Image-to-Image
Diffusers
Safetensors
English
StableDiffusionXLInpaintPipeline
anime
art
inpaint
inpainting
stable-diffusion
stable-diffusion-xl
Instructions to use ShinoharaHare/Waifu-Inpaint-XL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ShinoharaHare/Waifu-Inpaint-XL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ShinoharaHare/Waifu-Inpaint-XL", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
ComfyUI Issue & Solution
#4
by runtome3w3 - opened
When using this model in ComfyUI with the official workflow, it produces incorrect results.
After investigation, ComfyUI incorrectly identifies the model as an eps-prediction model (likely due to missing metadata), while it should be recognized as a v-prediction model.
Solution:
- Install "ComfyUI-V-Prediction-Node" plugin.
- Use the "Add Parameterization Info" node to manually set the model to v-prediction.
Thanks for providing the workaround.
It should work without it now, so I'm closing this.
ShinoharaHare changed discussion status to closed