←
Robin Rombach875 posts
Robin Rombach avatar

Robin Rombach

@robrombach

long-term PhD student and intern. Generative Models at bfl.ai/, made with ❤️

◷ Joined July 2019▧ 63 Photos and videos
Robin Rombach avatar
Robin Rombach@robrombach·Oct 6

FLUX 3 is the strongest world model in the world.

Post attachment

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.

Post attachment
Elvis Nava avatar
⟳ Robin Rombach retweeted
Elvis Nava@elvisnavah·Nov 16

last week we trained the #1 WAM/VAM with no benchmaxxing

Today we are previewing FLUX-mimic-x, our new frontier Video-Action Model. We achieve the #1 spot on the RoboLab benchmark among real-time "system 1" models, as well as impressive zero-shot generalization across embodiments including grippers and dexterous hands. FLUX-mimic-x is a 7B-parameter model based on our updated mimic-video recipe and trained on top of FLUX 3 by @bfl_ai. The model is never trained on simulation data or any other data from the RoboLab embodiment beyond that of the original DROID dataset. Our model can be deployed on any robot and any task with minimal adaptation, running on-device and in real-time.

1:03
Robin Rombach avatar
Robin Rombach@robrombach·Nov 16

SOTA, again 😍

Post attachment

Today we are previewing FLUX-mimic-x, our new frontier Video-Action Model. We achieve the #1 spot on the RoboLab benchmark among real-time "system 1" models, as well as impressive zero-shot generalization across embodiments including grippers and dexterous hands. FLUX-mimic-x is a 7B-parameter model based on our updated mimic-video recipe and trained on top of FLUX 3 by @bfl_ai. The model is never trained on simulation data or any other data from the RoboLab embodiment beyond that of the original DROID dataset. Our model can be deployed on any robot and any task with minimal adaptation, running on-device and in real-time.

1:03
Yuki avatar
⟳ Robin Rombach retweeted
Yuki@y_m_asano·Nov 13

🍌 What if an image generator could see? @GoogleDeepMind's Vision Banana showed it can, but kept data, recipe and weights closed. So we rebuilt it fully open: ✨ FLUX.2 Klein 4B/9B finetune w/ public data only ✨ 73.9 vs Vision Banana’s 69.9 mIoU zero-shot on Cityscapes ✨We release code + 148 checkpoints for the community/ Aaand we innovate: 📈 We develop a new test-time scaling recipe we call “legend-ensembling”: this gives strong gains by applying more compute without retraining anything. 🔗 openvisionbanana.github.io 📄 arxiv.org/abs/2611.15844 A @FunAILab work from A. Jadon, @v_pariza, @FragileGoodwill, @jonaruthardt, @ASophiaKoepke, @abursuc and me.

0:45
Robin Rombach avatar
Robin Rombach@robrombach·Nov 12

FLUX-mimic goes brrr 🔥

Today we’re announcing a joint research project with @BMW Group on video-action models for industrial manipulation. We trained FLUX-mimic on automotive tasks using production parts and fixtures: assembly, insertion, kitting and cable routing. On our dexterous robot platform, it achieved success rates of up to 100% and consistently outperformed other models, even with 4x less training data. Collecting task-specific data is the biggest cost of bringing learned policies into factories today. From day one, we’ve believed that working closely with industrial partners on real production data is the only path to deployment.

1:03
Elvis Nava avatar
⟳ Robin Rombach retweeted
Elvis Nava@elvisnavah·Nov 1

"shocking" capability jumps in robotics always happen when someone aligns a robotics skill to another quasi-identical skill that existing frontier models already massively pretrain on for llm-as-robot (astra), it's visual computer use for real time dexterity (VAM/WAM), it's video pretraining

I don't really understand the surprise 1. They added robotics tasks framed as computer use to the training distribution, even if "not much" 2. They win at visual servoing tasks that can be framed as visual computer use. the model burned lots of flops on very related tasks in training 3. They can't solve dexterity or fast real time control this way, by design. You need "baked" system 1 weights for that and this method won't give you that 4. Still, it seems pretty clear that this will be the shape of system 2 when you need generality during deployment

arcads AI avatar
⟳ Robin Rombach retweeted
arcads AI@arcads_ai·Oct 28

Flux 3 Max is insane: > 22X Faster than Seedance 2.5 > Similar quality Live on arcads.ai today

0:34
V Krishna Adithya avatar
⟳ Robin Rombach retweeted
V Krishna Adithya@krishnavadithy1·Oct 22

X compression does do justice. FLUX Video upscale is amazing + fast + cheap!

The FLUX Video Upscaler received a full upgrade. It’s now the best video upscaler on the market, while costing less than Topaz Astra 2 and being twice as fast. Upscale any video up to 4K. Link to try it in the comments.

0:30
fal avatar
⟳ Robin Rombach retweeted
fal@fal·Oct 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.

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.

0:15
Justine Moore avatar
⟳ Robin Rombach retweeted
Justine Moore@venturetwins·Oct 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!

0:32
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.

Post attachment
Black Forest Labs avatar
⟳ Robin Rombach retweeted
Black Forest Labs@bfl_ai·Oct 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.

0:15
Robin Rombach avatar
Robin Rombach@robrombach·Oct 19

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.

Post attachment
Thomas Wolf avatar
⟳ Robin Rombach retweeted
Thomas Wolf@Thom_Wolf·Oct 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

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.