Instructions to use xinsir/controlnet-union-sdxl-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xinsir/controlnet-union-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-union-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
- Draw Things
- DiffusionBee
Any example of how use inpainting?
Please, I would like an example of how to use inpainting with ControlNet Union. I have looked a lot, but I couldn't find anything.
HI @CristianLabhouse Have you faced the issue during the run time for mismatch of matrix multiplication in the inpainting ?
RuntimeError: mat1 and mat2 shapes cannot be multiplied (2x2048 and 1536x1280)
Please, I would like an example of how to use inpainting with ControlNet Union. I have looked a lot, but I couldn't find anything.
There is example available in the git repo
During the run time, you might get RuntimeError: mat1 and mat2 shapes cannot be multiplied (2x2048 and 1536x1280)
I was capable to fix the ...(2x2048 and 1536x1280) error. The problem is that is not getting the right json file with the network configuration. To fix it, I downloaded the model and rename some files in order to use the promax capabilities. I didn't find another way to choose the config file without modify the library directly. So.. go to the model:
https://huggingface.co/xinsir/controlnet-union-sdxl-1.0/tree/main
Rename "config_promax.json" to "config.json" and "diffusion_pytorch_model_promax.safetensors" to "diffusion_pytorch_model.safetensors" and run the code again.