Jonas Müller

Exploring the latent space at @bfl_ml

[Robin Rombach @robrombach]

Seeing Martin Scorsese using FLUX for storyboarding and scene exploration was absolutely insane. Experiencing how one of the absolute masters of cinema & filmmaking uses the technology that we developed, his curiosity and creativity, and the way he prompted our models, was humbling.

I am grateful to call Martin Scorsese an advisor to BFL, and to explore the next, multimodal and interactive phases of visual AI with him.

[Black Forest Labs @bfl_ai]

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.

[Jonas Müller @jdotmueller]

@FLUXByBFL a photo of a serene hut by a lake in the mountains

[Black Forest Labs @bfl_ai]

FLUX.2 is here - our most capable image generation & editing model to date.

Multi-reference. 4MP. Production-ready. Open weights.

Into the new.

[Robin Rombach @robrombach]

upgrade incoming.

[Robin Rombach @robrombach]

FLUX is now also in Meta AI. What a day.

🥵

[Yam Levi @YamLevi350625]

Kontext dev is out now!

Quality is of the utmost importance to us in BFL so we took a bit extra time to get this right, can't wait to see what people will dream up :)

#flux #kontext #fluxkontext

[Jonas Müller @jdotmueller]

A lot of hard work went into this. Exciting to finally share this. And a [dev] model is upcoming too

[Black Forest Labs @bfl_ai]

Today we're releasing FLUX.1 Kontext - a suite of generative flow matching models that allow you to generate and edit images.

Unlike traditional text-to-image models, Kontext understands both text AND images as input, enabling true in-context generation and editing.

[Robin Rombach @robrombach]

@elonmusk @durov @grok @durov use https://t.co/SZSG2A5oHu instead, we support high loads and high quality.

[Anjney Midha @AnjneyMidha]

Caption this

[Black Forest Labs @bfl_ai]

Today, we are excited to share that we are adding high-resolution capabilities to FLUX1.1 [pro]. Extending its functionality to support 4x higher image resolutions (up to 4MP) while maintaining an impressive generation time of only 10 seconds per sample.

[Black Forest Labs @bfl_ai]

We are excited to release FLUX1.1 [pro], our most advanced and efficient model yet, alongside the general availability of the beta BFL API.

[Black Forest Labs @bfl_ai]

We are actively hiring across several roles, check out our website or job board for detailed job descriptions.

[PrimerYang @yangzhizheng1]

My first flux-Dev Lora model training was completed successfully. This is a graphic illustration style lora. I used 78 images some of them from @araminta_k .I will upload the lora model to huggingface later
prompt: a girl walking on the street,surrounded by a group of pigeons

[Andrej Karpathy @karpathy]

Very exciting! Congrats Robin and the @bfl_ml team (of Stable Diffusion fame) on the launch!

The open sourced FLUX.1 image gen model looks very strong, main page with examples:
https://t.co/QNeMz5jnE8

Clean/readable (inference) code on GitHub:
https://t.co/y8HodIJxLk

[Jonas Müller @jdotmueller]

I love working with this team. They are all so amazing and talented people!

[Black Forest Labs @bfl_ai]

We are excited to announce the launch of Black Forest Labs. Our mission is to develop and advance state-of-the-art generative deep learning models for media and to push the boundaries of creativity, efficiency and diversity.

[Robin Rombach @robrombach]

🔥 I am so damn excited to announce the launch of Black Forest Labs. We set ourselves on a mission to advance state-of-the-art, high-quality generative deep learning models for images and video, and make them available to the broadest audience possible.

Today, we release FLUX.1

[Black Forest Labs @bfl_ai]

We are excited to announce the launch of Black Forest Labs. Our mission is to develop and advance state-of-the-art generative deep learning models for media and to push the boundaries of creativity, efficiency and diversity.

[Patrick Esser @pess_r]

wouldn't be where we are are without @EMostaque ❤️

[Robin Rombach @robrombach]

Party time! The SD3 paper made it to arxiv: https://t.co/BjRvdYgv6N

Key takeaways:
- flow matching is very nice.
- back to work with @pess_r and a fantastic team ♥️

The paper is full of details on improved flow matching, scaling and engineering. Enjoy!