# 3D Face Reconstruction

## API METHODS

| HTTP type |               name              |
| --------- | :-----------------------------: |
| POST      | [/run\_pipeline](#run_pipeline) |

### /run\_pipeline

Getting face texture and head model parameters of 3D head model from photo.

For visualization use [GLB Constructor Service](/service-apis-for-creating-virtual-avatars/getting-started/glb-constructor.md).

Model parameters:

<table><thead><tr><th width="281.3333333333333">Parameter</th><th width="95">Type</th><th>Description</th></tr></thead><tbody><tr><td><code>result.face.textureUrl</code></td><td>string</td><td>UV Texture path saved .png file into /static directory.</td></tr><tr><td><code>result.face.blendShapes</code></td><td>list</td><td>Shape blendshapes. List 80 long with float.</td></tr><tr><td><code>result.face.blinkCorrectionCoeff</code></td><td>int</td><td>Coefficient for corrective blink blendshape.</td></tr><tr><td><code>result.hair.color</code></td><td>string</td><td>Hex RGB color code of hair.</td></tr><tr><td><code>result.hair.type</code></td><td>string</td><td>Type of hairstyle (long/short/ponytail and  straight/wavy).</td></tr><tr><td><code>result.gender</code></td><td>string</td><td>Gender class of input image.</td></tr><tr><td><code>result.skin.color</code></td><td>string</td><td>Hex RGB color code of skin.</td></tr><tr><td><code>result.accessories</code></td><td>list</td><td>List of accessories. List of strings.</td></tr></tbody></table>

## Method for 3D Face Reconstruction

<mark style="color:green;">`POST`</mark> `https://api.metahumansdk.io/face_recon/run_pipeline`

Getting face texture and head model parameters of 3D head model from photo.

#### Request Body

| Name                                           | Type   | Description                                                                                                      |
| ---------------------------------------------- | ------ | ---------------------------------------------------------------------------------------------------------------- |
| token<mark style="color:red;">\*</mark>        | string | Registered token.                                                                                                |
| image\_bytes<mark style="color:red;">\*</mark> | binary | Photo of a person in full face or half a turn. Supported file formats: JPG, PNG, HEIC. Maximum file size: 10 MB. |

{% tabs %}
{% tab title="200: OK The request is successful" %}

```javascript
{
  "result": {
    "face": {
      "textureUrl": "/static/input_image_texture.png",
      "blendShapes": [
        -1.7523525953292847,
        ...
        1.5906388759613037
      ],
      "blinkCorrectionCoeff": 1.0096107066555675
    },
    "hair": {
      "color": "#160406",
      "type": "long_straight"
    },
    "skin": {
      "color": "#965e53"
    },
    "accessories": [],
    "gender": "Female"
  }
}
```

{% endtab %}

{% tab title="422: Unprocessable Entity Error while processing" %}

```
{
    "error": {
            "code": int
            "message": str
    }
}
```

Check in [ERRORS](/service-apis-for-creating-virtual-avatars/errors/3d-face-reconstruction.md) section for possible error response examples.
{% endtab %}
{% endtabs %}

***


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.metahumansdk.io/service-apis-for-creating-virtual-avatars/api-methods/3d-face-reconstruction.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.