| license: mit | |
| tags: | |
| - inpainting | |
| - vision.cpp | |
| pipeline_tag: image-to-image | |
| # GGUF models for MI-GAN | |
| MI-GAN is a model for image inpainting. The weights in this repository are | |
| converted for lightweight inference on consumer hardware with | |
| [vision.cpp](https://github.com/Acly/vision.cpp). | |
| * Original repository: [Picsart-AI-Research/MI-GAN (Github)](https://github.com/Picsart-AI-Research/MI-GAN) | |
| * Original weights: [Weights (Google Drive)](https://drive.google.com/drive/folders/1xNtvN2lto0p5yFKOEEg9RioMjGrYM74w) | |
| ## Run | |
| Example inference with [vision.cpp](https://github.com/Acly/vision.cpp): | |
| ```sh | |
| vision-cli migan -m MIGAN-512-places2-F16.gguf -i input.png mask.png -o output.png | |
| ``` | |