# jantic/DeOldify

A Deep Learning based project for colorizing and restoring old images (and video!)

Repository: https://github.com/jantic/DeOldify
Canonical: https://ross.abutalabs.com/products/deoldify
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2024-10-19T17:17:35+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2863, "days_push": 683, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18481, forks 2643 (observed 2026-08-28T04:11:26.723186+00:00)

## What it is
DeOldify is a deep learning project for colorizing and restoring old black-and-white images and videos, with artistic and stable model variants. The repository was archived in October 2024 and is no longer maintained.

## Use cases
- colorize old black and white photos
- restore and colorize old family photographs
- colorize historical video footage
- add color to vintage images with deep learning
- colorize old images in a browser or notebook

## When to choose
- you need a proven, well-known image colorization model with pretrained weights
- you want to colorize old photos or videos via Colab or hosted services
- you're doing research or experimentation with colorization models

## When to avoid
- you need an actively maintained project with bug fixes and support
- you want a modern, up-to-date deep learning codebase
- you need production support or new features

## Facets
- artifact type: application
- maturity: abandoned
- function: image-processing, deep-learning, machine-learning
- domain: image-processing, deep-learning, machine-learning, media
- platform: python, cross-platform
- tags: colorization, photo-restoration, video-colorization, gan, archived, gpu

## Member repositories
- jantic/DeOldify (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:26.723186+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 2026-08-29T17:02:01.954784+00:00, confidence not recorded.
  - readme: https://github.com/jantic/DeOldify (fetched 2026-08-28T04:11:26.723186+00:00, sha 7c521d4d5221)
- Data as of 2026-08-30T08:39:29.467469+00:00.