https://github.com/Tohrusky/Final2x
2^x Image Super-Resolution
https://github.com/Tohrusky/Final2x
artificial-intelligence ccrestoration computer-vision cross-platform electron i18n image-processing low-level-vision ncnn pytorch super-resolution typescript vue3
Last synced: 21 days ago
JSON representation
2^x Image Super-Resolution
- Host: GitHub
- URL: https://github.com/Tohrusky/Final2x
- Owner: Tohrusky
- License: bsd-3-clause
- Created: 2023-06-19T02:31:56.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-12-14T21:45:05.000Z (4 months ago)
- Last Synced: 2025-03-18T23:33:33.695Z (27 days ago)
- Topics: artificial-intelligence, ccrestoration, computer-vision, cross-platform, electron, i18n, image-processing, low-level-vision, ncnn, pytorch, super-resolution, typescript, vue3
- Language: TypeScript
- Homepage:
- Size: 1.6 MB
- Stars: 6,226
- Watchers: 39
- Forks: 477
- Open Issues: 14
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- AiTreasureBox - Tohrusky/Final2x - 04-05_6248_0](https://img.shields.io/github/stars/Tohrusky/Final2x.svg)|2^x Image Super-Resolution| (Repos)
- awesome - Tohrusky/Final2x - 2^x Image Super-Resolution (TypeScript)
- awesome - Tohrusky/Final2x - 2^x Image Super-Resolution (TypeScript)
README





[](https://github.com/Tohrusky/Final2x/actions/workflows/CI-test.yml)
[](https://github.com/Tohrusky/Final2x/actions/workflows/CI-build.yml)
[](https://github.com/Tohrusky/Final2x/actions/workflows/Release.yml)

This is a powerful tool that allows for image super-resolution to arbitrary sizes using [multiple models](./src/renderer/src/utils/ModelOptions.ts), designed to enhance the resolution and quality of images, making them clearer and more detailed.
- News🎉: We are thrilled to announce the release of Final2x v2.0.0, which marks a major milestone as we transition to utilizing [ccrestoration](https://github.com/TensoRaws/ccrestoration) (PyTorch) for our algorithm implementation.
- News🎉: Want to enhance your video? Try [FinalRip](https://github.com/TensoRaws/FinalRip)!### Comparison
![]()
use Final2x to perform 4x super-resolution on a 256x256 Hutao RGBA image
## Screenshots
### Installation
##### [Download the latest release from here.](https://github.com/Tohrusky/Final2x/releases)
#### Windows
Just Run! Furthermore, you can use package mananger to install and upgrade.
##### winget
```bash
winget install Final2x
```#### MacOS
```bash
sudo spctl --master-disable
# Disable Gatekeeper, then allow applications downloaded from anywhere in System Preferences > Security & Privacy > General
xattr -cr /Applications/Final2x.app
```In first time, you need to run the command above in terminal to allow the app to run.
#### Linux
For Linux User, you need to install the dependencies first.
Make sure you have Python >= 3.9 and PyTorch >= 1.13 installed
```bash
pip install Final2x-core
Final2x-core -h # check if the installation is successful
apt install -y libomp5 xdg-utils
```### Reference
The following references were referenced in the development of this project:
- [Final2x-core](https://github.com/Tohrusky/Final2x-core)
- [ccrestoration](https://github.com/TensoRaws/ccrestoration)
- [PyTorch](https://github.com/pytorch/pytorch)
- [ncnn](https://github.com/Tencent/ncnn)
- [naive-ui](https://github.com/tusen-ai/naive-ui)
- [electron-vite](https://github.com/alex8088/electron-vite)### License
This project is licensed under the BSD 3-Clause - see
the [LICENSE file](https://github.com/Tohrusky/Final2x/blob/main/LICENSE) for details.### Acknowledgements
Feel free to reach out to the project maintainers with any questions or concerns~