FLUX.1

FLUX.1 is a family of image models for developers and creators who want to generate and edit images on their own hardware or servers.

• Text to image: FLUX.1 [schnell], [dev] and Krea [dev] generate images from written prompts.
• Image editing: Kontext [dev] edits existing images, while Fill [dev] replaces selected areas or extends an image beyond its borders.
• Structural guidance: Canny and Depth models guide generation with edges or depth information from an input image.
• Image variations: Redux [dev] produces variations of an existing image.

Black Forest Labs provides Python inference code for local use, with optional TensorRT support for NVIDIA deployments. Open weights allow control over deployment, fine-tuning and customization. Its separate hosted API processes requests on Black Forest Labs' infrastructure and also provides models without downloadable weights.

The inference code and FLUX.1 [schnell] use Apache 2.0. The listed [dev] models use the FLUX.1-dev Non-Commercial License; commercial model use requires separate licensing.

This listing covers FLUX.1 local models, not the separate hosted API product. FLUX.1-schnell uses Apache 2.0, while FLUX.1-dev and its listed dev variants use the FLUX.1-dev Non-Commercial License. The repository’s Apache-licensed inference code does not replace a checkpoint’s model terms.