# Recover Faces

### Model Overview

**Recover Faces** is a specialized facial reconstruction model designed to restore recognizable facial detail from low-resolution, damaged, or heavily compressed images. When facial information is missing or unreadable, Recover Faces reconstructs plausible features rather than strictly preserving original pixels.

This model is typically combined with another enhancement. Face Recovery includes both Realistic and Creative variants, allowing users to balance fidelity and recovery strength based on source quality. Because these models are reconstructive by design, results may include subtle changes to expressions or smoothing of skin, hair, or fine facial details in order to produce a coherent, usable face.

Recover Faces is intended for portraits and people-focused imagery where standard upscaling cannot recover meaningful facial structure.

### Key Capabilities

* Reconstructs facial detail from extremely low-resolution or damaged images
* Automatically detects and processes multiple faces within a single image
* Enables usable portrait results where traditional upscaling fails

### Model Pricing

<table data-header-hidden data-full-width="false"><thead><tr><th width="119.84765625">Text</th><th width="60.390625" data-type="number">Number</th><th width="59.5390625" data-type="number"></th><th width="60.0859375" data-type="number"></th><th width="60.265625" data-type="number"></th><th width="59.94140625" data-type="number"></th><th width="59.5390625" data-type="number"></th><th width="60.34375" data-type="number"></th><th width="59.9296875" data-type="number"></th><th width="59.828125" data-type="number"></th><th width="59.5078125" data-type="number"></th></tr></thead><tbody><tr><td><code>Output MP</code></td><td>1</td><td>4</td><td>8</td><td>16</td><td>24</td><td>32</td><td>40</td><td>50</td><td>64</td><td>100</td></tr><tr><td><code>Credits</code></td><td>1</td><td>1</td><td>1</td><td>1</td><td>1</td><td>2</td><td>2</td><td>3</td><td>3</td><td>5</td></tr></tbody></table>

### Getting Started

**Endpoint**

* <https://api.topazlabs.com/image/v1/restore-gen/async>
  * `model` — `"Faces"`

**Model-Specific Parameters**

* `strength` — decimal between 0 and 1, default 0.8
* `noise_sigma` — decimal between 0.001 and 0.1, default 0.015
* `blur_sigma` — decimal between 0.01 and 2.0, default 0.4
* `noise_seed` — integer between 1 and 2000, default 1
* `reference_uri` — string, optional

{% hint style="info" %}
This model works best on smaller images, where the *face* in the input image is less than 512 x 512 pixels. For larger images, we recommend using [`Detail Faces`](/image-models/gigapixel/detail-faces.md).
{% endhint %}

### Examples

<table data-card-size="large" data-view="cards"><thead><tr><th align="center"></th><th data-hidden data-card-cover data-type="image">Cover image</th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td align="center">Click to view</td><td><a href="/files/tXrX8PeOGS625oD640Pu">/files/tXrX8PeOGS625oD640Pu</a></td><td><a href="https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FCrowd%201.png&#x26;src1label=Before&#x26;src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FRecover%20Crowd%204xCrowd%201.png&#x26;src2label=After&#x26;zoom=1">https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FCrowd%201.png&#x26;src1label=Before&#x26;src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2FRecover%20Crowd%204xCrowd%201.png&#x26;src2label=After&#x26;zoom=1</a></td></tr></tbody></table>


---

# 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://developer.topazlabs.com/image-models/gigapixel/recover-faces.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.