Instructions to use diffusers/controlnet-canny-sdxl-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use diffusers/controlnet-canny-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("diffusers/controlnet-canny-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
Running in webui?
I had issues running this model inside the WebUI with SDXL 1.0 Base. Any tips?
We don't actively use WebUI. So, not sure.
I haven't been able to get anything SDXL related to work with Auto 1111, ComfyUI works like a dream though. Switched for SDXL usage. I don't regret it as it's a much better setup as soon as you are used to it.
Edit: (Might I suggest normalbae or softedge next for training? My SDXL animations really need Depth+Normalbae and a softedge outline for stability. I'm currently using it but Canny isn't the best for full outlines as I assume its for fine detail, lineart was okay but I always had the best results for full outlines with softedge. Thanks for the controlnets!)
appreciate it :)