OrganizationCompany
Black Forest Labs
Black Forest Labs is a German AI lab based in Freiburg im Breisgau, founded in 2024 by Robin Rombach, Andreas Blattmann and Patrick Esser. It develops the FLUX image models and raised a $300 million Series B in December 2025.
Founded 2024Website bfl.ai Era Generative AI for everyone
What it is
Black Forest Labs is a German AI lab based in Freiburg im Breisgau. It develops the FLUX family of image models, and its hosted models are offered through its API and partners [1][2][5].
Origins
The lab was founded in 2024 by Robin Rombach, Patrick Esser and Andreas Blattmann together with seven others [1]. The founders were researchers behind latent diffusion and Stable Diffusion [1]. Latent diffusion generates images in a compressed representation rather than at full pixel size.
Black Forest Labs announced itself on 1 August 2024 with a $31 million seed round led by Andreessen Horowitz, and with the FLUX.1 image models [2]. Angel investors in the seed round included Brendan Iribe, Michael Ovitz, Garry Tan, Timo Aila and Vladlen Koltun. Follow-on investment came from General Catalyst and MätchVC [2].
Key features
The model line has been released in steps: FLUX.1 (August 2024), FLUX1.1 [pro] (October 2024), FLUX.1 Kontext (May 2025), FLUX.2 (November 2025) and FLUX 3 (July 2026) [1].
The company releases models in tiers. Hosted [pro] and [max] models are available through its API and partners, and open-weight [dev] and [schnell]/[klein] models are released for download [2][5].
FLUX was integrated into xAI's Grok in August 2024 and into Mistral's Le Chat in November 2024 [1]. In September 2025 Adobe Photoshop (beta) added FLUX.1 Kontext Pro to generative fill [1].
On 1 December 2025 the company raised a $300 million Series B at a $3.25 billion post-money valuation, co-led by Salesforce Ventures and Anjney Midha (AMP) [4]. Other Series B participants included a16z, NVIDIA, Northzone, Creandum, General Catalyst, Temasek, Canva and Figma Ventures. Customers named in the round include Adobe, fal.ai, Picsart, ElevenLabs, VSCO and Vercel [4].
Place in development
Robin Rombach is the company's CEO [6]. Wikipedia cites reports of about 100 employees by August 2026, including staff in San Francisco [1]. The company's line now runs from the 2024 FLUX.1 models to FLUX 3, launched in July 2026 [1][6].
CapabilitiesImage generation
TechniquesGenerative models
ApplicationsCreative tools
Ecosystem & regionOpen sourceEurope
20261
-
ReleaseBlack Forest Labs announces the multimodal FLUX 3
On 23 July 2026 Black Forest Labs announced FLUX 3, a model family for images, video, audio and actions. The video model became generally available on 4 August 2026.
20253
-
FundingBlack Forest Labs raises $300 million at a $3.25 billion valuation
On 1 December 2025 the German image-model developer Black Forest Labs said it had raised a $300 million Series B co-led by Salesforce Ventures and Anjney Midha's AMP, valuing the company at $3.25 billion.
-
ReleaseBlack Forest Labs releases FLUX.2
On 25 November 2025 Black Forest Labs released the FLUX.2 image models, with hosted pro and flex variants and the open-weight 32B dev model. The smaller klein models followed in January 2026.
-
ReleaseBlack Forest Labs introduces FLUX.1 Kontext
On 29 May 2025 Black Forest Labs introduced FLUX.1 Kontext, a model family for editing existing images from instructions, released in closed and open-weight forms.
20242
-
ReleaseBlack Forest Labs releases FLUX1.1 [pro] and its API
On 2 October 2024 Black Forest Labs released FLUX1.1 [pro], a faster version of its text-to-image model, and made its BFL API generally available at 4 cents per image.
-
ReleaseBlack Forest Labs launches with the FLUX.1 image models
On 1 August 2024 Black Forest Labs announced itself and released the FLUX.1 text-to-image models, backed by a $31 million seed round led by Andreessen Horowitz.
Models and products over time
5-
2024
-
Aug 1, 2024
FLUX.1
Model
FLUX.1 is a family of 12-billion-parameter text-to-image models released by Black Forest Labs on 1 August 2024 in pro, dev and schnell variants. The dev version is open-weight, and the variants carry different licenses.
-
Oct 2, 2024
FLUX1.1 [pro]
Model
A closed text-to-image model from Black Forest Labs, released on 2 October 2024 and available only through an API. Black Forest Labs said it generates six times faster than its predecessor, and it reached the top of the Artificial Analysis image arena leaderboard.
-
Aug 1, 2024
FLUX.1
Model
-
2025
-
May 29, 2025
FLUX.1 Kontext
Model
FLUX.1 Kontext is a family of image models from Black Forest Labs, announced on 29 May 2025, that generates and edits pictures from both text and image inputs. Its open-weight dev variant followed in June 2025.
-
Nov 25, 2025
FLUX.2
Model
FLUX.2 is Black Forest Labs' image generation and editing model family, released on 25 November 2025, spanning hosted tiers and open-weight releases, with support for 4-megapixel output and up to 10 reference images.
-
May 29, 2025
FLUX.1 Kontext
Model
-
2026
-
Jul 23, 2026
FLUX 3
Model
FLUX 3 is a multimodal model family from Black Forest Labs, announced on 23 July 2026, covering images, video, audio and action prediction. Its video model became generally available on 4 August 2026.
-
Jul 23, 2026
FLUX 3
Model
People1
Founders2
Notes and sources
- Flux (text-to-image model)https://en.wikipedia.org/wiki/Flux_(text-to-image_model)
- Announcing Black Forest Labshttps://bfl.ai/announcements/24-08-01-bfl
- Black Forest Labs raises $300M at $3.25B valuationhttps://techcrunch.com/2025/12/01/black-forest-labs-raises-300m-at-3-25b-valuation
- FLUX.2: Frontier Visual Intelligencehttps://bfl.ai/blog/flux-2
- Black Forest Labs launches FLUX 3, capable of generating images and 20-second video with audiohttps://venturebeat.com/technology/black-forest-labs-launches-flux-3-capable-of-generating-images-and-20-second-video-with-audio-but-in-limited-release-to-start
Cite this page: Black Forest Labs. TellWorld, https://www.tellworld.net/companies/black-forest-labs. Updated 2026-11-08