# fzliu/style-transfer

An implementation of "A Neural Algorithm of Artistic Style" by L. Gatys, A. Ecker, and M. Bethge. http://arxiv.org/abs/1508.06576.

Repository: https://github.com/fzliu/style-transfer
Canonical: https://ross.abutalabs.com/products/style-transfer
Language: Python
License Family: other
Last push: 2017-08-30T05:57:48+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": 4011, "days_push": 3290, "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 1535, forks 380 (observed 2026-08-28T04:04:59.782221+00:00)

## What it is
A Python implementation of the Gatys et al. neural style transfer algorithm built on Caffe, applying the artistic style of one image onto a content image. It supports pretrained VGG16, VGG19, GoogLeNet, and CaffeNet models with GPU acceleration via CUDA.

## Use cases
- apply the style of a painting to a photo
- neural style transfer with vgg19
- reproduce the Gatys artistic style algorithm
- stylize images using caffe on gpu
- turn my photo into a starry night style image
- experiment with deep learning image stylization

## When to choose
- you specifically want the original Gatys et al. algorithm
- you already have Caffe installed and working
- you want a simple single-script implementation to study or modify

## When to avoid
- you need a maintained tool or modern PyTorch/TensorFlow support
- you want fast feed-forward or real-time style transfer
- your environment only supports Python 3 without Caffe

## Facets
- artifact type: library
- maturity: abandoned
- function: image-processing, deep-learning, machine-learning
- domain: image-processing, deep-learning, computer-vision, artificial-intelligence
- platform: python
- tags: neural-style-transfer, caffe, gatys, vgg, artistic-style, python2, linux, macos, gpu

## Member repositories
- fzliu/style-transfer (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:59.782221+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 2026-08-30T04:31:08.968930+00:00, confidence not recorded.
  - readme: https://github.com/fzliu/style-transfer (fetched 2026-08-28T04:04:59.782221+00:00, sha f8e5d0040cd6)
- Data as of 2026-08-30T08:39:29.467469+00:00.