Based on real human preferences
The model draws on ratings from 60 people who reviewed thousands of face photos, so the score reflects shared human rating patterns.
Try this free face analysis test with one clear photo. Get a model estimate on a familiar 10-point scale. Upload photo guide
Upload multiple photos of the same person for a more objective score.
Our model was trained on thousands of face photos rated by 60 real people. It learns from how people rated those photos, instead of calculating a score from facial landmarks alone.
To reduce the effect of one unusual photo—such as lighting or a temporary physical state—we recommend up 3–5 photos of the same person. We combine their results for a more stable, more objective estimate.
Use a front-facing photo with even lighting. The model was trained only on natural, bare-faced photos, so studio portraits, filters, and retouching can distort its score. Add 3–5 similar photos for a steadier estimate. Upload 3–5 photos, compare their scores, and choose the one that works best for your profile.
The chart below is a visual reference for the 1–10 scale. Higher scores reflect how the model estimates the appeal of a particular photo, not an objective measure of a person.
Treat it as a rough guide when comparing your own photos. Do not use it to infer someone's background or gender, or to compare people across demographic groups.
Questions, answered
FaceAnalysis estimates how appealing a face appears in a specific photo. It gives that photo a 1–10 model score, so you can compare different profile-photo options.
Yes. FaceAnalysis is free to use with no limit on the number of photos you can analyze. Each result is a 1–10 model estimate that you can use to compare profile pictures.
Our model was trained on thousands of face photos rated by 60 real people. Instead of calculating a score from facial landmarks alone, it learns from how people rated those photos. Lighting, pose, expression, and image quality can still affect the result.
You can use FaceAnalysis with just one photo. For a steadier estimate, we recommend up 3–5 similar photos, since lighting, expression, or a temporary change in appearance can affect any one result.
Use a clear, front-facing photo of one person, with both eyes visible and even lighting. The model was trained only on natural, bare-faced photos, so studio portraits, beauty filters, retouching, and other edits can distort its score. Avoid group photos, blurry images, and extreme angles. No. The score is a model estimate for one particular photo, based on shared patterns in real people's ratings. Use it to compare photos, not as a final judgment about your appearance or value.