Here is Google DeepMind's Sima agent following different instructions inside a world generated by Genie 3.

This is what it looks like in Genie 3.

Something fun we discovered: you can use #Genie3 to step into and explore your favorite paintings. Here's a short visit to Edward Hopper's "Nighthawks".

Another one. Already a powerful painting, but moving around it yourself gives a totally different feeling. Jacques Louis David's "The Death of Socrates" => #Genie3

I got the Google DeepMind team to test Genie 3 with one of my artworks

𝕒𝕟𝕠𝕥𝕙𝕖𝕣 𝕕𝕒𝕪 𝕒𝕟𝕠𝕥𝕙𝕖𝕣 𝕡𝕝𝕒𝕟𝕖𝕥 🪐🌉🌃

Imagen 4 is now available on vertex, including Imagen 4 Fast, which is a really good and cheap model!

You have generated over 100M videos in Flow 🤯. We are SO grateful for your continued enthusiasm + support. As a token of our appreciation, here are two updates: 1.) AI credits are DOUBLED for all Ultra users 2.) We're launching FlowbyGoogle, your new source for Flow tips and

🍌

We can now train AI inside the mind of another AI. 🤯 🌍 Our world model, Genie 3, imagines and generates new worlds on the fly. 🤖 Our embodied agent, Sima, is dropped in and learns to navigate them autonomously. The entire loop—from the environment to the action—is generated

It's only Monday but this week is already serving

Our new native image generation and editing is state-of-the-art, and ranked #1 in the world. And we're rolling it out for free to everyone today. You’ve got the tools. Now go bananas. Ideas & inspiration in the 🧵below.

we've now entered the year of the 🍌

Check out what you can do when you mix Gemini's world knowledge with the ability to show things visually. Multimodal communication abilities unlock new use cases!

Veo 3 portrait mode is now there!

so good.

We’re proud to announce that Genie 3 has been named one of TIME’s Best Inventions of 2025. Genie 3 is our groundbreaking world model capable of generating interactive, playable environments from text or image prompts. Find out more → goo.gle/3KGqiYa

Don't miss out!