# jcjohnson/neural-style

Torch implementation of neural style algorithm

Repository: https://github.com/jcjohnson/neural-style
Canonical: https://ross.abutalabs.com/products/neural-style
Language: Lua
License: MIT
License Family: permissive
Last push: 2018-02-23T01:21:20+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4019, "days_push": 3114, "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 18284, forks 2641 (observed 2026-08-28T04:11:26.533565+00:00)

## What it is
A Torch (Lua) implementation of the Gatys et al. neural style transfer algorithm, which combines the content of one image with the artistic style of another using convolutional neural networks. It was one of the most popular reference implementations of the technique.

## Use cases
- apply the style of a painting to a photograph
- reproduce results from the Neural Algorithm of Artistic Style paper
- experiment with convolutional neural network style transfer
- generate artistic stylized images from content and style image pairs
- learn how style transfer works in code

## When to choose
- you specifically need the classic Gatys optimization-based style transfer algorithm
- you are working in the Torch/Lua ecosystem
- you want a well-known reference implementation for research or study

## When to avoid
- you need actively maintained software or modern framework support
- you want fast real-time or feed-forward style transfer
- you prefer PyTorch, TensorFlow, or other modern deep learning frameworks

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, image-processing, computer-vision
- platform: lua
- tags: neural-style-transfer, torch, gan-free, research-code, style-transfer, gpu, linux, macos

## Member repositories
- jcjohnson/neural-style (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:26.533565+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 2026-08-29T17:02:05.423009+00:00, confidence not recorded.
  - readme: https://github.com/jcjohnson/neural-style (fetched 2026-08-28T04:11:26.533565+00:00, sha da6b50edf17f)
- Data as of 2026-08-30T08:39:29.467469+00:00.