Instructions to use diffusers/FLUX.1-Canny-dev-nf4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use diffusers/FLUX.1-Canny-dev-nf4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("diffusers/FLUX.1-Canny-dev-nf4", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
guidance_scale in the sample code
#1
by raulc0399 - opened
in the sample code the guidance_scale is 30.0, while in the base dev model the guidance_scale is normally 3.5 or 4.0.
is 30.0 correct here?
@raulc0399 the guidance scale for flux tools fill/canny/depth works differently, more like a controlnet, hence the numbers are larger