# robbiebarrat/art-DCGAN

Modified implementation of DCGAN focused on generative art. Includes pre-trained models for landscapes, nude-portraits, and others.

Repository: https://github.com/robbiebarrat/art-DCGAN
Canonical: https://ross.abutalabs.com/products/art-dcgan
Language: Lua
License: NOASSERTION
License Family: other
Topics: gan, generative-art, art, painting
Last push: 2022-02-17T01:11:31+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3311, "days_push": 1659, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2003, forks 327 (observed 2026-08-28T04:06:04.545322+00:00)

## What it is
A modified Torch implementation of DCGAN focused on generating artworks, with support for 128x128 images and resuming training from checkpoints. It ships pre-trained generator and discriminator models for landscapes, portraits, nude-portraits, and abstract landscapes.

## Use cases
- generate abstract landscape paintings with a gan
- generate portrait paintings using pretrained models
- train a dcgan on my own artwork dataset
- resume gan training from a checkpoint with a different dataset
- experiment with generative art models

## When to choose
- you want to generate or experiment with AI-generated paintings using classic GANs
- you need pre-trained art models for landscapes or portraits
- you want a simple, hackable DCGAN codebase to modify and retrain

## When to avoid
- you need modern high-resolution diffusion or transformer-based image generation
- you require a maintained framework with active support or a permissive license
- you cannot run Torch or lack GPU resources for training

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: machine-learning, deep-learning, artificial-intelligence, graphics
- platform: lua
- tags: gan, dcgan, generative-art, torch, pretrained-models, painting, gpu, linux, macos

## Member repositories
- robbiebarrat/art-DCGAN (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:04.545322+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 2026-08-30T03:01:55.690535+00:00, confidence not recorded.
  - readme: https://github.com/robbiebarrat/art-DCGAN (fetched 2026-08-28T04:06:04.545322+00:00, sha 7b73af759aeb)
- Data as of 2026-08-30T08:39:29.467469+00:00.