Model Card for StableNormal

This repository contains the weights of StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

Usage

See the Github repository: https://github.com/Stable-X/StableNormal 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/StableNormal", "StableNormal_turbo", trust_repo=True, yoso_version='yoso-normal-v0-3')

# Apply the model to the image
normal_image = predictor(input_image)

# Save or display the result
normal_image.save("output/normal_map.png")