# reiinakano/fast-style-transfer-deeplearnjs

Demo of in-browser Fast Neural Style Transfer with deeplearn.js library

Repository: https://github.com/reiinakano/fast-style-transfer-deeplearnjs
Canonical: https://ross.abutalabs.com/products/fast-style-transfer-deeplearnjs
Homepage: https://reiinakano.github.io/fast-style-transfer-deeplearnjs
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2018-11-29T15:47:56+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": 3266, "days_push": 2834, "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 1352, forks 112 (observed 2026-08-28T04:04:28.343261+00:00)

## What it is
A browser-based demo of Fast Neural Style Transfer running entirely client-side with the deeplearn.js library, letting users stylize images or webcam input without any server-side processing. The repository is deprecated and no longer maintained, with its functionality superseded by arbitrary-image-stylization-tfjs and ml5.js.

## Use cases
- stylize photos with neural style transfer in the browser
- run a neural network fully client-side without uploading images
- demo deep learning models with deeplearn.js
- apply artistic style filters to webcam input
- learn how to deploy pretrained style transfer models in a web app

## When to choose
- you need a reference implementation of in-browser style transfer with deeplearn.js
- you want a privacy-preserving demo where images never leave the user's machine
- you are studying how style transfer models are packaged for the browser

## When to avoid
- you need a maintained or production-ready style transfer tool
- you want arbitrary style images without training a new model per style
- your build environment cannot handle the deprecated bower/npm toolchain
- you need mobile-friendly low-bandwidth usage since each style model is ~6.6MB

## Facets
- artifact type: application
- maturity: abandoned
- function: machine-learning, image-processing, deep-learning
- domain: deep-learning, image-processing, computer-vision, web-development
- platform: browser
- tags: neural-style-transfer, deeplearnjs, in-browser-inference, deprecated, demo, web-server

## Member repositories
- reiinakano/fast-style-transfer-deeplearnjs (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:28.343261+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 2026-08-30T04:42:10.730557+00:00, confidence not recorded.
  - readme: https://github.com/reiinakano/fast-style-transfer-deeplearnjs (fetched 2026-08-28T04:04:28.343261+00:00, sha 39a0351070f6)
  - homepage: https://reiinakano.github.io/fast-style-transfer-deeplearnjs (fetched 2026-08-29T12:01:05.044869+00:00, sha c0fe3fb6d0f9)
- Data as of 2026-08-30T08:39:29.467469+00:00.