---
title: Ideogram 4.0 | Runware Docs
url: https://runware.ai/docs/models/ideogram-4-0
description: Open-weight design-focused text-to-image model with strong typography, layout control, transparent backgrounds, and 2K output
---
# Ideogram 4.0

![Ideogram 4.0](https://assets.runware.ai/covers/ideogram-4-0.jpg)

Ideogram 4.0 is Ideogram's most capable text-to-image model for design-heavy image generation. It is built for frontier text rendering across languages, structured prompt control through natural language or JSON, bounding-box layout control, transparent background generation, and high-fidelity 2K output. It is well suited to posters, branded graphics, packaging, product visuals, typography-led compositions, and other workflows where design precision matters as much as visual quality.

- **Status**: live
- **ID**: `ideogram:4@0`
- Try in Playground
- **Creator**: Ideogram
- **Release Date**: June 3, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Image, Checkpoint

## Pricing

$0.03 from, per run · ~18s per request

**Rates** (per run)

- Turbo: `$0.03`
- Default: `$0.06`
- Quality: `$0.10`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/ideogram-4-0/examples#example-municipal-sewer-crew-sticker-pack) · 1440p: `$0.06` (~25s)
- [text-to-image](https://runware.ai/docs/models/ideogram-4-0/examples#example-thermal-battery-video-thumbnail) · 1440p: `$0.06` (~18s)
- [text-to-image](https://runware.ai/docs/models/ideogram-4-0/examples#example-alpine-survival-game-key-art) · 1440p: `$0.06` (~18s)
- [structured-prompt](https://runware.ai/docs/models/ideogram-4-0/examples#example-community-radio-host-campaign-portrait) · 1792×2240: `$0.10` (~18s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Provide exactly one of: `positivePrompt`, `settings.structuredPrompt`.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `2K (1:1)` | `2048x2048` |
| `2K (1:2)` | `1440x2880` |
| `2K (2:1)` | `2880x1440` |
| `2K (2:3)` | `1664x2496` |
| `2K (3:2)` | `2496x1664` |
| `2K (4:5)` | `1792x2240` |
| `2K (5:4)` | `2240x1792` |
| `2K (9:16)` | `1440x2560` |
| `2K (16:9)` | `2560x1440` |
| `2K (5:8)` | `1600x2560` |
| `2K (8:5)` | `2560x1600` |
| `2K (3:4)` | `1728x2304` |
| `2K (4:3)` | `2304x1728` |
| `2K (9:22)` | `1296x3168` |
| `2K (22:9)` | `3168x1296` |
| `2K (9:23)` | `1152x2944` |
| `2K (23:9)` | `2944x1152` |
| `2K (3:8)` | `1248x3328` |
| `2K (8:3)` | `3328x1248` |
| `2K (5:12)` | `1280x3072` |
| `2K (12:5)` | `3072x1280` |
| `2K (1:3)` | `1024x3072` |
| `2K (3:1)` | `3072x1024` |

## Notes

Ideogram 4.0 is driven by a structured JSON prompt. You can drive it two ways, and each request must use exactly one:

- **Natural language** via `positivePrompt`. It's automatically expanded into the structured form before generation.
- **Structured JSON** via `settings.structuredPrompt`. Passed to the model directly, skipping that expansion, for explicit control over composition, text, and layout.

See the `settings.structuredPrompt` parameter for the field reference, the [Structured prompts](https://runware.ai/docs/models/ideogram-4-0/guides/structured-prompts) guide for when to use each mode, and [Text and design output](https://runware.ai/docs/models/ideogram-4-0/guides/text-and-design) for typography and layout.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/ideogram-4-0#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/ideogram-4-0#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/ideogram-4-0#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Image output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/ideogram-4-0#request-outputformat)

- **Type**: `string`
- **Default**: `JPG`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`JPG\`: Best for photorealistic images with smaller file sizes (no transparency).
- \`PNG\`: Lossless compression, supports high quality and transparency (alpha channel).
- \`WEBP\`: Modern format providing superior compression and transparency support.

> [!NOTE]
> \*\*Transparency\*\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \`PNG\`, \`WEBP\`, \`TIFF\`). \`JPG\` does not support transparency.

**Allowed values**: `JPG` `PNG` `WEBP`

### [outputQuality](https://runware.ai/docs/models/ideogram-4-0#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/ideogram-4-0#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/ideogram-4-0#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/ideogram-4-0#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/ideogram-4-0#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (1 property)`

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/ideogram-4-0#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

### [ttl](https://runware.ai/docs/models/ideogram-4-0#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/ideogram-4-0#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/ideogram-4-0#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `20`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/ideogram-4-0#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `ideogram:4@0`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/ideogram-4-0#request-positiveprompt)

- **Type**: `string`
- **Min**: `2`

Text prompt describing elements to include in the generated output. Automatically expanded into a structured prompt before generation.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/ideogram-4-0#request-width)

- **Type**: `integer`
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/ideogram-4-0#request-height)

- **Type**: `integer`
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [copyrightDetection](https://runware.ai/docs/models/ideogram-4-0#request-settings-copyrightdetection)

- **Path**: `settings.copyrightDetection`
- **Type**: `boolean`

Opt into post-generation copyright detection using Hive likeness and logo checks.

### [renderingSpeed](https://runware.ai/docs/models/ideogram-4-0#request-settings-renderingspeed)

- **Path**: `settings.renderingSpeed`
- **Type**: `string`
- **Default**: `DEFAULT`

Generation speed/quality tradeoff.

**Allowed values**:

- `TURBO` Fastest generation.
- `DEFAULT` Balanced speed and quality.
- `QUALITY` Best quality.

### [structuredPrompt](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt)

- **Path**: `settings.structuredPrompt`
- **Type**: `object (16 properties)`

`settings.structuredPrompt` is a structured prompt passed to the model directly. A natural-language `positivePrompt` is automatically expanded into this structured form before generation, so use `settings.structuredPrompt` when you want explicit control over the result. It must include `high_level_description` and `compositional_deconstruction`, with its `background` and `elements`. Extra fields beyond the documented ones are accepted.

A few rules the field definitions don't capture:

- **Include exactly one of `art_style` or `photo`** in `style_description`, depending on whether the image is illustrated or photographic.
- **Key order matters** — keep fields in the order the model expects, as shown in the example. The `style_description` order also differs between photo and non-photo images.
- **`bbox` is row-first** — `[ymin, xmin, ymax, xmax]` on a 0–1000 top-left canvas, so build it as `[top, left, bottom, right]`.

**Examples**:

```json
"settings": {
  "structuredPrompt": {
    "high_level_description": "A vintage travel poster of a coastal town at sunset.",
    "style_description": {
      "aesthetics": "Retro mid-century travel poster",
      "lighting": "Warm golden-hour glow",
      "medium": "Screen-printed poster",
      "art_style": "Flat vector illustration",
      "color_palette": ["#E8A33D", "#2E5E78", "#F2E9D8"]
    },
    "compositional_deconstruction": {
      "background": "Mediterranean harbor under a warm sunset sky with soft golden light.",
      "elements": [
        {"type": "obj", "bbox": [400, 120, 760, 880], "desc": "White sailboats moored along the stone pier"},
        {"type": "text", "bbox": [60, 100, 200, 900], "text": "VISIT THE COAST", "desc": "Bold retro headline across the top"}
      ]
    }
  }
}
```

#### [compositional\_deconstruction](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-compositional_deconstruction)

- **Path**: `settings.structuredPrompt.compositional_deconstruction`
- **Type**: `object (7 properties)`
- **Required**: true

Scene breakdown into background and individual elements.

##### [background](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-compositional_deconstruction-background)

- **Path**: `settings.structuredPrompt.compositional_deconstruction.background`
- **Type**: `string`
- **Required**: true

Environment, framing, and lighting context.

##### [elements](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-compositional_deconstruction-elements)

- **Path**: `settings.structuredPrompt.compositional_deconstruction.elements`
- **Type**: `array of objects (5 properties)`
- **Required**: true

Objects and text to place in the scene.

##### [type](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-compositional_deconstruction-elements-type)

- **Path**: `settings.structuredPrompt.compositional_deconstruction.elements.type`
- **Type**: `string`

Element type. Use 'obj' for a visual object and 'text' for rendered text.

**Allowed values**: `obj` `text`

##### [bbox](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-compositional_deconstruction-elements-bbox)

- **Path**: `settings.structuredPrompt.compositional_deconstruction.elements.bbox`
- **Type**: `array of integers`
- **Min**: `0`
- **Max**: `1000`
- **Min items**: `items: 4`

Element placement as \[ymin, xmin, ymax, xmax\].

##### [color\_palette](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-compositional_deconstruction-elements-color_palette)

- **Path**: `settings.structuredPrompt.compositional_deconstruction.elements.color_palette`
- **Type**: `array of strings`

Hex colors for this element.

##### [desc](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-compositional_deconstruction-elements-desc)

- **Path**: `settings.structuredPrompt.compositional_deconstruction.elements.desc`
- **Type**: `string`

Detailed description of the element.

##### [text](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-compositional_deconstruction-elements-text)

- **Path**: `settings.structuredPrompt.compositional_deconstruction.elements.text`
- **Type**: `string`
- **Min**: `1`

Text content to render. Only applies when `type` is 'text'.

#### [high\_level\_description](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-high_level_description)

- **Path**: `settings.structuredPrompt.high_level_description`
- **Type**: `string`
- **Required**: true

One or two sentences describing the full image, including subject and style.

#### [style\_description](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-style_description)

- **Path**: `settings.structuredPrompt.style_description`
- **Type**: `object (6 properties)`

Styling guidance for the image.

##### [aesthetics](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-style_description-aesthetics)

- **Path**: `settings.structuredPrompt.style_description.aesthetics`
- **Type**: `string`

Overall aesthetic direction.

##### [art\_style](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-style_description-art_style)

- **Path**: `settings.structuredPrompt.style_description.art_style`
- **Type**: `string`

Art style for non-photographic images.

##### [color\_palette](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-style_description-color_palette)

- **Path**: `settings.structuredPrompt.style_description.color_palette`
- **Type**: `array of strings`

Hex colors guiding the overall palette.

##### [lighting](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-style_description-lighting)

- **Path**: `settings.structuredPrompt.style_description.lighting`
- **Type**: `string`

Lighting setup and mood.

##### [medium](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-style_description-medium)

- **Path**: `settings.structuredPrompt.style_description.medium`
- **Type**: `string`

Artistic medium or capture format.

##### [photo](https://runware.ai/docs/models/ideogram-4-0#request-settings-structuredprompt-style_description-photo)

- **Path**: `settings.structuredPrompt.style_description.photo`
- **Type**: `string`

Photographic style for photo-realistic images.

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/ideogram-4-0#request-advancedfeatures-watermark)

- **Path**: `advancedFeatures.watermark`
- **Type**: `object (6 properties)`

Configuration object for adding watermarks to generated videos. Watermarks can be applied using either text or image content with customizable positioning and appearance. You must provide either `text` or `image` content for the watermark, but not both.

**Text watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "© 2025 Company",
    "displayPosition": "bottom-right",
    "opacity": 0.6,
    "fontColor": "#ffffff",
    "bgColor": "#000000"
  }
}
```

**Image watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "image": "c64351d5-4c59-42f7-95e1-eace013eddab",
    "displayPosition": "top-left",
    "opacity": 0.6
  }
}
```

**Tiled watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "PREVIEW",
    "tiled": true,
    "opacity": 0.4,
    "fontColor": "#cccccc"
  }
}
```

#### [text](https://runware.ai/docs/models/ideogram-4-0#request-advancedfeatures-watermark-text)

- **Path**: `advancedFeatures.watermark.text`
- **Type**: `string`
- **Min**: `2`
- **Max**: `32`

Watermark text.

#### [image](https://runware.ai/docs/models/ideogram-4-0#request-advancedfeatures-watermark-image)

- **Path**: `advancedFeatures.watermark.image`
- **Type**: `string`

Watermark image (UUID, URL, Data URI, or Base64).

#### [displayPosition](https://runware.ai/docs/models/ideogram-4-0#request-advancedfeatures-watermark-displayposition)

- **Path**: `advancedFeatures.watermark.displayPosition`
- **Type**: `string`

Watermark position.

**Allowed values**: `top-left` `top-center` `top-right` `center-left` `center-center` `center-right` `bottom-left` `bottom-center` `bottom-right` `tiled`

#### [opacity](https://runware.ai/docs/models/ideogram-4-0#request-advancedfeatures-watermark-opacity)

- **Path**: `advancedFeatures.watermark.opacity`
- **Type**: `float`
- **Min**: `0.1`
- **Max**: `1`
- **Step**: `0.01`

Watermark opacity.

#### [fontColor](https://runware.ai/docs/models/ideogram-4-0#request-advancedfeatures-watermark-fontcolor)

- **Path**: `advancedFeatures.watermark.fontColor`
- **Type**: `string`

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/ideogram-4-0#request-advancedfeatures-watermark-bgcolor)

- **Path**: `advancedFeatures.watermark.bgColor`
- **Type**: `string`

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/ideogram-4-0#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/ideogram-4-0#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [imageUUID](https://runware.ai/docs/models/ideogram-4-0#response-imageuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/ideogram-4-0#response-imageurl)

- **Type**: `string`
- **Format**: `uri`

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/ideogram-4-0#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/ideogram-4-0#response-imagedatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output image.

### [NSFWContent](https://runware.ai/docs/models/ideogram-4-0#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/ideogram-4-0#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

### [structuredPrompt](https://runware.ai/docs/models/ideogram-4-0#response-structuredprompt)

- **Type**: `object`

Structured prompt the model used for the generation. A natural-language `positivePrompt` is expanded into this form, which can be sent back as `settings.structuredPrompt` to iterate.

## Examples

### text-to-image (text-to-image)

![Municipal Sewer Crew Sticker Pack](https://assets.runware.ai/examples/ideogram-4-0/3fee7637-f61d-47d5-b7b4-76e6efd104b0.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "9ccbb280-edc4-4e20-9e3f-e2c86da6b206",
  "model": "ideogram:4@0",
  "positivePrompt": "Create a finished, print-ready landscape sticker sheet for a municipal sewer inspection crew, shown straight-on as clean standalone artwork rather than a product mockup. Arrange ten distinct kiss-cut decals in a balanced grid with generous spacing and thick white die-cut borders. The hero sticker must render the exact phrase “FLOW KNOWS” in large, perfectly legible condensed block lettering, integrated with a simplified underground pipe cross-section. Surround it with bold pictogram stickers depicting a robotic pipe-crawler camera, an open manhole with radiating scan lines, a high-pressure jet nozzle, a gas detector, crossed valve keys, a rubber safety boot, a utility map pin, a traffic cone, and a friendly water droplet wearing a hard hat. Use a visually distinctive late-1990s public-works safety manual aesthetic: crisp flat vector shapes, technical diagram details, chunky outlines, small halftone shadows, fluorescent chartreuse, cobalt blue, safety orange, white, and near-black. Energetic, competent, slightly playful, and highly legible at small sizes. Keep every icon stylistically consistent and fully contained within its own sticker silhouette. Dark navy sticker-sheet background. No logos, no brand names, no additional words, no packaging, no hands, no desk, no perspective distortion.",
  "width": 2560,
  "height": 1440,
  "settings": {
    "renderingSpeed": "DEFAULT"
  }
}
```

---

### text-to-image (text-to-image)

![Thermal Battery Video Thumbnail](https://assets.runware.ai/examples/ideogram-4-0/f03bc036-1d50-425d-916a-b085c36a7c3a.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "2945bd8d-43ef-4c8a-9c92-23e92ca0217a",
  "model": "ideogram:4@0",
  "positivePrompt": "Create a finished 16:9 YouTube documentary thumbnail about an underground thermal battery beneath a city. Show a dramatic cutaway landscape: a compact modern city and district-heating plant at street level, with the earth sliced open below to reveal a vast glowing cylindrical reservoir of hot sand, insulated pipes, heat arrows, and geological strata. Use a bold editorial screen-print aesthetic with crisp geometric forms, subtle halftone grain, and a limited palette of midnight navy, warm cream, electric orange, and signal red. Compose for immediate readability at small thumbnail size: place the underground reservoir prominently on the right, the tiny city silhouette across the upper horizon, and a clean dark area on the left for typography. Render the exact phrase “HEAT UNDERFOOT” in very large, legible, condensed uppercase cream lettering on two lines at left. High contrast, intelligent science-journalism mood, visually accurate engineering cues, strong depth and scale, no logos, no extra words, no interface elements, no border.",
  "width": 2560,
  "height": 1440,
  "settings": {
    "renderingSpeed": "DEFAULT"
  }
}
```

---

### text-to-image (text-to-image)

![Alpine Survival Game Key Art](https://assets.runware.ai/examples/ideogram-4-0/1a43d5cb-9c86-48f4-b407-38ed9b2bbec0.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "42539d1c-a04a-4581-9e96-6bc41940c485",
  "model": "ideogram:4@0",
  "positivePrompt": "Finished 16:9 landscape key art for a premium narrative survival video game. A weather-beaten orange cable-car maintenance gondola hangs above an immense glacial ravine during a violent whiteout. On its icy roof, a solitary alpine engineer in a charcoal insulated suit and safety harness reaches toward a sparking pulley assembly, dwarfed by the landscape. Thick cables sweep diagonally from the foreground into fog-shrouded mountain pylons, creating strong depth and visual tension. Wind drives ribbons of snow across the frame; faint amber work lights glow through the storm. Cinematic painterly realism fused with bold European mountain-rescue poster design and subtle technical linework. Restricted palette of snow white, deep cobalt blue, graphite black, and vivid safety orange. Place the exact title “CABLE ZERO” large and clearly legible in the upper-left quadrant, set in a heavy condensed industrial sans-serif with crisp geometric letterforms and slight wind-scoured distressing. Keep generous clear space around the title. Dramatic, austere, dangerous, highly polished commercial game key art; no characters facing the viewer, no logos, no interface, no borders, and no other readable text.",
  "width": 2560,
  "height": 1440,
  "settings": {
    "renderingSpeed": "DEFAULT"
  }
}
```

---

### structured-prompt (structured-prompt)

![Community Radio Host Campaign Portrait](https://assets.runware.ai/examples/ideogram-4-0/45233b57-3566-42c0-ae9a-477653cfadfa.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "f64afb42-4511-4882-b596-626bb01544cf",
  "model": "ideogram:4@0",
  "width": 1792,
  "height": 2240,
  "settings": {
    "structuredPrompt": {
      "high_level_description": "An elegant vertical exhibition poster for a nocturnal botanical event, combining luminous flowers with polished editorial typography.",
      "compositional_deconstruction": {
        "background": "A deep midnight botanical garden with soft mist, dramatic moonlight, and open negative space around the central title.",
        "elements": [
          {
            "type": "text",
            "bbox": [
              90,
              120,
              300,
              880
            ],
            "color_palette": [
              "#F4EBD0",
              "#D8A7B1"
            ],
            "desc": "Large elegant editorial title with crisp, highly legible lettering.",
            "text": "NIGHT BLOOM"
          },
          {
            "type": "obj",
            "bbox": [
              320,
              100,
              900,
              900
            ],
            "color_palette": [
              "#111827",
              "#355E3B",
              "#8B5CF6",
              "#F4EBD0"
            ],
            "desc": "Luminous nocturnal flowers and curling leaves arranged as a refined botanical centerpiece."
          }
        ]
      },
      "style_description": {
        "aesthetics": "Sophisticated, atmospheric, luxurious, and uncluttered.",
        "art_style": "Contemporary botanical poster illustration.",
        "color_palette": [
          "#111827",
          "#355E3B",
          "#8B5CF6",
          "#D8A7B1",
          "#F4EBD0"
        ],
        "lighting": "Soft moonlight with subtle floral glow.",
        "medium": "High-end digital editorial illustration."
      }
    },
    "renderingSpeed": "QUALITY"
  }
}
```