| --- |
| license: apache-2.0 |
| library_name: coreml |
| pipeline_tag: image-to-image |
| tags: |
| - coreml |
| - core-ml |
| - ios |
| - macos |
| - apple |
| - on-device |
| - face-restoration |
| - gan |
| - arxiv:2101.04061 |
| --- |
| |
| # GFPGAN — Core ML |
|
|
| *Face Restoration, 2021* |
|
|
| Blind face restoration with generative facial prior. Restores degraded face photos to high quality. 512×512 input/output. |
|
|
| <p><img src="https://huggingface.co/mlboydaisuke/GFPGAN-CoreML/resolve/main/media/6970a085d4.png" alt="GFPGAN demo" width="49%"> <img src="https://huggingface.co/mlboydaisuke/GFPGAN-CoreML/resolve/main/media/8b1a4b3168.png" alt="GFPGAN demo" width="49%"></p> |
|
|
| Core ML conversion of [TencentARC/GFPGAN](https://github.com/TencentARC/GFPGAN) for on-device inference on iPhone, iPad and Mac. Converted with `coremltools`; the packages are stateless, so all sequencing and buffering lives in your Swift code. |
|
|
| | | | |
| |---|---| |
| | Task | image to image | |
| | Upstream | [TencentARC/GFPGAN](https://github.com/TencentARC/GFPGAN) | |
| | Packages | 1 | |
| | Download size | 298 MB | |
| | Minimum iOS | 17.0 | |
| | Peak RAM | ~600 MB | |
|
|
| ## Files |
|
|
| | File | Size | Compute units | SHA-256 | |
| |---|---:|---|---| |
| | `GFPGAN.mlpackage.zip` | 298 MB | `all` | `929d0ab30fa739bd…` | |
| | **Total** | **298 MB** | | | |
|
|
| `compute_units` is not a suggestion -- it is the configuration the conversion was verified against. Moving a package to a different compute unit can silently change the numerics (FP16 attention overflow) or crash on the GPU. |
|
|
| ## Download |
|
|
| ```bash |
| hf download mlboydaisuke/coreml-zoo --include "gfpgan/*" --local-dir ./gfpgan |
| unzip './gfpgan/gfpgan/*.zip' -d ./gfpgan |
| ``` |
|
|
| ## Use in Swift |
|
|
| ```swift |
| import CoreML |
| |
| let config = MLModelConfiguration() |
| config.computeUnits = .all // as converted — see the table above |
| |
| // Unzip the .mlpackage, drop it into your Xcode target and Xcode compiles it |
| // at build time: |
| let model = try GFPGAN(configuration: config) |
| |
| // ...or compile a downloaded .mlpackage at runtime: |
| let compiled = try await MLModel.compileModel(at: mlpackageURL) |
| let model = try MLModel(contentsOf: compiled, configuration: config) |
| ``` |
|
|
| ## Demo |
|
|
| - **Models Zoo** — this model is downloadable and runnable inside the [Models Zoo app](https://apps.apple.com/app/id6762083207) on the App Store, no build required. |
|
|
| ## Conversion |
|
|
| - Pitfalls hit during conversion (FP16 overflow, ANE buffer limits, stride handling): [`docs/coreml_conversion_notes.md`](https://github.com/john-rocky/CoreML-Models/blob/master/docs/coreml_conversion_notes.md) |
| - Model index: [CoreML-Models](https://github.com/john-rocky/CoreML-Models) |
|
|
| ## License |
|
|
| The conversion inherits the upstream license: **Apache-2.0**. |
|
|
| > Apache-2.0 except the third-party components (StyleGAN2 / NVIDIA) listed in the upstream LICENSE. |
|
|
| ## Credits |
|
|
| - Upstream authors: [TencentARC/GFPGAN](https://github.com/TencentARC/GFPGAN), 2021 |
| - Core ML conversion: john-rocky (Daisuke Majima) |
|
|
