Bind a face GLB to a VRM

Start from a photo. The page reads the face on your device, makes a face-blendshape GLB from it, and drives a base VRM's expression blendshapes from that GLB's morphs, and (optionally) moves the VRM's face shape, hair shape and colors toward the photo. The skeleton, skin weights and existing blendshapes are not changed, and the hairstyle can be re-laid as waves, curls or coils or switched to a cut preset (no new hair is added).

Input

1. Face photo

Choose a photo or Use the webcam

A clear, front-facing face. The photo stays on this device.

On-device face model: loading…

Already have a face-blendshape GLB? Use it instead of a photo

Face-blendshape GLB (local file only)

2. Base VRM

Male (VRoid base, bundled) Female (VRoid base, bundled)

Use your own VRM instead (a local file or a URL)

A URL (GET) or a local file (overrides the choice above)

Match the photo

(optional and approximate; everything is applied to the VRM's own geometry and materials) Face shape: eye size and spacing, mouth width, jaw, nose / lips / chin depth (moves the face's base positions; every blendshape keeps working) Hair shape: volume, height, length and fringe of the existing hairstyle (needs a photo that shows the whole head) Facial hair: paint a mustache, beard or stubble onto the face texture when the photo has one (estimated from how dark the lower face is next to the cheeks; texture only, no geometry) Hair cut As in the photoKeep the VRM's cutShort cropBobLongAfro Texture Auto (estimated from the photo)StraightWavyCurlyCoily (re-lays each lock as a wave, curl or coil on the VRM's own hair cards; a cut preset replaces the photo's silhouette; braids, buns and ponytails are not possible) Scalp hug (pulls hair that the lift has raised off the skull back toward it, so it does not look like a wig; 0 keeps the full lift) Shape strength 100% Skin tone Hair color (read by an on-device hair segmenter) Eye color Brow color Color strength 70%

The hairstyle is the VRM's own hair cards, scaled, shifted and optionally re-laid (waves, curls, coils, or a cut preset); braids, buns and ponytails are not possible, and the texture guessed from the photo is a rough estimate you can override. The body and the skeleton are not changed, and the photo's texture is not painted onto the avatar. With a face GLB instead of a photo only the skin tone applies (there are no measurements or hair/eye/brow colors in it).

Bind

Network audit

(no requests)

Agent use: ?vrm=male|female|URL&run=1 auto-runs once a photo (or face GLB) is supplied from local disk; the result is on window.__webcli_result. window.__facebind.run({ vrm, image, shape: { strength }, hairShape: { strength, hug }, hairStyle: { cut, texture }, facialHair, bald, look: { skin, hair, iris, brow, strength } }) takes 'male' (default), 'female', a URL or a File for vrm and a File (or face: a face GLB's bytes) for the starting point, never a URL, for either.