US (users must be 18+).

If you’re an AI Ultra subscriber – the AI ​​subscription plan is priced at $249.99 – you can start building worlds right away by visiting Google Labs and going to Project Genie.

What does the Genius Project do?

A video released with Project Genie shows exactly how users can create custom virtual worlds. Importantly, Project Genie doesn’t just create a virtual environment; it also allows the user to create a character to explore and interact with the world. Users can even use prompts to create their own mini-games, using the arrow keys on their keyboard to control the character. (A reporter for The Verge quickly realized he could use Project Genie to create knockoffs of Zelda and Super Mario.)

Google claims that Project Genie can generate worlds at 720p resolution and 24 frames per second.

Considering the time and work that goes into creating video games, it’s remarkable that Project Genie can create such detailed and interactive environments using AI. That said, Project Genie is primarily a research project, and while it can be fun to play with, it’s not really. TO DO Nothing. (Continue reading to learn more about potential future applications.)

The worlds created have realistic physics and objects in the world react when the user interacts with them. Users can also modify and remix their virtual worlds as they wish.

LEFT:
Create a virtual world from scratch.
Credit: Google/YouTube

RIGHT:
Users can also modify the world as they wish.
Credit: Google/YouTube

Project Genie is powered by an experimental “world model.”

Project Genie is powered by Genie 3, which is a powerful “world model”. (Google says Nano Banana and Gemini are also used to generate worlds.) A world model is an AI program that can generate a virtual world from text, images, and other inputs. Google actually teased Genie 3 in August 2025, calling it a “key stepping stone on the path to AGI.”

The new Project Genie homepage states: “Genie 3 represents a major advancement in capabilities – allowing agents to predict how a world is evolving and how their actions affect it. Genie 3 lets you explore an unlimited range of realistic environments.

Artificial general intelligence, or AGI, is a term for a hypothetical AI tool capable of performing most tasks as competently (or more) than the average human. This means it could do your job with little or no supervision. To achieve true AGI, AI companies must create models that can make sense of the environment and understand how to interact with it.

Examples of virtual worlds created by Genie 3.
Credit: Google

Global models are an emerging frontier in AI research, and companies that create video models have attracted significant investment over the past year. AI company WorldLabs recently raised $230 million, while video template maker Luma AI raised $900 million.

Besides AGI, what are the practical uses of global models? As an example, automakers could build a world to safely test autonomous vehicles. There are also possible applications for education and video game development.

Again, AI Ultra subscribers in the United States can start using Project Genie immediately.

A virtual world created by Project Genie.
Credit: Google/YouTube

A virtual world created by Project Genie.
Credit: Google/YouTube

A virtual world created by Project Genie.
Credit: Google/YouTube