Asset 20 8 2
Does AI recommend your business? Run the free check →

Join 15,000 business owners, marketers and entrepreneurs. The Sunday newsletter you'll be annoyed only arrives once a week.

Article

How to Use Project Genie: Create and Explore AI Worlds

Project Genie is a Google Labs research prototype that turns a text prompt, an image or a Street View location into an interactive world you can walk, drive or fly through. It's available to Google AI Ultra subscribers aged 18 or over. You get 30 seconds to set up your world and 60 seconds to explore it, using your keyboard.

It runs on Genie 3, Google DeepMind's world model, and Google announced Genie 4 on 27 October 2026 with real-time audio and scene steering, coming soon to Project Genie. Below is how to use it today, prompts to try and what to expect from the update, all from Google's own help and Labs pages.

Who can use Project Genie

  • You need a Google AI Ultra subscription in a country where Ultra is available. Google's US page lists Ultra from $99.99 a month, as of October 2026.
  • You must be 18 or older and sign in with a personal Google Account.
  • If you don't have access, you can still open the Gallery and watch worlds other people have made.
  • Generating worlds doesn't use your AI credits, because it's an early research prototype.

How to create your first world

  1. Go to labs.google/fx/projectgenie and sign in with your personal Google Account.
  2. Click Create with Project Genie. If demand is high you may have to wait; Google says to watch the page for your turn.
  3. When it's your turn, you've got 30 seconds to create your world.
  4. Sketch it one of three ways: describe the environment and the character in the text fields, pick a location in Street View with a style, or click Roll the dice for a surprise.
  5. Choose First person or Third person view.
  6. Optionally tweak the preview image with Add, Change or Remove.
  7. Click Next. Generation takes a few moments, so stay on the page; exploring starts automatically.

Controls and your 60 seconds

ActionKey
MoveW, A, S, D
Jump or ascendSpacebar
Turn the cameraArrow keys
Time leftProgress bar at the top of the screen

When the timer ends you can reuse your prompts for a new world, revisit the same world (which can come out differently), download a video of your run, or start again from scratch. That download is the part I'd use for content: a short clip of a world built around your product, your town or your brand story is an unusual post for social.

Prompts to try

Google's own examples split every prompt into an environment and a character, and say how the character moves. These follow the same pattern; copy one and change the details.

A shopfront world for a small business

Copy this prompt

Environment: A sunny high street in a small seaside town with a bright blue florist's shop, buckets of tulips on the pavement and bunting between lamp posts.
Character: A delivery bike with a basket of flowers, ridden in third person, smooth steering and gentle braking.

A product launch teaser

Copy this prompt

Environment: A minimalist white studio with soft daylight, a single plinth in the centre and long shadows on a polished concrete floor.
Character: A small camera drone in first person that can rise, hover and circle slowly around the plinth.

A playful brand mascot run

Copy this prompt

Environment: A cosy felted craft world with wool hills, button flowers and a stitched river with a little bridge.
Character: A round knitted owl in third person that waddles, hops over obstacles and flaps short distances.

Fixes for the known issues

Google lists these problems in its help article, with its suggested fixes:

  • Character runs backwards: press Spacebar to reset and regain control.
  • Can't control the character: if you uploaded a photo, make sure the character is centred and prominent; if it's a real-world scene, try making it more game-like.
  • Stream looks low quality or controls lag: Google says quality can drop with server load and there's a known delay it's working on.
  • World doesn't match your image: Genie 3 is an early research model and won't always stick closely to prompts, images or real physics.

To delete your data, open Project Genie, click More at the top right, then Delete Data.

What Genie 4 will add

Google's 27 October announcement says Genie 4 adds native audio generated on the fly, including ambient sound, music and dialogue, and lets you steer a scene in real time with plain language, such as moving the camera, changing the weather or adding new characters. It's rolling out to a limited group of trusted testers first and is coming soon to Ultra subscribers in Project Genie and to early access partners in the Gemini API and AI Studio.

Work with me

Want AI doing the heavy lifting in your marketing?

I build the systems that handle the boring 80 percent, so you get your week back. Done properly, with the human kept in.

Another Gemini feature that runs without you watching is covered in setting up Gemini scheduled actions.

Tools you can use alongside it

Project Genie works on its own, but these fit around it: Google Street View for picking a real place to start from, Nano Banana in the Gemini app for making a starting image to upload, Google Flow for turning ideas into longer clips, and any video editor such as CapCut or Clipchamp for trimming your downloaded run into a social post.

If you'd like help working out where tools like this fit in your marketing, you can work with me. I've spent 23 years in marketing and I'm happiest turning new tools into real campaigns. For the plan itself, see my guide to Google AI Ultra.

My verdict

Project Genie is a glimpse of where AI is heading rather than a daily business tool. If you already pay for Ultra, it's worth ten minutes to make a world and download a clip. I wouldn't upgrade to Ultra for it alone, at least not until Genie 4 lands.

Not sure where Genie fits among Google's other tools? Read which Google AI tool you need.

Frequently asked questions

What is Project Genie?

A Google Labs research prototype that creates interactive worlds from text, images or Street View that you can explore in real time.

Who can use Project Genie?

Google AI Ultra subscribers aged 18 or over, signed in with a personal Google Account, where Ultra is available.

How long can you explore a Project Genie world?

Google says you get 60 seconds to explore, after 30 seconds to create the world.

Does Project Genie use AI credits?

No. Google says you don't need AI credits to generate worlds while it's an early research prototype.

Is Genie 4 available in Project Genie?

Not yet. Google said on 27 October 2026 that Genie 4 is coming soon to Ultra subscribers in Project Genie.

Published and maintained by the Lilach Bullock team, covering marketing, AI and business growth.
Your buyers are asking AI who to use. Does it say you?

See for free whether ChatGPT, Claude, Perplexity, Gemini and Google name you, and get the plan to become the answer.

Check my AI visibility →
Sundays only

Get the Sunday newsletter.

One email a week. AI experiments, marketing tactics, and the workflows Lilach is building right now in her own business.

Subscribe free

Let’s get your marketing running on AI.

Book a free 30-minute call

We figure out what you need, where AI fits in, and what working together would look like.

Book the call →

Or take the 30-second calculator

You’ll see the hours and the money quietly leaking out of your week, and the three workflows worth building first.

Take the calculator →

Or grab the free AI resource library

Prompt packs, templates, checklists, and swipe files. The exact tools I build for paying clients. Yours, free.

Get the library →
Keep reading

More from the blog.