> For the complete documentation index, see [llms.txt](https://docs.aimlapi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aimlapi.com/api-references/image-models.md).

# Image Models

## Overview

Our API features the capability to generate images. We support various models for image generation, including both open-source and proprietary options.

We support multiple image models. You can find the [complete list](#all-available-image-models) along with API reference links at the end of the page.

## How to Generate an Image

### Select a model

First, decide which model you want to use. Models can be trained for specific tasks (e.g., realistic results), offer higher resolutions, or include features like negative prompts. You can read about our supported models and their features on our [main website](https://aimlapi.com/models?integration-category=Image+Generation).

### Imagine a prompt

Next, construct a prompt for the image. Depending on your needs, this prompt can include keywords that will shape the image: place, objects, quality, style, and other elements. This prompt is a crucial part of the image generation process and determines what will be displayed in the image.

### Configure metaparameters

Then, configure the metaparameters for your generation:

* **Steps**: The `n` parameter in the API controls the number of iterations the model will take to shape your image. Experiment with this parameter to achieve the best result for your prompt.
* **Size**: The `size` parameter controls the resolution of the resulting image. All models have minimum and maximum resolutions, sometimes with different aspect ratios. Experiment with this parameter as well.

### Quick Code Example

Here is an example of generation an image of a robot classroom using the `flux-pro` image model:

{% tabs %}
{% tab title="Python" %}
{% code overflow="wrap" %}

```python
import requests

url = "https://api.aimlapi.com/v1/images/generations/"

payload = {
  "model": "flux/schnell",
  "prompt": """
Create a classroom of young robots. 
The chalkboard in the classroom has 'AI Is Your Friend' written on it.
"""
}

headers = {
  #put your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
  "Authorization": "Bearer <YOUR_AIMLAPI_KEY>", 
  "content-type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)
response.raise_for_status()

print("Generation:", response.json())
```

{% endcode %}
{% endtab %}
{% endtabs %}

We obtained the following image by running that code example:

<div align="left"><figure><img src="/files/0LRyYsXxiWmkk36VVx5U" alt=""><figcaption><p><em>(And AI needs your clothes, your boots and your motorcycle.)</em></p></figcaption></figure></div>


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.aimlapi.com/api-references/image-models.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.