# vijishmadhavan/ArtLine

A Deep Learning based project for creating line art portraits.

Repository: https://github.com/vijishmadhavan/ArtLine
Canonical: https://ross.abutalabs.com/products/artline
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: movie-poster, colab, art-portraits, deep-learning, ai, portraits, generative-art, creative-coding, machine-learning, nogan, nogan-training
Last push: 2023-03-03T13:25:18+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2109, "days_push": 1279, "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 3630, forks 373 (observed 2026-08-28T04:08:12.028025+00:00)

## What it is
ArtLine is a deep learning project that converts portrait photos into line art portraits, with a ControlNet-based variant that adjusts style from written instructions. It is distributed as Jupyter/Colab notebooks with pretrained models.

## Use cases
- turn a portrait photo into line art
- create line art portraits from any face pose
- generate movie-poster style artwork from photos
- restyle a portrait using a text instruction with ControlNet
- cartoonize portrait images

## When to choose
- you want high-quality line art portraits without training your own model
- you want a quick Colab-based demo with no local GPU setup
- you need text-guided portrait restyling via ControlNet

## When to avoid
- you need a production API or maintained library integration
- you want general-purpose image-to-image stylization beyond portraits
- you need actively updated software - releases are infrequent

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, llm-inference
- domain: deep-learning, image-processing, artificial-intelligence, graphics
- platform: python, cross-platform
- tags: line-art, portrait-generation, generative-art, controlnet, colab, creative-coding, style-transfer, gpu

## Member repositories
- vijishmadhavan/ArtLine (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:12.028025+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 2026-08-29T18:31:53.809291+00:00, confidence not recorded.
  - readme: https://github.com/vijishmadhavan/ArtLine (fetched 2026-08-28T04:08:12.028025+00:00, sha 0095087c8906)
- Data as of 2026-08-30T08:39:29.467469+00:00.