# reiinakano/arbitrary-image-stylization-tfjs

Arbitrary style transfer using TensorFlow.js

Repository: https://github.com/reiinakano/arbitrary-image-stylization-tfjs
Canonical: https://ross.abutalabs.com/products/arbitrary-image-stylization-tfjs
Homepage: https://reiinakano.github.io/arbitrary-image-stylization-tfjs/
Language: JavaScript
License: Apache-2.0
License Family: permissive
Topics: style-transfer, neural-network, deep-learning, tensorflow-js, browser, artists, generative-art
Last push: 2022-12-03T03:20:33+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": 2850, "days_push": 1369, "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 1205, forks 211 (observed 2026-08-28T04:03:59.254828+00:00)

## What it is
A browser-based implementation of arbitrary neural style transfer built with TensorFlow.js, letting users stylize any photo in the style of any image entirely client-side. It includes a demo app with multiple model variants (MobileNet-v2 and Inception-v3 style networks, separable and plain convolution transformer networks) and support for combining two styles.

## Use cases
- apply a painting's style to my photos in the browser
- run style transfer without uploading images to a server
- combine two art styles into one stylized image
- demo of neural style transfer with TensorFlow.js
- stylize webcam pictures with any style image
- client-side deep learning image effects

## When to choose
- you need arbitrary (any-image) style transfer rather than a fixed set of pretrained styles
- privacy matters and images must never leave the user's device
- you want a dependency-free browser demo of TF.js inference

## When to avoid
- you need server-side or batch stylization of many images
- you need training or fine-tuning of style transfer models
- you need mobile-native performance or a native app integration

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: machine-learning, image-processing, computer-vision, web-development, graphics
- platform: browser
- tags: style-transfer, tensorflowjs, neural-style-transfer, generative-art, client-side-inference, browser-demo, web-server, javascript

## Member repositories
- reiinakano/arbitrary-image-stylization-tfjs (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:59.254828+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 2026-08-30T06:19:36.830728+00:00, confidence not recorded.
  - readme: https://github.com/reiinakano/arbitrary-image-stylization-tfjs (fetched 2026-08-28T04:03:59.254828+00:00, sha 843abced9d7d)
  - homepage: https://reiinakano.github.io/arbitrary-image-stylization-tfjs/ (fetched 2026-08-29T12:27:24.706659+00:00, sha e5580c45c5c4)
- Data as of 2026-08-30T08:39:29.467469+00:00.