---
title: Ideogram 3.0 Remix | Runware Docs
url: https://runware.ai/docs/models/ideogram-3-0-remix
description: Remix Ideogram 3.0 images with fresh styles and palettes
---
# Ideogram 3.0 Remix

![Ideogram 3.0 Remix](https://assets.runware.ai/covers/ideogram-3-0-remix.jpg)

Ideogram 3.0 Remix lets you rework existing images into new styles while it preserves layout and composition. Use it to test creative variants, adjust palettes, or adapt designs for new campaigns. Ideal for A/B testing, rapid iteration, and brand safe visual updates.

- **Status**: live
- **ID**: `ideogram:4@2`
- Try in Playground
- **Creator**: Ideogram
- **Release Date**: April 30, 2025
- **Zero Data Retention**: Yes
- **Capabilities**: Image to Image, Checkpoint

## Pricing

$0.03 from, per run · ~23s per request

**Rates** (per run)

- Turbo: `$0.03`
- Default: `$0.06`
- Quality: `$0.09`

**3 example generations**

- [masked-identity-preservation](https://runware.ai/docs/models/ideogram-3-0-remix/examples#example-adaptive-rain-cape-virtual-try-on) · 896×1152: `$0.06` (~23s)
- [reference-to-image](https://runware.ai/docs/models/ideogram-3-0-remix/examples#example-beekeeping-cooperative-textile-campaign-artwork) · 1024×1024: `$0.06` (~13s)
- [identity-preservation](https://runware.ai/docs/models/ideogram-3-0-remix/examples#example-subsea-engineer-leadership-headshot) · 832×1216: `$0.09` (~25s)

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

## Compatibility & Validation

When `providerSettings.ideogram.characterReferenceImages` is provided, `providerSettings.ideogram.styleType` is limited to `AUTO`, `REALISTIC`, `FICTION`.

---

When `providerSettings.ideogram.characterReferenceImagesMask` is provided, `providerSettings.ideogram.characterReferenceImages` requires at least 1 item.

---

When `providerSettings.ideogram.styleType` is `FICTION`, `providerSettings.ideogram.characterReferenceImages` is required.

---

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `1K (3:1)` | `1536x512` |
| `1K (~21:9)` | `1536x576` |
| `1K (~21:9)` | `1472x576` |
| `1K (~21:9)` | `1408x576` |
| `1K (~21:9)` | `1536x640` |
| `1K (~21:9)` | `1472x640` |
| `1K (~21:9)` | `1408x640` |
| `1K (~2:1)` | `1344x640` |
| `1K (~2:1)` | `1472x704` |
| `1K (2:1)` | `1408x704` |
| `1K (~2:1)` | `1344x704` |
| `1K (~16:9)` | `1280x704` |
| `1K (16:9)` | `1312x736` |
| `1K (~16:9)` | `1344x768` |
| `1K (~16:9)` | `1216x704` |
| `1K (5:3)` | `1280x768` |
| `1K (~5:3)` | `1152x704` |
| `1K (16:10)` | `1280x800` |
| `1K (~16:10)` | `1216x768` |
| `1K (3:2)` | `1248x832` |
| `1K (~3:2)` | `1216x832` |
| `1K (~3:2)` | `1088x768` |
| `1K (~4:3)` | `1152x832` |
| `1K (4:3)` | `1152x864` |
| `1K (~4:3)` | `1088x832` |
| `1K (~5:4)` | `1152x896` |
| `1K (5:4)` | `1120x896` |
| `1K (~5:4)` | `1024x832` |
| `1K (~5:4)` | `1088x896` |
| `1K (~5:4)` | `960x832` |
| `1K (~5:4)` | `1024x896` |
| `1K (~5:4)` | `1088x960` |
| `1K (~1:1)` | `960x896` |
| `1K (~1:1)` | `1024x960` |
| `1K (1:1)` | `1024x1024` |
| `1K (~1:1)` | `960x1024` |
| `1K (~1:1)` | `896x960` |
| `1K (~4:5)` | `960x1088` |
| `1K (~4:5)` | `896x1024` |
| `1K (~4:5)` | `832x960` |
| `1K (~4:5)` | `896x1088` |
| `1K (~4:5)` | `832x1024` |
| `1K (4:5)` | `896x1120` |
| `1K (~4:5)` | `896x1152` |
| `1K (~3:4)` | `832x1088` |
| `1K (3:4)` | `864x1152` |
| `1K (~3:4)` | `832x1152` |
| `1K (~2:3)` | `768x1088` |
| `1K (~2:3)` | `832x1216` |
| `1K (2:3)` | `832x1248` |
| `1K (~10:16)` | `768x1216` |
| `1K (10:16)` | `800x1280` |
| `1K (~3:5)` | `704x1152` |
| `1K (3:5)` | `768x1280` |
| `1K (~9:16)` | `704x1216` |
| `1K (~9:16)` | `768x1344` |
| `1K (9:16)` | `736x1312` |
| `1K (~9:16)` | `704x1280` |
| `1K (~1:2)` | `704x1344` |
| `1K (1:2)` | `704x1408` |
| `1K (~1:2)` | `704x1472` |
| `1K (~1:2)` | `640x1344` |
| `1K (~9:21)` | `640x1408` |
| `1K (~9:21)` | `640x1472` |
| `1K (~9:21)` | `640x1536` |
| `1K (~9:21)` | `576x1408` |
| `1K (~9:21)` | `576x1472` |
| `1K (~1:3)` | `576x1536` |
| `1K (1:3)` | `512x1536` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/ideogram-3-0-remix#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/ideogram-3-0-remix#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-3-0-remix#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/ideogram-3-0-remix#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-3-0-remix#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-3-0-remix#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-3-0-remix#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-3-0-remix#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-3-0-remix#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/ideogram-3-0-remix#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-3-0-remix#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-3-0-remix#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/ideogram-3-0-remix#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.

### [referenceImages](https://runware.ai/docs/models/ideogram-3-0-remix#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Required**: true
- **Min items**: `items: 1`

List of reference images (UUID, URL, Data URI, or Base64).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/ideogram-3-0-remix#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `ideogram:4@2`

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-3-0-remix#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `2000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

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

### [negativePrompt](https://runware.ai/docs/models/ideogram-3-0-remix#request-negativeprompt)

- **Type**: `string`
- **Min**: `1`
- **Max**: `2000`

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

**Learn more** (1 resource):

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

### [width](https://runware.ai/docs/models/ideogram-3-0-remix#request-width)

- **Type**: `integer`
- **Required**: true
- **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-3-0-remix#request-height)

- **Type**: `integer`
- **Required**: true
- **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)

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/ideogram-3-0-remix#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-3-0-remix#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/ideogram-3-0-remix#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-3-0-remix#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-3-0-remix#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-3-0-remix#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/ideogram-3-0-remix#request-advancedfeatures-watermark-bgcolor)

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

Background color in hex format.

**Provider Settings**

Parameters specific to this model provider. These must be nested inside the \`providerSettings.ideogram\` object.

### [characterReferenceImages](https://runware.ai/docs/models/ideogram-3-0-remix#request-providersettings-ideogram-characterreferenceimages)

- **Path**: `providerSettings.ideogram.characterReferenceImages`
- **Type**: `array of strings`
- **Min items**: `items: 1`

Character reference images to preserve consistent facial and body traits across generations.

### [characterReferenceImagesMask](https://runware.ai/docs/models/ideogram-3-0-remix#request-providersettings-ideogram-characterreferenceimagesmask)

- **Path**: `providerSettings.ideogram.characterReferenceImagesMask`
- **Type**: `array of strings`
- **Min items**: `items: 1`

Mask images for character reference images. Must match the number of character reference images.

### [magicPrompt](https://runware.ai/docs/models/ideogram-3-0-remix#request-providersettings-ideogram-magicprompt)

- **Path**: `providerSettings.ideogram.magicPrompt`
- **Type**: `string`
- **Default**: `AUTO`

Automatic prompt enhancement.

**Allowed values**:

- `AUTO` Content-based enhancement.
- `ON` Always enhance.
- `OFF` No enhancement.

### [renderingSpeed](https://runware.ai/docs/models/ideogram-3-0-remix#request-providersettings-ideogram-renderingspeed)

- **Path**: `providerSettings.ideogram.renderingSpeed`
- **Type**: `string`
- **Default**: `DEFAULT`

Generation speed/quality tradeoff.

**Allowed values**:

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

### [stylePreset](https://runware.ai/docs/models/ideogram-3-0-remix#request-providersettings-ideogram-stylepreset)

- **Path**: `providerSettings.ideogram.stylePreset`
- **Type**: `string`

Artistic style preset.

**Allowed values**: `80S_ILLUSTRATION` `90S_NOSTALGIA` `ABSTRACT_ORGANIC` `ANALOG_NOSTALGIA` `ART_BRUT` `ART_DECO` `ART_POSTER` `AURA` `AVANT_GARDE` `BAUHAUS` `BLUEPRINT` `BLURRY_MOTION` `BRIGHT_ART` `C4D_CARTOON` `CHILDRENS_BOOK` `COLLAGE` `COLORING_BOOK_I` `COLORING_BOOK_II` `CUBISM` `DARK_AURA` `DOODLE` `DOUBLE_EXPOSURE` `DRAMATIC_CINEMA` `EDITORIAL` `EMOTIONAL_MINIMAL` `ETHEREAL_PARTY` `EXPIRED_FILM` `FLAT_ART` `FLAT_VECTOR` `FOREST_REVERIE` `GEO_MINIMALIST` `GLASS_PRISM` `GOLDEN_HOUR` `GRAFFITI_I` `GRAFFITI_II` `HALFTONE_PRINT` `HIGH_CONTRAST` `HIPPIE_ERA` `ICONIC` `JAPANDI_FUSION` `JAZZY` `LONG_EXPOSURE` `MAGAZINE_EDITORIAL` `MINIMAL_ILLUSTRATION` `MIXED_MEDIA` `MONOCHROME` `NIGHTLIFE` `OIL_PAINTING` `OLD_CARTOONS` `PAINT_GESTURE` `POP_ART` `RETRO_ETCHING` `RIVIERA_POP` `SPOTLIGHT_80S` `STYLIZED_RED` `SURREAL_COLLAGE` `TRAVEL_POSTER` `VINTAGE_GEO` `VINTAGE_POSTER` `WATERCOLOR` `WEIRD` `WOODBLOCK_PRINT`

### [styleType](https://runware.ai/docs/models/ideogram-3-0-remix#request-providersettings-ideogram-styletype)

- **Path**: `providerSettings.ideogram.styleType`
- **Type**: `string`
- **Default**: `AUTO`

Visual style and rendering approach.

**Allowed values**: `AUTO` `GENERAL` `REALISTIC` `DESIGN` `FICTION`

## Response Parameters

### [taskType](https://runware.ai/docs/models/ideogram-3-0-remix#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-3-0-remix#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-3-0-remix#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/ideogram-3-0-remix#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/ideogram-3-0-remix#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/ideogram-3-0-remix#response-imagedatauri)

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

Data URI of the output image.

### [NSFWContent](https://runware.ai/docs/models/ideogram-3-0-remix#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/ideogram-3-0-remix#response-cost)

- **Type**: `float`

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

## Examples

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

![Beekeeping Cooperative Textile Campaign Artwork](https://assets.runware.ai/examples/ideogram-3-0-remix/e7180cab-a4a6-4ea0-ba76-5ca9c18dc300.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "c626638d-2b05-4002-99e0-117bdfe3bb7c",
  "model": "ideogram:4@2",
  "positivePrompt": "Transform the source apiary photograph into a finished hand-hooked wool tapestry illustration for a beekeeping cooperative’s seasonal campaign. Preserve the recognizable square composition: the single veiled beekeeper centered beside the open hive, the honeycomb frame held upright at chest height, receding rows of hive boxes, hillside, mountains, and broad sky. Reinterpret every surface through tactile looped wool, chunky embroidery, visible yarn fibers, simplified folk-art shapes, and carefully layered stitched contours. Render bees as small embroidered marks swirling gently around the frame. Use a sophisticated agricultural palette of honey gold, burnt orange, deep indigo, cream, dusty sage, and dark brown. Warm, grounded, optimistic mood; graphic depth created through stitch direction and contrasting thread density. Crisp handcrafted detail, balanced negative space, artisanal editorial quality, edge-to-edge textile artwork. No lettering, logo, border, frame, or photographic remnants.",
  "negativePrompt": "Photorealism, glossy digital painting, plastic texture, extra people, duplicated limbs, altered pose, missing honeycomb frame, chaotic composition, typography, captions, logos, watermark, textile shown hanging on a wall, room mockup.",
  "width": 1024,
  "height": 1024,
  "providerSettings": {
    "ideogram": {
      "renderingSpeed": "DEFAULT",
      "magicPrompt": "AUTO"
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/3df416eb-e518-4377-88c3-a1ba96c8a532.jpg"
    ]
  }
}
```

---

### masked-identity-preservation (masked-identity-preservation)

![Adaptive Rain Cape Virtual Try-On](https://assets.runware.ai/examples/ideogram-3-0-remix/14fd08c2-a4f6-49fd-a413-afe391bc320c.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "0eff6a3f-91bd-4f73-bdee-97b073f380be",
  "model": "ideogram:4@2",
  "positivePrompt": "Create a premium photorealistic virtual try-on image for an adaptive outerwear retailer. Preserve the source image's portrait composition, seated three-quarter pose, wheelchair geometry, cape silhouette, garment construction, reflective piping, sealed zipper, raised collar, and realistic fabric folds. Replace the source model with the exact person from the character reference, faithfully preserving her facial structure, eyes, hair, age, skin tone, and recognizable identity while making her posture natural in the wheelchair. Transform the plain studio into a rain-soaked contemporary tram platform at blue hour: wet slate paving, softly glowing amber shelter lights, a blurred tram arriving in the background, fine rain visible in the light, and subtle reflections beneath the chair. Keep the cobalt cape as the visual focus and show how it protects the lap and upper wheelchair frame. Eye-level camera, authentic documentary fashion photography, crisp face and garment, natural skin texture, restrained palette of cobalt blue, charcoal, silver, and warm amber. No logos, captions, signage, or advertising text.",
  "width": 896,
  "height": 1152,
  "providerSettings": {
    "ideogram": {
      "characterReferenceImages": [
        "https://assets.runware.ai/assets/inputs/1a316b30-bd11-429d-9718-4d5431927802.jpg"
      ],
      "characterReferenceImagesMask": [
        "https://assets.runware.ai/assets/inputs/72d0e3c3-0ff5-4941-a264-88dbaea63e86.png"
      ],
      "styleType": "REALISTIC",
      "renderingSpeed": "DEFAULT"
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/c951df21-79cc-4052-a0cb-d3e768bd4cbd.jpg"
    ]
  }
}
```

---

### identity-preservation (identity-preservation)

![Subsea Engineer Leadership Headshot](https://assets.runware.ai/examples/ideogram-3-0-remix/d30f4e1b-6651-4ac8-856a-2a315a689c95.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "8c54ee82-a7b3-413f-abd0-265a8831c06a",
  "model": "ideogram:4@2",
  "positivePrompt": "Create a premium, photorealistic environmental leadership headshot for a marine robotics company annual report. Remix the supplied control-room portrait while preserving its vertical mid-torso composition, camera angle, pose, research-vessel setting, and burnt-orange offshore coveralls. The subject must remain the same recognizable woman shown in the separate character identity reference: preserve her exact facial structure, deep brown skin, distinctive vitiligo around the left eye and jaw, close-cropped salt-and-pepper curls, dark brown eyes, age, body proportions, and calm authority. Apply restrained professional portrait retouching: correct the cool uneven white balance, soften temporary shine and under-eye shadows, reduce minor distractions, refine flyaway hairs, and retain pores, fine lines, natural skin texture, and the precise vitiligo pattern. Do not reshape or beautify her face. Use soft directional window light with a subtle sea-glass cyan edge light, realistic catchlights, balanced contrast, and clean editorial color grading. Render the control-room monitors and brushed-steel equipment as an understated, softly defocused background with no readable text or logos. Sharp focus on both eyes, natural 85mm portrait perspective, confident direct gaze, composed and credible mood, high-end corporate editorial photography.",
  "width": 832,
  "height": 1216,
  "providerSettings": {
    "ideogram": {
      "characterReferenceImages": [
        "https://assets.runware.ai/assets/inputs/d06ad08f-f7d0-4afc-b3fd-09015952b83d.jpg"
      ],
      "styleType": "REALISTIC",
      "renderingSpeed": "QUALITY"
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/f7d8edae-16c3-4ad2-9b8f-9c22c8ac9cbe.jpg"
    ]
  }
}
```