| license: bsd-3-clause | |
| tags: | |
| - super-resolution | |
| - vision.cpp | |
| pipeline_tag: image-to-image | |
| # GGUF models for Real-ESRGAN | |
| ESRGAN is a model for image super-resolution (upscaling). Real-ESRGAN refers to | |
| a collection of models trained to deal with common degradations in images. The | |
| weights in this repository are converted for lightweight inference on consumer | |
| hardware with [vision.cpp](https://github.com/Acly/vision.cpp). | |
| * Original repository: [xinntao/Real-ESRGAN (Github)](https://github.com/xinntao/Real-ESRGAN) | |
| * Original weights: [found here (Github)](https://github.com/xinntao/Real-ESRGAN/releases) | |
| ## Run | |
| Example inference with [vision.cpp](https://github.com/Acly/vision.cpp): | |
| ```sh | |
| vision-cli esrgan -m RealESRGAN-x4plus_anime-6B-F16.gguf -i input.png -o output.png | |
| ``` | |