Axel Sauer

314 posts

Axel Sauer banner
Axel Sauer

Axel Sauer

@AxSauer

Training models @bfl_ml

Beigetreten Ekim 2017
39 Folgt1.5K Follower
Axel Sauer retweetet
Black Forest Labs
Black Forest Labs@bfl_ml·
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.
Black Forest Labs tweet media
English
15
137
905
144.2K
Axel Sauer retweetet
Black Forest Labs
Black Forest Labs@bfl_ml·
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).
English
75
218
1.9K
439.4K
Axel Sauer retweetet
Black Forest Labs
Black Forest Labs@bfl_ml·
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.
Black Forest Labs tweet mediaBlack Forest Labs tweet mediaBlack Forest Labs tweet media
English
43
133
990
123.1K
Axel Sauer retweetet
Black Forest Labs
Black Forest Labs@bfl_ml·
FLUX.2 is here - our most capable image generation & editing model to date. Multi-reference. 4MP. Production-ready. Open weights. Into the new.
English
162
473
3K
481.3K
Axel Sauer retweetet
Robin Rombach
Robin Rombach@robrombach·
upgrade incoming.
Robin Rombach tweet media
English
104
46
522
196.1K
Axel Sauer retweetet
KREA AI
KREA AI@krea_ai·
today, we're making another step towards the future. introducing our first Real-time Video generation model. join the beta 👇
English
129
257
2.2K
1.1M
Axel Sauer retweetet
Anjney Midha
Anjney Midha@AnjneyMidha·
mistral, elevenlabs, black forest labs, lovable, helsing, granola european AI scene is on fire
English
49
45
743
79.7K
Axel Sauer retweetet
Black Forest Labs
Black Forest Labs@bfl_ml·
Today we are releasing FLUX.1 Krea [dev] - a new state-of-the-art open-weights FLUX model, built for photorealism. Developed in collaboration with @krea_ai, this model is focused on images with unique aesthetics. No “AI look”, no blown-out highlights, just natural detail.
English
78
316
2K
334.1K
Axel Sauer retweetet
Black Forest Labs
Black Forest Labs@bfl_ml·
We just shipped the Kontext Komposer + Kontext-powered Presets Transform any image without writing a single prompt: ✓ New locations/styles ✓ Relighting headshots ✓ Product placements ✓ Movie posters Live now for free on bfl.ai/play
English
48
170
1.1K
120.6K
Axel Sauer retweetet
Hila Chefer
Hila Chefer@hila_chefer·
Career update: Happy to share that I've joined Black Forest Labs @bfl_ml 🌲 to work on the next generation of vision foundation models 👀 So honored to work with this superstar team that I've always admired 🤩 Exciting things to come soon! 🚀
Hila Chefer tweet media
English
49
8
469
39.5K
Axel Sauer retweetet
clem 🤗
clem 🤗@ClementDelangue·
Kontext-dev by @bfl_ml is number one trending on @huggingface with at least 100 derivative models just a week after release. Let's go!
clem 🤗 tweet mediaclem 🤗 tweet media
English
8
12
128
27.6K
Axel Sauer retweetet
Black Forest Labs
Black Forest Labs@bfl_ml·
High quality image editing no longer needs closed models We release FLUX.1 Kontext [dev] - an open weights model for proprietary-level image editing performance. Runs on consumer chips. ✓ Open weights available ✓ Best in-class performance ✓ Self-serve commercial licensing
Black Forest Labs tweet media
English
98
356
2K
267.2K
Axel Sauer retweetet
PyTorch
PyTorch@PyTorch·
Make Flux go brrr on H100s without bells and whistles ⚡️ We're excited to provide a simple recipe, dubbed `flux-fast`, providing a 2.5x speedup on H100 GPUs. 🔗 Blog: hubs.la/Q03tBKP70 ➡️ Code: hubs.la/Q03tBF8-0 By Joel Schlosser & @RisingSayak
PyTorch tweet media
English
2
15
128
15.7K
Axel Sauer retweetet
KREA AI
KREA AI@krea_ai·
Krea 1 is now available to everyone. today, we're releasing the public beta of our first image model trained in collaboration with @bfl_ml to offer superior aesthetic control and image quality. learn how to use it for free 👇
English
37
102
725
289.3K
Axel Sauer retweetet
@levelsio
@levelsio@levelsio·
⏳ I saw @fofrAI using Flux Kontext to restore old photos So I tried to restore the oldest photo in the world with people on it from 1838 186 years ago in Paris It works remarkably well and seems to stay quite close to the original Then I turned it into a video with @Kling_ai 2.1 and added background sounds with @elevenlabs Video-to-SFX model Actually feels like you can travel back in time a bit now I've always hated black and white photos with a passion because it makes history look very far away when it's not, much of the world looked very much the same as it does today, especially in historical places like Paris
@levelsio tweet media@levelsio tweet media
@levelsio@levelsio

Okay this is really cool I thought maybe I can try using @bfl_ml's Flux Kontext to make group photos You'd think that'd be possible by now with regular AI models nowadays but it's still very hard Because finetuning/training Flux by default on ONE person means you overwrite EVERY concept of people, so when generating a "group photo" you end up with a photo of 4 clones of yourself (and no entering multiple LoRas of diff ppl doesn't work well, they start mixing properties) But with Flux Kontext, I can generate 1 photo per finetuned AI model (like gf first, then me), and then combine the two photos into one while maintaining their likeness. Well kinda, faces still get a bit mangled but it's a start Will try add this to Photo AI asapppp!

English
36
35
618
429.9K
Axel Sauer retweetet
Freepik
Freepik@freepik·
This video was made from one image using Flux Kontext and Freepik AI Video Generator. Character consistency is FINALLY REAL, and each iteration takes less than 10 seconds to generate. Tutorial in the next tweet 👇🏼🧵
English
16
32
360
36.7K

Entdecken

@ArtificialAnlys @krea_ai @bfl_ml @huggingface @RisingSayak @viccpoes @fofrAI @Kling_ai