Model Card for NiRNE

This repository contains the weights of NiRNE, the image-to-normal estimator of Hi3DGen

Usage

See the Github repository: https://github.com/lzt02/NiRNE 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("lzt02/NiRNE", "NiRNE", trust_repo=True)
# Generate normal map using alpha channel for masking
normal_map = predictor(rgba_image, data_type="object")  # Will mask out background, if alpha channel is avalible, else use birefnet
# Apply the model to the image
normal_image = predictor(input_image)
# Save or display the result
normal_image.save("output/normal_map.png")