---
title: DDColor-paper-tiny-fp16
canonical_url: "https://www.modelscope.cn/models/mlx-community/DDColor-paper-tiny-fp16"
md_url: "https://www.modelscope.cn/models/mlx-community/DDColor-paper-tiny-fp16.md"
repository: mlx-community/DDColor-paper-tiny-fp16
last_updated: 2026-06-24
license: apache-2.0
pipeline_tag: image-to-image
tasks:
  - image-to-image
base_model:
  - piddnad/DDColor-models
base_model_relation: finetune
parameters: 55.0M
tensor_type:
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 22
stars: 0
tags:
  - mlx
  - colorization
  - image-colorization
  - ddcolor
---

# DDColor-paper-tiny-fp16

> DDColor-paper-tiny-fp16 - mlx-community 在 ModelScope 开源的模型。mlx-community/DDColor-paper-tiny-fp16

mlx-community/DDColor-paper-tiny-fp16 是 ModelScope 魔搭社区上的 55.0M 参数image-to-image模型，采用 apache-2.0 许可，基于 piddnad/DDColor-models 构建。

- **Repository**: mlx-community/DDColor-paper-tiny-fp16
- **License**: apache-2.0
- **Tasks**: image-to-image
- **Parameters**: 55.0M
- **Base model**: piddnad/DDColor-models
- **Tags**: mlx, colorization, image-colorization, ddcolor
- **Downloads**: 22
- **Stars**: 0
- **Last updated**: 2026-06-24

Source: https://www.modelscope.cn/models/mlx-community/DDColor-paper-tiny-fp16

---

# mlx-community/DDColor-paper-tiny-fp16

[DDColor](https://github.com/piddnad/DDColor) automatic image colorization (ConvNeXt-T backbone,
`ddcolor_paper_tiny.pth`), converted to **Apple MLX** (`-fp16`) for Apple-Silicon inference via the
[`mlx-ddcolor-swift`](https://github.com/xocialize/mlx-ddcolor-swift) Swift package.

Fastest tier (~0.1 s). Lightest backbone — good for batch / on-device.

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.