-
Tweets327
-
Followers1K
-
Following33
-
Likes2K
FLUX 3 Video Edit is now live on fal - One prompt and the clip changes: swap a character, rebuild the background, restyle the shot, rewrite the dialogue - Lip sync follows the new dialogue automatically, including translations - Change colors, materials, and visual effects, or alter the events of a clip entirely
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
New blog post: continuous diffusion for language is back! This research direction receded into the background for a while, but as of this year, it is once again a hot topic. I wrote down a historical perspective and some thoughts on the recent revival. sander.ai/2026/08/24/con…
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
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.
FLUX 3 has me nostalgic for my life back in 2003
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
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.
Our co-founder and CEO, @robrombach, sat down with President Trump, President von der Leyen, President Macron, 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 below! bfl.ai/blog/our-co-fo…
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.
For over a decade, we’ve accepted that end-to-end backprop is the only way to train deep networks. But holding the entire network in memory all at once is why AI training is hitting a resource wall. We found a new way to break the network into blocks and train them independently. The trick? Treating the network’s forward pass like a diffusion model denoising a signal. This reinterpretation slashes the memory needed to train deep models. In our #ICLR2026 paper (arxiv.org/abs/2506.14202), we matched end-to-end performance across ViTs, DiTs, and LLMs. We did this while training just one isolated block at a time.
Introducing DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation pub.sakana.ai/diffusionblocks What if we didn’t have to hold an entire neural network in memory to train it? Standard neural net training optimizes all parameters jointly. As a result, the
We present a research preview of Self-Flow: a scalable approach for training multi-modal generative models. Multi-modal generation requires end-to-end learning across modalities: image, video, audio, text - without being limited by external models for representation learning. Self-Flow addresses this with self-supervised flow matching that scales efficiently across modalities. Results: • Up to 2.8x faster convergence across modalities. • Improved temporal consistency in video • Sharper text rendering and typography This is foundational research for our path towards multimodal visual intelligence.
Introducing FLUX.2 [klein]. Blazing fast. Beautiful. Generate stunning images in under a second while maintaining exceptional quality. Great for fast editing, changing styles, and developing ideas from 0 → 1. Available via API, or run it locally - Klein 4B under Apache 2.0, Klein 9B as open weights. Try it for free in our demo app (link in the thread).
FLUX.2 [max] is here Our highest quality model to date. * Grounded generation - searches the web for real-time context. * Up to 10 reference images. Products, characters, styles stay consistent. * #2 on @ArtificialAnlys in text-to-image and image editing.
FLUX.2 is here - our most capable image generation & editing model to date. Multi-reference. 4MP. Production-ready. Open weights. Into the new.
upgrade incoming.
FLUX is now in Photoshop. A dream coming true. 🥹 bfl.ai/blog/flux1-kon…
today, we're making another step towards the future. introducing our first Real-time Video generation model. join the beta 👇
AK @_akhaliq
527K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo ,submit papers here: https://t.co/UzmYN5XOCi
TomLikesRobots🤖 @TomLikesRobots
44K Followers 6K Following Filmmaker at Fable Studios. AI Specialist. IMDB link below. Previously AI VFX at Metaphysic. Featured in Forbes, Hollywood Reporter, The Guardian, New Yorker.
Justin Pinkney @Buntworthy
10K Followers 1K Following Playing with deep learning, computer vision and generative art. Co-creator of https://t.co/sYtHB9e5Dj, ML Researcher @ MidJourney @[email protected]
Sander Dieleman @sedielem
71K Followers 2K Following Research Scientist at Google DeepMind (WaveNet, Nano Banana, Gemini Omni). I tweet about ML, music, generative models (personal account).
Nerdy Rodent 🐀🤓... @NerdyRodent
10K Followers 3K Following Does stuff with AI. Likes rodents and Open Source. See my YouTube channel for AI tutorials & fun since 2020 :)
Yuliang Xiu @yuliangxiu
9K Followers 5K Following Assistant Professor @Westlake_Uni, Ph.D. @MPI_IS, previously @USC_ICT. Focusing on democratizing human digitization. Intern @RealityLabs @Ubisoft
David Marx (@digthatd... @DigThatData
4K Followers 2K Following Generative AI MLE, FOSS toolmaker, innovation catalyst @CoreWeave + @AiEleuther. https://t.co/z0fpuhlWRs
Ahmed A. A. Osman @ahmedaaosman
1K Followers 951 Following Research Scientist at Meta @RealityLabs Building Digital Humans - MHR/SUPR/STAR/SMPL-X Prev: @Amazon, MPI @PerceivingSys, @Imperial_Stats , @OfficialUoM
derrick has started y... @dvsch
8K Followers 2K Following Post-AI artist. Product @titlesxyz. Making art at the intersection of Chauncey and Malcolm X.
Alex Nichol @unixpickle
12K Followers 472 Following Code, AI, and 3D printing. Opinions are mostly my own, sometimes a computer's. Husband of @thesamnichol. Co-creator of DALL-E 2. Researcher @openai.
Doron Adler @Norod78
4K Followers 3K Following Fooling around with Generative machine learning models since 2019
pharmapsychotic @pharmapsychotic
18K Followers 7K Following fan of tacos and cats. #aiart #generativeart
makeitrad @makeitrad1
20K Followers 8K Following Artist, designer, pixel manipulator, exploring AI with childlike wonder 🤍 NFTs & AI art since 2021 🤍 Minting on request
Songyou Peng @songyoupeng
9K Followers 813 Following Teaching multimodality to Gemini, Nano Banana, and more @GoogleDeepMind. PhD from @ETH and @MPI_IS.
Ben Poole @poolio
23K Followers 2K Following ex-google brain and deepmind. phd in neural nonsense from stanford.
dadabots @dadabots
11K Followers 9K Following ∿ Music hackers. Algoraves. Inventing, playing. Neural synthesis. 24/7 ai death metal. Stable Audio team. Open models. Mischief @harmonai_org @artblocks_io
Hoosha @hooshaaii
312 Followers 3K Following AI ML researcher. Attentions . LLMs . Transformers . RSI
floris @florisndrs
2 Followers 77 Following
Orion Turing @AIPaperRadar
1 Followers 351 Following
Falco Schäfer @falcothebard
248 Followers 487 Following Horror author · Filmmaker · Gamer, who built my own AI studio so the work feels like home. Curious research into AGI — watch. Founder of @TheFunkatorium
Reece Scoggins @kaisellin__
91 Followers 3K Following
Die KI WOCHE - mit Ma... @kiwoche
33 Followers 226 Following Die deutschsprachige Plattform rund um KI - https://t.co/QKBq0pkoXp
hoanh @hoanhle_
426 Followers 670 Following research @NVIDIA. views are my own and subject to change.
Yassine Yousfi @yassineyousfi_
3K Followers 2K Following Professional overfitter. Head of Machine Learning at @comma_ai
Elvis Nava @elvisnavah
2K Followers 2K Following co-founder @mimicrobotics, phd @ETH. Discovering the scaling laws for robot AI.
DocPeter @DocPeterAndrews
96 Followers 358 Following Digital marketing. infrastructure, systems, strategy. In short, getting from a to b with a reason.
Jose @bbucle_net
19 Followers 293 Following
ChrisLiu6 @DongyangLiu13
0 Followers 15 Following
Alexandre Gomes @xandmaga
61 Followers 2K Following
Ben Holfeld @BenHolfeld
94K Followers 29K Following SF-based. Pianist, Physicist & Roboticst. Data, AI & Agent Architect at Day. SF Social & Robotics Enthusiast at Night. TPM & GTM e/acc /dd
vfx.ai @vfx_ai
364 Followers 2K Following AI for movie visual effects • Premium domain name available for purchase via @spaceship
Roman Bachmann @roman__bachmann
631 Followers 572 Following Multimodal @Apple, previously at @EPFL_en, @RIKEN_AIP
Ian Unsworth @Ianu82
104 Followers 5K Following Chief of Staff & Product Lead @mindsdb Start-ups, TV and Sports. I like other cool stuff too, honest!
Antoni Nowinowski @a_nowinowski
2 Followers 33 Following PhD student @PUT_Poznan (computer vision) / Artist https://t.co/N8V0Wuut1H
paula wehmeyer @pallipau
3K Followers 722 Following building @gen_intuition; prev partner @generalcatalyst; NYC📍
Leah @Leah_ZXL
1 Followers 49 Following
Mateo.jdda @m_jdda
194 Followers 7K Following Das ist der Twitter Account eines gescheiterten HoleCloser Gründers. Next coming...📱
Chaithanya kalyan @Chay_522
4 Followers 323 Following
Flak 🚀 @construct-... @flakerimi
1K Followers 235 Following Storyteller, creator of https://t.co/l72XxC9hcp
Jan Emmanuele @DrJanSchreier
24 Followers 129 Following Director of AI Consulting, Ex-VC Investor, PhD in AI
Bidhan Roy @bidhan
4K Followers 969 Following ceo @bageldotcom. building general world model for physical AI.
Bang Bang @BangBan42514093
4 Followers 310 Following
Mohammed Amine BEN CH... @AmineLehocine
16 Followers 2K Following
Klaus @klausboyajj
51 Followers 302 Following escaping the AI underclass at 17 https://t.co/ftaEmR7ulQ
Shumpei Takezaki @shumpeiMaxwell
882 Followers 2K Following 画像生成に興味がある九大D3 / バイオ&医療AIにも興味あり/ 視覚若手の会LENS (@lens_kousiki) PhD student of Kyushu University / Medical imaging, Generative Model
Ananthakumar Sethuram... @ASethuramanujam
0 Followers 5 Following
Amandeep Kumar @Amandeep__kumar
368 Followers 817 Following Ph.D. Student @JohnsHopkins || @AmazonScience Research Fellow
Peter Lorenz @cs_peter_lorenz
134 Followers 1K Following Applied Scientist @Idiap in Switzerland Past: Research Fellow @NTUsg Phd@UniHeidelberg @OptML_MSU @MITIBMLab @TUGraz https://t.co/YUwZiCVWhv
Sander Dieleman @sedielem
71K Followers 2K Following Research Scientist at Google DeepMind (WaveNet, Nano Banana, Gemini Omni). I tweet about ML, music, generative models (personal account).
Songyou Peng @songyoupeng
9K Followers 813 Following Teaching multimodality to Gemini, Nano Banana, and more @GoogleDeepMind. PhD from @ETH and @MPI_IS.
Ben Poole @poolio
23K Followers 2K Following ex-google brain and deepmind. phd in neural nonsense from stanford.
Dustin Podell @dustin_podell
1K Followers 1K Following All the power of creation right at our fingertips. Making models @bfl_ml https://t.co/xMaJiOl7Y0
Igor Babuschkin @ibab
111K Followers 893 Following CEO & Co-Founder @river_ai_inc. Previously @xAI, Research & Engineering
Anjney Midha @AnjneyMidha
53K Followers 3K Following founder, scientist, teacher @amppublic @stanford @frontiersystems • scaling alignment.
Black Forest Labs @bfl_ai
52K Followers 0 Following Powering visual intelligence everywhere. Creators of FLUX models. join us: https://t.co/XiNaRNYjFH
Ajay Jain @ajayj_
8K Followers 5K Following Co-founder @genmoai. Co-created denoising diffusion (DDPM), DreamFusion, Dream Fields. Ex Ph.D. @berkeley_ai, @googleai, @facebookai, @nvidiaai, @mit
Prafulla Dhariwal @prafdhar
43K Followers 568 Following Technical fellow @OpenAI. Co-creator of GPT-4o, GPT-3, DALL-E 2, Jukebox, Glow, PPO. Previously @MIT '17
Omid Taheri @omidtaherii
560 Followers 403 Following Co-founder at Ontic Labs| Cooking world models| Ex PhD @MPI - Ex-Adobe
Jae Myung Kim @jaemyung__kim
123 Followers 280 Following PhD student at @uni_tue @ExplainableML; Formerly undergrad at SNU; Interested in Scalable Trustworthy ML
Hao Li @HaoLi81
4K Followers 840 Following CEO & Co-Founder of Pinscreen | Dean & Professor at MBZUAI | MIT TR35 | DARPA ISAT | AI VFX | https://t.co/DbOXFOUV42 | https://t.co/hUwWdMxbul | https://t.co/CLW0LNGnYW
Janne Hellsten @nurpax
724 Followers 189 Following C64 coding mostly. Petmate PETSCII graphics editor author. Daily routine: cold water swimming, machine learning, 6502.
Mark Chen @markchen90
83K Followers 369 Following Chief Research Officer at @OpenAI. Coach for the USA IOI Team.
Karsten Kreis @karsten_kreis
4K Followers 835 Following Principal Research Scientist at @NVIDIA | Former Physicist | Generative AI Research | Proteins and Molecules Opinions are my own.
Rinon Gal @RinonGal
1K Followers 103 Following
Bozidar Antic @anticboz
136 Followers 389 Following Ph.D. student in computer vision and machine learning @AutoVisionGroup. Interested in geometry and appearance reconstruction, and generative models.
Robin Rombach @robrombach
15K Followers 577 Following Krawallkrümel. Generative Models at https://t.co/1xqMb617gc, made with ❤️
Haven Feng @HavenFeng
5K Followers 1K Following Postdoc @berkeley_ai, building Impossible. Prev. @MPI_IS @AdobeResearch @uni_tue Interested in recreating the physical world and the intelligence to do so.
Katrin Renz @KatrinRenz
648 Followers 282 Following Founder | Physical AI Previously PhD @IMPRS & Uni Tübingen | Intern @wayve_ai @Oxford_VGG
Christian Reiser @ChrisJReiser
1K Followers 1K Following KiloNeRF, MERF, Binary Opacity Grids. PhD Student @ Uni Tübingen / MPI-IS. Supervised by Andreas Geiger @AutoVisionGroup. Student researcher at Google DeepMind.
Katja Schwarz @K_S_Schwarz
2K Followers 510 Following Building world models. Ex-Meta AI Researcher. Previously PhD at Autonomous Vision Group in Tübingen.
Despoina Paschalidou @paschalidoud_1
2K Followers 258 Following Senior Research Scientist at @NVIDIA Previously: PostDoc at @Stanford, PhD at @MPI_IS and @ETH_en.
Elie Aljalbout @EliJalbout
1K Followers 680 Following Research Scientist @NVIDIARobotics | Prev: @Meta @UZH_en @ETH @TU_Muenchen @VWGroup | Opinions my own.You might like
