Black Forest Labs

Black Forest Labs just made Lenny Rachitsky's Lenny 100 - the list of the top 100 companies he'd most want to join right now, ranked on talent density, tackling ambitious problems, and upside. Most people assume that to build SOTA models, you need thousands of people. At BFL, we’ve proven that high talent density matters far more. We're a team of 100 building the standard for visual intelligence, and shipping frontier models that top global benchmarks and beat labs 100x our size. I'm so proud of the team we've built, and just as proud of what we've built together. If you want to do the best work of your career alongside world-class peers, we're hiring! https://bfl.ai/careers

FLUX Video Upscale: 2K and 4K for Video Create videos in 2K or 4K with sharper faces, cleaner textures, and finer background detail. FLUX 3 Video’s native upscaling is designed to retain FLUX 3’s style diversity, natural motion, and realism at higher resolutions, with faster results than 3rd party upscalers. You can also use it to upscale any video. Read more about it - https://lnkd.in/dGdKeyGn

FLUX 3 Video is #2 in the world on Arena. To celebrate, FLUX 3 Video is free to use in our playground until August 16th, 11:59pm PT (link in the comments). This is just the beginning of what’s coming. Up next: 4K, video editing, and multiple images & videos as reference input.

FLUX 3 Video is here. Serious, fun, creative, real, cinematic, whatever you need it to be. Moves between documentary realism, animation, product film, typography, and dialogue scenes with accurate motion, sound, and interaction. Text to video, image to video with multiple key frames, video continuation, and native audio with lipsync, effects, and ambience. Up to 20 seconds with native 1080p. Draft mode returns a fast preview of any prompt at a fraction of the cost. When a draft is right, send it back and FLUX 3 renders the same video at full quality. Available now in the API and in your favorite tool. 2K, 4K, and Open Weights coming soon.

FLUX 3 for robotics and the physical world. An early version of FLUX 3, our new frontier multimodal model, is now running on robots. mimic robotics was one of the first partners to gain early access to FLUX 3. Together we developed FLUX-mimic, a video-action model combining the FLUX 3 backbone with mimic's expertise in robot learning for dexterous manipulation and production deployment. It’s now running robots that have been tested and deployed at AUDI AG. “In partnership with mimic, Audi has been testing and deploying FLUX-mimic. We have seen these robots solve complex soft body manipulation work that would have been simply impossible with conventional robotics. For us, partnering with pioneering companies such as mimic and Black Forest Labs is essential in pushing the frontier of Physical AI.” — Christoph Schneider, Audi Production Lab. At Black Forest Labs, we believe the path to useful, interactive AI in physical and digital environments runs through a unified model that learns from text, images, video, and audio at scale and can be extended to predict actions. The same underlying architecture for visual creation can extend to frontier applications, from controlling robots and other physical systems to operating software through computer use. Read about our partnership with mimic through the link in the comments.

Introducing FLUX 3. One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style. FLUX 3 is a checkpoint on our mission to develop real-world visual intelligence: models that perceive, predict, and act across digital and physical environments. Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and AUDI AG in the comments. Over the next few weeks and months, we’ll make the following capabilities available, each after an early access phase for ensuring smooth rollout: • Video with native audio generation (now in early access, link in comments) • Action prediction through selected research and commercial partners • Image generation and editing • Fast variants and features for iterating cost efficiently • Open-weight access to a multimodal backbone, for content creation and action prediction

Robin talks to Jason Calacanis about models that understand the world, working with Martin Scorsese, and what's coming next from BFL 👀. Starts at 41:00. Full episode: https://lnkd.in/gvtM7b-r

You have a new Dev Playground for testing existing and upcoming FLUX models: 𝗖𝗼𝗺𝗽𝗮𝗿𝗲 𝗺𝗼𝗱𝗲𝗹𝘀 𝘀𝗶𝗱𝗲-𝗯𝘆-𝘀𝗶𝗱𝗲. Run the same prompt across multiple FLUX models at once and see the differences. 𝗖𝗼𝗻𝘁𝗿𝗼𝗹 𝗽𝗮𝗿𝗮𝗺𝗲𝘁𝗲𝗿𝘀. Adjust API parameters from the UI, so what you test is exactly what you build. 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗲. Test quality, latency, and cost. 𝗔𝗹𝘄𝗮𝘆𝘀 𝗰𝘂𝗿𝗿𝗲𝗻𝘁. It launches with our latest models and we'll keep adding new models. Link to try it: https://lnkd.in/e8yWfhvE

Our co-founder and CEO, Robin Rombach, sat down with President Trump, President von der Leyen, President Macron, Chancellor Merz and other world leaders at the G7 to stress the vital role of open innovation in AI. With openness under pressure around the world, Robin urged governments and industry to make open and responsible development the norm, not the exception. Check out his speech in the link below: https://lnkd.in/eMUMkrJp