mlboydaisuke/DDColor-Tiny-CoreML
DDColor Tiny — Core ML
Image Colorization, 2023
Automatic grayscale image colorization via dual decoders. 512×512 input.
<p><img src="https://huggingface.co/mlboydaisuke/DDColor-Tiny-CoreML/resolve/main/media/0d8f0d4385.jpg" alt="DDColor Tiny demo" width="49%"> <img src="https://huggingface.co/mlboydaisuke/DDColor-Tiny-CoreML/resolve/main/media/c83e15a3b5.png" alt="DDColor Tiny demo" width="49%"></p>
Core ML conversion of piddnad/DDColor 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 "ddcolor/*" --local-dir ./ddcolor
unzip './ddcolor/ddcolor/*.zip' -d ./ddcolorUse 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 DDColor_Tiny(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 — `sample_apps/DDColorDemo`, a standalone SwiftUI project.
- Models Zoo — this model is downloadable and runnable inside the Models Zoo app on the App Store, no build required.
Conversion
- Script: `convert_ddcolor.py`
- 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: piddnad/DDColor, 2023
- Core ML conversion: john-rocky (Daisuke Majima)
<!-- funnel:v1 -->
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.
<!-- /funnel:v1 -->
