🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Excited to share that "TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space" got accepted to SIGGRAPH 2025! It tackles disentangling complex visual concepts from as little as a single image and re-composing concepts across multiple images into a coherent

RefVNLI Towards Scalable Evaluation of Subject-driven Text-to-image Generation

Once you turn on sound, you can't turn it off again. Excited to introduce our latest model, Veo 3, that can generate video *and* audio. It also has better quality and prompt following as our evals demonstrate, but I think the model speaks for itself :) deepmind.google/models/veo

Another amazing model produced by a truly talented team. Can't wait to see what people do with it 😁

Excited to introduce our new Veo 2 capabilities! Now with reference powered video generation (including style!), camera controls, outpainting, object add/removal & many more: deepmind.google/models/veo/#ca… Also presenting Flow, our new AI filmmaking tool. labs.google/flow

#Veo3 is finally out!

Cutting-edge tomatoes 🔪 #Veo3 (Sound on!) 1. Slicing a felt tomato 👇

Generate your videos following reference assets or style images! Proud to have been part of this talented team Thomas Kipf Serena Zhang Yulia Rubanova Nikos Kolotouros Philipp Henzler Andrew Marmon Jieru Shiran Zada Inbar Mosseri

know your audience🧐 #Veo3 (Sound on🔊 Watch until the end!)

Creating beautiful things with #Veo3 🪄 Sound ON!🔊 Having audio makes this so much more captivating

Greenfield is our model whispering team. They are amazing — check out their tips!!

Follow the world experts in Veo 3 and other Google DeepMind models for more useful generation tips!

Excited to share that TokenVerse won Best Paper Award at SIGGRAPH 2025! 🎉 TokenVerse enables personalization of complex visual concepts, from objects and materials to poses and lighting, each can be extracted from a single image and be recomposed into a coherent result. 👇

Introducing Genie3, our realtime and interactive world model! 🌍

Genie 3 is here - it can generate an entire world simulation that you can interact with in real-time, just from a text prompt! It's pretty mind-blowing really when you stop to think about it, and it's rapidly improving - one day we will be able to build the Holodeck for real!

#Genie3 is a real, interactive, playable experience. We're having so much fun with it at work---in between meetings, during breaks. Here's Ruiqi Gao, Joe Ortiz, Rundi Wu following a pack of polar bears through a New York City street! Check out more on the webpage:

Genie 3 is 🔥

Good Knight 🏰⚔️🛡️

Our Genie 3 model shows the possibilities of generative video that is not only based on a prompt to generate the video, but also can be made interactive by taking into account actions the user takes to explore the environment that is generated. Now you can interact with your

Yesterday we announced Genie 3. One feature of the model that's especially fun to play with is starting worlds from existing videos. Here's a drone shot generated by Veo 3, with me taking control mid-flight.