# bryandlee/animegan2-pytorch

PyTorch implementation of AnimeGANv2

Repository: https://github.com/bryandlee/animegan2-pytorch
Canonical: https://ross.abutalabs.com/products/animegan2-pytorch
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: image2image, style-transfer, gan
Last push: 2023-01-06T10:26:08+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": 2024, "days_push": 1335, "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 4452, forks 640 (observed 2026-08-28T04:08:50.497330+00:00)

## What it is
A PyTorch implementation of AnimeGANv2, a GAN-based image-to-image style transfer model that converts photos into anime-style images. It provides pretrained weights loadable via torch.hub, including face portrait and painting styles.

## Use cases
- convert photos to anime style
- apply anime style transfer to portraits
- turn a face photo into a painting
- run animegan2 in pytorch
- load pretrained animegan2 weights via torch hub
- stylize images with a gan

## When to choose
- you want a simple PyTorch port of AnimeGANv2 with pretrained weights
- you need anime-style image stylization in a Python/PyTorch pipeline
- you want quick inference via torch.hub on CPU or CUDA

## When to avoid
- you need training code or the latest GAN research rather than inference
- you need a maintained project with active updates
- you need non-anime style transfer or video processing

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, machine-learning, computer-vision
- platform: python, cross-platform
- tags: animeganv2, style-transfer, gan, pytorch, image-to-image, torch-hub, pretrained-models, gpu

## Member repositories
- bryandlee/animegan2-pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:50.497330+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 2026-08-29T18:20:46.145594+00:00, confidence not recorded.
  - readme: https://github.com/bryandlee/animegan2-pytorch (fetched 2026-08-28T04:08:50.497330+00:00, sha 114b80a19ff0)
- Data as of 2026-08-30T08:39:29.467469+00:00.