Tim Dockhorn

@bfl_ai

[Elvis Nava @elvisnavah]

The team Just got set up at GTC Berlin. You should come over to the @mimicrobotics x @bfl_ai booth, it's really good!

[Black Forest Labs @bfl_ai]

FLUX 3 Image Klein is here.

Open Weights with the quality of a large frontier model. Customizable and fast.

5.6B parameters and runs on a single consumer GPU.

Native 4K, bounding boxes, and pixel-perfect editing.

[Tim Dockhorn @timudk]

@thegautamkamath @UWCheritonCS Big loss for the department!! CS860 was one of the highlights during Covid and always loved our conversations around Privacy x Generative Modeling.

[Tim Dockhorn @timudk]

@FidlerSanja @VeedaAI @ZGojcic @HuanLing6 Congrats @HuanLing6, @FidlerSanja, @ZGojcic, super exciting news!!

[Black Forest Labs @bfl_ai]

FLUX 3 Video is here.

Serious, fun, creative, real, cinematic, whatever you need it to be.

Native audio, Text to Video, Image to Video with multiple frames, video continuation, dialogue in multiple languages.

Comes with Draft mode so you can explore ideas fast at a fraction of the cost.

Up to 20 seconds and 1080p native.

Available in the API or in your favorite tool. 2K, 4K, and Open Weights coming soon.

[Tim Dockhorn @timudk]

@keremnalbant Insane work from you and the team!!!

[Ostris @ostrisai]

I have playing with @bfl_ai Black Forest Labs FLUX 3 for a few days now. (Thank you for the early access!) And I played with it... a lot. Some may say, too much. 😅 Here are some of my favorite gens. Needless to say, I love this model. Audio on! More in 🧵

[Tim Dockhorn @timudk]

@AnjneyMidha that's what makes it so fun

[Tim Dockhorn @timudk]

It never stops being exciting what you can achieve with good data, scaling compute, and careful engineering. Incredible effort by the entire team.

[Black Forest Labs @bfl_ai]

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 Video is now available in early access (link below).

Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.

[Tim Dockhorn @timudk]

@JamesTThorn thank you @JamesTThorn

[Tim Dockhorn @timudk]

@finbarrtimbers thank you @finbarrtimbers, hope you're settling in well at msft!!

[Tim Dockhorn @timudk]

@robrombach @dustin_podell sample connoisseur @dustin_podell

[Robin Rombach @robrombach]

Yesterday, I had the insane experience of joining the G7 summit in Evian and present our perspective on open innovation in AI to the G7+ world leaders.
With openness under pressure around the world, it is vital that we preserve a culture that makes open and responsible development the norm, not the exception

My full remarks below.

> Thank you, President Macron, for organizing this important conversation, and for bringing together this excellent group of people. I think I represent the youngest company in this room. I am Robin Rombach, co-founder and CEO of Black Forest Labs: a 90-person frontier AI lab, built on both sides of the Atlantic in Germany and the United States. We develop “world models”. These are visual AI models that understand and simulate our complex physical world.

Many of you have probably never heard of us. But if you’ve ever generated an AI image or AI video—I’m sure some of you have done so—you’ve probably encountered our research. Not far from here, at universities in Germany, our team pioneered and published many of the techniques that gave rise to visual generative AI. Our team has co-developed 3 of the top 5 most popular open generative AI models of all time, including Stable Diffusion, and the only open models as popular as DeepSeek.

We’ve talked a lot about language models today. They are remarkable. But language is a compressed, and ultimately limited, representation of the world. We are building models that learn from thousands of years of video, and can reason in complex visual environments—the rich, messy, complicated world we actually live in.

These are still early days, but this technology is going to transform every corner of the economy. For that reason, we believe that visual models, alongside language models, will soon be critical economic infrastructure.

That’s why we are passionately committed to open innovation. Sharing our technology openly means that businesses around the world can build their own AI systems, rather than renting them from a handful of companies. Open technology is vital for transparency, competition, and strategic independence in AI. A culture of open innovation made AI possible in the first place, including the transformer paper that gave birth to today’s language models, and we need to preserve that culture.

But we are fully aware that open innovation poses unique challenges, especially in image, video, and audio. Open AI models can be misused or modified to produce unlawful and deeply harmful content, and it can be difficult to withdraw these models once they're released.

Our commitment is to show that innovation in visual AI can be both open and responsible, not one or the other. This is partly a technical challenge, and we are making good progress. For example, our latest open models demonstrated over 10 times fewer vulnerabilities for sexual deepfakes and child abuse material than the open models released by other Big Tech firms.

But there is a role for governments too, from safety tools to evaluation standards to targeted regulation. For example, we have welcomed the leadership of the Trump Administration, as well as the European Union and the UK Government, in developing new legal strategies to combat sexual deepfakes.

It’s crucial that we strike the right balance. The future of our societies depends on getting this technology out into the world safely. But a climate of fear around open technology, or a focus on suppression over diffusion, will leave the world reliant on a handful of firms for critical infrastructure. We are ready to work with you all to make open and responsible innovation the norm, not the exception.

[Robin Rombach @robrombach]

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!

[Tim Dockhorn @timudk]

@thegautamkamath congrats Gautam !!

[Black Forest Labs @bfl_ai]

Martin Scorsese is an advisor to Black Forest Labs.

He's spent six decades shaping how the world sees stories. Now he's helping us shape visual intelligence with human taste and craft at the center.

We sat down with him for a working storyboarding session using FLUX.

[Black Forest Labs @bfl_ai]

The official FLUX MCP.

Create images inside Claude, Cursor, Hermes, and more.

Your agent automatically routes your request to the right FLUX model with expert-level prompting. From Klein for sub-second drafts to Pro for production-quality assets.

Play with website visuals, ad creatives, social content, product renders, concept art, and (most importantly) memes.

Link in the thread.

[Hila Chefer @hila_chefer]

New research from @bfl_ml 🥳
Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖
https://t.co/AshY8IkSEe

Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

[Pruna AI @PrunaAI]

FLUX.2 [flex] is now 3x to 4x faster ⚡

Working with @bfl_ml, we accelerated one of their top-ranked image model to ~5s per image generation and ~10s per image edit, making it the de facto standard for typography-heavy image generation.

The results:
- On one H200: ~4x faster
- On four H200s: ~3x faster
- Image generation in 13s/5s on single/multi-gpu
- Image edits from in 28s/10s on single/multi-gpu
- Leads the Pareto front for speed vs quality

Perfect for designers and teams who need fast iteration on typography-heavy visuals without compromising quality.

This is what AI efficiency looks like when done right: efficiency without quality loss!

Read our blog: https://t.co/XgfyspliZR
Try the official accelerated endpoint: https://t.co/Aq3z1zhWk0