Real-ESRGAN / README.md
boomb0om's picture
Added code
0a00b8e
|
raw
history blame
1.35 kB

Real-ESRGAN

PyTorch implementation of a Real-ESRGAN model trained on custom dataset. This model shows better results on faces compared to the original version. It is also easier to integrate this model into your projects.

You can try it in google colab

Installation


  1. Clone repo

    git clone https://https://github.com/sberbank-ai/Real-ESRGAN
    cd Real-ESRGAN
    
  2. Install requirements

    pip install -r requirements.txt
    
  3. Download pretrained weights and put them into weights/ folder

Usage


Basic example:

import torch
from PIL import Image
import numpy as np
from realesrgan import RealESRGAN

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

model = RealESRGAN(device, scale=4)
model.load_weights('weights/RealESRGAN_x4.pth')

path_to_image = 'inputs/lr_image.png'
image = Image.open(path_to_image).convert('RGB')

sr_image = model.predict(image)

sr_image.save('results/sr_image.png')