How to use from the
Use from the
MLX library
# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir DDColor-modelscope-fp16 mlx-community/DDColor-modelscope-fp16

mlx-community/DDColor-modelscope-fp16

DDColor automatic image colorization (ConvNeXt-L backbone, ddcolor_modelscope.pth), converted to Apple MLX (-fp16) for Apple-Silicon inference via the mlx-ddcolor-swift Swift package.

Best general tier. The recommended default โ€” strongest on archival / multi-object scenes.

A from-scratch MLX-Swift architecture port (no MLX donor) of DDColor: ConvNeXt encoder โ†’ quasi-UNet decoder โ†’ DETR-style multi-scale color decoder (100 color queries) โ†’ predicts the ab chroma channels, recombined with the source L (luminance). Grayscale / desaturated image in โ†’ colorized image at the same resolution out.

Use with mlx-ddcolor-swift (Swift / MLX)

// Package.swift โ†’ .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 โ†’ 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 โ‰ค 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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
0.2B params
Tensor type
F16
ยท
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for mlx-community/DDColor-modelscope-fp16

Finetuned
(3)
this model

Collection including mlx-community/DDColor-modelscope-fp16