So good to see this tradition grow stronger every year! The diffusion circle started with ~10 of us sitting on the floor of the eerily empty Baltimore Convention Center at ICML 2022, and we've kept it going ever since. We need more circles at conferences, diffusion or otherwise😁

Fun circle this year, see everyone at the next one! 🔵

Thanks all for coming and circling with us!

Come and join us for the circle at the circle! Whether youre deeply familiar or completely new to the world of Flow Matching/Diffusion the circle welcomes all! 🔵🌲

Diffusion Circle with forest vibes! 🌲 Since the original Diffusion Circle organizer @sedielem cannot make it to CVPR in person this year, we coordinated with him and are happy to host the Diffusion Circle this time. Stop by if you are interested in flow maps, multimodal diffusion models, variational flow matching, action prediction, and all the other hot denoising stuff. @sumith1896 and @dustin_podell will coordinate. Meeting point: Upper Lobby F / Exhibit Hall F Entrance; see attached pics. Happening Saturday, June 6, 3:30pm!

Excited to have Martin Scorsese as an advisor. Stories will always have to be personal, but they can be woven together with new tools. That's what we strive to build at Black Forest Labs.

Seeing Martin Scorsese using FLUX for storyboarding and scene exploration was absolutely insane. Experiencing how one of the absolute masters of cinema & filmmaking uses the technology that we developed, his curiosity and creativity, and the way he prompted our models, was humbling. I am grateful to call Martin Scorsese an advisor to BFL, and to explore the next, multimodal and interactive phases of visual AI with him.

today, we @amppublic are announcing a $500M profit pool we have set aside to help local communities navigate the AI transition over the next few years we'd love to hear ideas for the best way to distribute these funds anyone can submit here: amppublic.com/#public-wealth…

success and competence need repetition and volume.

Fixed vision encoders like DINO have driven impressive progress in more learnable representations for generative modeling - but there is no universal variant across modalities, and they do not scale with the generative model. We introduce our self-supervised framework, Self-Flow, that builds learnability directly into flow models, working in a unified and scalable way across image, video and audio. Particularly excited about the gains on video-action prediction: Beyond the overall success rate improving substantially, more complex tasks - like "Open and Place" - see some of the clearest gains. So many interesting research questions to explore to make 🤖 go brrr Super glad to be working with my amazing colleagues @hila_chefer, Dominik, @dustin_podell, Vikash, @Vinh_Suhi, Antonio and @robrombach - as well as the whole @bfl_ml team! arxiv: arxiv.org/abs/2603.06507 project page: bfl.ai/research/self-flow

New research from @bfl_ml 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 bfl.ai/research/self-flow Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

hot off the press — representation learning done right 🚀

future is wild, really excited for coding and agentic workflows with blazing fast speed ⚡️ kudos to @StefanoErmon @adityagrover_ @volokuleshov and the whole @_inception_ai team for pushing hard on the new paradigm!

🚨 FLUX.2 from @bfl_ml is here on fal - day 0 release! 🎨 Generate and edit images with incredible quality 🎯 HEX codes and JSON prompts for better control 🎬 Pro and Flex: High-fidelity images and text rendering ⚡ Dev: LoRA training for customization blog.fal.ai/flux-2-is-now-av…

FLUX.2, from @bfl_ml, is now available in ElevenLabs Image & Video. Real-world lighting and spatial accuracy. 4MP fidelity. Multi-reference control.

FLUX.2 is here - our most capable image generation & editing model to date. Multi-reference. 4MP. Production-ready. Open weights. Into the new.