# Create Any Image

## Overview

Instead of starting from an existing image (by using the parameters `imageFile` or `imageUrl`), you can choose to generate a new AI image using a prompt.

To create an AI image, use the parameter `imageFromPrompt`:

```sh
curl --request POST \
  --url https://image-api.photoroom.com/v2/edit \
  --header 'x-api-key: YOUR_API_KEY' \
  --form removeBackground=false \
  --form 'imageFromPrompt.prompt=three mugs on a table in a rustic coffee shop in a realistic style' \
  --form imageFromPrompt.seed=12345 \
  --output result.png
```

Result:

<figure><img src="https://2855892273-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1SYxn7dWbQYsNtUdJE3f%2Fuploads%2FsjEqvP6TzRhcUMPYrshZ%2Fresult.png?alt=media&#x26;token=247d9a68-a5ce-431b-8d83-941a01ca158c" alt="" width="375"><figcaption></figcaption></figure>

{% hint style="info" %}
Create Any Image generates an image with a background, but the API will perform a background removal by default: you can set `removeBackground=false` if you want to keep the generated background.
{% endhint %}

## Parameters

Create Any Image supports the following parameters:

### `imageFromPrompt.prompt`

Your text prompt to create the image with, for example `three coffee mugs on rustic countertop`, `a red car in a baroque style`, or `a tent on a snowy mountain`.

By default, a realistic style will be used, but you can specify the style you want in the prompt, like `in a cyberpunk style` to override it.

### `imageFromPrompt.seed` (optional)&#x20;

The seed to generate the image. The same prompt with the same seed will generate the same image.

### `imageFromPrompt.size`: (optional)&#x20;

The size and format of the generated.

The following values are supported:&#x20;

* `SQUARE_HD` (default)
* `LANDSCAPE_16_9`
* `LANDSCAPE_4_3`
* `PORTRAIT_16_9`
* `PORTRAIT_4_3`