Glowster

Fourteen sub-factors. One formula. No black box.

A score you can't interrogate is a horoscope. The model only does perception - it scores fourteen named sub-factors against a fixed written rubric. Every number you see (feature scores, your overall, your potential) is then computed by us with a published weighted formula. The model never hands you a number it made up.

Methodology · rubric v2.2.4

The five features and their sub-factors

Each feature counts toward your overall at the share shown, and the percentage beside a sub-factor is its share of that feature's score. Bone structure and face shape (jaw contour, facial proportions) are not analyzed: no habit changes them, so the model is never asked to grade them.

If your hair isn't visible in the photo (under a head covering, for example), Hair is not assessed and your overall is taken over the other four features.

Lower face

22% of overall
  • Definition - Visibility of the jaw-to-neck transition.
    Partly53%
  • Under-chin - Short-term puffiness under the chin, which responds to sleep, hydration and sodium. Never a read of weight or body size.
    Movable47%

Skin

24% of overall
  • Clarity - Visible breakouts and blemishes.
    Movable35%
  • Evenness - Redness and tone uniformity.
    Movable25%
  • Texture - Surface smoothness and visible pores.
    Partly20%
  • Hydration - Dull and dry versus healthy and supple.
    Movable20%

Eyes

20% of overall
  • Under-eye - Dark circles and puffiness of the under-eye area.
    Movable45%
  • Brows - Brow grooming and upkeep (not brow shape genetics).
    Movable30%
  • Freshness - How rested and alert the eye area looks - a fatigue signal, never an emotion read.
    Movable25%

Balance

14% of overall
  • Balance - Left-right evenness as presented in a front-facing photo.
    Partly60%
  • Grooming evenness - Evenness of grooming across the face.
    Movable40%

Hair

20% of overall
  • Cut - Quality and freshness of the current cut.
    Movable40%
  • Condition - Health, shine, and frizz.
    Movable35%
  • Style fit - How well the style frames the face as presented.
    Movable25%

Movable or partly movable

Every sub-factor is tagged by how much a 90-day plan can actually move it. Movable sub-factors (skin clarity, under-chin puffiness, brow upkeep) respond to grooming and lifestyle, pulled toward 88 at most. Partly movable ones get a smaller, capped gain of up to 8 points toward 80 - real but modest, reflecting genuine limits on how far habits alone can move them. Bone structure (jaw contour, facial proportions) does not move at all, so it is not analyzed and counts zero toward every score and your potential. Your potential is your current overall plus only the headroom earned this way, never raised above 88 on any single sub-factor. That is why our potential is a conservative estimate, not a promise and not a number designed to flatter you.

Confidence, not false precision

We run the scoring several times and measure how much the passes agree. Tight agreement reads as high confidence; lighting, angle, or a hat that blurs a sub-factor lowers it - and we tell you, rather than printing a precise-looking number we don't trust. Low-confidence reads are labeled as less certain than usual.

How a score is produced

  1. 01Your photo is normalized deterministically - same resize, same processing every time, so identical photos produce identical model input.
  2. 02The model scores fourteen sub-factors against fixed written band definitions (the rubric) - pure perception, no overall, no improvised judgment. The rubric is versioned; your score is stamped with the version that produced it.
  3. 03Score stability comes from the anchored rubric and the median-of-passes step below - not from suppressing the model's own sampling randomness, which we don't control.
  4. 04The full pass runs three times and we keep the median per sub-factor. If the passes disagree, we automatically run more passes before trusting the number, rather than reporting false precision.
  5. 05The app - not the model - computes your feature scores, overall, potential, and confidence from those sub-scores using the published weighted formula below.
  6. 06The photo is deleted from memory before the response returns. Only the numbers and a one-way fingerprint persist.

The result: upload the exact same photo file again and you get the same scorecard. Why AI face scores drift →

What we will never score

The output schema physically has no fields for these - it is not a policy toggle, the model cannot return them:

We don't score "masculinity" or "femininity". We think such scores are both scientifically hollow and corrosive - and we built the schema so we can't drift into them.

The honest caveats

This is a measurement of a photo, not of you - lighting, angle, and camera quality are part of what any vision model sees, which is why check-ins ask for consistent conditions. Scores are rubric-anchored opinions of an AI model, useful for tracking your own change over time - they are not clinical assessments, percentile claims against humanity, or anything medical. For skin or health concerns, see a professional, not an app.

Photo handling details: what happens to your photo.

Get scored - $2.99 →