> For the complete documentation index, see [llms.txt](https://docs.fermat.app/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.fermat.app/ai-tool-catalogue/photoshooting-and-styling/generate-models.md).

# Generate models

## Step by step guide

To create the perfect model for your brand, follow these steps:

{% stepper %}
{% step %}

### Open the AI tool

1. Go to [Fermat.app](https://fermat.app/) and log into your account.
2. Open: '[Generate models](https://toolmaker.fermat.app/tool/create-photo-shoots-051d7b7f-16db-4f75-b076-ef88baba2acd)' tool.
   {% endstep %}

{% step %}

### Describe your model

Provide a text description of the model you want to generate. [Learn more](https://letsenhance.io/blog/article/ai-text-prompt-guide/) about how to write a good prompt.

{% hint style="info" %}
Example: Full body shot of a young woman. She wears an oversized white linen cropped long-sleeve shirt with side pocket, lilac eyelet shorts, layered gold necklaces, and an arm cuff. Detailed features include medium-length brown hair styled in a casual updo, soft makeup highlighting natural skin tone, and subtle earrings. The setting is a photography studio, she poses against a off-white background.
{% endhint %}

{% hint style="info" %}
Optionally, you can click the <mark style="color:purple;">blue magic wand button</mark> to refine your description. Alternatively, upload a reference image and press the same button to analyze it and generate an accurate description based on the attached image.
{% endhint %}
{% endstep %}

{% step %}

### Set aspect ratio

Define the aspect ratio of the output image.
{% endstep %}

{% step %}

### Generate image

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

{% hint style="warning" %}
Review the output and, if necessary, **refine the prompt** for better results.
{% endhint %}

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

{% embed url="<https://youtu.be/LiLcHiXcbIY>" %}

### (Optional) Choose a reference image:

You can upload a reference image to guide the AI, enabling it to capture the composition, lighting, shading, and other visual elements with precision.

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