🎨 Real-ESRGAN needs your contributions. Any contributions are welcome, such as new features/models/typo fixes/suggestions/maintenance, etc. See CONTRIBUTING.md. All contributors are list here.
We like open-source and want to develop practical algorithms for general image restoration. However, individual strength is limited. So, any kinds of contributions are welcome, such as:
- New features
- New models (your fine-tuned models)
- Bug fixes
- Typo fixes
- Suggestions
- Maintenance
- Documents
- etc
- Fork and pull the latest Real-ESRGAN repository
- Checkout a new branch (do not use master branch for PRs)
- Commit your changes
- Create a PR
Note:
- Please check the code style and linting
- The style configuration is specified in setup.cfg
- If you use VSCode, the settings are configured in .vscode/settings.json
- Strongly recommend using
pre-commit hook
. It will check your code style and linting before your commit.- In the root path of project folder, run
pre-commit install
- The pre-commit configuration is listed in .pre-commit-config.yaml
- In the root path of project folder, run
- Better to open a discussion before large changes.
- Welcome to discuss 😎. I will try my best to join the discussion.
0️⃣ The most straightforward way of improving model performance is to fine-tune on some specific datasets.
Here are some TODOs:
- optimize for human faces
- optimize for texts
- support controllable restoration strength
1️⃣ There are also several issues that require helpers to improve. If you can help, please let me know 😄