Check if you have hunter eyes. The AI evaluates canthal tilt, upper/lower eyelid exposure, eye socket depth, brow-eye distance, and eye shape to show how close your eye area is to the Hunter Eyes ideal.
A clear front-facing photo, neutral expression, even light. Your free scan stays on this device.
Explore a sample free result. Select a measurement to see its lines and points, then try your own photo.
Almond-like opening
Select a measurement to inspect its construction.
Measured span Comparison / reference
Image-left tiltInner to outer eye corner on the left side of the photograph.Measured from this photograph
Your free geometry score summarizes measured symmetry and proportions on your device. Add AI for a more complete assessment across six dimensions and a separate score out of 100.
Eye-spacing ratio 1.21; visible face length / width 1.20.
Evidence: eye spacing · face lengthMeasured spacing is ready for the optional AI interpretation and scoring.
Keep camera distance and expression the same when comparing a second photo.
Closest outline: heart. Jaw / cheek width 0.82.
Evidence: jaw widthA frontal outline does not establish profile depth or bone structure.
Compare hair tucked behind the sides with your usual framing.
Texture and tone need a visible-photo interpretation; no skin score is assigned by the free landmark scan.
Brightness and sharpness describe the image, not skin health.
Use even daylight and an unfiltered photo for any later appearance review.
Hair, brows and eyewear can be reviewed in the optional AI report using the same six-dimension method.
Landmark geometry alone does not assess your current hairstyle.
Change only one framing choice and compare the outline you prefer.
Eye and mouth measurements are available; expression interpretation belongs to the optional photo review.
The free scan does not infer emotions or personality.
Compare a relaxed expression with a comfortable smile under the same light.
Exposure and image detail pass the basic review checks for this scan.
Passing these checks does not certify every feature as measurable or provide a calibrated confidence level.
Use an eye-level camera, soft front light and a consistent lens distance.
The free plate preserves left and right canthal angles, visible eye opening and brow spacing. The qualitative review uses our six dimensions and does not assign a Hunter Eyes total or infer eye-socket depth from a front photo.
Start with the measurable relationships. Add a photo-grounded review when you want context, limitations and practical comparisons.
Visible spacing and proportions between eyes, brows, nose, mouth and outline, using supplied measurements where available.
No assumption that closeness to one ratio makes a face more attractive.
The visible cheek, jaw and chin silhouette and how it appears in the supplied views.
A frontal photo cannot establish profile projection, bone structure or a 3D reconstruction.
Texture, tone and contrast that can actually be seen in this photograph.
Lighting, makeup, filters and compression can alter appearance. No skin-health or biological-age inference.
How hair volume, parting, brows, facial hair and eyewear frame visible features.
Advice is an optional styling experiment. No prediction of an anatomical change or guaranteed score improvement.
Visible eye opening, gaze direction and mouth expression in the specific frame.
No inference of personality, trustworthiness, dominance or actual emotional state.
Light direction, camera angle, distance, focus, framing and background distraction.
Describe the image conditions separately from the face. A poor photograph is not a low-quality face.
Read the complete assessment standard, compare the specialist methods, or learn to take consistent comparison photographs.
Learn relationships across the whole face rather than prescribing a geometric ideal. Attention maps require caution: they do not establish causal explanations.
Peer-reviewed · International Journal of Multimedia Information RetrievalPredict the distribution of human ratings, including disagreement, rather than only an average. Reported Pearson correlation is not a percentage of correct beauty judgments.
Conference paper · code and checkpoint workflow availableProvides a candidate model baseline and LiveBeauty data for studying live-image aesthetics. The live-streaming and retouching domain differs from ordinary portrait photos.
arXiv preprint · not presented here as peer-reviewedSeparates model prediction routes for shape, skin, hair, light, background, expression and pose. Component terms explain that model's prediction, not real-world causes of attraction.
arXiv preprint · preregistered exploratory studyComparison with human raters found that the studied commercial models gave higher, more compressed absolute ratings despite tracking relative order.
Peer-reviewed · Aesthetic Plastic SurgeryUses independent images and human raters to evaluate predictions. This is a useful validation pattern; it does not validate our product.
Where a free scan is offered, it runs on your device and shows measured geometry, a geometry reference score where offered, and a six-dimension baseline. Dimensions that require a photo interpretation are clearly marked for optional AI review.
No. The current single-portrait AI report provides six dimension scores and a total out of 100 using our authored rubric. It is an AI reference score for the photograph, not a calibrated human-panel prediction. Human-rating prediction and calibration remain research objectives.
The optional $2.79 topic report interprets the supplied photographs through six dimensions. Each dimension includes its score out of 100, an observation, cited evidence, its limitation and a practical comparison to try. The total is the rounded mean of all six dimension scores. Your report is saved privately in your account.
Specialist tools retain their separately defined geometry, classification or community scale. The six-dimension framework does not replace those constructions or convert them into one new beauty score.
No. They inform the method and proposed evaluation. The research library identifies what each paper studied, its publication status and our adoption status. We have not deployed the cited specialist prediction models or completed independent human-rating validation.
