Jump to content

Flux (text-to-image model)

From Wikipedia, the free encyclopedia

Flux
Original author(s)Black Forest Labs
Developer(s)Black Forest Labs
Initial releaseAugust 2024
Stable release
Flux 1.1 Pro (model)[1] / 2 October 2024
Repository
TypeText-to-image model
License
Websiteblackforestlabs.ai

Flux (also known as FLUX.1) is a text-to-image model developed by Black Forest Labs, based in Freiburg im Breisgau, Germany. Black Forest Labs was founded by Robin Rombach, Andreas Blattmann, and Patrick Esser.[2] As with other text-to-image models, Flux generates images from natural language descriptions, called prompts.

History

[edit]

Black Forest Labs was founded in 2024 by former employees of Stability AI.[3] All three founders had previously researched the artificial intelligence image generation at Ludwig Maximillian University of Munich as research assistants under Björn Ommer.[4][5][6] They published their research results on image generation in 2022, which resulted in Stable Diffusion.[6][7] In August 2024, Flux was integrated into the Grok chatbot developed by xAI and available as part of premium feature on X (formerly Twitter).[8][9][10][11] Investors in Black Forest Labs include Andrerssen Horowitz, Brendan Iribe, Michael Ovitz, Garry Tan, and Vladlen Koltun.[12] The company received an initial investment of US$31 million.[13][14]

Models

[edit]

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 12 billion parameters.[12] The models are released under different licences with Schnell (meaning Fast in German language) released as open-source software under Apache License, Dev released as source-available software under a non-commercial licence, and Pro released as proprietary software and only available as API that can be licensed by third-party users.[15][16] Users retained the ownership of resulting output regardless of models used.[17][18]

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 of Automatic1111 WebUI).[12][19]

An improved flagship model, Flux 1.1 Pro was released on 2 October 2024.[20][21] Two additional modes were added later, 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 on 6 November 2024.[22][23][24]

Related to the Flux is text-to-video model SOTA, currently under development.[12]

Reception

[edit]

According to a test performed by Ars Technica, 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 more consistently over previous models such as Stable Diffusion XL.[25]

Flux has been criticised for its very realistic generated images. According to media reports, depictions ranged from an image of Donald Trump posing with guns to disturbing scenes, which triggered discussions about ethical implications of technologies developed by Black Forest Labs.[4][10]

After the release of the model, social media X was flooded with Flux-generated images.[26][27] Black Forest Labs has not provided exact details of the data used to train the model.[22] 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.[28][25]

References

[edit]
  1. ^ "Announcing FLUX1.1 [pro] and the BFL API". Black Forest Labs. 2 October 2024. Retrieved 17 November 2024.
  2. ^ Killian, Nicolas (27 August 2024). "Black Forest Labs: Sie sind ein Teil von jener Kraft". Die Zeit (in German). ISSN 0044-2070. Archived from the original on 4 October 2024. Retrieved 17 November 2024.
  3. ^ Growcoot, Matt (5 August 2024). "AI Image Generator Made by Stable Diffusion Inventors on Par With Midjourney and DALL-E". PetaPixel. Retrieved 17 November 2024.
  4. ^ a b "Black Forest Labs unter Beschuss: Schockierende KI-Bilder sorgen für…". AlleAktien (in German). 22 August 2024. Retrieved 17 November 2024.
  5. ^ Hermes, Ann Kathrin (8 August 2024). "Black Forest Labs: KI-Tools aus dem Schwarzwald". trend.at (in German). Retrieved 17 November 2024.
  6. ^ a b Schwär, Hannah (15 August 2024). "Black Forest Labs: Die Schwarzwald-KI, auf die Elon Musk setzt". Capital.de (in German). Retrieved 17 November 2024.
  7. ^ "High-Resolution Image Synthesis with Latent Diffusion Models". Computer Vision & Learning Group. Archived from the original on 16 November 2024. Retrieved 17 November 2024.
  8. ^ Puscher, Frank. "Generative AI. Black Forest Labs und Flux.1: Vom Superstar zum Buhmann in fünf Tagen". MEEDIA (in German). Archived from the original on 27 September 2024. Retrieved 17 November 2024.
  9. ^ Bomke, Luisa. "Flux.1 – ein deutscher KI-Bildgenerator dreht mit Grok frei". Handelsblatt (in German). Archived from the original on 30 August 2024. Retrieved 17 November 2024.
  10. ^ a b Weatherbed, Jess (14 August 2024). "xAI's new Grok-2 chatbots bring AI image generation to X". The Verge. Archived from the original on 17 November 2024. Retrieved 17 November 2024.
  11. ^ Metz, Rachel (21 August 2024). "This Tiny Startup Is Helping Musk's Grok With Image Generation". Bloomberg News. Retrieved 19 November 2024.
  12. ^ a b c d "Announcing Black Forest Labs". Black Forest Labs. 1 August 2024. Archived from the original on 17 November 2024. Retrieved 17 November 2024.
  13. ^ Steinschaden, Jakob (12 August 2024). "Black Forest Labs: 31 Mio. Dollar für Herausforderer von OpenAI und Midjourney". Trending Topics (in German). Archived from the original on 28 August 2024. Retrieved 17 November 2024.
  14. ^ Nuñez, Michael (1 August 2024). "Stable Diffusion creators launch Black Forest Labs, secure $31M for FLUX.1 AI image generator". VentureBeat. Archived from the original on 8 October 2024. Retrieved 17 November 2024.
  15. ^ "Get Flux". Black Forest Labs. Archived from the original on 16 November 2024. Retrieved 17 November 2024.
  16. ^ Wiggers, Kyle (3 October 2024). "Black Forest Labs, the startup behind Grok's image generator, releases an API". TechCrunch. Archived from the original on 4 October 2024. Retrieved 17 November 2024.
  17. ^ "flux/model_licenses/LICENSE-FLUX1-dev at main · black-forest-labs/flux". GitHub. Archived from the original on 15 September 2024. Retrieved 18 November 2024. Outputs. We claim no ownership rights in and to the Outputs. You are solely responsible for the Outputs you generate and their subsequent uses in accordance with this License. You may use Output for any purpose (including for commercial purposes), except as expressly prohibited herein. You may not use the Output to train, fine-tune or distill a model that is competitive with the FLUX.1 [dev] Model.
  18. ^ "API Agreement - BFL Docs (Pro)". Black Forest Labs. 1 August 2024. Archived from the original on 3 October 2024. Retrieved 18 November 2024. Output. Company claims no ownership rights in and to the Outputs, and Developer and Users may use the Output for their own personal or commercial purposes, subject to any restrictions set forth herein or in the Flux Service Terms. For the avoidance of doubt, Outputs do not include any components of the Flux API or the Flux AI model, such as its weights or parameters.
  19. ^ 田口和裕 (18 August 2024). "話題の画像生成AI「FLUX.1」をStable Diffusion用の「WebUI Forge」で動かす（高速化も試してみました） (1/6)". ASCII.jp (in Japanese). ASCII Media Works. Retrieved 21 November 2024.
  20. ^ "Announcing FLUX1.1 [pro] and the BFL API". Black Forest Labs. 2 October 2024. Retrieved 17 November 2024.
  21. ^ Franzen, Carl (3 October 2024). "Black Forest Labs releases Flux 1.1 Pro and an API". VentureBeat. Retrieved 17 November 2024.
  22. ^ a b Growcoot, Matt (7 November 2024). "Flux AI Introduces Raw Mode That 'Captures the Genuine Feel of Candid Photography'". PetaPixel. Retrieved 19 November 2024.
  23. ^ Bastian, Matthias (6 November 2024). "Flux 1.1 Pro AI image model adds "amateur" RAW photo mode and 4K image generation". The Decoder. Retrieved 17 November 2024.
  24. ^ "Introducing FLUX1.1 [pro] Ultra and Raw Modes". Black Forest Labs. 6 November 2024. Archived from the original on 12 November 2024. Retrieved 17 November 2024.
  25. ^ a b Edwards, Benj (2 August 2024). "FLUX: This new AI image generator is eerily good at creating human hands". Ars Technica. Retrieved 17 November 2024.
  26. ^ Zeff, Maxwell (14 August 2024). "Meet Black Forest Labs, the startup powering Elon Musk's unhinged AI image generator". TechCrunch. Archived from the original on 17 November 2024. Retrieved 17 November 2024.
  27. ^ Schwarzer, Matthias (16 August 2024). "Drogen, Bomben und Gewalt: KI-Bildgenerator von Elon Musk zeigt alles – mit deutscher Technik". RND.de (in German). Retrieved 17 November 2024.
  28. ^ Künne, Christoph (7 August 2024). "FLUX.1: Neuer KI-Bildgenerator". DOCMA (in German). Archived from the original on 31 August 2024. Retrieved 17 November 2024.
[edit]
Wikimedia Commons has media related to Flux (text-to-image model).
Retrieved from "https://en.wikipedia.org/w/index.php?title=Flux_(text-to-image_model)&oldid=1259817111"