---
title: Prompting — MiniMax H3 Image | Runware Docs
url: https://runware.ai/docs/models/minimax-h3-image/guides/prompting
description: "How to write text-to-image prompts for MiniMax H3 Image: sizing by preset, exact dimensions or no size, and planning the task and layout before the details."
---
### [Introduction](https://runware.ai/docs/models/minimax-h3-image/guides/prompting#introduction)

MiniMax H3 Image generates an image from a prompt and an optional size, and it **follows instructions closely**: how many subjects, where each one stands, which way it faces and which part of the frame stays empty. Write the prompt **as a plan of the image**, starting with what it is for, then the layout, then the details and the light.

![An isometric 3D diorama of a small office on a floating square slab against a pale lavender background, with six white desks in two rows of three, four people at work, the two back-left desks empty, a monstera in the back-left corner and a low bookshelf along the back-right edge, and the left half of the frame empty](https://runware.ai/docs/assets/output-hero.CgYUiFK5_Z7ESqM.jpg)

> **Prompt**: A wide hero illustration for a project management app's landing page. An isometric 3D diorama of a small open-plan office built on a single square floor slab, floating on a plain pale lavender background and seen from the front-right corner. The slab sits in the right half of the frame, and the left half is empty pale lavender with nothing in it, kept clear for a headline. On the slab, six white desks stand in two rows of three, each with one open laptop and one coral desk chair. Four people work at the desks, and the two desks on the left of the back row are empty, their chairs pushed in. A tall potted monstera stands in the back-left corner of the slab, a low white bookshelf runs along the back-right edge, and a round mustard rug lies under the front row. Smooth matte clay materials in white, lavender, coral and mustard, soft light from the upper left, gentle ambient occlusion where the desks meet the floor. Clean 3D product illustration, no text, no logos.

Every count and position in the prompt **is an instruction**. It names which two desks stay empty, the left pair in the back row, and those are the two the render leaves free.

This guide covers the request, the three ways to size it, and how to structure a prompt so each decision in the image is yours. Quoted text, infographics and UI screens have their own guide, [text and layouts](https://runware.ai/docs/models/minimax-h3-image/guides/text-and-layouts). [Prompt optimizer](https://runware.ai/docs/models/minimax-h3-image/guides/prompt-optimizer) covers turning off the prompt rewrite, and [editing images](https://runware.ai/docs/models/minimax-h3-image/guides/editing-images) and [multi-reference composition](https://runware.ai/docs/models/minimax-h3-image/guides/multi-reference-composition) start from images you already have.

### [The request](https://runware.ai/docs/models/minimax-h3-image/guides/prompting#the-request)

A text-to-image request **needs only the prompt**, and the size is optional. This is the request behind the hero:

**TypeScript**:

```typescript
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'minimax:h3@image',
  positivePrompt: 'A wide hero illustration for a project management app\'s landing page. An isometric 3D diorama of a small open-plan office built on a single square floor slab, floating on a plain pale lavender background and seen from the front-right corner. The slab sits in the right half of the frame, and the left half is empty pale lavender with nothing in it, kept clear for a headline. On the slab, six white desks stand in two rows of three, each with one open laptop and one coral desk chair. Four people work at the desks, and the two desks on the left of the back row are empty, their chairs pushed in. A tall potted monstera stands in the back-left corner of the slab, a low white bookshelf runs along the back-right edge, and a round mustard rug lies under the front row. Smooth matte clay materials in white, lavender, coral and mustard, soft light from the upper left, gentle ambient occlusion where the desks meet the floor. Clean 3D product illustration, no text, no logos.',
  width: 2560,
  height: 1440
})
```

**Python**:

```python
import asyncio
import os

from runware import Runware

async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "minimax:h3@image",
            "positivePrompt": "A wide hero illustration for a project management app's landing page. An isometric 3D diorama of a small open-plan office built on a single square floor slab, floating on a plain pale lavender background and seen from the front-right corner. The slab sits in the right half of the frame, and the left half is empty pale lavender with nothing in it, kept clear for a headline. On the slab, six white desks stand in two rows of three, each with one open laptop and one coral desk chair. Four people work at the desks, and the two desks on the left of the back row are empty, their chairs pushed in. A tall potted monstera stands in the back-left corner of the slab, a low white bookshelf runs along the back-right edge, and a round mustard rug lies under the front row. Smooth matte clay materials in white, lavender, coral and mustard, soft light from the upper left, gentle ambient occlusion where the desks meet the floor. Clean 3D product illustration, no text, no logos.",
            "width": 2560,
            "height": 1440
        })

asyncio.run(main())
```

**cURL**:

```bash
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "imageInference",
      "taskUUID": "7e2c4a91-5b3f-4d8e-a1c6-9f0b3d5e7a24",
      "model": "minimax:h3@image",
      "positivePrompt": "A wide hero illustration for a project management app's landing page. An isometric 3D diorama of a small open-plan office built on a single square floor slab, floating on a plain pale lavender background and seen from the front-right corner. The slab sits in the right half of the frame, and the left half is empty pale lavender with nothing in it, kept clear for a headline. On the slab, six white desks stand in two rows of three, each with one open laptop and one coral desk chair. Four people work at the desks, and the two desks on the left of the back row are empty, their chairs pushed in. A tall potted monstera stands in the back-left corner of the slab, a low white bookshelf runs along the back-right edge, and a round mustard rug lies under the front row. Smooth matte clay materials in white, lavender, coral and mustard, soft light from the upper left, gentle ambient occlusion where the desks meet the floor. Clean 3D product illustration, no text, no logos.",
      "width": 2560,
      "height": 1440
    }
  ]'
```

**CLI**:

```bash
runware run minimax:h3@image \
  positivePrompt="A wide hero illustration for a project management app's landing page. An isometric 3D diorama of a small open-plan office built on a single square floor slab, floating on a plain pale lavender background and seen from the front-right corner. The slab sits in the right half of the frame, and the left half is empty pale lavender with nothing in it, kept clear for a headline. On the slab, six white desks stand in two rows of three, each with one open laptop and one coral desk chair. Four people work at the desks, and the two desks on the left of the back row are empty, their chairs pushed in. A tall potted monstera stands in the back-left corner of the slab, a low white bookshelf runs along the back-right edge, and a round mustard rug lies under the front row. Smooth matte clay materials in white, lavender, coral and mustard, soft light from the upper left, gentle ambient occlusion where the desks meet the floor. Clean 3D product illustration, no text, no logos." \
  width=2560 \
  height=1440
```

**JSON**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "7e2c4a91-5b3f-4d8e-a1c6-9f0b3d5e7a24",
  "model": "minimax:h3@image",
  "positivePrompt": "A wide hero illustration for a project management app's landing page. An isometric 3D diorama of a small open-plan office built on a single square floor slab, floating on a plain pale lavender background and seen from the front-right corner. The slab sits in the right half of the frame, and the left half is empty pale lavender with nothing in it, kept clear for a headline. On the slab, six white desks stand in two rows of three, each with one open laptop and one coral desk chair. Four people work at the desks, and the two desks on the left of the back row are empty, their chairs pushed in. A tall potted monstera stands in the back-left corner of the slab, a low white bookshelf runs along the back-right edge, and a round mustard rug lies under the front row. Smooth matte clay materials in white, lavender, coral and mustard, soft light from the upper left, gentle ambient occlusion where the desks meet the floor. Clean 3D product illustration, no text, no logos.",
  "width": 2560,
  "height": 1440
}
```

- `positivePrompt` takes **1 to 32,000 characters**. With `settings.promptOptimizer` on, which is the default, MiniMax **rewrites the prompt into a detailed scene description** before generating. The response does not include the rewritten version.
- The size comes from `resolution` or from `width` and `height`, **never both**.
- `width` and `height` **go together**, and a request with only one of them is rejected.

> [!NOTE]
> [MiniMax H3 Image Highspeed](https://runware.ai/docs/models/minimax-h3-image-highspeed) takes the same parameters and limits, so any request in this guide runs on it with only `model` changed to `minimax:h3@image-highspeed`. It generates faster and bills its image tokens at a higher rate.

### [Choosing the size](https://runware.ai/docs/models/minimax-h3-image/guides/prompting#choosing-the-size)

The three ways to size a request answer different questions. A preset sets **how many pixels** and leaves the shape to the model, `width` and `height` set **exactly which frame**, and leaving the size out returns 4K.

#### [Resolution presets](https://runware.ai/docs/models/minimax-h3-image/guides/prompting#resolution-presets)

`resolution` takes `1K`, `2K` or `4K`, and **the model sets the width and height itself**. With no reference image it **picks the aspect ratio from the prompt**, so a preset request should name its orientation in words. The fitness story below asked for "a vertical 9:16 story image" at `2K` and sent no dimensions.

![A woman with long braided hair in a sage green top and black leggings standing in tree pose on a cork mat in a bright studio, in the lower part of a vertical frame below an empty white wall](https://runware.ai/docs/assets/output-preset.DkrVe0B1_ZoA1h8.jpg)

*2K preset, returned at 1536 × 2720*

> **Prompt**: A vertical 9:16 story image for a fitness app's morning mobility series. A woman in her thirties with long braided hair, wearing a sage green sports top and black leggings, stands in tree pose on a cork yoga mat, facing the camera, her palms pressed together at her chest and her right foot resting against her left inner thigh. Her whole figure, from her head to her feet, fits in the lower two thirds of the frame, with the mat under her feet. The same plain white studio wall continues up through the upper third of the frame, with nothing on it, kept clear for a title card. Pale oak floor, soft morning light from a tall window out of frame on the left, a soft shadow falling to the right. Natural skin texture, true-to-life color, clean fitness editorial photography, no text, no logos.

**Read the dimensions** from the file. This 9:16 request came back at 1536 × 2720, close to 9:16 but not exact, so a layout that needs the exact ratio should send `width` and `height`. With reference images, the preset follows their ratio instead, which [editing images](https://runware.ai/docs/models/minimax-h3-image/guides/editing-images) covers.

#### [Exact sizes](https://runware.ai/docs/models/minimax-h3-image/guides/prompting#exact-sizes)

Send `width` and `height` when **the image fills a fixed slot**, such as a link preview or a banner. The pair is **generated exactly as given**, never scaled or rounded, so a 1200 × 630 request returns a 1200 × 630 file with no crop step. It has to fit three limits:

- The area is **between 655,360 and 20,000,000 pixels**.
- Each side is **between 468 and 7,745 pixels**.
- The aspect ratio is **between 1:3 and 3:1**.

The area floor **rules out small renders**. It equals 1024 × 640, so 1080 × 1080 passes and 800 × 800 is rejected. At the top, the largest square is 4472 × 4472.

![A modern timber cabin with a glowing glass front on the right third of a wide frame, seen across a still lake at blue hour, with open water and evening sky across the left half](https://runware.ai/docs/assets/output-exact-size.DMwa3-nx_1LlzLo.jpg)

*1200 × 630, as requested*

> **Prompt**: A wide link preview image for a vacation rental listing, the card shown when the listing is shared. A modern timber cabin with a full-height glass front and a cedar deck stands at the edge of a pine forest on the right third of the frame, seen at eye level from across a calm lake. Warm interior light glows through the glass. The left half of the frame is still water and pale evening sky with nothing in it, kept clear for the listing title. Blue-hour light, a faint reflection of the cabin on the water, soft mist over the far shore. Photoreal architectural photography, no text, no people.

Choose the size **before writing the layout**. Positions such as "the right third" and "the left half" are measured against the frame you send, so a layout written for this wide card has to be rewritten for a vertical slot.

#### [Leaving the size out](https://runware.ai/docs/models/minimax-h3-image/guides/prompting#leaving-the-size-out)

A request with no `resolution`, `width` or `height` **comes back at 4K**, at a ratio the model picks. **Name the orientation in the prompt** the same way as with a preset.

![Painterly concept art of a stilted wooden fishing village on a green cliff above a turquoise bay, with three sailboats at a pier on the left and a stone watchtower on the headland to the right](https://runware.ai/docs/assets/output-no-size.C1iIPxHo_ZceDSO.jpg)

*No size sent, returned at 5472 × 3072*

> **Prompt**: Wide landscape-format environment concept art for an open-world adventure game. A fishing village of stilted wooden houses climbs a steep green cliff above a turquoise bay, linked by rope bridges and narrow stairways. Three small sailboats are moored at a long wooden pier in the foreground on the left, and a stone watchtower stands on the headland on the right. Seen from the water at a low angle, with the village filling the center of the frame. Late afternoon sun from the right, warm light on the house walls, cool blue shadows in the cliff crevices, sea spray around the rocks below. Painterly game concept art with crisp detail in the foreground and soft atmospheric haze in the distance, no text, no characters.

**4K uses about four times the image tokens** of `1K` or `2K`, and those two use about the same. Send `2K` when the image will never be shown larger, and leave the size out when you want the full 4K.

### [Structuring the prompt](https://runware.ai/docs/models/minimax-h3-image/guides/prompting#structuring-the-prompt)

MiniMax's advice for this model is to **put the task before the style** and **the layout before the details**. The two product tiles below share a subject and a size. The first prompt is one line, and the second plans the image in that order.

![Three plain running shoes in gray, white and pale blue on a wooden shelf against a dark gray wall](https://runware.ai/docs/assets/output-structure-short.B7cM4NNq_2jbrpH.jpg)

*Short prompt*

> **Prompt**: Three plain running shoes on a shelf, no logos or stripes.

![Three running shoes in side profile with their toes pointing left, coral, slate blue and off-white from left to right, evenly spaced on a pale concrete shelf below an empty warm gray wall](https://runware.ai/docs/assets/output-structure-full.c8OIf7y__Z14gskt.jpg)

*Structured prompt*

> **Prompt**: A square product tile for an online running store's new arrivals page. Three running shoes stand in a single row on a floating pale concrete shelf, evenly spaced, shown in side profile with every toe pointing left, from left to right in coral, slate blue and off-white. The camera is at shelf height, looking straight on. The row sits in the lower half of the frame, and the upper half is a plain warm gray wall with nothing on it. Each shoe has an engineered knit upper with a visible weave, a thick foam midsole with a matte finish and a rubber outsole with a fine tread. Soft diffused light from above and slightly left, a narrow highlight along each midsole, short soft contact shadows on the shelf. Photoreal e-commerce product photography, no text, no logos.

Both went through the prompt optimizer, which **expands a short prompt into a full scene** before generating, so the one-line version still returns a finished product shot. The shoe colors, the way they face, the camera height and the background in it are **choices MiniMax made for you**.

The structured prompt, clause by clause:

**[Task]** A square product tile for an online running store's new arrivals page, **[Layout]** Three running shoes stand in a single row on a floating pale concrete shelf, evenly spaced, shown in side profile with every toe pointing left, from left to right in coral, slate blue and off-white, **[Viewing angle]** The camera is at shelf height, looking straight on, **[Empty space]** The row sits in the lower half of the frame, and the upper half is a plain warm gray wall with nothing on it, **[Details]** Each shoe has an engineered knit upper with a visible weave, a thick foam midsole with a matte finish and a rubber outsole with a fine tread, **[Style]** Soft diffused light from above and slightly left, a narrow highlight along each midsole, short soft contact shadows on the shelf. Photoreal e-commerce product photography, **[Exclusions]** no text, no logos

**Name the task** first. "A square product tile for an online running store's new arrivals page" says what the image is and where it will run before any detail does. A catalog tile and a lifestyle ad of the same shoes call for different framing, and the opening clause is where that gets decided.

Set the layout **before the details**. The count, the order of the colors, the direction the toes point, the camera height and the empty upper half are all settled before a word about knit or foam. Dense layouts such as an infographic follow the same order section by section, which [text and layouts](https://runware.ai/docs/models/minimax-h3-image/guides/text-and-layouts) covers.

Describe the style **through what is visible**. "Soft diffused light from above and slightly left, a narrow highlight along each midsole" names a light source and the surface it falls on, and the model can render both. A word like "premium" leaves the model to guess what premium looks like.

Keep the requirements **free of contradictions**. "Minimalist" next to a list of ten props, or "overcast" next to "hard midday shadows", asks for two images in one prompt. Lead with the details that must be right and cut the ones that do not matter.

#### [Counts and positions](https://runware.ai/docs/models/minimax-h3-image/guides/prompting#counts-and-positions)

Write **every count as a number** and **every position against the frame**. The team photo below lists five people from left to right, one clause each, so every outfit and prop belongs to one person.

![Five colleagues standing in a row in front of a white brick wall: an older bearded man in a navy blazer, a red-haired woman in a mustard sweater holding a laptop, a man in a denim jacket with crossed arms in the middle, a black-haired woman in a green dress with a hand on his shoulder, and a young man in a gray hoodie and glasses holding a tablet](https://runware.ai/docs/assets/output-counts.CT0ZJ4DW_1xkK64.jpg)

> **Prompt**: A team photo for a design studio's About page. Five colleagues stand in a single row in front of a white-painted brick wall, evenly spaced, full length, all facing the camera. From left to right: a tall man in his fifties with a short gray beard, in a navy blazer over a white shirt; a woman in her twenties with a curly red bob, in a mustard sweater, holding a closed laptop against her chest; a man in his thirties in a denim jacket over a white T-shirt, standing in the middle with his arms crossed; a woman in her forties with straight black hair, in a green linen shirt dress, resting one hand on the shoulder of the man in the middle; a young man in a gray hoodie and round glasses, holding a tablet at his side. Shot at eye level with a 35mm lens, the row centered, with an even strip of wall above their heads and pale wooden floor below their feet. Soft even light from a large window on the left, natural skin texture, true-to-life color, editorial team portrait photography, no text, no logos.

Anchor relationships **to the frame** as well. The hand on the shoulder is aimed at "the man in the middle", a place in the frame. "The man to her left" would depend on which way she faces.

### [Tips](https://runware.ai/docs/models/minimax-h3-image/guides/prompting#tips)

1. **Open with the task.** Name what the image is and where it will run before any detail.
    
2. **Plan the layout before the details.** Count, placement, viewing angle and empty space come first, then materials and light.
    
3. **Write counts as numbers and positions against the frame.** "Two rows of three" and "second from the left" leave nothing for the model to settle, and "her left" depends on which way she faces.
    
4. **Describe style in visible terms.** Name the light and the materials instead of "premium" or "high-end".
    
5. **Cut contradictions.** Two clauses that disagree ask for two images. Keep the one that matters.
    
6. **End with what to leave out.** Exclusions such as "no text, no logos" go in the prompt itself, as its last clause.
    
7. **Name the orientation when the model picks the shape.** With a preset or no size at all, the prompt decides the aspect ratio.
    
8. **Send exact dimensions for fixed slots.** `width` and `height` come back exactly as sent, so the file needs no crop.
    
9. **Send a preset below 4K when you can.** `1K` and `2K` use about the same image tokens, and a request with no size returns 4K at about four times as many.