cooking up something tasty for tomorrow...

Excited to share our new generative video model, Veo 3, now with audio!

Also a new generative image model

Bars! #veo3

It's fun to play with #Veo3

A band playing together #Veo3

Tough twister challenge #Veo3

#Veo3 is coming

One step, another step, oops #Veo3

Prompt Theory (Made with Veo 3) What if AI-generated characters refused to believe they were AI-generated?

Seeing text-to-text regression work for Google’s massive compute cluster (billion $$ problem!) was the final result to convince us we can reward model literally any world feedback. Paper: arxiv.org/abs/2506.21718 Code: github.com/google-deepmin… Just train a simple encoder-decoder

The wait is over. Google Gemini App is now shipping Veo 3 *globally* for all Pro members! That means India, Indonesia, all of Europe, and more are starting to get access to create videos right now. As a member, you'll get 3 video generations per day, and that credit will replenish

Want to be part of a team redefining SOTA for generative video models? Excited about building models that can reach billions of users? The Veo team is hiring! We are looking for amazing researchers and engineers, in North America and Europe. Details below:

Now generally available: Veo 3 and Veo 3 Fast on #VertexAI 🎉 Here are some of the core features to try out now ↓ 🧵

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. 🧵

Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯 From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning,

The new Gemini 2.5 image model🍌is by far the best out there with a whopping +180 ELO point lead in image editing & it really excels at character consistency. Available for free in the Google Gemini App right now. Try uploading an image & playing around with it, it's pretty amazing!

Sora 2 is here.

Veo 3.1 is out! More creative controls from our latest model.

This is Gemini 3: our most intelligent model that helps you learn, build and plan anything. It comes with state-of-the-art reasoning capabilities, world-leading multimodal understanding, and enables new agentic coding experiences. 🧵