@robrombach

Krawallkrümel. Generative Models at https://xitter.cf/t.co/1xqMb60zqE, made with ❤️

 Black Forest
Joined July 2019
  • Tweets863
  • Following586
  • Followers15.6K
61Media
FLUX 3 is the strongest world model in the world.
Black Forest Labs
@bfl_aiOct 6
FLUX 3 is #1 on Physics-IQ, @GoogleDeepMind's benchmark for physical world understanding in video models. How Physics-IQ works: given the start of a real filmed experiment, can a model predict what physically happens next? Tests span fluid dynamics, optics, solid mechanics, magnetism and thermodynamics, covering how liquids flow, light behaves and objects interact. In most cases, we substantially outperform all other frontier models, Seedance 2.5, MiniMax H3, Gemini Omni 1.1 Flash, Veo 3.1 and Sora 2, Cosmos3. The FLUX 3 base model outperforms all other foundation models, while FLUX 3 paired with a physics verification layer scores even higher. The FLUX 3 backbone, with its strong physics understanding, gives FLUX 3 Action it’s strong action prediction for robotics, while also giving FLUX 3 Video physically accurate motion when you’re creating content, making ads, films and product shots.
54
81
23
880
101,139
Looking into the future together with @JensenHuang during GTC Berlin.
14
12
333
9,995
🔥🤖🔥
Elvis Nava
@elvisnavahOct 21
The team Just got set up at GTC Berlin. You should come over to the @mimicrobotics x @bfl_ai booth, it's really good!
1
62
3,461
Robin Rombach retweeted
fal
@falOct 19
FLUX 3 Max is a great example of what two teams working at the frontier can accomplish together. Excited to keep building with @bfl_ai.
Black Forest Labs
@bfl_aiOct 19
Introducing FLUX 3 Max. Fastest in the west. Fast enough to try anything. And everything. Generate a 10-second video in 12 seconds. Tied for #1 in image-to-video. 22× faster than Seedance 2.5 at the same quality. FLUX 3 is a model designed for customization. @fal adapted and optimized it to create FLUX 3 Max.
8
10
144
9,459
Robin Rombach retweeted
Justine Moore
@venturetwinsOct 19
This new video model from @fal x @bfl_ai is remarkable. All of these clips were text-to-video, generated in <10 seconds (22x faster than Seedance 2.5 🤯). AI video no longer needs to be painfully slow and expensive. We're entering a new era!
fal
@falOct 19
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai. FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds. For the next three weeks, FLUX 3 Max is 75% off, making it the most affordable frontier video model at its quality level.
38
37
1
491
33,893
Robin Rombach retweeted
Black Forest Labs
@bfl_aiOct 19
Introducing FLUX 3 Max. Fastest in the west. Fast enough to try anything. And everything. Generate a 10-second video in 12 seconds. Tied for #1 in image-to-video. 22× faster than Seedance 2.5 at the same quality. FLUX 3 is a model designed for customization. @fal adapted and optimized it to create FLUX 3 Max.
95
107
60
990
72,518
so fast 🔥
fal
@falOct 19
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai. FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds. For the next three weeks, FLUX 3 Max is 75% off, making it the most affordable frontier video model at its quality level.
4
9
93
4,053
Robin Rombach retweeted
Thomas Wolf
@Thom_WolfOct 18
The most built-upon model on the Hugging Face Hub isn’t Llama or Qwen. It’s FLUX.1-dev from Black Forest Labs, a German lab: 43k derivative models. Europe trained ~8% of the open-model compute on the Hub, but ~18% of what people build on top of it is European. Build or surrender? Build, and build open. See you at GTC Berlin this week
Arthur Mensch
@arthurmenschOct 16
Should Europe leave frontier AI to the Americans and the Chinese? The idea has gained ground in Europe. It is a fundamental mistake. Build or surrender: for now, the choice is still ours. Full article below.

Build or surrender

Article · @arthurmensch
23
37
2
339
16,976
Robin Rombach retweeted
Arthur Mensch
@arthurmenschOct 16
Should Europe leave frontier AI to the Americans and the Chinese? The idea has gained ground in Europe. It is a fundamental mistake. Build or surrender: for now, the choice is still ours. Full article below.

Build or surrender

Article · @arthurmensch
268
762
230
3,858
434,001
Robin Rombach retweeted
Alex Patrascu
@maxescuOct 15
Holy shit... I think Higgsfield discovered a gold mine here with Flux 3 upscaling. This has so many applications! Imagine how much archival footage we can restore. Just watch this 👇
🤝 Paid partnership
Higgsfield AI 🧩
@higgsfieldOct 15
FLUX 3 Upscaler from @bfl_ai is live on Higgsfield. > 50% faster and 50% cheaper than before > Upscale and sharpen any video > FLUX 3 Video now generates in native 2K and 4K Available now, with 7 days of exclusive access on Higgsfield.
20
16
2
172
13,267
Robin Rombach retweeted
Higgsfield AI 🧩
@higgsfieldOct 15
FLUX 3 Upscaler from @bfl_ai is live on Higgsfield. > 50% faster and 50% cheaper than before > Upscale and sharpen any video > FLUX 3 Video now generates in native 2K and 4K Available now, with 7 days of exclusive access on Higgsfield.
🤖 Made with AI
39
245
13
517
76,827
👀👀👀
Stephen
@stephenbtlOct 15
FLUX 3 Image Klein is out now, it's only 5.6B and we also worked on almost all quantizations - you can run it on almost all RTX cards now. Go play with it, it's also the best at Editing. We have something new coming next week! 👀
1
26
2,502
🔥 go train your own kleine weights
Ostris
@ostrisaiOct 15
Ostris AI Toolkit has day 0 support for FLUX 3 Image Klein. Thank you @bfl_ai for the early access and the amazing model! github.com/ostris/ai-toolkit…

Add Support for FLUX.3 Image Klein Base by jaretburkett · Pull Request #1078 · ostris/ai-toolkit

github.com
3
3
64
5,793
we just released the best open weight image model: FLUX 3 Image Klein is super efficient, richtig klein & mega nice. pls try it out and share feedback 🙏 It literally runs on everything and is ideally suited for local development.
Black Forest Labs
@bfl_aiOct 15
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.
54
32
3
536
31,501
Robin Rombach retweeted
Andreas Blattmann@andi_blattOct 15
FLUX 3 Image Klein is here! Bounding-Box control, pixel-perfect editing, multi-ref and a lot more - with only 5.6B parameters. Weights are available on HF! This model is a massive leap forward for applications that need to run locally. Go use it 🌲
Black Forest Labs
@bfl_aiOct 15
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.
3
7
69
3,912
8
4
1
126
6,487
Robin Rombach retweeted
Scenario
@Scenario_ggOct 12
Nanobanana 2.1 vs FLUX 3
6
10
57
7,679
Robin Rombach retweeted
Black Forest Labs
@bfl_aiOct 13
GTC Berlin, next week. The team will be on the ground, come find us. FLUX 3 Action at the @Nebius booth. FLUX 3 Image and Video at the NVIDIA booth, and a @mimicrobotics robot running FLUX-mimic. @robrombach will be speaking on stage on Oct 22, 9AM for a panel and 4PM for a keynote. We are hosting Afterglow, on Oct 21 with @FactoryAI, @modal and @NVIDIAAI, link in thread.
7
18
3
89
7,285
Robin Rombach retweeted
Anjney Midha
@AnjneyMidhaOct 7
hundreds of MI355x and B300 nodes now live on nationalcompute.com subsidized for all .edu and .govs it’s time to scale the frontier ecosystem for the public benefit
87
85
48
979
243,145
Robin Rombach retweeted
Justine Moore
@venturetwinsOct 2
We've definitely cracked multi-turn editing without image degradation 🤯 I took this old Chloe ad and wanted to see if FLUX 3 could swap out everything - dresses, couch, wallpaper, makeup, logo - while maintaining the structure. Nine turns later and no artifacts!
Black Forest Labs
@bfl_aiOct 1
Introducing FLUX 3 Image. Control every pixel. Make precise multi-turn edits without changing any other pixel. Lay out the image exactly how you want using bounding boxes. Generate in up to 4K to preserve details. Use up to 10 references to compose an image. Commercial Weights available for companies running image generation at scale. Open Weights version of FLUX 3 Image is launching in the coming weeks.
27
43
5
606
82,516
Load more