
crafting pixels in the forest @bfl_ai prev: Research Engineer @pika_labs, Open Source AI @huggingface. Co-created diffusers 🧨
Paris
Joined January 2016
- Tweets1.5K
- Following69
- Followers6K
- Likes9.1K
Suraj Patil retweeted
Over the past week, I’ve been overwhelmed by the love and support of friends, industry colleagues, and people I've never met. Thank you to everyone who has shown kindness to my family and me. It means the world to me.
I came to the United States 53 years ago, and becoming an American citizen is one of the greatest gifts and proudest moments of my life. NVIDIA has been my life’s work. Building it into the company it is today alongside my colleagues has been a privilege and an honor. Nowhere but in America could a company like NVIDIA be possible. I love our country, and I love NVIDIA.
I did not live up to the standards expected of everyone at NVIDIA, and I have made serious mistakes in my personal life. I created problems for the Board that I deeply regret. I own my mistakes completely, and I am committed to cooperating with the Board’s independent investigation.
Since my departure, I’ve seen an outpouring of calls from NVIDIA’s employees, investors, business partners, and customers for me to return as CEO. Many continue to reach out to me directly as the company navigates complex technology, market, competitive, and geopolitical dynamics. NVIDIA is a once-in-a-generation company. If the Board of Directors decides that my return is in the best interest of our shareholders, our employees, the company, and America, I would be honored to answer these calls and return as CEO.
Thank you again to everyone who has shared their good wishes. I am profoundly humbled by your support. To my family: I love you, and I will spend the rest of my life being worthy of yours.
Jensen
Suraj Patil retweeted
SOTA, again 😍
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.
Suraj Patil retweeted
I’ve been at BFL for 18 months now, if you wanna do the job of your life and work at the frontier? Join us, feel free to DM as well 🌲💙
Black Forest Labs is on the inaugural 2026 AI 100.
Thanks @NewcomerMedia @BessemerVP for the recognition.
Join us. Links in 🧵
Suraj Patil retweeted
Introducing Carbon-X: The best open DNA model.
We midtrained a 14B model on DNA and text, and it beats every open language model and matches GPT-6.1 Sol at 1,000x lower cost.
Ask it about a sequence, what a mutation does, or to generate new DNA.
huggingface.co/HuggingFaceBi…
Suraj Patil retweeted
1/ The tokenizer is a new scaling axis!
We introduce an approach for diffusable representation learning that's principled, scalable, and works when DINO/LeJEPA collapse.
We get joint tokenizer+diffusion scaling laws and it's compute-optimal vs raw diffusion
w/ @drfeifei @GordonWetzstein @jcjohnss @ericryanchan @vincesitzmann @KyleSargentAI
Thread, Paper, and Blogpost below
Suraj Patil retweeted
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.
Suraj Patil retweeted
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.
Suraj Patil retweeted
FLUX 3 is the strongest world model in the world.
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.
Suraj Patil retweeted
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.
Suraj Patil retweeted
Introducing FLUX 3 Action.
An open weights 7B World Action Model that achieves first place on the RoboLab benchmark.
It outperforms the previous best open model by 6.1 percentage points while using 56% fewer parameters and running up to 3.95x faster.
FLUX 3 Action removes the usual trade-off between world action model performance and VLA speed: it still predicts video and actions together, but plans more than twice as far ahead and runs faster per second of robot motion than the strongest open VLA.
Teams can fine-tune FLUX 3 Action on their own demonstrations to create policies for a particular robot and task. Together with @nvidia, we also integrated FLUX 3 Action natively into @huggingface's LeRobot, with fine-tuning recipes included and edge deployment on NVIDIA Jetson.
Beyond robotics, we’re also seeing promising results training task-specific policies for acting in simulated environments like gaming, controlling a vehicle, computer use, and wherever else a model needs to understand a visual environment and then choose what to do next.
FLUX 3 Action builds on the same image, video, and audio pretraining as FLUX 3, but uses a smaller architecture designed for practical deployment. In midtraining, we trained the model to predict actions and future frames together.
We’re releasing the weights, code, fine-tuning recipe, benchmarks, and reproducible examples so researchers and developers can build on the model with their own robots, environments, and tasks (see below).
Suraj Patil retweeted
Today we release FLUX 3 Action - an open-weight 7B world-action model, achieving SOTA performance and efficiency on various leaderboards such as RoboLab.
I am incredible proud of the team - and both backbone and embodiment-specific finetunes are open weight, alongside the training recipes!
Introducing FLUX 3 Action.
An open weights 7B World Action Model that achieves first place on the RoboLab benchmark.
It outperforms the previous best open model by 6.1 percentage points while using 56% fewer parameters and running up to 3.95x faster.
FLUX 3 Action removes the usual trade-off between world action model performance and VLA speed: it still predicts video and actions together, but plans more than twice as far ahead and runs faster per second of robot motion than the strongest open VLA.
Teams can fine-tune FLUX 3 Action on their own demonstrations to create policies for a particular robot and task. Together with @nvidia, we also integrated FLUX 3 Action natively into @huggingface's LeRobot, with fine-tuning recipes included and edge deployment on NVIDIA Jetson.
Beyond robotics, we’re also seeing promising results training task-specific policies for acting in simulated environments like gaming, controlling a vehicle, computer use, and wherever else a model needs to understand a visual environment and then choose what to do next.
FLUX 3 Action builds on the same image, video, and audio pretraining as FLUX 3, but uses a smaller architecture designed for practical deployment. In midtraining, we trained the model to predict actions and future frames together.
We’re releasing the weights, code, fine-tuning recipe, benchmarks, and reproducible examples so researchers and developers can build on the model with their own robots, environments, and tasks (see below).
Suraj Patil retweeted
no VLA - just gpt6 astra calibrates itself and solves the task of putting lego blocks into a box
anyone can try this without owning physical so100, the entire thing is done in MuJoCo simulation huggingface.co/buckets/mishi…
Suraj Patil retweeted
FLUX 3 Video now has fast, precise editing.
The fastest and lowest cost video editing model in the world.
In our internal benchmarking, it’s also ahead of other leading models in the accuracy and precision of edits.
Edit an existing video by:
• Adding, removing, or replacing objects and characters
• Replacing backgrounds
• Editing text
• Changing colors, materials, visual effects
• Changing or translating dialogue with accurate lip sync
• Changing the events of a clip
Suraj Patil retweeted
Anatomy of Microduck 🤏🦆 :
* 15 robotis dyanmixel XL330-family servos
* rockchip RK3566 compute
* np-f550 battery
* camera, 8×8 ToF LiDAR + dual IMUs
mishig-microduck-anatomy.hf.…
Suraj Patil retweeted
We have a huge news to share today!
Today we are unveiling the first truly accessible RL robot - welcome Microduck
A 25 cm tiny open-source biped with 15 actuators and packed with sensors (camera, speaker, LiDAR, NFC, bluetooth, wifi, etc) that you train yourself with reinforcement learning.
It's also playable out of the box with more than half a dozen fun and playful pre-trained policies to have it walk, sit, crouch, roller-skate, pick up objects with its articulated beak, and recover on its own.
And all for less than $400.
See all the details, play with the simulator and order it at: pollen-robotics.com/microduc…
(video with sound on 🔊)
Suraj Patil retweeted
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.
Link to use it in the thread
Suraj Patil retweeted
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.
Suraj Patil retweeted
Two years later our first video model - FLUX 3 Video - is finally released🥹. This is such a strong, fun and versatile model made by the best team in the world @bfl_ai. We will add further variants and generation from references in the near future. I am also super excited about the upcoming open weight, action prediction and image variants of FLUX 3.
Suraj Patil retweeted
A preview of FLUX 3 is now available on Hermes agent for 48h.
Hermes chains shots into full short films, one prompt end to end. They're running a short film contest all week: @NousResearch has the details.
Or try it in person: FLUX 3 live at our SF event, this Friday.
FLUX 3 Preview is now publicly available, only on Hermes Agent and free on all Nous Portal paid subs for the next 48 hours.
Create a short film with it tagging @NousResearch and @bfl_ai - the 3 best entrants by 7PM PT on August 1st will receive:
1st place: 1 year of free FLUX 3 generation (20/day) + $2,000 Portal credits + Nous hoodie
2nd place: $1,000 credits + hoodie
3rd place: $500 credits + hoodie
First 100 new signups using code L1YSMYDB get a free month of Nous Portal Plus with full video gen access.
First 25 upgrades using code KEQHYO3X get $20 off.
portal.nousresearch.com/sign…
> hermes update














