import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Stable-X/yoso-delight-v0-4-base", torch_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]Model Card for StableDelight
This repository contains the weights of StableDelight: Revealing Hidden Textures by Removing Specular Reflections.
Usage
See the Github repository: https://github.com/Stable-X/StableDelight regarding installation instructions.
The model can then be used as follows:
import torch
from PIL import Image
# Load an image
input_image = Image.open("path/to/your/image.jpg")
# Create predictor instance
predictor = torch.hub.load("Stable-X/StableDelight", "StableDelight_turbo", trust_repo=True)
# Apply the model to the image
delight_image = predictor(input_image)
# Save or display the result
delight_image.save("output/delight.png")
- Downloads last month
- 555