Instructions to use xinsir/controlnet-canny-sdxl-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xinsir/controlnet-canny-sdxl-1.0 with Diffusers:
pip install -U diffusers transformers accelerate
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline controlnet = ControlNetModel.from_pretrained("xinsir/controlnet-canny-sdxl-1.0") pipe = StableDiffusionControlNetPipeline.from_pretrained( "fill-in-base-model", controlnet=controlnet ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Edge-Drawing Parameter-Free Filter version
#2
by GeroldMeisinger - opened
would you be interested in training a version with the "Edge-Drawing Parameter-Free" filter (EDPF)? It's a edge filter similar to Canny but uses a modern algorithm for edge-detection which requires no parameter tuning (Canny was invented in 1986, Edge Drawing in 2012). the gray-version of EDPF is implemented in opencv-contrib-python and pretty easy to use (https://gitlab.com/-/snippets/3601881)
see https://huggingface.co/GeroldMeisinger/control-edgedrawing for the SD1 version