My suggested steps for quick installation:

Clone https://github.com/ai-forever/Real-ESRGAN
Get the models and move to project Real-ESRGAN/weights: https://huggingface.co/ai-forever/Real-ESRGAN/tree/main or https://huggingface.co/ai-forever/Real-ESRGAN
As it's customary, a python environment is helpful and worked for me on a conda python 3.10 env
cd into project Real-ESRGAN/
python -m pip install -r requirements.txt
python setup.py develop
Set the target resolution in main.py, i.e. load_weights RealESRGAN_x8.pth and model scale (model = RealESRGAN(device, scale=4)) where scale=2/4/8
Execute: python main.py

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.

This is not an official implementation. We partially use code from the original repository

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

Installation

pip install git+https://github.com/sberbank-ai/Real-ESRGAN.git

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', download=True)

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')