Flux (also known as FLUX.1) is a
text-to-image model
A text-to-image model is a machine learning model which takes as input a natural language description and produces an image matching that description. Such models began to be developed in the mid-2010s, as a result of advances in deep neural netwo ...
developed by Black Forest Labs, based in
Freiburg im Breisgau
Freiburg im Breisgau (; abbreviated as Freiburg i. Br. or Freiburg i. B.; Low Alemannic: ''Friburg im Brisgau''), commonly referred to as Freiburg, is an independent city in Baden-Württemberg, Germany. With a population of about 230,000 (as o ...
, Germany. Black Forest Labs were founded by former employees of
Stability AI. As with other text-to-image models, Flux
generates images
An image is a visual representation of something. It can be two-dimensional, three-dimensional, or somehow otherwise feed into the visual system to convey information. An image can be an artifact, such as a photograph or other two-dimension ...
from
natural language
In neuropsychology, linguistics, and philosophy of language, a natural language or ordinary language is any language that has evolved naturally in humans through use and repetition without conscious planning or premeditation. Natural languag ...
descriptions, called ''
prompts''.
History
Black Forest Labs were founded in 2024 by Robin Rombach, Andreas Blattmann, and Patrick Esser, former employees of Stability AI.
All three founders had previously researched the artificial intelligence image generation at
Ludwig Maximillian University of Munich as research assistants under Björn Ommer.
They published their research results on image generation in 2022, which resulted in creation of
Stable Diffusion.
Investors in Black Forest Labs included venture capital firm
Andreessen Horowitz
Andreessen Horowitz (also called a16z, legal name AH Capital Management, LLC) is a private American venture capital firm, founded in 2009 by Marc Andreessen and Ben Horowitz. The company is headquartered in Menlo Park, California.
Andreessen H ...
,
Brendan Iribe
Brendan Trexler Iribe (; born August 12, 1979) is an American game programmer, entrepreneur and the original CEO and co-founder of Oculus VR, Inc. and Scaleform. He is the managing partner at BIG Ventures, an early-stage venture fund.
Early li ...
,
Michael Ovitz
Michael Steven Ovitz (born December 14, 1946) is an American businessman, investor, and philanthropist. He was a talent agent who co-founded Creative Artists Agency (CAA) in 1975 and served as its chairman until 1995. Ovitz later served as preside ...
,
Garry Tan
Garry Tan (; born 1981) is the founder of Initialized Capital. He previously co-founded Posterous and Posthaven. He was also an early employee at Palantir Technologies, and a partner at Y Combinator.
Early life and education
Tan was born in 19 ...
, and
Vladlen Koltun.
The company received an initial investment of million.
In August 2024, Flux was integrated into the
Grok
''Grok'' is a neologism coined by American writer Robert A. Heinlein for his 1961 science fiction novel ''Stranger in a Strange Land''. While the ''Oxford English Dictionary'' summarizes the meaning of ''grok'' as "to understand intuitively or ...
chatbot developed by
xAI and made available as part of premium feature on
X (formerly Twitter).
Grok later switched to its own text-to-image model
Aurora
An aurora (plural: auroras or aurorae), also commonly known as the polar lights, is a natural light display in Earth's sky, predominantly seen in high-latitude regions (around the Arctic and Antarctic). Auroras display dynamic patterns of bri ...
in December 2024.
On 18 November 2024,
Mistral AI
Mistral AI, headquartered in Paris, France specializes in artificial intelligence (AI) products and focuses on open-weight large language models, (LLMs). Founded in April 2023 by former engineers from Google DeepMind and Meta Platforms, the co ...
announced that its ''Le Chat'' chatbot had integrated Flux Pro as its image generation model.
On 21 November 2024, Black Forest Labs announced the release of Flux.1 Tools, a suite of editing tools designed to be used on top of existing Flux models. The tools consisting of Flux.1 Fill for
inpainting
Inpainting is a conservation process where damaged, deteriorated, or missing parts of an artwork are filled in to present a complete image. This process is commonly used in image restoration. It can be applied to both physical and digital art ...
and outpainting, Flux.1 Depth for control based on extracted
depth map
In 3D computer graphics and computer vision, a depth map is an image or image channel that contains information relating to the distance of the surfaces of scene objects from a viewpoint. The term is related (and may be analogous) to ''depth ...
of input images and prompts, Flux.1 Canny for control based on extracted
canny edges of input images and prompts, and Flux.1 Redux for mixing existing input images and prompts. Each tools are available in both Dev and Pro variants.
In January 2025, Black Forest Labs announced a partnership with
Nvidia
Nvidia CorporationOfficially written as NVIDIA and stylized in its logo as VIDIA with the lowercase "n" the same height as the uppercase "VIDIA"; formerly stylized as VIDIA with a large italicized lowercase "n" on products from the mid 1990s to ...
for inclusion of Flux models as foundation models for Nvidia's
Blackwell Blackwell may refer to:
Places
;Canada
* Blackwell, Ontario
;United Kingdom
* Blackwell, County Durham, England
* Blackwell, Carlisle, Cumbria, England
* Blackwell (historic house), South Lakeland, Cumbria, England
* Blackwell, Bolsover, Alfr ...
microarchitecture. The company also announced the release of , designed for customisation and
fine-tuning
In theoretical physics, fine-tuning is the process in which parameters of a model must be adjusted very precisely in order to fit with certain observations. This had led to the discovery that the fundamental constants and quantities fall into suc ...
of Flux-generated images and a partnership with German media company
Hubert Burda Media
Hubert Burda Media Holding is a German media group with headquarters in Offenburg. It originated as a small printing business, founded by Franz Burda Snr in Philippsburg, in 1903.
In 1986, the corporate group was divided up between Franz Jnr ...
for usage of Flux Pro as part of content creation.
Models
Flux is a series of text-to-image models. The models are based on a hybrid architecture that combines multimodal and parallel diffusion transformer blocks scaled to 12billion parameters.
The models are released under different licences with ''Schnell'' (meaning Fast or Quick in
German language
German ( ) is a West Germanic language mainly spoken in Central Europe. It is the most widely spoken and official or co-official language in Germany, Austria, Switzerland, Liechtenstein, and the Italian province of South Tyrol. It is als ...
) released as
open-source software
Open-source software (OSS) is computer software that is released under a license in which the copyright holder grants users the rights to use, study, change, and distribute the software and its source code to anyone and for any purpose. Ope ...
under
Apache License, ''Dev'' released as
source-available software
Source-available software is software released through a source code distribution model that includes arrangements where the source can be viewed, and in some cases modified, but without necessarily meeting the criteria to be called open-source ...
under a non-commercial licence, and ''Pro'' released as
proprietary software
Proprietary software is computer software, software that is deemed within the free and open-source software to be non-free because its creator, publisher, or other rightsholder or rightsholder partner exercises a legal monopoly afforded by modern ...
and only available as
API
An application programming interface (API) is a way for two or more computer programs to communicate with each other. It is a type of software interface, offering a service to other pieces of software. A document or standard that describes how ...
that can be licensed by third-party users.
Users retained the ownership of resulting output regardless of models used.
The models can be used either online or locally by using generative AI user interfaces such as
ComfyUI and
Stable Diffusion WebUI Forge (a
fork
In cutlery or kitchenware, a fork (from la, furca ' pitchfork') is a utensil, now usually made of metal, whose long handle terminates in a head that branches into several narrow and often slightly curved tines with which one can spear foods ...
of Automatic1111 WebUI).
An improved flagship model, Flux 1.1 Pro was released on 2 October 2024.
Two additional modes were added on 6 November, Ultra which can generate image at four times higher resolution and up to 4 megapixel without affecting generation speed and Raw which can generate hyper-realistic image in the style of
candid photography
A candid photograph is a photograph captured without creating a posed appearance. The candid nature of a photograph is unrelated to the subject's knowledge about or consent to the fact that photographs are being taken, and are unrelated to the s ...
.
Related to Flux is
text-to-video model SOTA, under development .
Reception
According to a test performed by ''
Ars Technica
''Ars Technica'' is a website covering news and opinions in technology, science, politics, and society, created by Ken Fisher and Jon Stokes in 1998. It publishes news, reviews, and guides on issues such as computer hardware and software, sc ...
,'' the outputs generated by Flux.1 Dev and Flux.1 Pro are comparable with
DALL-E 3 in terms of prompt fidelity, with the photorealism closely matched
Midjourney 6 and generated human hands with more consistency over previous models such as Stable Diffusion XL.
Flux has been criticised for its very realistic generated images. According to media reports, depictions ranged from an image of
Donald Trump
Donald John Trump (born June 14, 1946) is an American politician, media personality, and businessman who served as the 45th president of the United States from 2017 to 2021.
Trump graduated from the Wharton School of the University of ...
posing with guns to disturbing scenes, which triggered discussions about ethical implications of technologies developed by Black Forest Labs.
After the release of the model, social media
X was flooded with Flux-generated images.
Black Forest Labs has not provided exact details of the data used to train the model.
''Ars Technica'' suspected that Flux is based on a large, unauthorised collection of images
scraped from the internet, a controversial practice with potential legal consequences.
Third-party integrations
While Black Forest Labs does not offer direct access to their models on their website, the Flux models are widely available through various third-party platforms for creative and professional use. These include repositories on platforms like
Hugging Face
Hugging Face, Inc. is an American company that develops tools for building applications using machine learning. It is most notable for its Transformers library built for natural language processing applications and its platform that allows users ...
and Replicate.
References
External links
*
Flux models on Hugging FaceFlux models on ReplicateFlux models on FAL.ai
{{Artificial intelligence navbox
Unsupervised learning
Text-to-image generation
Deep learning software applications
Artificial intelligence art
Open-source artificial intelligence
2024 establishments in Germany