Real-ESRGAN-inference

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.

Real-ESRGAN is an upgraded ESRGAN trained with pure synthetic data is capable of enhancing details while removing annoying artifacts for common real-world images.

You can try it in google colab

• Paper: Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
• Official github

Installation

1. Clone repo

   git clone https://github.com/boomb0om/Real-ESRGAN-colab
   cd Real-ESRGAN-colab

2. Install requirements

   pip install -r requirements.txt

3. Download pretrained weights and put them into weights/ folder

Usage

Basic usage:

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')

Examples

Low quality image:

Real-ESRGAN result:

Low quality image:

Real-ESRGAN result:

Low quality image:

Real-ESRGAN result: