# Extract garment

## Introduction

This tool automatically detects and extracts any garment worn by a model, isolating it for further editing, analysis, or reuse. You can extract a garment from a photoshoot or sketch image.

## Step by step guide

To extract garments from photoshoots, follow these steps:

{% stepper %}
{% step %}

### Open the AI tool

1. Go to [Fermat.app](https://fermat.app/) and log into your account.
2. Open: '[Extract garment](https://toolmaker.fermat.app/tool/extract-garment-546dd57b-d14f-463f-804d-744c977560ae)' tool.
   {% endstep %}

{% step %}

### Select a page

There are two pages, each with a specific purpose. These pages are:

* Extract garment from photoshoot
* Extract garment from sketch
  {% endstep %}

{% step %}

### Specify which garment to extract

{% hint style="info" %}
Example: sweater
{% endhint %}
{% endstep %}

{% step %}

### Choose the photoshoot image/ sketch

{% hint style="success" %}
Supported formats: JPEG, PNG, and WEBP
{% endhint %}
{% endstep %}

{% step %}

### Generate image

Click on the *'Generate'* button and let the AI process your inputs. In a few seconds, you will have your new design.

<figure><img src="/files/VdVrhY9fXvz0BJIfRGwQ" alt=""><figcaption></figcaption></figure>
{% endstep %}
{% endstepper %}

(tutorial)

### (Optional) Add extra details

You can provide extra details about the garment you want to extract to make sure the AI takes them into consideration.

{% hint style="info" %}
Example: The sweater is knitted and made of wool.
{% endhint %}

<figure><img src="/files/d1zNDErZNsuIgD5EeGTQ" alt=""><figcaption></figcaption></figure>


---

# 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.fermat.app/ai-tool-catalogue/apparel-and-accessories/extract-garment.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.