Veo 3 is rolling out. Now available in 70+ markets for AI Pro and Ultra subscribers.

The Sentence (Short Sci-Fi Film Made with Veo 3) This is my latest short film made with Veo 3, and the longest one I've done so far. It took 3 days from writing to final render. The story explores a newly introduced form of capital punishment. What begins as a routine sentence

3.5M organic views on TikTok of Bigfoot selling a $100 gadget. 4 shots. 4 prompts. You may not like it, but this is what the future of advertising looks like 🤣

I may be a terrible person but Veo 3 sinkhole videos are my favorite new genre of comedy

What's the best way to make AI video with sound? 🔉 I ran a head-to-head comparison between: - Veo 3 (w/ native audio) - Kling 2.1 (w/ native audio) - Hailuo 2.0 (w/ MM Audio) - Veo 2 (w/ MM Audio) Veo 3 is the best, but I'm surprised by the clear #2...

New open source music model from our team! They worked really hard to get this prepped and out the door. Looking forward to hearing what folks do with it!

I asked Veo 3 to take me around the world and here's what happened... 👇 1. It turned me into a flamenco singer in Spain 🇪🇸

This may be the best AI commercial we’ve ever made. We worked with one of the best directors in the world to create a wild new ad for Kalshi (Last one hit 100M views) Here’s a breakdown of how we made it in ONE WEEK (prompt included) 👇🏼🧵

Very excited to share that an advanced version of Gemini Deep Think is the first to have achieved gold-medal level in the International Mathematical Olympiad! 🏆, solving five out of six problems perfectly, as verified by the IMO organizers! It’s been a wild run to lead this

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵

1/ The first big announcement: Google DeepMind has unveiled Genie 3 A new frontier for world models, the first AI that generates interactive 3D worlds in real time at 24 fps. The breakthrough: minutes of consistency at 720p using only text descriptions. No pre-built 3D models

They solved environmental consistency with Genie 3, and this was an emergent capability. You can see the trees remain the same even after being out of line of sight. Visual memory extends back one minute now. Google is on a steady path to a real world simulator.

wtf.. this is mindblowing.. GoogleDeepMind just dropped Genie 3 you can generate interactive 3D world with text, navigate with keys and.. interact in real time.. AI is crazy 10 examples: 1. navigate to a car and open the door.. omg

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.

🚨🍌Breaking News: Gemini-2.5-Flash-Image-Preview (“nano-banana”) by Google DeepMind now ranks #1 in Image Edit Arena. In just two weeks: 🟡“nano-banana” has driven over 5 million community votes in the Arena 🟡Record-breaking 2.5M+ votes casted for this model alone 🟡It has

Our team at DeepMind is hiring a research scientist to work on MultiModal Generative models, anywhere in Europe! Apply or reach out if you're interested! job-boards.greenhouse.io/deepmind/jobs/…

Incredible milestone: an advanced version of Gemini 2.5 Deep Think achieved gold-medal performance at the ICPC World Finals, a top global programming competition, solving an impressive 10/12 problems. Such a profound leap in abstract problem-solving - congrats to @googledeepmind!

Super excited to be collaborating with Commonwealth Fusion Systems Commonwealth Fusion Systems to use AI to accelerate fusion development - and move closer to a sustainable future with limitless clean energy

lmarena.ai Google DeepMind

Awesome to see Veo 3.1 top the LMArena video leaderboards by a large distance with big improvements over Veo 3.0 for text-to-video (+30) and image-to-video (+70)! 🔥Huge congrats to the team! Try it for yourself in flow.google and the Google Gemini App