Google Genie

Google Labs have announced Google Genie- an early research prototype powered by their Genie 3 model that lets users create and explore infinitely diverse worlds.

It’s US only at the moment and accessed as part of an AI Ultra account subscription but there is a gallery of demo content that gives a sense of the possibilities.

Essentially, users are able to design characters and worlds using text and visual prompts. Nano Banana Pro generates an image preview that can be refined and once complete, users are able to enter the environment which is generated in real-time as you move around.

I can think of a few use cases in terms of immersive simulations and emergency planning training, but it’s probably also very useful for gaming environment design and film making in terms of set visualisation and shot design.

But if you’ve ever harboured an ambition to transform yourself into a fish, ant or paper plane, this may be for you.