# Reduce colors

## Introduction

Color discrepancies can often present significant challenges, impacting the final visual effect of printed designs. With Fermat you can quantize your prints, optimize them for printing, and ensure accurate and consistent results every time. This guide will show you how to quantize your prints easily.

## Step by step guide

To quantize your patterns, follow these steps:

{% stepper %}
{% step %}

### Open the AI tool

1. Go to [Fermat.app](https://fermat.app/) and log into your account.
2. Open: '[Reduce colors](https://toolmaker.fermat.app/tool/quantize-your-pattern-0f92a291-305a-4a22-92e0-ca355994e4a5)' tool.
   {% endstep %}

{% step %}

### Upload your print

Upload a print that you want o quantize.

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

{% step %}

### Set a number of colors

Set the number of colors that you want to keep.
{% endstep %}

{% step %}

### (Optional) Specify which colors

You can optionally specify which colors you want to keep.

{% hint style="warning" %}
Define the colors in HEX value. Separate them with commas or the tool might not work as expected.
{% endhint %}
{% endstep %}

{% step %}

### Generate image

Click the 'Generate' button to quantize the provided print.

<figure><img src="/files/VdVrhY9fXvz0BJIfRGwQ" alt="" width="563"><figcaption><p>Generate button</p></figcaption></figure>
{% endstep %}
{% endstepper %}

{% embed url="<https://youtu.be/-qQ7oHm9sg0>" %}
This video demonstrates how to quantize your pattern.
{% endembed %}

## Example

<figure><img src="/files/dBdCFynYvHXtJLePnCb2" 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/graphic-and-prints/reduce-colors.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.