Black Forest Labs, a generative AI research community, led by Robin Rombach, Patrick Esser, and Andreas Blattmann — the original co-creators of the Stable Diffusion series of models, recently announced its official launch.
The company aims to develop and advance state-of-the-art generative deep learning models for various forms of media, such as images and videos, and to push the boundaries of creativity, efficiency, and diversity.
Secured €28M funding
The company has secured $31M (approximately €28M) in a series seed funding round led by main investor Andreessen Horowitz, with notable participation from angel investors Brendan Iribe, Michael Ovitz, Garry Tan, Timo Aila, and Vladlen Koltun, as well as other renowned experts in AI research and company building.
The company has also received follow-up investments from General Catalyst and MätchVC to support further its mission of bringing state-of-the-art AI from Europe to a global audience.
Additionally, Black Forest Labs announced the formation of its advisory board, which includes Michael Ovitz, who brings extensive experience in the content creation industry, and Prof. Matthias Bethge, a pioneer of neural style transfer and a leading expert in open European AI research.
“Today, as the first step towards this goal, we release the FLUX.1 suite of models that push the frontiers of text-to-image synthesis,” says the company.
Meet FLUX.1
FLUX.1 suite of text-to-image models that define a new state-of-the-art in image detail, prompt adherence, style diversity, and scene complexity for text-to-image synthesis.
To strike a balance between accessibility and model capabilities, FLUX.1 comes in three variants: FLUX.1 [pro], FLUX.1 [dev] and FLUX.1 [schnell]:
- FLUX.1 [pro]: Offers state-of-the-art performance image generation with top-of-the-line prompt following, visual quality, image detail, and output diversity.
- FLUX.1 [dev]: FLUX.1 [dev] is an open-weight, guidance-distilled model for non-commercial applications. Directly distilled from FLUX.1 [pro], FLUX.1 [dev] obtains similar quality and prompt adherence capabilities, while being more efficient than a standard model of the same size, says the company.
- FLUX.1 [schnell]: The fastest model tailored for local development and personal use. FLUX.1 [schnell] is openly available under an Apache2.0 license.
All public FLUX.1 models are based on a hybrid architecture of multimodal and parallel diffusion transformer blocks and scaled to 12B parameters.
FLUX.1 [pro] and [dev] surpass popular models like Midjourney v6.0, DALL·E 3 (HD) and SD3-Ultra in each of the following aspects: Visual Quality, Prompt Following, Size/Aspect Variability, Typography and Output Diversity. FLUX.1
The investor
Based out of California, Andreessen Horowitz (known as a16z) is a stage-agnostic venture capital firm with $19.2B in assets under management across multiple funds, including the $1.4B Bio funds, the $3.1B Crypto funds, and the Cultural Leadership Fund.
The company invests in seed to late-stage technology companies across the consumer, enterprise, bio/healthcare, crypto, and fintech spaces.
“We’re thrilled to partner with Robin, Patrick, Andreas, and the entire BFL team on this journey. Their commitment to open source, technical excellence, and fostering a collaborative AI ecosystem aligns perfectly with our vision for the future of artificial intelligence,” says Andreessen Horowitz.
01
From Mexico City to Rotterdam: How the Dutch Startup Visa launched Estefania Hernandez’s HR tech revolution