Tool · prototype

Body Calculator

Drop in a full-body photo — on your device, nothing uploaded — and it reads the frame it can from the silhouette, then scores it two ways: the Black Pill lens and a conventional one. No sliders. It pairs with the Face Calc, and the two combine into an Overall looks rating below.
Read this first — methodology & limitations
The body is harder to read than the face. This is a mirror of two methodologies, not a verdict on a person. It estimates the frame straight from the image — joint positions from 33 pose landmarks, plus the body outline from an on-device segmentation mask — to compute ratios the literature actually uses: waist-to-hip (Singh 1993), a waist-to-height adiposity proxy (Tovée & Cornelissen show body-fat is the single strongest cue for female bodies), the shoulder-to-waist V-taper (Dixson) and leg-to-torso (Sorokowski). But the ceiling is lower than the face: clothing, pose, camera angle and arms-at-your-sides all corrupt the silhouette, a single frontal view has no depth (it can’t see a gut side-on), and true body-fat / muscle / height can’t be measured from pixels — only proxied. Unsupported crops and seated, bent, or side-on poses are refused rather than graded from extrapolated joints. When a trained model (models/body-beauty.onnx) is present it scores the headline — on-device, still no upload — and the geometry becomes the transparent breakdown beneath it; until then the geometry scores both. Everything runs locally; the image never leaves your browser. This is a transparent prototype, not a clinical tool — and unlike the face, nothing credible rates a body’s aesthetics. For the body-fat percentage it can only proxy, a caliper or BIA check at a gym or clinic gives a usable number — or, to track it at home, a body-fat smart scale like the Wyze Scale X (best for trends under consistent conditions, not a precise one-off reading). For best results: face forward, full body in frame, arms slightly away from your sides, fitted clothing.
Step 1 · Your photo
Upload Camera
Drop a clear, front-facing, full-body photo here — head to feet, standing square. Upper-body shots still work, at reduced accuracy. Click to choose. Saved on your device, never uploaded.
Loading the on-device pose model…
Stays on this device. Your photo is read in your browser and never uploaded. It’s saved locally so it survives page switches, and is cleared the moment you drop a new one or hit Reset.
Step 2 · Your numbers optional
Height and scale weight are direct entries. Body-fat is less certain: type a device estimate or choose the closest silhouette. These inputs add scale and leanness context, but they remain self-reported, validation-pending signals.
Manual inputs are off — this is a photo-only read (shape and distribution, no absolute scale or leanness-by-the-numbers). Untick to add self-reported context.
What it reads — and how
Frame & proportions — from 33 pose landmarks: shoulder span, hip span, torso vs. leg length, and left/right symmetry.
Silhouette widths — from an on-device segmentation mask, the body’s actual width at the shoulders, the narrowest waist, and the widest hips — which is what makes waist-to-hip and the V-taper measurable at all.
Adiposity proxy — waist width against standing height: an uncalibrated frontal waist-width-to-height proxy, displayed but not scored. A front photo can’t see depth, so it doesn’t convert to the real waist-circumference adiposity index — not true body-fat or BMI, and clothing and angle move it.
Proxied, not measured: true body-fat %, muscle vs. fat, absolute height and weight, and anything depth-dependent (a gut, posture, glutes) that a single frontal photo physically cannot see. The panel proxies what it can and flags the rest rather than faking a number. See The Bone Pill for why one number is a mirror, not a verdict.
No body yet. Drop a full-body or upper-body photo and the score appears here — switch lenses any time.