Today, we’re announcing Veo 2: our state-of-the-art video generation model which produces realistic, high-quality clips from text or image prompts. 🎥 We’re also releasing an improved version of our text-to-image model, Imagen 3 - available to use in ImageFX through

Can’t wait for everyone to give this a try. 🔥This has been long in the making by a fantastic team. Bringing multiple characters, objects, scenes or literally anything you want into your generations with Veo’s stunning visual quality is a big unlock for visual storytelling,

Reference-powered video aka ingredients to video is now available at labs.google/flow/about! With Veo, you can always be a kid at heart❤️ Proud of the incredible team, it's been a blast :) Thomas Kipf Yulia Rubanova Nikos Kolotouros Philipp Henzler Andrew Marmon jieru@ Roni Paiss

Ingredients to Video is live, and eggs is one of them! 🍳 Try it out at labs.google/flow/about So proud of this amazing work from the team Thomas Kipf Serena Zhang Nikos Kolotouros Yulia Rubanova Philipp Henzler jieru@ Roni Paiss Shiran Zada Inbar Mosseri

We cooked something exciting up for you! 🧑‍🍳 Your vision, brought to life: Transform any reference image(s) into videos exactly as you envision them and even star in them yourself. This has been so much fun to work on with an amazing team: Thomas Kipf, Serena Zhang, Yulia Rubanova,

Amazing new capabilities 🚀 Super excited to be part of the reference and character control efforts!

To celebrate almost 1 year at Google, here's me wearing a noogler hat! You've probably seen tons of #veo results, but it's pretty mindblowing to see how far we've come 🔥

There are so many things one can do with Veo Ingredients. Like for example, a 3D animation version of me holding this cute little G Wagon. It even has my name on the license plate 😁

In filmmaking, consistency is key to a strong narrative. Using Flow, you can build stories with consistent characters, scenes, and objects across multiple clips— giving you more creative control.

Our team at GDM is hiring! Consider applying if you’re excited to work on state-of-the-art media generation! job-boards.greenhouse.io/deepmind/jobs/…

Check out our new model that launched on YouTube!

Ingredients to video now supports sound! 🔊🔊🔊 Check it out!

We are organizing the 3rd edition of the workshop on AI for 3D Content Creation today at #ICCV2025! Come join us for a great lineup of speakers! Huge thanks to Hezhen Hu @ ICCV2025 for running the show! Website: ai3dcc.github.io

* apply 🙃

Excited to build models that simulate the world? 🌐🌐🌐 Our team is hiring!! See posts below for Research Scientists and Engineers. The roles are somewhat fluid, but rule of thumb is the RS typically require a PhD. Preference for London or Toronto. Apply here: 👇👇