# jayleicn/animeGAN

A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing.

Repository: https://github.com/jayleicn/animeGAN
Canonical: https://ross.abutalabs.com/products/jayleicn-animegan
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: pytorch, generative-adversarial-network, dataset
Last push: 2022-08-24T04:29:50+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3473, "days_push": 1470, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1277, forks 196 (observed 2026-08-28T04:04:13.242139+00:00)

## What it is
A simple PyTorch implementation of DCGAN focused on generating anime face images, including a pretrained model and Jupyter notebook demos. It also provides a cleaned dataset of ~115,000 anime face images collected from Danbooru with face detection cropping.

## Use cases
- generate anime face images with a GAN
- learn how to train DCGAN in PyTorch
- download a large anime face dataset
- experiment with latent space interpolation
- reproduce an anime image generation pipeline from scraping to training

## When to choose
- you want a minimal, readable GAN implementation to learn from
- you need an anime face dataset for generative model experiments
- you want pretrained DCGAN weights to play with in a notebook

## When to avoid
- you need production-quality or high-resolution image generation
- you want the latest GAN architectures like StyleGAN or diffusion models
- you need commercial use of the dataset (non-commercial only)

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, image-processing, data-generation
- domain: deep-learning, image-processing, artificial-intelligence
- platform: python
- tags: gan, dcgan, pytorch, anime-faces, dataset, jupyter-notebook

## Member repositories
- jayleicn/animeGAN (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:13.242139+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 2026-08-30T05:02:50.171449+00:00, confidence not recorded.
  - readme: https://github.com/jayleicn/animeGAN (fetched 2026-08-28T04:04:13.242139+00:00, sha af858dcbf7a1)
- Data as of 2026-08-30T08:39:29.467469+00:00.