> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pornx.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Prompt writing basics

> Learn how to structure an effective image prompt on PornX, including subject, action, setting, lighting, and camera term ordering.

A prompt is a description of what you want the image to contain. Structure matters more than length: a well-ordered short prompt outperforms a long unstructured one.

## Prompt structure

Write elements in this order, from most to least important:

| Position | Element        | Example                             |
| -------- | -------------- | ----------------------------------- |
| 1        | Subject        | `a woman in her 20s, red hair`      |
| 2        | Action or pose | `lying on a bed, looking at camera` |
| 3        | Setting        | `hotel room, evening`               |
| 4        | Lighting       | `warm side light, soft shadows`     |
| 5        | Camera         | `close-up, shallow depth of field`  |
| 6        | Style          | `high detail`                       |
| 7        | Quality tags   | `sharp focus, detailed skin`        |

You don't need every element. Start with subject and action: add the rest to correct specific problems with the output.

## Good vs bad prompts

**Bad:** `sexy woman, hot, beautiful, amazing photo, best quality`

This is all sentiment and no description. The model has nothing specific to work with.

**Good:**

<Prompt description="`a woman in her late 20s, dark skin, black lingerie, sitting on a white bed, window light from the left, shallow depth of field`" icon="input-text" actions={["copy"]} />

This gives the model subject, clothing, setting, lighting, and camera in one sentence.

## What Prompt Enhancer does

PornX automatically enhances prompts. You can toggle it off in the settings panel if you want the output to follow your exact wording.

## Negative prompts

A negative prompt tells the model what to exclude. Access it via the **Advanced** toggle.

Common negatives:

<Prompt description="`blurry, deformed hands, extra fingers, bad anatomy, watermark, text`" icon="input-text" actions={["copy"]} />

Don't overload the negative prompt: five to eight terms is enough. More than that and the model starts ignoring all of them.

## Tips

* Put the subject first, so the model weights earlier tokens more heavily
* Be specific about body type, hair, clothing, and setting rather than using vague descriptors like "beautiful" or "perfect"
* Add lighting terms to fix flat or overexposed results: `soft natural light`, `dramatic side light`, `backlit`
* Use style and quality tags at the end, not the beginning
* If you're getting consistent artifacts, add the specific problem to your negative prompt

<CardGroup cols={2}>
  <Card title="Advanced Prompting" icon="sliders" href="/prompting/advanced">
    Weights, negatives, and token order.
  </Card>

  <Card title="Model-specific tips" icon="lightbulb" href="/prompting/model-specific">
    Prompting quirks per model.
  </Card>
</CardGroup>