Black Forest Labs
In plain wordsA German AI company founded in 2024 by original creators of Stable Diffusion, which makes the FLUX image-generation models.
A German generative-AI company that develops the FLUX family of text-to-imagetext-to-image model, n.: An AI system that creates a picture from a written description, such as 'a fox reading a newspaper, in watercolor', usually within seconds. and image-editing models. FLUX.1 (August 2024), a 12-billion-parameter diffusiondiffusion model, n.: An AI that learns to create images, sound or video by practicing noise removal: shown pictures buried under static, it learns to clean them up, then builds new ones starting from pure static. transformer trained with flow matchingflow matching, n.: A way to train generators that learns, for every point between random noise and real data, which direction to move, so that noise can be steered smoothly into new examples., was released in three variants — a fast model under the Apache 2.0 license, an open-weight model for non-commercial use and a proprietary model served through an API — and quickly became a leading open image model; FLUX.1 Kontext (2025) added instruction-based image editing, and FLUX.2 followed in November 2025. Its models have powered image generation in xAI's Grok (2024), Mistral's Le Chat, Adobe Photoshop and Meta's Vibes app.
Origin
Founded in 2024 in Freiburg im Breisgau, Germany, by Robin Rombach, Andreas Blattmann and Patrick Esser, lead authors of the latent diffusion research behind Stable Diffusion, after they left Stability AIStability AI, prop. n.: A London company that paid for and released Stable Diffusion, a free image-generating AI anyone could download, and later models for video, audio and 3D..
Related
- text-to-image modeltext-to-image model, n.: An AI system that creates a picture from a written description, such as 'a fox reading a newspaper, in watercolor', usually within seconds.
- Stable DiffusionStable Diffusion, prop. n.: A widely used image-generating AI whose model files were released for anyone to download, so people could run it on their own computers and adapt it.
- latent diffusion modellatent diffusion model, n.: A diffusion image generator that works on a shrunken, compressed version of each picture instead of the full-size pixels, which makes it far cheaper to train and run.
- flow matchingflow matching, n.: A way to train generators that learns, for every point between random noise and real data, which direction to move, so that noise can be steered smoothly into new examples.
- Stability AIStability AI, prop. n.: A London company that paid for and released Stable Diffusion, a free image-generating AI anyone could download, and later models for video, audio and 3D.
- RunwayRunway, prop. n.: A New York company that makes AI tools for generating and editing video, used by filmmakers and artists; it helped create the image generator Stable Diffusion.
Mentioned in
RunwayRunway, prop. n.: A New York company that makes AI tools for generating and editing video, used by filmmakers and artists; it helped create the image generator Stable Diffusion.