| --- |
| library_name: mlx |
| license: apache-2.0 |
| license_link: https://github.com/piddnad/DDColor/blob/main/LICENSE |
| base_model: piddnad/DDColor-models |
| pipeline_tag: image-to-image |
| tags: |
| - mlx |
| - colorization |
| - image-colorization |
| - ddcolor |
| --- |
| |
| # mlx-community/DDColor-modelscope-fp16 |
|
|
| [DDColor](https://github.com/piddnad/DDColor) automatic image colorization (ConvNeXt-L backbone, |
| `ddcolor_modelscope.pth`), converted to **Apple MLX** (`-fp16`) for Apple-Silicon inference via the |
| [`mlx-ddcolor-swift`](https://github.com/xocialize/mlx-ddcolor-swift) Swift package. |
|
|
| Best general tier. The recommended default — strongest on archival / multi-object scenes. |
|
|
| A from-scratch MLX-Swift architecture port (no MLX donor) of DDColor: ConvNeXt encoder → quasi-UNet |
| decoder → DETR-style multi-scale color decoder (100 color queries) → predicts the **ab** chroma |
| channels, recombined with the source **L** (luminance). Grayscale / desaturated image in → colorized |
| image at the same resolution out. |
|
|
| ## Use with mlx-ddcolor-swift (Swift / MLX) |
|
|
| ```swift |
| // Package.swift → .package(url: "https://github.com/xocialize/mlx-ddcolor-swift", from: "0.1.0") |
| import DDColor |
| |
| let colorizer = try DDColorColorizer.fromPretrained( |
| weightsPath, // model.safetensors from this repo |
| config: DDColorConfig(tier: .large), // .tiny for paper-tiny |
| dtype: .float16) |
| let colorized: CGImage = colorizer(sourceCGImage) // grayscale → color, source resolution |
| ``` |
|
|
| Or as an MLXEngine `imageColorize` ModelPackage (`MLXDDColor.DDColorPackage`), which resolves this repo |
| automatically via the Hub. |
|
|
| ## Parity |
|
|
| Architecture parity-locked against the PyTorch oracle (piddnad/DDColor) on the CPU stream, fp32: |
| **max_abs ≤ 1.5e-6** (large) / **3.3e-6** (tiny) on the model's ab output. The cv2-exact LAB pre/post |
| pipeline matches the reference `ColorizationPipeline` to **~9e-4 mean** BGR error. This `-fp16` build is |
| visually identical to fp32 (**cosine 1.000000**, mean 0.04/255 on colorized output). |
| |
| Weights: Apache-2.0 (piddnad/DDColor). Port code: MIT. |
| |
