✨ Happy to share that my new blog post about Gaussian Splatting, based on a group meeting in the lab of Tali Dekel, was selected as an Editors' Pick by Towards Data Science ✨ w michal geyer

🥳

a flow of good news today! thanks Linoy Tsaban🎗️ Manuel Brack @ EMNLP and the 🤗 team🌷

Introducing Lumiere 📽️ The new video diffusion model we've been working on Google AI * Text-to-Video * Image-to-Video * Stylized Generation * Inpainting * Cinemagraphs and more 🎨 W/ amazing team incl. Hila Chefer omer tov Inbar Mosseri Tali Dekel Deqing Sun Oliver Wang

Sora performance scales with compute

…Sorry, we were on mute. Today we’re launching Sound Effects on Pika. Now you can seamlessly generate and integrate sound into your videos. Either prompt the sound you want, or let Pika automatically generate it based on the content of your video. If that sounds great, it’s

Introducing Evolutionary Model Merge: A new approach bringing us closer to automating foundation model development. We use evolution to find great ways of combining open-source models, building new powerful foundation models with user-specified abilities! sakana.ai/evolutionary-m…

Ryan made this language-free system that lets you surf through image-space, just by following the things you feel pulled towards. The demo takes a bit to hone in but it's worth it, produces a feeling that's totally different from other image models right now

Very excited for this one! If you are working on video generation, submit your work and join us :)

There's still time to submit to our workshop! Would love to see your work on controllable video generation 🫵

We have decided to extend our deadline to 𝟒𝐭𝐡 𝐨𝐟 𝐉𝐮𝐧𝐞! If you have a piece of work on controllable video generation that you want ✨the world ✨ to see, turn it into a 4-pager and submit to our workshop 👩‍💻🧑‍💻 would love to see you at ICML2024! ICML Conference

Presenting M-SDF this week at #CVPR2024 ! Come to our poster on Wednesday morning to say hi and learn/hear about training Flow Matching generative model with our new 3D representation

Self-supervised representation learning (DINO) + test time optimization=DINO-tracker! Achieving SOTA tracking results across long range occlusions. Congrats Narek Tumanyan Assaf Singer and OneViTaDay on the great work! 🦖🦖

Some amazing work by Google researchers on personalization of video models. Their work allows for video subject-driven generation and style-driven generation with some seriously impressive results 🤯 imagine the possibilities web: still-moving.github.io

Animating LoRAs with Still-Moving? Still-Moving is a technique that uses a Motion Adapter to align a customized text-to-image model to a text-to-video model 🎥 The technique is model agnostic, the paper demonstrates it works both on Google's internal model Lumiere but also

Excited to be back in the city of my alma mater attending ICML Conference ! Join us this Saturday for our "Text, Camera, Action! Frontiers in Controllable Video Generation" workshop. Let's chat about diffusion models, interpretability, and AI safety! DM me if you want to connect!

Today at Hall A8! Join us!

Incredible!

Future be like tab tab tab

📣📣 Hiring a PhD-Intern 📣📣 Work with me on Dynamic 3D Gaussians at the Meta Boston office for 6 months in summer 2025! Apply here: metacareers.com/jobs/105497412… + write me your questions / link your most relevant work via email or twitter.