Skip to content
ModelListedExternal
Browse files

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.

Sourcehuggingface.co/ai-forever/Real-ESRGAN/tree/8110204ebf8d25c031b66c26c2d1098aa831157e
KindOtherVersionRevision 8110204Bgrade

Model source

Kind
Other
File size
63.9–64.1 MB
Version
vRevision 8110204
Updated
Oct 20, 2026
Downloads
0
Source
Hugging Face

Source description

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.

Usage

Code for using model you can obtain in our repo.

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')

Sources

1 source
Hugging FacePrimaryVersion 8110204ebf8d25c031b66c26c2d1098aa831157e
huggingface.co/ai-forever/Real-ESRGAN/tree/8110204ebf8d25c031b66c26c2d1098aa831157e

Verified Oct 20

Download files

Model artifacts

3 artifacts

RealESRGAN_x2.pth

pth · 64.0 MB · SHA-256 c830d067d54f…e899 · Hugging Face

Download file

RealESRGAN_x4.pth

pth · 63.9 MB · SHA-256 aa00f09ad753…3400 · Hugging Face

Download file

RealESRGAN_x8.pth

pth · 64.1 MB · SHA-256 8b72fb469d12…ff5e · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 4huggingface.co/ai-forever/Real-ESRGAN

--- language: - ru - en tags: - PyTorch thumbnail: "https://github.com/sberbank-ai/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') ```

NoteOct 20huggingface.co/ai-forever/Real-ESRGAN

Source context: 0 downloads · 266 likes · Repo ai-forever/Real-ESRGAN

NoteAug 4huggingface.co/ai-forever/Real-ESRGAN

Source context: 0 downloads · 251 likes · Repo ai-forever/Real-ESRGAN