Instructions to use xinsir/controlnet-openpose-sdxl-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xinsir/controlnet-openpose-sdxl-1.0 with Diffusers:
pip install -U diffusers transformers accelerate
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline controlnet = ControlNetModel.from_pretrained("xinsir/controlnet-openpose-sdxl-1.0") pipe = StableDiffusionControlNetPipeline.from_pretrained( "fill-in-base-model", controlnet=controlnet ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
what is this model diffusion_pytorch_model_twins.safetensors
#3
by Fantasyworld - opened
This comment has been hidden
It is a model with similar performance and different style. The pose will be more precise but aesthetic score will be lower.
It is a model with similar performance and different style. The pose will be more precise but aesthetic score will be lower.
which one is more precise and which one has better aesthetic score?
twins is more precise, and default is better in aesthetic
Would the same principle apply for Canny and Canny v2 ?
No, Canny v2 is a better model than canny, from every aspect.