We built RealSmile because most face rating tools are either vague ("you're a 7!"), expensive, or quietly uploading your photos to a database. We wanted something different — specific, measurable, and actually private.
RealSmile started as a smile analyzer. The research on Duchenne smiles — genuine vs. fake — is well-established and fascinating, but nobody had made it accessible in a simple tool. So we built one. Upload a photo, get told whether your smile reaches your eyes, and get specific feedback on what to adjust.
People wanted more. They asked for golden ratio analysis, jawline scoring, canthal tilt measurement. So we expanded — and kept the same philosophy throughout: real measurements in real units (degrees, ratios, percentiles), not arbitrary 1–10 scores with no explanation. That output now ships as a detailed face report any visitor can read end-to-end before paying for anything.
Every metric we measure has a research basis. Canthal tilt correlates with attractiveness ratings in peer-reviewed studies. FWHR is linked to dominance perception. Golden ratio facial proportions have been documented since Da Vinci. We're not making this up — we're making established science usable.
People who want to understand why some photos perform better than others — and what to change. Our tools tell you exactly what the camera is picking up.
Headshot lighting, expression, and facial presentation all affect first impressions. We help you understand what your professional photo is communicating.
People tracking changes from mewing, skincare, weight loss, or other routines. Objective baseline measurements let you see what's actually changing.
The looksmaxxing test runs all 17 metrics at once. The individual metric pages let you explore each one in depth.
17 facial metrics in one analysis: symmetry, canthal tilt, FWHR, jawline angle, hunter eyes, golden ratio, and more. Scored against population averages with a personalized improvement plan.
Genuine vs. fake smile detection based on Duchenne smile research — measures eye muscle engagement vs. mouth-only smiles.
Upload two photos and see which one scores higher. Useful for picking the best dating app or LinkedIn photo.
Facial proportions vs. the golden ratio (1.618). Analyzes facial thirds, eye spacing, and nose-to-mouth ratios.
Beauty score based on facial proportions, symmetry, and expression. Includes what's pulling the score up or down.
Honest AI analysis of what actually makes a face score high or low — and why you look worse in photos than real life.
Bilateral symmetry comparison across jawline, eyes, brows, and mouth. Measured in percentages, not vibes.
Individual Metrics — also measured in the looksmaxxing test
Gonial angle in degrees + definition score
Eye angle — positive tilt is rated most attractive
Lid hooding, tilt, and brow ridge prominence
Facial width-to-height ratio — key masculinity metric
Oval, square, round, heart, oblong, or diamond
All 5 key markers of facial masculinity scored
The AI identifies 68 key points on your face — eyes, brows, nose, mouth corners, jawline, and chin — from a single photo.
It calculates real measurements: symmetry percentages, angle degrees (canthal tilt, gonial angle), distance ratios (FWHR, golden ratio). These are math, not opinions.
Each metric is scored against population averages and research-backed ideal ranges. You get a percentile rank, not a random number.
All tools use @vladmandic/face-api, built on TensorFlow.js. On desktop browsers, analysis runs entirely client-side — your photo never leaves your device. On mobile, photos are processed via a secure server and immediately discarded. No photos are ever stored, shared, or used for model training.
Every metric we measure is grounded in published research. Here's the key history.
Luca Pacioli, with illustrations by Leonardo da Vinci, published "De Divina Proportione" — applying the golden ratio (1.618) to human facial proportions. This is the mathematical foundation of our golden ratio analysis.
French neurologist Duchenne de Boulogne showed that genuine smiles activate two muscles: the zygomaticus major (mouth) and orbicularis oculi (eyes). Posed smiles use only the mouth. This is the basis of our smile analyzer.
Paul Ekman and Wallace Friesen catalogued every human facial movement into Action Units. Their research confirmed humans detect fake smiles in 33 milliseconds — faster than conscious thought.
Studies establish that facial width-to-height ratio (FWHR) correlates with perceived dominance, and positive canthal tilt (+3° to +8°) with perceived attractiveness. These became core looksmaxxing metrics.
Modern AI detects 68 facial landmarks in milliseconds and computes measurements that once required manual analysis by researchers. RealSmile puts this in your browser — free, private, instant.
Desktop analysis runs entirely in your browser. Your photo is never uploaded to any server — the AI runs locally using WebGL. This isn't a marketing claim; it's technically how the tool works.
We don't build profiles, store measurements, or use your photos for training. Analysis is ephemeral — nothing persists after you close the tab.
Every tool works without signup, login, or email. You can analyze your face completely anonymously.
Your facial data is never shared with advertisers, data brokers, or anyone else. We use only anonymous analytics (page views, not faces) to improve the tools.
Every metric and correlation we cite references a peer-reviewed study. We link to the original research so you can verify claims yourself. Our research page lists every citation with journal, year, and key finding.
We use face-api.js (68-point iBUG 300-W model) for landmark detection and publish our measurement methodology. We disclose limitations: 2D photo analysis is inherently less precise than 3D imaging, and scores are relative, not diagnostic.
Articles are reviewed and updated when new research is published or when tools we review change their features or pricing. Last updated dates are shown on every article.
When we compare our tools to competitors, we disclose that we built RealSmile. We test competing tools ourselves and report both strengths and weaknesses. We don't fabricate competitor shortcomings.
Questions about a result, a metric you don't understand, or feedback on the tools — we read every message and respond within 24 hours.
17 metrics, real measurements, no fluff. Takes about 60 seconds.
No signup required. Photos never leave your device.