Images to 3D head

Automatic multi-view 3D head reconstruction technology delivered as a REST API to empower your applications and pipelines with likeness-driven digital people.

Loading preview...
# 1. Open a session — returns an avatar id and photo upload URLs
curl -X POST https://api.cloud.keentools.io/v1/avatar/init \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "image_count": 5 }'

# 2. Upload each photo to its pre-signed URL
curl -X PUT "$UPLOAD_URL" \
  -H "Content-Type: image/jpeg" \
  --data-binary @photo-1.jpg

# 3. Start reconstruction on the session
curl -X POST https://api.cloud.keentools.io/v1/avatar/$AVATAR_ID/process \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "focal_length_type": { "focal_length_type": "estimate_common" } }'

# 4. Download the result — OBJ + texture, delivered as a ZIP
curl -L -X GET "https://api.cloud.keentools.io/v1/avatar/$AVATAR_ID/get-3d-model?mesh_format=obj&texture=jpg" \
  -H "Authorization: Bearer $API_KEY" \
  -o head.zip

How it works

Multi-view input

Two or more photos from any anglesno calibration, rigs or depth-sensing hardware.

Loading preview...

Realistic texture

Projected from your source photos and seamlessly blended, with automatic colour correction.

Loading preview...

Facial expressions

Each photo's expression captured as exportable blendshapes.

Camera solve

Focal length and camera positions estimated automatically for every shot.

Loading preview...

Custom blendshapes

Exportable shapes for morphing and animation — poke an expression to play it.

MetaHuman topology

Every head ships in MetaHuman-compatible topology — drop-in ready for Unreal Engine.