# naoto0804/pytorch-AdaIN

Unofficial pytorch implementation of 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization' [Huang+, ICCV2017]

Repository: https://github.com/naoto0804/pytorch-AdaIN
Canonical: https://ross.abutalabs.com/products/pytorch-adain
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, style-transfer, cnn, instance-normalization
Archived: true
Last push: 2024-01-23T00:48:00+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3200, "days_push": 954, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1181, forks 215 (observed 2026-08-28T04:03:54.070620+00:00)

## What it is
An unofficial PyTorch implementation of the AdaIN paper 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization' (Huang+, ICCV 2017). It provides scripts for applying arbitrary artistic styles to content images and for training the style transfer network.

## Use cases
- apply an artistic style to a photo
- transfer painting style onto images in real time
- mix multiple styles with interpolation weights
- preserve content color while stylizing
- train a custom AdaIN style transfer model
- batch stylize a directory of images

## When to choose
- you want fast arbitrary style transfer in PyTorch
- you need to reproduce or extend the AdaIN ICCV 2017 paper
- you want pretrained decoder and VGG weights ready to use
- you need multi-style mixing or color preservation options

## When to avoid
- you need video style transfer
- you want a maintained GUI or web app rather than scripts
- you need official author-supported code
- you need style transfer on mobile or edge devices

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, deep-learning, computer-vision
- platform: python, cross-platform
- tags: style-transfer, adain, pytorch, neural-style-transfer, unofficial-implementation, gpu

## Member repositories
- naoto0804/pytorch-AdaIN (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:54.070620+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 2026-08-30T06:25:12.629294+00:00, confidence not recorded.
  - readme: https://github.com/naoto0804/pytorch-AdaIN (fetched 2026-08-28T04:03:54.070620+00:00, sha 8b363ae63547)
- Data as of 2026-08-30T08:39:29.467469+00:00.