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
- Draw Things
- DiffusionBee
Training Data
#8
by Dasix - opened
it looks like there is something wrong, whether you follow the example code in generating the images? The controlnet strength is recommend to set 1.0 and the image resultion is recommend to be bucket of 1024 * 1024. The training data consist of high quality data including wallpaper, midjourney, nijijourney, photograth and so on, i test the model with some styled model such as bluepencil and it work well, so please check you code again and follow the example code.
Anyway, if you can't run it correctly,you can seed me the control image and the prompt, tell me the base model and I run it offline to test.
