Google rolls out Project Genie: What is it, how it works, and availability

Google has started rolling out Project Genie, an experimental AI prototype that lets select users create, explore and remix interactive worlds powered by its Genie 3 world model

Google has begun rolling out access to Project Genie, an experimental research prototype that allows users to create, explore and remix interactive worlds using AI-generated environments. The prototype is available to Google AI Ultra subscribers aged 18 and above in the US. Project Genie is built on Google’s Genie 3 world model and is a way for users to experiment with immersive world creation, following limited testing with select users.

What is Project Genie

Project Genie is a web-based prototype developed in Google Labs and powered by Genie 3, along with Nano Banana Pro and Gemini. It is designed to give users direct access to Google’s general-purpose world model, which simulates dynamic environments that respond in real time to user actions. The prototype builds on Google’s earlier preview of Genie 3 in August 2025, which demonstrated the model’s ability to generate interactive worlds rather than static 3D scenes.

What can Project Genie do

Google said that Project Genie centres on three core capabilities: world sketching, world exploration and world remixing.

 

With world sketching, users can create environments using text prompts as well as generated or uploaded images. They can define characters, landscapes and modes of movement, such as walking, driving or flying. Google said that for finer control, world sketching is integrated with Nano Banana Pro, allowing users to preview and adjust images before entering the world. Users can also choose perspectives, including first-person or third-person views, before beginning exploration.

 

As per the company, world exploration allows users to navigate these environments as they are generated in real time. As users move through the world, Project Genie predicts and creates the path ahead based on their actions. Camera angles can also be adjusted while traversing the environment.

 

With world remixing, users can build on existing worlds by modifying their underlying prompts. Project Genie also allows users to explore curated worlds through a gallery or the built-in randomiser for inspiration, and then remix them into new experiences. Once finished, users can download videos of their worlds and explorations.

Limitations

Project Genie is an experimental research prototype, and Google has outlined several current limitations. Generated environments may not always closely match prompts, images or real-world physics. Character controls can sometimes be less responsive, and world generations are currently limited to 60 seconds. Some Genie 3 capabilities previewed earlier, such as prompt-driven events that dynamically change the world during exploration, are not included in this prototype.

 

Google said the prototype is being released to better understand how people will use world models across AI research and generative media, building on feedback from earlier trusted testers.

Availability

Access to Project Genie is rolling out for Google AI Ultra subscribers in the US aged 18 and above. Google said the prototype will expand to more regions in the future, though no timeline has been announced.