Ross ROSS = Recommend OSS · open-source software intelligence for agents

reiinakano/fast-style-transfer-deeplearnjs

Demo of in-browser Fast Neural Style Transfer with deeplearn.js library observed · 2026-08-28

github.com/reiinakano/fast-style-transfer-deeplearnjs · homepage · TypeScript · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

32/100

  • Activity 0
  • Release rhythm 35
  • Longevity 100

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 3266
  • days_rel: n/a
  • days_push: 2834
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1352 stars · 112 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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 The repository is deprecated and no longer maintained, with its functionality superseded by arbitrary-image-stylization-tfjs and ml5.js.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

application · maturity abandoned

machine-learning image-processing deep-learning deep-learning image-processing computer-vision web-development browser neural-style-transfer deeplearnjs in-browser-inference deprecated demo web-server

2 sources

Member repositories

RepositoryRoleHealth v2
reiinakano/fast-style-transfer-deeplearnjsmain32

For agents

markdown · JSON · MCP: product_card(name="reiinakano/fast-style-transfer-deeplearnjs")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem