---
title: Text and design — Ideogram 4.6 | Runware Docs
url: https://runware.ai/docs/models/ideogram-4-6/guides/text-and-design
description: "How to use Ideogram 4.6 for designs where the words have to be right: quoted copy, type hierarchy, placement, dense layouts at 4K and non-Latin scripts."
---
### [Introduction](https://runware.ai/docs/models/ideogram-4-6/guides/text-and-design#introduction)

An image model that learns lettering as texture knows what text looks like, not how a word is spelled, so a poster comes back with **a headline that almost reads**. Ideogram builds its models around the opposite: text that is spelled right and placed where you asked.

Ideogram 4.6 carries that into event posters, packaging, app screens and printed menus, and at up to 4096 pixels on a side it renders **small print at a size a printer can use**. The poster below is one prompt, with no text added afterward.

![A film festival poster with the headline CINEMA UNDER THE STARS on three lines, the dates below it, an indigo and coral duotone photo of a crowd watching an outdoor screen, and a coral footer with the venue and web address](https://runware.ai/docs/assets/hero.BF-64NwD_Z8Fjes.jpg)

*2720 × 4096*

> **Prompt**: A printed poster for an outdoor summer film festival. A photograph of a crowd on picnic blankets in a city park at dusk, watching a large inflatable screen, fills the lower two thirds, printed as a duotone of deep indigo and warm coral. Across the top, the headline "CINEMA UNDER THE STARS" in huge heavy condensed sans-serif capitals in cream, stacked on three lines, and directly below it "Every Friday · July 4 – August 29" in a smaller medium weight. At the bottom, a solid coral strip with "Free entry · Riverside Park · cinemaunderthestars.org" in indigo. Clean grid, sharp print quality.

This guide covers quoting exact copy, building a type hierarchy, placing text on a layout, dense layouts at 4K and non-Latin scripts. Every prompt here runs with **Magic Prompt off**, so the layout that comes back is the one the prompt describes.

### [Quoting exact copy](https://runware.ai/docs/models/ideogram-4-6/guides/text-and-design#quoting-exact-copy)

Put every word that must appear **inside double quotes**. The quotes mark the difference between copy to render and a description of the image, and they are how the model knows where one line ends and the next begins.

![An off-white app subscription screen with a speech bubble and globe illustration, the headline Speak Spanish in 10 minutes a day, three checked feature lines, a $9.99 / month card and a dark green Start free trial button](https://runware.ai/docs/assets/quoted.DfjEOe26_Z6sSr3.jpg)

> **Prompt**: A clean mobile app subscription screen for a language learning app, shown flat and full-frame with no phone frame: a warm off-white background, a friendly flat illustration of a speech bubble and a small globe in the upper third, the headline "Speak Spanish in 10 minutes a day" in a bold rounded sans-serif below it, three short lines with green check marks reading "Daily lessons that fit your commute", "Practice with real conversations" and "Track your streak", a pale green card reading "$9.99 / month" with "Cancel anytime" under it in small gray type, and a wide dark green button reading "Start free trial" at the bottom.

**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: 'ideogram:4.6@0',
  positivePrompt: 'A clean mobile app subscription screen for a language learning app, shown flat and full-frame with no phone frame: a warm off-white background, a friendly flat illustration of a speech bubble and a small globe in the upper third, the headline "Speak Spanish in 10 minutes a day" in a bold rounded sans-serif below it, three short lines with green check marks reading "Daily lessons that fit your commute", "Practice with real conversations" and "Track your streak", a pale green card reading "$9.99 / month" with "Cancel anytime" under it in small gray type, and a wide dark green button reading "Start free trial" at the bottom.',
  width: 1152,
  height: 2048,
  settings: {
    magicPrompt: 'off'
  }
})
```

**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": "ideogram:4.6@0",
            "positivePrompt": "A clean mobile app subscription screen for a language learning app, shown flat and full-frame with no phone frame: a warm off-white background, a friendly flat illustration of a speech bubble and a small globe in the upper third, the headline \"Speak Spanish in 10 minutes a day\" in a bold rounded sans-serif below it, three short lines with green check marks reading \"Daily lessons that fit your commute\", \"Practice with real conversations\" and \"Track your streak\", a pale green card reading \"$9.99 / month\" with \"Cancel anytime\" under it in small gray type, and a wide dark green button reading \"Start free trial\" at the bottom.",
            "width": 1152,
            "height": 2048,
            "settings": {
                "magicPrompt": "off"
            }
        })

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": "c3a8f1e6-7d24-4b90-9e5a-2f6b8d1c4a73",
      "model": "ideogram:4.6@0",
      "positivePrompt": "A clean mobile app subscription screen for a language learning app, shown flat and full-frame with no phone frame: a warm off-white background, a friendly flat illustration of a speech bubble and a small globe in the upper third, the headline \"Speak Spanish in 10 minutes a day\" in a bold rounded sans-serif below it, three short lines with green check marks reading \"Daily lessons that fit your commute\", \"Practice with real conversations\" and \"Track your streak\", a pale green card reading \"$9.99 / month\" with \"Cancel anytime\" under it in small gray type, and a wide dark green button reading \"Start free trial\" at the bottom.",
      "width": 1152,
      "height": 2048,
      "settings": {
        "magicPrompt": "off"
      }
    }
  ]'
```

**CLI**:

```bash
runware run ideogram:4.6@0 \
  positivePrompt="A clean mobile app subscription screen for a language learning app, shown flat and full-frame with no phone frame: a warm off-white background, a friendly flat illustration of a speech bubble and a small globe in the upper third, the headline \"Speak Spanish in 10 minutes a day\" in a bold rounded sans-serif below it, three short lines with green check marks reading \"Daily lessons that fit your commute\", \"Practice with real conversations\" and \"Track your streak\", a pale green card reading \"\$9.99 / month\" with \"Cancel anytime\" under it in small gray type, and a wide dark green button reading \"Start free trial\" at the bottom." \
  width=1152 \
  height=2048 \
  settings.magicPrompt=off
```

**JSON**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "c3a8f1e6-7d24-4b90-9e5a-2f6b8d1c4a73",
  "model": "ideogram:4.6@0",
  "positivePrompt": "A clean mobile app subscription screen for a language learning app, shown flat and full-frame with no phone frame: a warm off-white background, a friendly flat illustration of a speech bubble and a small globe in the upper third, the headline \"Speak Spanish in 10 minutes a day\" in a bold rounded sans-serif below it, three short lines with green check marks reading \"Daily lessons that fit your commute\", \"Practice with real conversations\" and \"Track your streak\", a pale green card reading \"$9.99 / month\" with \"Cancel anytime\" under it in small gray type, and a wide dark green button reading \"Start free trial\" at the bottom.",
  "width": 1152,
  "height": 2048,
  "settings": {
    "magicPrompt": "off"
  }
}
```

Give every quoted string **its own place and its own style** in the prompt. Words outside the quotes are read as description, so "green check marks" came back as drawn check marks rather than as text.

The screen is 1152 × 2048, a 9:16 frame on the 32-pixel grid. Any size on that grid works, so **generate at the shape of the screen** the design is for instead of cropping a square.

### [Building a type hierarchy](https://runware.ai/docs/models/ideogram-4-6/guides/text-and-design#building-a-type-hierarchy)

A layout reads in order because its lines differ in size, weight and style. Describe that **for each line**, from top to bottom.

![A kraft paper bag of dog food on an oak floor, printed in forest green with TRAILHOUND at the top, Salmon & Sweet Potato in a large serif above a line drawing of a running dog, and GRAIN-FREE · 12 LB (5.4 KG) at the bottom](https://runware.ai/docs/assets/label.-T0XAGHu_1z1r83.jpg)

> **Prompt**: E-commerce product photograph of a matte kraft paper bag of premium dog food standing upright on a light oak floor against a plain warm white wall. The bag carries a clear type hierarchy printed in dark forest green: the brand name "TRAILHOUND" in small wide letter-spaced sans-serif capitals at the top, the recipe "Salmon & Sweet Potato" in a large bold serif in the middle above a simple line drawing of a running dog, and "GRAIN-FREE · 12 LB (5.4 KG)" in tiny sans-serif capitals at the bottom. Soft daylight from the left, crisp print detail.

The bag has three levels, and the prompt gives each one **a size, a style and a position**. Give the largest size to **the line a shopper reads first**, here the recipe. "A clear type hierarchy" tells the model the sizes are meant to contrast.

Describe type **by its traits**: serif or sans-serif, weight, width, capitals or lowercase, letter spacing.

### [Placing text on the layout](https://runware.ai/docs/models/ideogram-4-6/guides/text-and-design#placing-text-on-the-layout)

For a layout with several blocks of copy, **anchor each block to a region** of the frame, such as the left half, a panel or a footer strip.

![A square conference card with a photo of a smiling silver-haired woman on the left and a navy panel on the right with a SPEAKER tag, the name Maya Okafor, her title, the talk title and a footer reading DEVSUMMIT 2027 · Oct 14–16 · Austin](https://runware.ai/docs/assets/speaker-card.BVS3efRA_2r3Ue5.jpg)

> **Prompt**: A square social media speaker announcement card for a software conference. The left half is a photograph of a smiling woman in her forties with short silver hair and a black blazer against a soft blue backdrop. The right half is a solid deep navy panel: at the top a small electric blue tag reading "SPEAKER", below it the name "Maya Okafor" in a large bold white sans-serif, then "VP of Engineering, Northwind Labs" in a smaller light gray weight, then the talk title "Shipping AI features without breaking production" in medium white type across three lines. Along the bottom of the navy panel, a thin electric blue rule and "DEVSUMMIT 2027 · Oct 14–16 · Austin" in small white capitals.

The prompt reads like **a layout spec**: the photo takes the left half, the navy panel the right, and inside the panel each line has a slot from top to bottom, down to the rule above the footer. Every block has a slot, which is what makes the prompt a template: change the name, the title and the photo to make the next speaker's card.

### [Dense layouts at 4K](https://runware.ai/docs/models/ideogram-4-6/guides/text-and-design#dense-layouts-at-4k)

A menu or a spec sheet packs many short strings into one frame, and at print size the small lines are what break first. Organize the prompt **the way the layout is read**: describe the shape of one item once, then list every item as labeled fields in reading order.

![A cream brunch menu headed HARBOR & HEARTH with three sections, EGGS, GRIDDLE and SIDES, each listing three dishes with a dotted leader to a right-aligned price and a small italic line at the bottom, with a magnified inset of the italic line at the foot of the page](https://runware.ai/docs/assets/menu.Cu61Gwpc_UWQsQ.jpg)

*2720 × 4096*

> **Prompt**: A printed one-page brunch menu for a neighborhood restaurant on cream textured paper, shown flat and full-frame, dark brown ink, generous margins. At the top, the restaurant name "HARBOR & HEARTH" in a bold serif, and below it "Brunch · Saturday & Sunday · 9 am – 2 pm" in small italic. Below that, three sections, each under a small letter-spaced capital heading and a thin rule. Every dish sits on one line: the dish name in a regular serif on the left and its price aligned right, with a thin dotted leader between them. Section "EGGS" lists three dishes. Dish 1: name "Shakshuka", price "$16". Dish 2: name "Crab Benedict", price "$22". Dish 3: name "Garden Omelet", price "$15". Section "GRIDDLE" lists three dishes. Dish 4: name "Buttermilk Pancakes", price "$13". Dish 5: name "Brioche French Toast", price "$14". Dish 6: name "Chicken & Waffles", price "$19". Section "SIDES" lists three dishes. Dish 7: name "Thick-Cut Bacon", price "$6". Dish 8: name "Smashed Potatoes", price "$5". Dish 9: name "Seasonal Fruit", price "$7". At the bottom, one line in small italic: "Ask about our seasonal specials · Gluten-free bread available".

After stating the layout of a dish once, the prompt lists **every dish as numbered, labeled fields**, section by section. The labels keep each string attached to its dish, so the nine prices land on the right nine lines. This menu also ran at `high`, the tier for the version that ships.

At 2720 × 4096, the italic line at the foot of the page is **real text with clean letterforms**, sized to read on a printed page, and the dotted leaders stay crisp. A 2K render of the same 2:3 page holds about a third of those pixels, so render dense print layouts at the size they will be printed.

**Keep each item to a name and a price.** Names, prices and a short line of small print render reliably. A one-line description under each of nine dishes is where a list this long drifts, with descriptions landing on the wrong dish, so set descriptions and body copy in your own layout on top of the image.

### [Non-Latin scripts](https://runware.ai/docs/models/ideogram-4-6/guides/text-and-design#non-latin-scripts)

Quoted copy can be in another script. **Paste the text in its own script**, and describe its direction and style the same way you would for English.

![A blush pink skincare ad with a frosted white serum bottle on a pink stone pedestal, a Korean headline and product line across the top and a deep rose badge at the bottom right](https://runware.ai/docs/assets/script-korean.DWlXDUlN_1qUpC0.jpg)

*Korean*

> **Prompt**: A 4:5 social media ad for a Korean skincare brand: a tall frosted white serum bottle with a rose gold cap stands on a pale pink stone pedestal against a soft blush background, with a few drops of water on the stone. Across the top, the Korean headline "물광 피부의 시작" in a large clean bold sans-serif in deep rose, and below it "히알루론산 수분 세럼 50ml" in a smaller light weight. A small rounded deep rose badge at the bottom right reads "신제품" in white. Soft diffused studio light, clean and minimal.

![A deep teal sale banner with black headphones on the left and an Arabic headline, a yellow discount line and a white button on the right](https://runware.ai/docs/assets/script-arabic.BrH7r7rB_ZNYVy4.jpg)

*Arabic, right to left*

> **Prompt**: A 4:5 social media sale banner for an electronics store with Arabic text in a right-to-left layout: a pair of matte black over-ear headphones floats on the left against a deep teal background with a soft spotlight. On the right, the headline "عروض نهاية الأسبوع" in large bold Arabic lettering in white, below it "خصم 30% على السماعات" in a smaller weight in bright yellow, and a white rounded button reading "تسوق الآن" in deep teal. Modern, high contrast, crisp edges.

**Write the direction into the prompt.** The Arabic banner asked for a right-to-left layout and got one, and the discount kept the Western digits it was written with, so type digits in the form the design should print.

**Have a native speaker check** every non-Latin result before it ships. A wrong character in a script you do not read looks exactly like a right one.

### [Tips](https://runware.ai/docs/models/ideogram-4-6/guides/text-and-design#tips)

1. **Quote every word that must appear.** The quotes separate the copy from the description of the image.
    
2. **Give each line a size, a style and a place.** Describe the hierarchy line by line, from top to bottom.
    
3. **Anchor blocks to regions.** A half, a panel or a footer strip gives every piece of copy a slot, and a layout with fixed slots can be reused as a template.
    
4. **State a repeated pattern once.** "The dish name on the left and its price aligned right, with a thin dotted leader between them" covers every item, and numbered, labeled fields keep each string on its line.
    
5. **Render print layouts at print size.** Small type needs the pixels, and 4096 on a side gives them.
    
6. **Turn Magic Prompt off for layouts.** The layout that comes back is then the one the prompt describes.
    
7. **Proofread before shipping.** Check prices, dates and every non-Latin line, ideally with a native speaker.
    

To hold a design to exact brand colors, see [Brand colors](https://runware.ai/docs/models/ideogram-4-6/guides/brand-colors).