Ben Poole

Real-world models are here! Stoked to share how we're bringing real-world locations to life by integrating Street View into Genie. Try it now at labs.google/fx/projectgenie and read the blog for more info: blog.google/innovation-and…

Fortunate to work with this team every day, ACT-2 is a big leap. Working on real Solves is a blast. Next Stop: Recursive Solve Improvement

1/2 Introducing Nano Banana 2 Lite! We are working hard at the next frontier model, but in the meantime enjoy this fast and cheap Nano Banana (Pico Banana?). It returns images in only a few seconds, and with most of the smarts of the NB2 model! deepmind.google/models/gemini-…

We’re shipping 2 major releases:
 🔘 Nano Banana 2 Lite: our fastest and cheapest Gemini Image model 🔘 Gemini Omni Flash: now available via the Gemini API and in @GoogleAIStudio to help developers generate and edit high-quality videos.

After 15 years (4 internships and exactly 8 years full-time), today is my last day at Google. Growing up as a scientist at Brain and DeepMind was an incredible privilege, and I'm so thankful for the people who made it such a special place. I went from editing decision trees by hand as an intern, to exploring representation learning, latent-variable models, and diffusion as an AI researcher, to kicking off a new wave in generative 3D with DreamFusion, to scaling up generative models with Veo, Genie, and Omni. We're just beginning to build systems that can understand and simulate the real world, and I'm excited to see what’s next 🧠🐸🚀

@fal dope

We just open-sourced 3DREAL ! A new render-to-real IC-LoRA for LTX-2.3 from fal: turn any 3D / CG / game render into high 3d render, photorealistic, film-quality video, keeping your exact composition and camera move using the first frame.

@sirbayes @ValentinDeBort1 Thanks for all the teaching, managing, and mentorship! GenMo was such a rad team, hope our paths cross again soon!

@poolio @ValentinDeBort1 Sorry to see you go, but it was a privilege and pleasure to have you on my team for a while (back in the good ol’ days :)

@ZhengyangGeng hah good luck, enjoy :)

@poolio Congrats on the incredible run, Ben! 🥳 Also… is that desk with the view up for grabs? lol asking for a friend

@ajayj_ thanks for pulling me into 3D! love you've still got the pineapple profile :)

@poolio What a journey! And a pleasure having a chance to work together for a small part of it

@MartinNebelong cheers, martin! thanks for all the inspirational demos over the years.

@poolio Been a privilege to get to hang out with you on a few occasions.. very excited about seeing what you'll create outside of Google 💪

@giffmana @kastnerkyle shout out deanna

@poolio @kastnerkyle Love that hoodie, still my favorite of all those that i have.

@matt_slotnick @sam__silv join the party today

@sam__silv @poolio weekday pizza hacker lunch incoming

@scott_linderman woohoo exciting!

I'm excited to share what we're building at Engram! This team is incredible, and we're working on one of the most interesting problems in AI right now: how to build models that are tailored to each person and continually learn from experience. Come join us!

Thanks to @Cannes_Lions for recognizing Project Genie with the Grand Prix in Digital Craft: "The real breakthrough happens when creativity unlocks what technology can become" canneslions.com/news/cannes-li…

Huge congratulations to the Project Genie team on taking home the Cannes Lions Grand Prix for AI Craft! 🎉 Thank you @Cannes_Lions for recognizing how Genie pushes beyond conventional creative limitations to achieve outcomes unattainable without frontier AI… Another unexpected consequence of scaling world models :) Try it yourself here: labs.google/projectgenie

@midjourney 👋😎

Midjourney will be announcing its first hardware project tomorrow (Wednesday 6/17) at 6pm PT. Stay tuned for a livestream of our in-person launch event in San Francisco. If you're in town and want an invite, reply below, we have just a few slots left.

@mo_norouzi @ideogram_ai awesome work, congrats to the team!

So proud of what the @ideogram_ai team pulled off. The #1 open weight image model in the world and small enough to run on your consumer GPU 🚀

@finbarrtimbers woohoo congrats!

Today was my second day at Microsoft Superintelligence, where I’ll be working on post-training, with a particular focus on tool use.

Exciting news: Gemini Omni Flash is now #1 in the Video Arena (both Text-to-Video and Image-to-Video)! For Text-to-Video this is a massive +158 pt improvement over Veo 3.1 (1080p) and a large +61 pt lead over the next best model, Seedance 2.0. Congrats @GoogleDeepMind for this huge milestone!