Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
About this project
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration. It is part of the image generation stack, covering the pipeline from prompt to rendered picture rather than a hosted image service. It is maintained by xinntao and published as a public repository you can read, fork and run yourself.
On GitHub the repository is tagged amine, denoise, esrgan, image-restoration, jpeg-compression, pytorch, real-esrgan and super-resolution, which is a fair summary of what it covers. In practice that means model loading, sampling controls, upscaling and batch workflows running on your own GPU, which matters when you need privacy, reproducibility or volume without per-image billing.
It is written mainly in Python and released under BSD-3-CLAUSE, a permissive license — commercial use is fine as long as copyright notices are kept. The last commit was on August 6, 2024; treat it as a stable reference implementation rather than a project under active development.
To try it, clone the repository and follow its README; that file is the canonical install guide. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.
Key facts as recorded on GitHub: 37,553 stars; 4,544 forks; primary language Python; license BSD-3-CLAUSE; last commit on August 6, 2024; topics amine, denoise, esrgan, image-restoration, jpeg-compression, pytorch.