Image-to-Image
Diffusers
Safetensors
English
StableDiffusionXLInpaintPipeline
anime
art
inpaint
inpainting
stable-diffusion
stable-diffusion-xl
Instructions to use ShinoharaHare/Waifu-Colorize-XL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ShinoharaHare/Waifu-Colorize-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-Colorize-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
Is it enable to recognize multiple people?
#3
by Scorpion989 - opened
I successfully colored your picture,but I chose a picture with multiple characters but failed. Was it because it wasn't supported?and i want to know can controlnet work?I try to use controlnet but it cant work.My workflow frequently generates images with this color style,I tried to crop the picture to single character but it still doesn't work.please help .