---
title: Ideogram 4.5 | Runware Docs
url: https://runware.ai/docs/models/ideogram-4-5
description: Text-to-image generation and multi-image editing built for drift-free iteration
---
# Ideogram 4.5

![Ideogram 4.5](https://assets.runware.ai/covers/ideogram-4-5.jpg)

Ideogram 4.5 is Ideogram's image generation and editing model, built for iterative work that keeps untouched regions intact across repeated edits. It generates images from text at 1K and 2K presets, and edits a source image using up to four more images as references, with an optional mask to limit where changes land. It suits product imagery, campaign variations, interior restyling, and pose changes guided by a skeleton reference.

- **Status**: live
- **ID**: `ideogram:4.5@0`
- Try in Playground
- **Creator**: Ideogram
- **Release Date**: September 30, 2026
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

$0.008 from, per run · ~26s per request

**Rates** (per run)

- Very low: `$0.008`
- Low: `$0.03`
- Medium: `$0.06`
- High: `$0.20`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/ideogram-4-5/examples#example-regional-polka-album-cover) · 2048×2048: `$0.20` (~26s)
- [text-to-image](https://runware.ai/docs/models/ideogram-4-5/examples#example-industrial-ambient-album-cover) · 2048×2048: `$0.20` (~24s)
- [reference-to-image](https://runware.ai/docs/models/ideogram-4-5/examples#example-nocturnal-moth-count-social-post) · 1536×1024: `$0.20` (~32s)
- [inpaint](https://runware.ai/docs/models/ideogram-4-5/examples#example-marine-archaeologist-linocut-portrait): `$0.20` (~26s)

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

## Compatibility & Validation

When `inputs.maskImage` is provided, `width/height` cannot be used.

---

When `inputs.maskImage` is provided, `inputs.referenceImages` is limited to 4 items.

---

When `inputs.referenceImages` is provided, `settings.magicPrompt` cannot be used.

---

When `inputs.referenceImages` is provided, `width` must be at least `256` and `height` must be at least `256`.

---

When `inputs.referenceImages` is not provided, `settings.quality` is limited to `low`, `medium`, `high`.

---

When `inputs.referenceImages` is not provided, dimensions are limited to `2048×2048`, `1440×2880`, `2880×1440`, `1664×2496`, `2496×1664`, `1792×2240`, `2240×1792`, `1440×2560`, `2560×1440`, `1600×2560`, `2560×1600`, `1728×2304`, `2304×1728`, `1296×3168`, `3168×1296`, `1152×2944`, `2944×1152`, `1248×3328`, `3328×1248`, `1280×3072`, `3072×1280`, `1024×3072`, `3072×1024`, `1024×1024`, `896×1120`, `1120×896`, `864×1152`, `1152×864`, `832×1248`, `1248×832`, `800×1280`, `1280×800`, `720×1280`, `1280×720`, `720×1440` or `1440×720`.

---

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

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/ideogram-4-5#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/ideogram-4-5#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-4-5#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/ideogram-4-5#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-4-5#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-4-5#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-4-5#request-deliverymethod)

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

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns complete results directly in the API response.
- `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-4-5#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-4-5#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/ideogram-4-5#request-safety-checkcontent)

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

Enable or disable content safety checking. Increases total generation time.

### [ttl](https://runware.ai/docs/models/ideogram-4-5#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-4-5#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/ideogram-4-5#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.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [maskImage](https://runware.ai/docs/models/ideogram-4-5#request-inputs-maskimage)

- **Path**: `inputs.maskImage`
- **Type**: `string`
- **File size**: `up to 25 MB`

Image used to specify which areas of the input image should be edited (UUID, URL, Data URI, or Base64). White marks the area to edit, black is preserved. Applies to the first reference image, must match its dimensions and contain both white and black areas.

### [referenceImages](https://runware.ai/docs/models/ideogram-4-5#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `5`
- **File size (each)**: `up to 25 MB`
- **Aspect ratio (each)**: `1:6 to 6:1`

List of reference images (UUID, URL, Data URI, or Base64). The first image is the source to edit, the rest guide the edit.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/ideogram-4-5#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `ideogram:4.5@0`

Identifier of the model to use for generation.

**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-4-5#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `10000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

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

### [width](https://runware.ai/docs/models/ideogram-4-5#request-width)

- **Type**: `integer`

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-4-5#request-height)

- **Type**: `integer`

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)

### [seed](https://runware.ai/docs/models/ideogram-4-5#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `2147483647`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Settings**

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

### [copyrightDetection](https://runware.ai/docs/models/ideogram-4-5#request-settings-copyrightdetection)

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

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

### [magicPrompt](https://runware.ai/docs/models/ideogram-4-5#request-settings-magicprompt)

- **Path**: `settings.magicPrompt`
- **Type**: `string`

Automatic prompt enhancement.

**Allowed values**: `auto` `on` `off`

### [quality](https://runware.ai/docs/models/ideogram-4-5#request-settings-quality)

- **Path**: `settings.quality`
- **Type**: `string`
- **Default**: `high`

Rendering quality.

**Allowed values**: `very_low` `low` `medium` `high`

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/ideogram-4-5#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-4-5#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/ideogram-4-5#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-4-5#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-4-5#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-4-5#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/ideogram-4-5#request-advancedfeatures-watermark-bgcolor)

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

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/ideogram-4-5#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-4-5#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-4-5#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/ideogram-4-5#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/ideogram-4-5#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/ideogram-4-5#response-imagedatauri)

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

Data URI of the output image.

### [seed](https://runware.ai/docs/models/ideogram-4-5#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/ideogram-4-5#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/ideogram-4-5#response-cost)

- **Type**: `float`

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

## Examples

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

![Regional Polka Album Cover](https://assets.runware.ai/examples/ideogram-4-5/ae304860-92aa-4509-b163-64bfcec7fc9f.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "d61e1534-0b41-4245-90cc-528160e1294c",
  "model": "ideogram:4.5@0",
  "positivePrompt": "Create a finished square album cover for a contemporary Midwestern brass-and-accordion dance record. The visual concept celebrates small-town water towers as cheerful regional landmarks. Use bold vernacular typography and a flat, meticulously registered screen-print aesthetic inspired by vintage community dance posters, agricultural seed packets, and geometric quilt blocks, while remaining entirely original.\n\nThe exact main title must read: “WATER TOWER WALTZES”. Set it in enormous condensed slab-serif capitals across the upper half, perfectly legible and correctly spelled. Arrange the words as three tightly stacked lines, using the letterforms as the main architecture of the composition. The exact artist name must read: “THE PRAIRIE SIGNALS”. Place it in smaller arched capitals along the bottom. Include no other words or lettering.\n\nBelow and partially interwoven with the title, depict three distinct small-town water towers in simplified graphic silhouette: one classic riveted sphere on narrow legs, one tall cylindrical tank, and one squat vintage tank with a conical roof. Add a tiny accordion, trumpet, tuba, and snare drum arranged like decorative folk emblems between the tower legs. Suggest a lively outdoor summer polka with rhythmic zigzags, radiating sunbursts, wheat sprigs, checkered bands, and pairs of tiny dancing figures, all reduced to crisp emblematic shapes.\n\nPalette: warm uncoated paper cream, tomato red, cornflower blue, mustard yellow, and deep bottle green, with subtle ink overlap creating occasional secondary colors. Strong flat shapes, slightly imperfect screen-print edges, restrained paper grain, no gradients, no photorealism. Jubilant, neighborly, energetic mood. Balanced square composition with excellent hierarchy and generous outer margins. The lettering must remain dominant and readable at thumbnail size. Produce only the standalone front cover artwork, straight-on and edge-to-edge: no vinyl record, CD case, packaging mockup, room setting, frame, hands, stickers, logos, or extra text.",
  "width": 2048,
  "height": 2048,
  "settings": {
    "magicPrompt": "on"
  }
}
```

---

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

![Industrial Ambient Album Cover](https://assets.runware.ai/examples/ideogram-4-5/8263f2a9-0ec8-4835-b76f-fd34feb07607.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "60572676-b63d-4edb-8cb0-51a3ed50fcf2",
  "model": "ideogram:4.5@0",
  "positivePrompt": "Create a finished square album cover for an experimental industrial-ambient record assembled from hydrophone recordings and maintenance sounds captured at a North Sea storm-surge barrier. The cover must feel like a commissioned release from a discerning independent electronic label, not a mockup.\n\nVisual content: an austere overhead view of a vast concrete tidal gate at low tide, reduced to bold geometric forms. A narrow steel maintenance ladder descends through the center into dark rippling water; tiny safety-orange inspection markers and cable lines establish scale. Merge documentary industrial photography with screen-printed technical diagrams: subtle depth contours, current-direction arrows, registration crosses, measured grid lines, and a faint waveform derived from moving water. Strong negative space, crisp hierarchy, tactile uncoated-paper texture, restrained halftone grain, slightly imperfect ink registration. Palette limited to deep oxidized teal, wet silt brown, warm bone, black, and vivid safety orange. Mood: cold, precise, maritime, meditative, quietly ominous.\n\nTypography is essential and must be highly legible. Set the exact album title “LOW TIDE MAINTENANCE” in large condensed uppercase sans-serif lettering, stacked across the upper-left quadrant with confident editorial spacing. Set the exact artist name “NORTH SEA SIGNAL UNIT” in smaller uppercase monospaced lettering along the lower-left edge. Add the exact catalog number “NSU–04” in tiny type at the upper-right. Integrate the lettering into the grid while preserving strong readability at thumbnail size. Use no other words, letters, numbers, logos, stickers, borders, or advisory labels.\n\nFlat, front-facing cover artwork filling the entire 2048 by 2048 canvas; no vinyl record, jewel case, frame, hands, room setting, perspective presentation, app interface, or product mockup.",
  "width": 2048,
  "height": 2048,
  "settings": {
    "magicPrompt": "on"
  }
}
```

---

### reference-to-image (reference-to-image)

![Nocturnal Moth Count Social Post](https://assets.runware.ai/examples/ideogram-4-5/ff116c61-218c-422d-b083-a6aaf5d701d2.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "74ded038-1022-42d2-bd47-383d7a7068c9",
  "model": "ideogram:4.5@0",
  "positivePrompt": "Edit the first reference image into a finished landscape social media event graphic for a nature center while preserving its recognizable composition: retain the exact centered moth sheet, the two biologists in their original positions and poses, the equipment table below, the surrounding tree shapes, and the original straight-on framing. Transform the photograph into the visual language of the second reference image: a bold two-color silkscreen print on warm cream recycled paper, deep midnight blue shadows, fluorescent chartreuse highlights, simplified botanical silhouettes, visible halftone dots, tactile paper grain, and subtly imperfect ink registration. Keep the people natural and clearly identifiable as field biologists rather than turning them into abstract figures. Make the illuminated sheet the brightest focal point and add several accurately shaped moth silhouettes around its light. Use the open upper area for clean, highly legible event typography. Set the exact headline “MOTH NIGHT” in large condensed uppercase lettering, followed by “JULY 18 · 9 PM–MIDNIGHT” and “RIVERBEND NATURE CENTER” in smaller uppercase type. Add the short footer “FREE COMMUNITY MOTH COUNT” along the bottom edge. Integrate the lettering as part of the silkscreen design, with strong hierarchy, generous spacing, and no extra words. Energetic, educational, welcoming, slightly mysterious nighttime mood. Professional campaign artwork ready to publish as a standalone social media post, edge-to-edge design only, not shown inside a phone, app, browser, frame, or mockup; no logo and no clickable button.",
  "width": 1536,
  "height": 1024,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/48f05dc4-d7ed-4648-ad1b-59f82428ae60.jpg",
      "https://assets.runware.ai/assets/inputs/2049c6c8-9eac-4666-aa75-43fc9a7ed1fd.jpg"
    ]
  }
}
```

---

### inpaint (inpaint)

![Marine Archaeologist Linocut Portrait](https://assets.runware.ai/examples/ideogram-4-5/40b5679a-3fb1-464b-8116-cc4b4b192577.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "ac35a0d3-a50e-42a2-87d1-e24cfbc491bc",
  "model": "ideogram:4.5@0",
  "positivePrompt": "Edit only the masked archaeologist, transforming her entire photographic figure into a sophisticated hand-carved reduction linocut illustration for an oceanographic institute annual report. Preserve her exact identity, facial expression, stance, proportions, silhouette, clothing design, folded hood, placement, and scale. Render the figure with bold carved contours, expressive directional gouge marks, tactile ink texture, and carefully registered overlapping blocks in deep marine navy, oxidized copper, muted coral, and warm ivory. Keep the face recognizable and dignified, using restrained carved hatching rather than photorealistic skin. The result should feel like a contemporary museum-quality print commissioned to celebrate field science: graphic, human, precise, and materially rich. Preserve every unmasked part of the original photograph exactly, including the continuous sand-colored studio background, lighting, floor transition, grounded shadow, framing, and empty space. Do not alter or illustrate the background. No added objects, symbols, marine life, borders, typography, logos, labels, or signatures.",
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/42a77fdb-0c3c-40b3-96be-49c949169768.jpg"
    ],
    "maskImage": "https://assets.runware.ai/assets/inputs/b2179cf0-9856-44d9-9f38-8073682ec1d1.png"
  }
}
```