> 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.md).

# Precision Upscaling

Precision Upscaling for Images

* **Clean upscales of good sources.** You need a bigger version of a reasonably good image with no recovered or generated detail.
* **Fidelity over recovery.** Print reproduction, archival masters, forensic or scientific imagery, or any pipeline where "the model invented that" is unacceptable.
* **Graphics, product shots, and close inspection.** Anything that will be compared pixel for pixel against the original.
* **Specialized sources.** Very small images (Low Resolution 2), illustrations and renders (Art & CGI), text and logos (Text & Shapes), transparent PNGs (Transparent Image Upscale), and small or degraded faces (Recover Faces / Face Recovery 3).

{% hint style="success" %}
We recommend using **Standard 2** for precision upscaling.
{% endhint %}

<table data-view="cards"><thead><tr><th></th><th></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><strong>Standard 2</strong></td><td>Faithful, general-purpose upscaling for most images.</td><td><a href="https://4007072434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJkSwaYgAsTQke14gpXAF%2Fuploads%2FYDLk41ND0n3B5ZXTohfH%2FStandard_2_slider.jpg?alt=media&#x26;token=b1a25216-c164-4a53-8dad-b934e95c0ab2">https://4007072434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJkSwaYgAsTQke14gpXAF%2Fuploads%2FYDLk41ND0n3B5ZXTohfH%2FStandard_2_slider.jpg?alt=media&#x26;token=b1a25216-c164-4a53-8dad-b934e95c0ab2</a></td><td><a href="https://developer.topazlabs.com/image-models/upscaling-and-enhancement/precision/standard-2.md">Standard 2</a></td></tr><tr><td><strong>High Fidelity 3</strong></td><td>Maximum detail retention for high-resolution, professional photos.</td><td><a href="https://4007072434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJkSwaYgAsTQke14gpXAF%2Fuploads%2F9o9FiUMFgmBA7y85d4MI%2Fharvey_slider.jpg?alt=media&#x26;token=c445cd1f-3ae1-47f0-b7a0-6408867d2123">https://4007072434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJkSwaYgAsTQke14gpXAF%2Fuploads%2F9o9FiUMFgmBA7y85d4MI%2Fharvey_slider.jpg?alt=media&#x26;token=c445cd1f-3ae1-47f0-b7a0-6408867d2123</a></td><td><a href="https://developer.topazlabs.com/image-models/upscaling-and-enhancement/precision/high-fidelity-3.md">High Fidelity 3</a></td></tr><tr><td><strong>Transparent Image Upscale</strong></td><td>Upscales PNGs while preserving the alpha channel.</td><td><a href="https://4007072434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJkSwaYgAsTQke14gpXAF%2Fuploads%2FFdkCsneXQrcJOJuuqMeP%2FTransparent_Image_Upscale_slider.jpg?alt=media&#x26;token=1cb2b430-a194-425c-b4fa-33449c2068a0">https://4007072434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJkSwaYgAsTQke14gpXAF%2Fuploads%2FFdkCsneXQrcJOJuuqMeP%2FTransparent_Image_Upscale_slider.jpg?alt=media&#x26;token=1cb2b430-a194-425c-b4fa-33449c2068a0</a></td><td><a href="https://developer.topazlabs.com/image-models/upscaling-and-enhancement/precision/transparent-image-upscale.md">Transparent Image Upscale</a></td></tr><tr><td><strong>Face Recovery 3</strong></td><td>Advanced restoration for badly degraded faces.</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://developer.topazlabs.com/image-models/upscaling-and-enhancement/precision/face-recovery-3.md">Face Recovery 3</a></td></tr><tr><td><strong>Detail Faces</strong></td><td>Adds realistic detail to faces in AI-generated images.</td><td><a href="https://938351258-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fik4tc42rkpL9SRR51NLK%2Fuploads%2FiYp97mkbF2junbvthulg%2FDetail%20Faces%20Slider.jpg?alt=media&amp;token=d648f4a7-cbb9-42da-a46a-e7d30ddf83c2">Detail Faces Slider.jpg</a></td><td><a href="https://developer.topazlabs.com/image-models/upscaling-and-enhancement/precision/detail-faces.md">Detail Faces</a></td></tr></tbody></table>

{% hint style="warning" %}
Standard 1, Text & Shapes, Art & CGI, Low Resolution 1, Low Resolution 2, High Fidelity 1, High Fidelity 2, Face Recovery 1, and Face Recovery 2 are legacy models and are no longer recommended. Wonder 3.5 replaces Text & Shapes, Art & CGI, Low Resolution 1, and Low Resolution 2. Face Recovery 3 replaced Face Recovery 1 and Face Recovery 2. High Fidelity 3 replaces High Fidelity 2. These models will be retired no sooner than December 9, 2026. See [Model Deprecations](https://developer.topazlabs.com/resources/model-deprecations.md) for dates and migration steps.
{% endhint %}

### Endpoints

| Endpoint                                               | Models                               |
| ------------------------------------------------------ | ------------------------------------ |
| `https://api.topazlabs.com/image/v1/enhance/async`     | Standard 2, High Fidelity 3          |
| `https://api.topazlabs.com/image/v1/enhance-gen/async` | Detail Faces                         |
| `https://api.topazlabs.com/image/v1/restore-gen/async` | Face Recovery 3                      |
| `https://api.topazlabs.com/image/v1/tool/async`        | Transparent Image Upscale (PNG only) |

Requests are `multipart/form-data`. Pass the image as the `image` field (or reference a previous upload with `source_id` or `source_url`), set `model` to the value shown on the model's page, and set the output size with `output_width` and/or `output_height`. The response returns a `process_id` and `eta`; poll `GET /status/{process_id}` and download the result from `GET /download/{process_id}`.

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

```bash
curl -X POST "https://api.topazlabs.com/image/v1/enhance/async" \
  -H "X-API-Key: $TOPAZ_API_KEY" \
  -F "image=@photo.jpg" \
  -F "model=Standard V2" \
  -F "output_width=3840" \
  -F "output_format=png"
```

{% 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", "Standard V2");
form.append("output_width", "3840");
form.append("output_format", "png");

const response = await fetch("https://api.topazlabs.com/image/v1/enhance/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/enhance/async",
        headers={"X-API-Key": os.environ["TOPAZ_API_KEY"]},
        files={"image": image},
        data={
            "model": "Standard V2",
            "output_width": "3840",
            "output_format": "png",
        },
    )

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

{% endtab %}
{% endtabs %}

### Parameters

Request parameters (`image`, `source_id`, `source_url`, `model`, `output_format`, `webhook_url`) are the same for every image endpoint and are listed on the [Request Parameters](https://developer.topazlabs.com/getting-started/request-parameters.md) page. `/enhance/async`, `/enhance-gen/async`, and `/tool/async` also accept `output_width`, `output_height`, and `crop_to_fill` to set the output size. Model settings are listed on each model's page.

### Limitations

Most models accept up to 256 MP input and output, with each output side up to 32,000 pixels. Transparent Image Upscale accepts and returns PNG only.

### 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><a href="https://developer.topazlabs.com/getting-started/image-quickstart.md">Image Quickstart</a></td></tr><tr><td><i class="fa-file-brackets-curly">:file-brackets-curly:</i></td><td><h4>API Reference</h4></td><td>View our API reference to view the entire schema.</td><td><a href="https://developer.topazlabs.com/reference/">https://developer.topazlabs.com/reference/</a></td></tr><tr><td><i class="fa-square-root-variable">:square-root-variable:</i></td><td><h4>Model Pricing</h4></td><td>Learn how we price our models.</td><td><a href="https://developer.topazlabs.com/getting-started/model-pricing.md">Model Pricing</a></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.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.
