# Image Generation

{% hint style="info" %}
**Good to know:** Prompts are one of the most important things to master when generating content (not just images!) with hyunGPT.
{% endhint %}

To generate images with hyunGPT, use the `/image generate` command. The following options are required:

* **Prompt**: The prompt of your image. The more descriptive you are, the better.&#x20;
* **Model:** The model that you'll use to generate your image. Models starting with `HYUN` are hyunGPT's custom models, with `HYUN_ANYTHING` being our latest and most advanced model. We also have many other recent models such as `DALLE-3` and `SDXL`.
* **Style:** This is the style of your image. For example, if you would like your image to be in the style of Disney, you might choose the `DISNEY` style. If you would like no style (image only follows your prompt), select `NO_STYLE`
* **Ratio:** This is the dimensions of your image! The format is `height:width`, so selecting 16:9 will create a rectangle image.

If you would like to further customize your generated images, feel free to explore our additional options...

* **Images:** This specifies the amount of images you would like to generate. You can make up to 10 at a time! *<mark style="color:red;">(Subscribers only)</mark>*
* **Negative Prompt:** The negative prompt is what you DON'T want your image to include. For example, if you wanted to generate a picture of a street but don't want it to be blurry, you could put "blurry" in the negative prompt.
* **Steps:** Steps are the amount of iterations the image generator goes through to make your image. Generally, 30 steps tends to work well, but anything less than that can result in incomplete images.
* **CFG:** The CFG (classifier-free guidance scale) determines how much the image follows your prompt. A low number means that it doesn't follow your prompt as much, while a high number means it follows your prompt exactly. Think about it as controlling how creative the model can be!
* **Seed:** This is the starting point of your image. Seeds can be any number, and it's usually selected randomly. If you use the same seed twice, you'll most likely get around the same image.
* **Enhance Prompt:** If you're not good at writing prompts, don't worry! hyunGPT offers a setting for you to use AI to enhance your prompt, and by toggling this on, AI will make your prompt better in the background. *<mark style="color:red;">(Subscribers only)</mark>*

Awesome! Now you know about all the options for generating your images! We can't wait to see what you can make with hyunGPT!


---

# 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.hyungpt.app/image-commands/image-generation.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.
