Instructions to use xinsir/controlnet-scribble-sdxl-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xinsir/controlnet-scribble-sdxl-1.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("xinsir/controlnet-scribble-sdxl-1.0", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
Scribble and canny v2 have the same hash.
#2
by hoalongntc - opened
I found that the scribble controlnet and canny v2 have the same hash:
b3e4ac47bc814019d50dc842f579301440deb6d8f09ee1b91a30f527ace1b852
Is this a mistake or this model can handle both?
yes, v2 is a more powerful model, at first i just establish a single canny model card, I want to let people use model in this line, however I found if I want to let more people know the power of v2, I need to establish another model card and display its result carefully. V2 is an anyline anywidth model and can generally generate better result when you input canny conditions.