Free tool · runs in your browser
How pretty am I? Upload a straight-on photo and get a pretty-scale percentage built from eight measured proportions: symmetry, golden ratio, facial thirds, face width, midface, eye corners, jaw and eye spacing. You see each line on your photo and which readings raised or lowered the number.
Drop a photo, paste one, or choose a file
Straight-on, whole face visible, even light. JPG, PNG or WebP.
Runs in your browser. Your photo is never uploaded.
How it is measured
Each of the eight readings is scored against a published reference band: full marks anywhere inside the band, less the further it falls outside. The weighted total is the face score (1–10) used by the face rating tool, and the pretty scale shows where that score sits on the scale's own range: 0% at the lowest score any photo can get, 100% at the top. Because it is computed, the same photo always gets the same percentage.
Sources
The measurement and its reference ranges come from published research. Studies use different methods and populations, so compare your number with the range shown on this page rather than with other tools.
Langlois JH, Kalakanis L, Rubenstein AJ, et al. (2000). Maxims or myths of beauty? A meta-analytic and theoretical review. Psychological Bulletin. doi:10.1037/0033-2909.126.3.390
Meta-analysis: people largely agree on who is attractive, across ages and cultures.
Langlois JH, Roggman LA (1990). Attractive faces are only average. Psychological Science. doi:10.1111/j.1467-9280.1990.tb00079.x
Averaged composite faces were rated more attractive than most individual faces.
Perrett DI, May KA, Yoshikawa S (1994). Facial shape and judgements of female attractiveness. Nature. doi:10.1038/368239a0
The most attractive faces were not simply average, so averageness is only part of the picture.
Rhodes G (2006). The evolutionary psychology of facial beauty. Annual Review of Psychology. PubMed 16318594
Review of the main factors in facial attractiveness: averageness, symmetry and sex-typical features.
Kartynnik Y, Ablavatski A, Grishchenko I, Grundmann M (2019). Real-time facial surface geometry from monocular video on mobile GPUs. arXiv. arXiv:1907.06724
The face-mesh model that places the 468 surface landmarks this tool measures from.
Ablavatski A, Vakunov A, Grishchenko I, et al. (2020). Real-time pupil tracking from monocular video for digital puppetry. arXiv. arXiv:2006.11341
The iris model that adds 10 eye landmarks (478 in total), used for pupil-based reference lines.
Our own data: how much each reading moves when the same face is photographed again is published on the methodology page. How we choose sources.
Related tools
Face Rating
The same measurement as a 1–10 score.
PSL Score Test
The same measurement on the 1–8 PSL scale.
Facial Harmony Test
How many proportions sit inside their bands.
Color Analysis
Your color season and undertone.
Lash Map Tool
The lash map that suits your eye shape.
Eyebrow Mapping Tool
Brow start, arch and tail on your face.
FAQ
No measurement answers that by itself. This test measures one ingredient, proportion, and leaves out skin, hair, makeup, expression and style, which change how people see a face as much as bone does. Read the number as how balanced your proportions measure in this photo.
It is a proportion score. It is the same measurement as the face rating tool, shown as a percentage instead of a number out of 10.
Many pretty scale sites use different points, different ideal values or an AI model that guesses. This tool publishes its bands and draws its lines on your photo, so you can check what was measured.
A lot. A close selfie with a wide-angle lens widens the nose and narrows the face; a tilted or turned head shifts every reading. Take the photo at arm's length or further, straight on, eyes level and face relaxed.
No. Everything runs in your browser and nothing is sent to a server.
A controlled scan, every reading against its ideal band, bone vs trainable, a plan, and a 3D model on Face ID iPhones.