LaMa — Core ML

Image Inpainting, 2022

Resolution-robust large mask inpainting. Draw over unwanted objects to remove them. Fast Fourier convolutions for global context. 800×800 input.

Core ML conversion of advimman/lama 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.

Files

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

hf download mlboydaisuke/coreml-zoo --include "lama/*" --local-dir ./lama
unzip './lama/lama/*.zip' -d ./lama

Use in 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 LaMa(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

• Sample app — lama-cleaner-iOS, a standalone iOS project.
• Models Zoo — this model is downloadable and runnable inside the Models Zoo app on the App Store, no build required.

Conversion

• Pitfalls hit during conversion (FP16 overflow, ANE buffer limits, stride handling): docs/coreml_conversion_notes.md
• Model index: CoreML-Models

License

The conversion inherits the upstream license: Apache-2.0.

Credits

• Upstream authors: advimman/lama, 2022
• Core ML conversion: john-rocky (Daisuke Majima)

---

More models in this format: Core ML Model Zoo — 46 models, each with the recipe that produced it.

Want a different model on-device? Open a request — free, open weights only; the export and its measured numbers get published publicly.