Black Forest Labs Open Models: Model List and Licenses

September 27, 2026

About Black Forest Labs

Black Forest Labs is the AI company behind the FLUX image generation models, which it releases on its black-forest-labs organization on Hugging Face. For local image generation it is a standard publisher alongside Stable Diffusion.

What It Releases

• FLUX.1 (2024 to 2025): the fast schnell and the high-quality dev, plus Kontext for editing, Depth and Canny for control, and Krea-dev (all about 12B).
• FLUX.2 (November 2025 onward): the large FLUX.2-dev (about 32B) and, in January 2026, the small, fast FLUX.2 [klein] (4B and 9B). According to its model card, klein is the company’s fastest image model, unifying generation and editing in a single compact architecture with sub-second generation, and the 4B runs on consumer GPUs like the RTX 3090 and 4070.

Licenses

Terms differ by size even within the same series, so take care.

• Apache-2.0 (commercial use allowed): FLUX.1-schnell and FLUX.2 [klein] 4B and its base model
• Non-commercial licenses: FLUX.1-dev and its derivatives (Kontext, Krea and others) use the FLUX.1 [dev] Non-Commercial License; FLUX.2-dev and FLUX.2 [klein] 9B use the FLUX Non-Commercial License

Most non-commercial models require agreeing on Hugging Face before download. This summary is not legal advice; read each model’s license text before use.

Running Them Locally

• There are no official GGUF builds (as of 2026-09-26); official FP8 and NVFP4 versions exist. GGUF builds for ComfyUI come from third parties.
• On a consumer GPU, FLUX.2 [klein] 4B is the easiest and allows commercial use. Image models load a text encoder and VAE besides the main model, so check the memory needed for all components in the tables in our articles.

Sources: the model card of black-forest-labs/FLUX.2-klein-4B; the model list of the black-forest-labs organization on Hugging Face (all as of 2026-09-26).

Our Coverage and Data

Local Model Watch has not published an article on Black Forest Labs’s models yet. The model list below is collected by code from Hugging Face every day. Part of our publisher index; model families link to their family pages.

At a Glance

Recent Models on Hugging Face

The publisher lists 38 models in total on Hugging Face. Below are up to 15 of the most recent generative models (text, image, video, audio and so on), the scope of this site, per organization. Classifiers, feature extractors, research components and repositories without a model card are omitted, and the publisher’s own quantized builds and helper variants are folded into the row of the original model. Parameter counts are left blank for repositories that pack weights into integer types, where Hugging Face’s count is not the real parameter count.

From the Hugging Face API. Last changed 2026-09-27 (JST). Collected by code.

Last updated 2026-09-27 (JST). The explanation at the top of this page was written with the help of AI from the primary sources it cites. The tables and lists under “Our Coverage and Data" are assembled by code from our article log and the Hugging Face API.