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

# Prompting Basics

> How to write effective Midjourney prompts through the Legnext API — wording, structure, and where parameters go.

Every image or video task starts with the `prompt` field in your request body.
This page covers how to write that string well. The guidance comes from upstream
Midjourney documentation; which flags and values your prompt may use is defined
by the [image parameter matrix](/getting-started/image-parameters), which is
generated from the backend validation spec. When the two disagree, the matrix
wins.

## Keep it short and specific

Short, descriptive phrases consistently beat long instructions. Describe the
snapshot you want, not the process of making it.

<Note>
  Avoid: *Show me a picture of lots of blooming California poppies, make them
  bright, vibrant orange, and draw them in an illustrated style with colored
  pencils*

  Prefer: `Colored pencil illustration of bright orange California poppies`
</Note>

Three wording habits that measurably change results:

* **Use precise synonyms.** "Big" is vague; "gigantic" or "enormous" gives the
  model a stronger signal.
* **Use numbers, not plurals.** "Three cats" is controllable; "cats" is not.
  Collective nouns work too — "a flock of birds".
* **Describe what you want, not what you don't.** Saying "no cake" in the text
  can still produce a cake. To exclude things, use the
  [`--no` parameter](/getting-started/image-parameters) instead of negations in
  the text itself.

## The seven detail dimensions

A one-word prompt works — the model fills every gap with its default style.
That means more variety and less control. Anything you care about must be
spelled out. When a result disappoints, check which of these dimensions you
left unspecified:

| Dimension   | Question          | Examples                                                |
| ----------- | ----------------- | ------------------------------------------------------- |
| Subject     | Who or what?      | person, animal, character, object, location             |
| Medium      | In what form?     | photo, oil painting, illustration, sculpture, pixel art |
| Environment | Where?            | indoors, underwater, in the city, on the moon           |
| Lighting    | What kind?        | soft, ambient, overcast, neon, studio lights            |
| Color       | Which palette?    | vibrant, muted, monochromatic, pastel, duotone          |
| Mood        | What feeling?     | playful, calm, gloomy, energetic                        |
| Composition | How is it framed? | portrait, closeup, headshot, bird's-eye view            |

```text theme={null}
Gigantic whale drifting over a desert city, gouache painting, golden-hour
light, muted pastel palette, serene mood, wide aerial view --v 8.2 --ar 16:9
```

## Vocabulary that moves the needle

Single adjectives in the right slot change the image dramatically. Useful
starting points, grouped by what they control:

* **Artistic medium** — `______ style cat`: block print, ballpoint pen sketch,
  cyanotype, graffiti, risograph, ukiyo-e, watercolor, pixel art, cross stitch,
  oil painting, cut paper.
* **Time period** — `illustration of a ______ cat`: 1700s, 1920s, 1950s, 1980s
  each carry a distinct visual language.
* **Emotion** — `______ cat`: shy, determined, joyful, sleepy.
* **Color** — `______ colored cat`: sepia, pastel, duotone, iridescent,
  grayscale, neon, acid green.
* **Environment** — `______ cat`: tundra, jungle, desert, salt flat, crystal
  forest, ocean.

Treat these as probes: swap one word at a time and compare, rather than
rewriting the whole prompt between runs. For reproducible comparisons, pin
[`--seed`](/getting-started/image-parameters).

## Anatomy of a full prompt

A prompt string can carry three kinds of content:

1. **Text** — the description above. Required.
2. **Image references** — image URLs that steer content or style, attached via
   image prompts or reference parameters (`--sref`, `--oref`, `--cref`). Which
   of these a given model version accepts varies sharply — `--cref` is rejected
   across the whole v8 family, and `--oref` exists only on v8.0. Check the
   [parameter matrix](/getting-started/image-parameters) before using them.
3. **Parameters** — flags appended at the end of the string, e.g.
   `--ar 16:9 --stylize 150`. They control rendering, not content.

```text theme={null}
https://cdn.example.com/forest-ref.png Misty pine forest at dawn --sref https://cdn.example.com/style.png --v 8.2 --ar 3:2
```

<Tip>
  Pin a version explicitly. When `--v` is omitted the API renders as v7, and
  parameter support differs across versions — a prompt tuned on the default may
  fail or change meaning on v8.2. See [Models](/getting-started/models) for
  version selection.
</Tip>

## Next steps

Once the basics feel predictable, move to
[Advanced Prompting](/getting-started/prompting-advanced): multi-prompts and
weights, permutation prompts, negative prompting, and rendered text.