# AnimeGAN

Use AnimeGANv3 to make your own animation works, including turning photos or videos into anime.

Repository: https://github.com/TachibanaYoshino/AnimeGANv3
Canonical: https://ross.abutalabs.com/products/animegan
Homepage: https://tachibanayoshino.github.io/AnimeGANv3/
Language: Python
License Family: other
Topics: animegan, animeganv2, animeganv3, tensorflow, onnx, colab, coreml, huggingface, tflite
Last push: 2025-08-23T03:05:16+00:00
Link (homepage): https://tachibanayoshino.github.io/AnimeGANv3/

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 38, release rhythm 8, longevity 100
- inputs: {"age_days": 1721, "days_push": 375, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2036, forks 265 (observed 2026-08-28T04:06:08.095720+00:00)

## What it is
AnimeGAN is a family of TensorFlow-based generative adversarial network models (v1, v2, v3) that convert landscape photos and videos into anime-style images, with pretrained styles like Miyazaki Hayao, Makoto Shinkai, and Kon Satoshi. It includes inference scripts, video conversion tools, training code, and ONNX export support.

## Use cases
- convert photos to anime style
- turn videos into anime
- apply Ghibli-style filter to images
- train a photo animation GAN
- run anime style transfer with onnx
- stylize landscape photos like Makoto Shinkai

## When to choose
- you want pretrained anime style transfer for photos or videos
- you need a lightweight generator for fast inference
- you want to train or fine-tune a photo animation model in TensorFlow

## When to avoid
- you need a maintained project with an active license and community
- you require PyTorch-first workflows (though a community PyTorch port exists)
- you need general-purpose image editing rather than anime stylization

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, computer-vision, artificial-intelligence
- platform: python, cross-platform
- tags: gan, anime-style-transfer, photo-to-anime, tensorflow, onnx, video-processing, style-transfer, gpu

## Member repositories
- TachibanaYoshino/AnimeGANv3 (main) score 40
- TachibanaYoshino/AnimeGANv2 (mirror) score 23
- TachibanaYoshino/AnimeGAN (mirror) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:08.095720+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 2026-08-29T17:58:42.467956+00:00, confidence not recorded.
  - readme: https://github.com/TachibanaYoshino/AnimeGANv3 (fetched 2026-08-28T04:06:08.095720+00:00, sha aca3ad52aebe)
  - homepage: https://tachibanayoshino.github.io/AnimeGANv3/ (fetched 2026-08-29T08:53:02.457156+00:00, sha 8edc4e4712d0)
- Data as of 2026-08-30T08:39:29.467469+00:00.