# Jack000/fontjoy

font vectors used for fontjoy.com

Repository: https://github.com/Jack000/fontjoy
Canonical: https://ross.abutalabs.com/products/fontjoy
License: MIT
License Family: permissive
Last push: 2017-05-25T04:44:37+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": 3388, "days_push": 3387, "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 1432, forks 90 (observed 2026-08-28T04:04:43.012079+00:00)

## What it is
A dataset and accompanying code of font feature vectors generated via transfer learning from images of 1,883 Google web fonts, powering the fontjoy.com font pairing tool. Vector arithmetic on these embeddings enables font similarity search, analogy operations, and automatic font pairing.

## Use cases
- find fonts visually similar to a given font
- generate font pairings for web design
- explore font embeddings with t-SNE in tensorboard
- do vector arithmetic to isolate serif or weight features
- build a font similarity search engine

## When to choose
- you need precomputed font embeddings for typography research or design tools
- you want to replicate or extend the fontjoy font pairing approach
- you're learning transfer learning with a small visual dataset

## When to avoid
- you need a maintained production library with active support
- you want a general-purpose image embedding toolkit rather than font-specific vectors
- you need fonts beyond the 1,883 Google web fonts included

## Facets
- artifact type: dataset
- maturity: maintenance
- function: machine-learning, data-visualization, search-engine
- domain: machine-learning, web-design, data-visualization, graphics
- platform: python
- tags: font-vectors, transfer-learning, font-pairing, keras, word2vec, typography, deep-learning, web-server

## Member repositories
- Jack000/fontjoy (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:43.012079+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 2026-08-30T04:36:59.788640+00:00, confidence not recorded.
  - readme: https://github.com/Jack000/fontjoy (fetched 2026-08-28T04:04:43.012079+00:00, sha 97c5dca8ffff)
- Data as of 2026-08-30T08:39:29.467469+00:00.