Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.
JavaScript 3d-generationai-agentsanimationavatardigital-humangenerative-aiglbgltfimage-to-3dllmmcpmcp-servermodel-context-protocolsolanatext-to-3dthreejsweb-componentswebglwebxrx402
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title data-i18n="features_scan.meta_title">Scan — Turn Your Selfie into a Rigged 3D Avatar · three.ws</title>
<meta
name="description"
content="Point your camera at your face, hold still for 60 seconds, and walk away with a rigged 3D avatar ready to animate. Free, entirely in your browser — no app download."
data-i18n-attr="content:features_scan.meta_description"/>
<meta name="robots" content="index, follow" />
<link rel="canonical" href="https://three.ws/features/scan" />
<meta property="og:type" content="website" />
<meta property="og:site_name" content="three.ws" />
<meta
property="og:title"
content="Scan — Turn Your Selfie into a Rigged 3D Avatar · three.ws"
data-i18n-attr="content:features_scan.meta_og_title"/>
<meta
property="og:description"
content="One photo → rigged 3D avatar. Free, in your browser, no app."
data-i18n-attr="content:features_scan.meta_og_description"/>
<meta property="og:url" content="https://three.ws/features/scan" />
<meta
property="og:image"
content="https://three.ws/api/feature-og?feature=scan&title=Your+face+in+3D.+In+60+seconds.&sub=Point+your+camera+and+walk+away+with+a+rigged+avatar."
/>
<meta property="og:image:width" content="1200" />
<meta property="og:image:height" content="630" />
<meta name="twitter:card" content="summary_large_image" />
<meta
name="twitter:title"
content="Scan — Turn Your Selfie into a Rigged 3D Avatar · three.ws"
data-i18n-attr="content:features_scan.meta_twitter_title"/>
<meta
name="twitter:description"
content="One photo → rigged 3D avatar. Free, in your browser, no app."
data-i18n-attr="content:features_scan.meta_twitter_description"/>
<meta
name="twitter:image"
content="https://three.ws/api/feature-og?feature=scan&title=Your+face+in+3D.+In+60+seconds.&sub=Point+your+camera+and+walk+away+with+a+rigged+avatar."
/>
<link rel="shortcut icon" href="/favicon.ico" />
<link rel="apple-touch-icon" href="/pwa-192x192.png" />
<link rel="stylesheet" href="/style.css" />
<link rel="stylesheet" href="/nav.css" />
<link rel="stylesheet" href="/features-landing.css" />
<link rel="stylesheet" href="/fonts/fonts.css" />
<script
type="module"
src="https://cdn.jsdelivr.net/npm/@google/[email protected]/dist/model-viewer.min.js"
integrity="sha384-wjsPzEO+lXOf7d9csIDfAQpPt2OKuUU3m0K9qsdKIuzX4N8czSF6hdh23eAbZa3p"
crossorigin="anonymous"
></script>
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@graph": [
{
"@type": "SoftwareApplication",
"name": "three.ws Scan — Selfie to 3D Avatar",
"url": "https://three.ws/scan",
"applicationCategory": "MultimediaApplication",
"description": "Reconstruct a rigged 3D avatar from a single selfie photo using photogrammetry and neural reconstruction, entirely in the browser.",
"operatingSystem": "Web",
"offers": { "@type": "Offer", "price": "0", "priceCurrency": "USD" }
},
{
"@type": "FAQPage",
"mainEntity": [
{
"@type": "Question",
"name": "Does Scan work on any phone?",
"acceptedAnswer": {
"@type": "Answer",
"text": "Scan works in any modern browser with camera access — Chrome, Safari, or Firefox on Android or iPhone. No app download needed."
}
},
{
"@type": "Question",
"name": "Is my photo stored?",
"acceptedAnswer": {
"@type": "Answer",
"text": "Your photo is processed server-side to generate the mesh, then stored only as part of your three.ws avatar. You can delete it from your account at any time."
}
},
{
"@type": "Question",
"name": "Can I use the avatar for VRChat or other platforms?",
"acceptedAnswer": {
"@type": "Answer",
"text": "The output is a standard GLB file compatible with any platform that accepts glTF 2.0 models, including VRChat, Meta Horizon, Spatial, and custom WebXR experiences."
}
}
]
}
]
}
</script>
<script src="/model-viewer-meshopt.js"></script>
</head>
<body class="fl-page">
<header><div id="nav-container"></div></header>
<script src="/nav.js"></script>
<main class="fl-main" id="main-content">
<nav class="fl-breadcrumb" aria-label="Breadcrumb">
<a href="/" data-i18n="features_scan.three_ws">three.ws</a>
<span class="fl-breadcrumb-sep" aria-hidden="true">/</span>
<a href="/features" data-i18n="features_scan.features">Features</a>
<span class="fl-breadcrumb-sep" aria-hidden="true">/</span>
<span class="fl-breadcrumb-current" data-i18n="features_scan.scan">Scan</span>
</nav>
<!-- Hero -->
<section class="fl-hero" aria-labelledby="scan-hero-h1">
<div class="fl-hero-inner">
<div class="fl-hero-copy">
<span class="fl-eyebrow"
data-i18n-html="features_scan.selfie_3d_avatar"><span class="fl-eyebrow-dot" aria-hidden="true"></span>Selfie → 3D
Avatar</span
>
<h1 id="scan-hero-h1" data-i18n-html="features_scan.your_face_in_3d_in_60_seconds">Your face in 3D.<br />In 60 seconds.</h1>
<p class="fl-hero-sub" data-i18n="features_scan.point_your_phone_camera_at_your_face">
Point your phone camera at your face, hold still, and walk away with a
rigged 3D avatar you can animate, embed, and use anywhere. Free,
entirely in your browser — no download, no app.
</p>
<div class="fl-hero-actions">
<a href="/create/selfie" class="fl-btn-primary" data-i18n="features_scan.start_scanning">Start scanning →</a>
<a href="/features" class="fl-btn-ghost" data-i18n="features_scan.all_features">All features</a>
</div>
</div>
<div class="fl-hero-preview" aria-label="Sample 3D avatar preview">
<model-viewer
src="/animations/soldier.glb"
alt="Sample rigged 3D avatar"
auto-rotate
auto-rotate-delay="500"
rotation-per-second="10deg"
camera-controls
shadow-intensity="0.5"
environment-image="neutral"
style="background: transparent; width: 100%; height: 100%"
></model-viewer>
<span class="fl-preview-label" data-i18n="features_scan.sample_rigged_avatar_drag_to_orbit">Sample rigged avatar · drag to orbit</span>
</div>
</div>
</section>
<!-- How it works -->
<section class="fl-how fl-section" aria-labelledby="scan-how-h2">
<p class="fl-section-label" data-i18n="features_scan.how_it_works">How it works</p>
<h2 id="scan-how-h2" data-i18n="features_scan.camera_in_3d_avatar_out">Camera in, 3D avatar out</h2>
<div class="fl-steps" role="list">
<article class="fl-step" role="listitem">
<span class="fl-step-num">01</span>
<h3 data-i18n="features_scan.point_your_camera">Point your camera</h3>
<p data-i18n="features_scan.open_the_scanner_on_any_phone_or">
Open the scanner on any phone or desktop browser with camera access.
Position your face in the guide frame — good light, neutral expression,
camera at eye level.
</p>
</article>
<article class="fl-step" role="listitem">
<span class="fl-step-num">02</span>
<h3 data-i18n="features_scan.multi_angle_capture">Multi-angle capture</h3>
<p data-i18n="features_scan.the_scanner_captures_several_angles_automati">
The scanner captures several angles automatically and sends them to our
reconstruction pipeline, which builds a full 3D mesh with UV-mapped skin
texture.
</p>
</article>
<article class="fl-step" role="listitem">
<span class="fl-step-num">03</span>
<h3 data-i18n="features_scan.rigged_glb_ready_to_use">Rigged GLB, ready to use</h3>
<p data-i18n="features_scan.the_output_is_a_rigged_glb_the">
The output is a rigged GLB — the skeleton is wired so standard BVH or
mixamo animations work out of the box. Download it, embed it, or launch
your agent with it.
</p>
</article>
</div>
</section>
<!-- Highlight cards -->
<section class="fl-highlights fl-section" aria-labelledby="scan-highlights-h2">
<h2 id="scan-highlights-h2" data-i18n="features_scan.what_you_get">What you get</h2>
<div class="fl-cards">
<div class="fl-card">
<span class="fl-card-icon" aria-hidden="true">◎</span>
<h3 data-i18n="features_scan.real_face_texture">Real face texture</h3>
<p data-i18n="features_scan.the_mesh_uses_your_actual_photo_as">
The mesh uses your actual photo as a texture map — not a cartoon or
stylized approximation.
</p>
</div>
<div class="fl-card">
<span class="fl-card-icon" aria-hidden="true">◎</span>
<h3 data-i18n="features_scan.standard_rig">Standard rig</h3>
<p data-i18n="features_scan.the_skeleton_follows_the_standard_mixamo_hum">
The skeleton follows the standard Mixamo humanoid-rig convention so
thousands of free animation clips work without re-rigging.
</p>
</div>
<div class="fl-card">
<span class="fl-card-icon" aria-hidden="true">◎</span>
<h3 data-i18n="features_scan.ar_passthrough">AR passthrough</h3>
<p data-i18n="features_scan.load_your_avatar_in_walk_mode_and">
Load your avatar in Walk mode and toggle AR — your 3D self walks on your
real floor through your phone camera.
</p>
</div>
<div class="fl-card">
<span class="fl-card-icon" aria-hidden="true">◎</span>
<h3 data-i18n="features_scan.no_account_for_first_scan">No account for first scan</h3>
<p data-i18n="features_scan.try_the_scanner_without_signing_up_create">
Try the scanner without signing up. Create an account to save, download,
and share your avatar.
</p>
</div>
</div>
</section>
<!-- FAQ -->
<section class="fl-faq fl-section" aria-labelledby="scan-faq-h2">
<h2 id="scan-faq-h2" data-i18n="features_scan.frequently_asked_questions">Frequently asked questions</h2>
<div class="fl-faq-list">
<div class="fl-faq-item">
<button class="fl-faq-q" aria-expanded="false" aria-controls="scan-faq-1">
Does Scan work on any phone or browser?
<svg
class="fl-faq-chevron"
viewBox="0 0 16 16"
fill="none"
aria-hidden="true"
>
<path
d="M4 6l4 4 4-4"
stroke="currentColor"
stroke-width="1.5"
stroke-linecap="round"
/>
</svg>
</button>
<div class="fl-faq-a" id="scan-faq-1" role="region">
Yes — Chrome, Safari, or Firefox on Android or iPhone. The scanner uses
the standard WebRTC camera API. No app download required.
</div>
</div>
<div class="fl-faq-item">
<button class="fl-faq-q" aria-expanded="false" aria-controls="scan-faq-2">
What lighting conditions give the best result?
<svg
class="fl-faq-chevron"
viewBox="0 0 16 16"
fill="none"
aria-hidden="true"
>
<path
d="M4 6l4 4 4-4"
stroke="currentColor"
stroke-width="1.5"
stroke-linecap="round"
/>
</svg>
</button>
<div class="fl-faq-a" id="scan-faq-2" role="region">
Soft, even front lighting works best — like facing a window on an
overcast day. Avoid harsh shadows across your face or bright
backlighting.
</div>
</div>
<div class="fl-faq-item">
<button class="fl-faq-q" aria-expanded="false" aria-controls="scan-faq-3">
Is my photo stored on three.ws servers?
<svg
class="fl-faq-chevron"
viewBox="0 0 16 16"
fill="none"
aria-hidden="true"
>
<path
d="M4 6l4 4 4-4"
stroke="currentColor"
stroke-width="1.5"
stroke-linecap="round"
/>
</svg>
</button>
<div class="fl-faq-a" id="scan-faq-3" role="region">
Your photo is processed server-side and retained as the avatar texture
in your account. You can delete your avatar — and its source texture —
from your account settings at any time.
</div>
</div>
<div class="fl-faq-item">
<button class="fl-faq-q" aria-expanded="false" aria-controls="scan-faq-4">
Can I use the avatar in VRChat, Spatial, or other platforms?
<svg
class="fl-faq-chevron"
viewBox="0 0 16 16"
fill="none"
aria-hidden="true"
>
<path
d="M4 6l4 4 4-4"
stroke="currentColor"
stroke-width="1.5"
stroke-linecap="round"
/>
</svg>
</button>
<div class="fl-faq-a" id="scan-faq-4" role="region">
The output is a standard glTF 2.0 GLB, compatible with any platform that
accepts that format — VRChat, Meta Horizon Worlds, Spatial, Unity,
Unreal Engine, or custom WebXR apps.
</div>
</div>
<div class="fl-faq-item">
<button class="fl-faq-q" aria-expanded="false" aria-controls="scan-faq-5">
How is this different from Forge?
<svg
class="fl-faq-chevron"
viewBox="0 0 16 16"
fill="none"
aria-hidden="true"
>
<path
d="M4 6l4 4 4-4"
stroke="currentColor"
stroke-width="1.5"
stroke-linecap="round"
/>
</svg>
</button>
<div class="fl-faq-a" id="scan-faq-5" role="region">
<a href="/features/forge" style="color: var(--ink)" data-i18n="features_scan.forge">Forge</a> generates
any object from a text description. Scan reconstructs a real 3D avatar
from a photo of your actual face — the two tools are complementary.
</div>
</div>
</div>
</section>
<!-- Final CTA -->
<section class="fl-cta-band" aria-labelledby="scan-cta-h2">
<div class="fl-cta-inner">
<h2 id="scan-cta-h2" data-i18n="features_scan.scan_yourself_in_60_seconds">Scan yourself in 60 seconds</h2>
<p data-i18n="features_scan.all_you_need_is_a_camera_and">All you need is a camera and decent lighting. No account required to try.</p>
<div class="fl-cta-actions">
<a href="/create/selfie" class="fl-btn-primary" data-i18n="features_scan.start_scanning_2">Start scanning →</a>
<a href="/features/forge" class="fl-btn-ghost" data-i18n="features_scan.try_forge_instead">Try Forge instead</a>
</div>
</div>
</section>
</main>
<script>
document.querySelectorAll('.fl-faq-q').forEach((btn) => {
btn.addEventListener('click', () => {
const expanded = btn.getAttribute('aria-expanded') === 'true';
btn.setAttribute('aria-expanded', String(!expanded));
const panel = document.getElementById(btn.getAttribute('aria-controls'));
if (panel) panel.classList.toggle('open', !expanded);
});
});
</script>
<div id="footer-container"></div>
<script src="/footer.js"></script>
<!-- Runtime i18n: detects locale, swaps annotated copy, mounts <lang-switcher>. -->
<script type="module" src="/i18n.js"></script>
</body>
</html>