Machine Learning

Real-ESRGAN GUI – graphical image enlargement tool

Real-ESRGAN GUI is a graphical frontend for Real-ESRGAN, a neural network-based image restoration and enlargement system. It provides an alternative to working directly with the Real-ESRGAN-ncnn-vulkan command-line utility.

The application is written in Python using Tkinter. Images are processed locally, with support for photographs, illustrations and anime artwork. Different models can be selected according to the type of image being enlarged.

One of its more useful capabilities is producing images at arbitrary sizes rather than being restricted to the scaling factors supported by individual models. The program can perform several upscaling passes and then reduce the result to the requested dimensions.

This is free and open source software.

Key Features

  • Provides a graphical interface for Real-ESRGAN-ncnn-vulkan.
  • Also supports the Real-CUGAN image upscaling backend.
  • Enlarge photographs, illustrations, anime artwork and other raster images.
  • Choose between different upscaling models, including models intended for general photographs and anime.
  • Specify an arbitrary output size rather than being limited to a model’s native scaling factor.
  • Perform multiple upscaling passes followed by downsampling to reach the required dimensions.
  • Uses Lanczos downsampling by default, with other algorithms available.
  • Process individual images or batch process images in a directory.
  • Enlarge animated GIF files by extracting, processing and recombining their frames.
  • Preserve frame durations when reconstructing animated GIFs.
  • Drag and drop image files or directories directly onto the application window.
  • Automatically generate output filenames with suffixes indicating the selected scale or dimensions.
  • Adjust tile sizes to control GPU memory usage during processing.
  • Use additional compatible models placed in the application’s models directory.
  • Supports an alternative executable from the maintained Upscayl-NCNN backend.
  • Automatically select a light or dark interface according to the desktop theme.
  • Provides a multilingual interface, with English used when a translation is unavailable.
  • Cross-platform support – runs on Linux, macOS and Windows.

Website: github.com/TransparentLC/realesrgan-gui
Support:
Developer: TransparentLC
License: GNU Affero General Public License v3.0

Software in action

Real-ESRGAN GUI is written in Python. Learn Python with our recommended free books and free tutorials.


Related Software

Image Upscaler Tools
Final2xEnhance your images with super-resolution
UpscaylUses sophisticated AI models to enhance images
UpscalerUpscale and enhance images
Real-ESRGAN GUIAI image enlargement tool
chaiNNerNode-based image processing GUI
Anime4KCPPHigh-performance upscaling for anime images and videos
AeternumSimple and minimal image upscaler
waifu2x ncnnImage upscaler / denoiser built on the ncnn inference framework
Open Photo AIAI-powered photo restoration, enhancement and upscaling
upscaler-hollowaykeanhoImage and video upscaling
jdPixelUpscalerUpscale images per pixel

Read our verdict in the software roundup.


Best Free and Open Source Software LinuxLinks helps you discover the best free and open source software for Linux. Explore our extensive collection of recommended applications, including alternatives to popular proprietary software.

We also publish software reviews, Linux tutorials, hardware reviews, free programming books and articles covering the wider open source community. Browse our Linux resources to discover more.

Know a useful free and open source Linux application we haven't covered? Suggest a program for inclusion.

Has your software been featured on LinuxLinks? Display one of our Featured on LinuxLinks badges on your website or GitHub README.
Subscribe

Please read our Comment Policy before commenting.

Notify of
guest
0 Comments
Oldest
Newest Most Voted