Views
No views yet
coremltools; the packages are stateless, so all sequencing and buffering lives in your Swift code.| Task | image to image |
| Upstream | TencentARC/GFPGAN |
| Packages | 1 |
| Download size | 298 MB |
| Minimum iOS | 17.0 |
| Peak RAM | ~600 MB |
| 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.1hf download mlboydaisuke/coreml-zoo --include "gfpgan/*" --local-dir ./gfpgan
2unzip './gfpgan/gfpgan/*.zip' -d ./gfpgan1import CoreML
2
3let config = MLModelConfiguration()
4config.computeUnits = .all // as converted — see the table above
5
6// Unzip the .mlpackage, drop it into your Xcode target and Xcode compiles it
7// at build time:
8let model = try GFPGAN(configuration: config)
9
10// ...or compile a downloaded .mlpackage at runtime:
11let compiled = try await MLModel.compileModel(at: mlpackageURL)
12let model = try MLModel(contentsOf: compiled, configuration: config)docs/coreml_conversion_notes.mdApache-2.0 except the third-party components (StyleGAN2 / NVIDIA) listed in the upstream LICENSE.