> For the complete documentation index, see [llms.txt](https://developer.topazlabs.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.topazlabs.com/image-models/upscaling-and-enhancement/precision/face-recovery-3.md).

# Face Recovery 3

Improved face restoration for low-resolution images

<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="https://4007072434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJkSwaYgAsTQke14gpXAF%2Fuploads%2FPOlLmEXscToalB3nhCen%2Frecovery3_indian_man_portrait_slider.jpg?alt=media&#x26;token=a3f99414-cc37-4c41-9b58-60e0d5c84bc3">https://4007072434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJkSwaYgAsTQke14gpXAF%2Fuploads%2FPOlLmEXscToalB3nhCen%2Frecovery3_indian_man_portrait_slider.jpg?alt=media&#x26;token=a3f99414-cc37-4c41-9b58-60e0d5c84bc3</a></td><td><a href="https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_indian_man_portrait_before.jpeg&#x26;src1label=Before&#x26;src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_indian_man_portrait_after.png&#x26;src2label=After&#x26;zoom=1.0">https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_indian_man_portrait_before.jpeg&#x26;src1label=Before&#x26;src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_indian_man_portrait_after.png&#x26;src2label=After&#x26;zoom=1.0</a></td></tr><tr><td align="center">Click to view</td><td><a href="https://4007072434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJkSwaYgAsTQke14gpXAF%2Fuploads%2FKhBaXQvJCToGYcOCCbKO%2Frecovery3_pexels_16845071_slider.jpg?alt=media&#x26;token=312e70cb-e186-4fe8-9ab9-e8c2b7af6835">https://4007072434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJkSwaYgAsTQke14gpXAF%2Fuploads%2FKhBaXQvJCToGYcOCCbKO%2Frecovery3_pexels_16845071_slider.jpg?alt=media&#x26;token=312e70cb-e186-4fe8-9ab9-e8c2b7af6835</a></td><td><a href="https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_pexels_16845071_before.webp&#x26;src1label=Before&#x26;src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_pexels_16845071_after.png&#x26;src2label=After&#x26;zoom=1.0">https://compare.topazlabs.com/share/image?src1=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_pexels_16845071_before.webp&#x26;src1label=Before&#x26;src2=https%3A%2F%2Fdownloads.topazlabs.com%2Fweb-assets%2Fmodel-examples%2Frecovery3_pexels_16845071_after.png&#x26;src2label=After&#x26;zoom=1.0</a></td></tr></tbody></table>

### Model Overview

**Face Recovery 3** restores recognizable facial detail from low-resolution, damaged, or heavily compressed images. It produces more realistic, natural-looking faces than earlier versions and automatically detects and processes every face in the image.

It works best when faces in the input are smaller than 512 × 512 pixels. For larger faces, use Detail Faces.

### Best Use Cases

* **Badly degraded portraits.** Recover faces that other models leave unrecognizable.
* **Old and scanned photos.** Restore faces in archival and family images.
* **Low-resolution people photos.** Make small faces usable at higher resolutions.
* **Group shots.** Process every face in the image in one request.
* **Restoration pipelines.** Pair with Dust & Scratch 2 and an upscaler for full photo restoration.

### Endpoint

`https://api.topazlabs.com/image/v1/restore-gen/async`

### Model Parameters

| Parameter  | Type      | Required / Default                           | Accepted values      | Description                      |
| ---------- | --------- | -------------------------------------------- | -------------------- | -------------------------------- |
| `model`    | `string`  | Required                                     | `"Face Recovery V3"` | —                                |
| `strength` | `decimal` | <p>Optional<br>Default: <code>1.0</code></p> | `0.0` to `1.0`       | How strongly faces are restored. |

For request parameters shared by every image endpoint, see Request Parameters. The full schema is also available in our API Reference page.

### Model Pricing

**Face Recovery 3** costs 1 credit per every 24 MP of generated output. The below table includes a list of common output resolutions with associated credit costs.

| Resolution | Typical Source       | Output MP | Credits |
| ---------- | -------------------- | --------- | ------- |
| 640×480    | VGA                  | 0.31      | 1       |
| 1280×720   | 720p                 | 0.92      | 1       |
| 1920×1080  | 1080p                | 2.07      | 1       |
| 2560×1440  | 1440p                | 3.69      | 1       |
| 3840×2160  | 4K UHD               | 8.29      | 1       |
| 4000×3000  | 12 MP phone          | 12.00     | 1       |
| 5472×3648  | 20 MP camera         | 19.96     | 1       |
| 6000×4000  | 24 MP camera         | 24.00     | 1       |
| 7680×4320  | 8K UHD               | 33.18     | 2       |
| 7952×5304  | 42 MP camera         | 42.18     | 2       |
| 8192×5464  | 45 MP camera         | 44.76     | 2       |
| 9504×6336  | 61 MP camera         | 60.22     | 3       |
| 11648×8736 | 100 MP medium format | 101.76    | 5       |

| Output MP | 1 | 4 | 8 | 16 | 24 | 32 | 40 |
| --------- | - | - | - | -- | -- | -- | -- |
| Credits   | 1 | 1 | 1 | 1  | 1  | 2  | 2  |

{% hint style="info" %}
For more accurate credit cost estimates, we recommend using our [Credit Calculator](https://developer.topazlabs.com/credit-calculator).
{% endhint %}

### Example Request

{% tabs %}
{% tab title="cURL" %}

```bash
curl -X POST "https://api.topazlabs.com/image/v1/restore-gen/async" \
  -H "X-API-Key: $TOPAZ_API_KEY" \
  -F "image=@photo.jpg" \
  -F "model=Face Recovery V3" \
  -F "strength=0.8"
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
import fs from 'fs';
import FormData from 'form-data';

const form = new FormData();
form.append("image", fs.createReadStream("photo.jpg"));
form.append("model", "Face Recovery V3");
form.append("strength", "0.8");

const response = await fetch("https://api.topazlabs.com/image/v1/restore-gen/async", {
  method: 'POST',
  headers: {
    'X-API-Key': process.env.TOPAZ_API_KEY,
    ...form.getHeaders(),
  },
  body: form,
});

if (!response.ok) {
  throw new Error(`Request failed: ${response.status} ${await response.text()}`);
}

console.log(await response.json());
```

{% endtab %}

{% tab title="Python" %}

```python
import os
import requests

with open("photo.jpg", "rb") as image:
    response = requests.post(
        "https://api.topazlabs.com/image/v1/restore-gen/async",
        headers={"X-API-Key": os.environ["TOPAZ_API_KEY"]},
        files={"image": image},
        data={
            "model": "Face Recovery V3",
            "strength": "0.8"
        },
    )

response.raise_for_status()
print(response.json())
```

{% endtab %}
{% endtabs %}

### Limitations

Works best when faces in the input are smaller than 512 × 512 pixels.

### Helpful Resources

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><i class="fa-play">:play:</i></td><td><h4>Image Quickstart</h4></td><td>Quickly get started with our Image API.</td><td></td></tr><tr><td><i class="fa-codepen">:codepen:</i></td><td><h4>Model Playground</h4></td><td>Test and create with our models.</td><td><a href="https://playground.topazlabs.com/">https://playground.topazlabs.com/</a></td></tr><tr><td><i class="fa-square-root-variable">:square-root-variable:</i></td><td><h4>Credit Calculator</h4></td><td>Pricing for specific outputs, batches, and more.</td><td></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://developer.topazlabs.com/image-models/upscaling-and-enhancement/precision/face-recovery-3.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
