---
title: Real-ESRGAN
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Real-ESRGAN"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Real-ESRGAN.md"
repository: AI-ModelScope/Real-ESRGAN
last_updated: 2024-03-21
library_name:
  - pytorch
frameworks:
  - pytorch
language:
  - ru
  - en
downloads: 5057
stars: 4
tags:
  - PyTorch
---

# Real-ESRGAN

> Real-ESRGAN - AI-ModelScope 在 ModelScope 开源的模型。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.

- **Repository**: AI-ModelScope/Real-ESRGAN
- **Tags**: PyTorch
- **Downloads**: 5057
- **Stars**: 4
- **Last updated**: 2024-03-21

Source: https://www.modelscope.cn/models/AI-ModelScope/Real-ESRGAN

---

# 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.

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.

- [Paper](https://arxiv.org/abs/2107.10833)
- [Original implementation](https://github.com/xinntao/Real-ESRGAN)
- [Our github](https://github.com/sberbank-ai/Real-ESRGAN)

## Usage

Code for using model you can obtain in our [repo](https://github.com/sberbank-ai/Real-ESRGAN).
```python
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')
```