Originally posted to Huggingface.

Full Flux Tools Guide, including example workflows, live now!

If you're looking to get started using Flux, check out our Guide here.

FLUX.1 Canny [dev] LoRA is a LoRA extracted from FLUX.1 Canny [dev], a 12 billion parameter rectified flow transformer capable of generating an image based on a text description while following the structure of a given input image. For more information, please read our blog post. The LoRA is applicable to FLUX.1 [dev].

Key Features

1. Cutting-edge output quality.

2. It blends impressive prompt adherence with maintaining the structure of source images based on canny edges.

3. Trained using guidance distillation, making FLUX.1 Canny [dev] LoRA more efficient.

4. Open weights to drive new scientific research, and empower artists to develop innovative workflows.

5. Generated outputs can be used for personal, scientific, and commercial purposes as described in the FLUX.1 [dev] Non-Commercial License.

Usage

We provide a reference implementation of FLUX.1 Canny [dev], as well as sampling code, in a dedicated github repository. Developers and creatives looking to build on top of FLUX.1 Canny [dev] are encouraged to use this as a starting point.