| license: apache-2.0 | |
| library_name: coreml | |
| tags: | |
| - coreml | |
| - inpainting | |
| - object-removal | |
| # LaMa (Core ML) | |
| A mirror of the LaMa inpainting model in Core ML format (800×800 image + mask in, image out), as converted by | |
| [john-rocky](https://huggingface.co/mlboydaisuke/LaMa-CoreML) from | |
| [advimman/lama](https://github.com/advimman/lama) (Samsung AI Center). | |
| Inputs: `image` (800×800 BGRA), `mask` (800×800 grayscale, white = area to fill). Output: `output` (800×800 image). | |
| All credit to the LaMa authors: *Resolution-robust Large Mask Inpainting with Fourier Convolutions* | |
| ([paper](https://arxiv.org/abs/2109.07161)). LaMa's code is Apache-2.0; see [LICENSE](LICENSE). | |