# piddnad/DDColor

[ICCV 2023] DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders

Repository: https://github.com/piddnad/DDColor
Canonical: https://ross.abutalabs.com/products/ddcolor
Language: Python
License: Apache-2.0
License Family: permissive
Topics: computer-vision, image-colorization, pytorch
Last push: 2026-01-17T17:06:40+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 62, release rhythm 35, longevity 96
- inputs: {"age_days": 1349, "days_push": 228, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1496, forks 169 (observed 2026-08-28T04:04:53.545501+00:00)

## What it is
DDColor is the official PyTorch implementation of an ICCV 2023 paper on photo-realistic automatic image colorization using dual decoders and learnable color tokens. It provides pretrained models and inference/training code for colorizing black-and-white photos and recoloring stylized imagery.

## Use cases
- colorize old black and white family photos
- restore historical photographs with realistic colors
- convert grayscale images to color automatically
- recolor anime game landscapes into realistic style
- run image colorization inference with pretrained models
- train a custom image colorization model

## When to choose
- you need state-of-the-art automatic photo colorization
- you want pretrained models with Hugging Face, ModelScope, or Replicate integration
- you want to colorize old photos or stylized artwork with PyTorch

## When to avoid
- you need real-time video colorization on CPU
- you want a simple GUI tool rather than a Python library
- you cannot use GPU acceleration or PyTorch

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, artificial-intelligence
- platform: python, cross-platform
- tags: image-colorization, pytorch, iccv-2023, pretrained-models, photo-restoration, deep-learning, gpu

## Member repositories
- piddnad/DDColor (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:53.545501+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:33:14.374480+00:00, confidence not recorded.
  - readme: https://github.com/piddnad/DDColor (fetched 2026-08-28T04:04:53.545501+00:00, sha ca6479a8d733)
- Data as of 2026-08-30T08:39:29.467469+00:00.