How it works
From two photos to a number you can check.
No votes, no vibes, and no AI deciding how you look. Four steps, the same every time.
Two photos
A front shot and a side profile. A pose and blur gate rejects anything it can’t measure properly, rather than scoring a bad photo.
468 landmarks
Facial landmark detection places 468 points — eye corners, alar base, vermilion border, gonion — on each image.
75 measurements
A deterministic engine computes 75 geometric ratios, angles and distances, and scores each against its published ideal range.
Score and plan
The measurements roll up into a harmony score and tier — then get ranked by which ones you could actually move.
The measurement
Every point, placed precisely.
468 landmarks per photo — eye corners, alar base, vermilion border, gonion. The distances and angles between them are the measurements: canthal tilt, FWHR, gonial angle, midface ratio. No interpretation and no opinion, just geometry.

What you’ll see
Every measurement is shown with your reading, its ideal range, and the study it comes from. Nothing is a black box, and nothing is a vibe.
Ranges drawn from published facial anthropometry — Farkas, Powell, Naini, Sarver, Mommaerts and others.
How the score is built →What gets measured
75 measurements. Six clusters.
Every measurement is shown with your reading, its ideal range, and its citation. 49 of the 75 use different ranges for men and women, because the research does.
- 14JawGonial angle · Jaw/cheek width · Ramus
- 14EyesCanthal tilt · Eye spacing · Canthal angle
- 12NoseNasal width · Nasofrontal angle
- 10LipsUpper-to-lower ratio · Philtrum
- 10ProportionsFacial thirds · Fifths · Lower face
- 7MidfaceFWHR · Midface ratio · Tapering
+ 8 more feed a separate bilateral symmetry score
The pattern they form is your archetype: see all six
- Hunter
- Classic
- Soft
- Striking
- Boyish
- Mature
Where you land
A tier you can trace back to a measurement.
Your score maps onto the plain-language tier and the PSL tier the looksmax community actually uses. Both come from the same measured number.
- 98+True AdamApex
- 94+Adamlite
- 88+ChadElite
- 82+Chadlite
- 72+HTNAbove average
- 55+MTNAverage
- 40+LTNBelow average
- 28+Sub5
- 18+Sub3
The tier is the least useful part of your result. The ranked list of fixable measurements underneath it is the part you can act on.
Every tier explained →Your AI coach
AI that has read your measurements.
The coach sees your actual numbers — which ratios came back weak, which are already inside their range. Ask anything and the answer is built around your face, not generic advice.

Your daily plan
A plan built from your numbers.
Morning, evening, every day — built around the measurements you can actually move, and explicit about the ones you can’t. Re-scan and the plan updates against the new numbers.

What we don’t do
The things we deliberately left out.
No golden ratio in the score
Phi and the classical canons are computed and shown, but kept out of the composite. They’re art-historical prescriptions, not research findings.
No global percentiles
You’ll never see “top 3% worldwide”, because nobody has that dataset. Percentiles are stated against GlowAI’s own users, and labelled that way.
No attractiveness verdict
The composite is a geometric score. It describes proportions against published ranges — not how attractive you are, and not your worth.
Stop guessing. Start measuring.
Honest answers
What you’re probably wondering.
Sources
Ideal ranges are taken from published anthropometric literature. Every metric in the app carries its own citation; these are the works the set is built on.
- Farkas LG. Anthropometry of the Head and Face. 2nd ed. Raven Press, 1994. (opens in a new tab)
The reference dataset for human craniofacial measurement — the source of most normative ranges in use today.
- Powell N, Humphreys B. Proportions of the Aesthetic Face. Thieme-Stratton, 1984. (opens in a new tab)
Defines the profile angles — nasofrontal, nasofacial, nasomental, mentocervical — used in the side-profile analysis.
- Naini FB. Facial Aesthetics: Concepts and Clinical Diagnosis. Wiley-Blackwell, 2011. (opens in a new tab)
Modern synthesis of facial proportion assessment, and the source for several vertical-thirds and horizontal-fifths ranges.
- Sarver DM. Esthetic Orthodontics and Orthognathic Surgery. Mosby, 1998. (opens in a new tab)
Soft-tissue analysis — lip projection, smile arc and incisor display.
- Mommaerts MY, et al. Published work on facial proportion and orthognathic planning. (opens in a new tab)
Contemporary maxillofacial ranges, including midface and chin projection.
- Steiner CC. Cephalometrics for you and for me. Am J Orthod, 1953. (opens in a new tab)
The Steiner analysis — the cephalometric baseline for skeletal relationships.
- Tweed CH. The Frankfort-mandibular incisor angle in diagnosis and treatment planning. (opens in a new tab)
The Tweed triangle, behind the mandibular-plane and incisor-angle metrics.
- Google. MediaPipe Face Mesh / Face Landmarker. (opens in a new tab)
The landmark detector that places 468 points on each photo, before any measurement is computed.
Updated





