---
title: GPT-Image-2.5 Sunburst | Runware Docs
url: https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst
description: Premium image generation and editing with precise control across iterative edits
---
# GPT-Image-2.5 Sunburst

![GPT-Image-2.5 Sunburst](https://assets.runware.ai/covers/openai-gpt-image-2-5-sunburst.jpg)

GPT-Image-2.5 Sunburst is OpenAI's most capable model for image generation and editing, designed for premium workflows that need tighter control across detailed and iterative edits. It combines strong reference-subject preservation, localized changes, natural lighting and textures, complex layout handling, and consistent visual direction for production-ready campaign creative, polished product imagery, and other demanding visual design work.

- **Status**: live
- **ID**: `openai:gpt-image@2.5-sunburst`
- Try in Playground
- **Creator**: OpenAI
- **Release Date**: September 8, 2026
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

~$0.0611 typical run

**Rates** (per 1M tokens)

- Text input: `$5.00`
- Image input: `$8.00`
- Image output: `$30.00`

**4 example generations**

- [inpaint](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst/examples#example-dance-festival-risograph-portrait): `$0.0152` (~20s)
- [transparent-background](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst/examples#example-maritime-mystery-streaming-series-poster): `$0.0541` (~40s)
- [reference-to-image](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst/examples#example-museum-textile-conservator-editorial-portrait): `$0.0682` (~34s)
- [text-to-image](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst/examples#example-industrial-thermal-camera-colorways): `$0.167` (~1m 8s)

billed per token, so a request costs what the model produced · times vary, measured end to end · [How pricing works](https://runware.ai/docs/platform/pricing)

## Compatibility & Validation

When `inputs.maskImage` is provided, `inputs.referenceImages` is required.

---

When `settings.background` is `transparent`, `outputFormat` is limited to `PNG`, `WEBP`.

---

`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/openai-gpt-image-2-5-sunburst#request-tasktype)

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

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#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/openai-gpt-image-2-5-sunburst#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#request-outputformat)

- **Type**: `string`
- **Required**: conditional — Required when settings.background is provided
- **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/openai-gpt-image-2-5-sunburst#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/openai-gpt-image-2-5-sunburst#request-webhookurl)

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

Specifies a webhook URL where JSON responses will be sent 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/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#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/platform/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#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/openai-gpt-image-2-5-sunburst#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#request-safety-checkcontent)

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

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

### [ttl](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#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/openai-gpt-image-2-5-sunburst#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#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/openai-gpt-image-2-5-sunburst#request-inputs-maskimage)

- **Path**: `inputs.maskImage`
- **Type**: `string`

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. The model treats the mask as guidance rather than a hard boundary, so edits can extend past its shape. With several reference images the mask applies to the first.

### [referenceImages](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `16`

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/openai-gpt-image-2-5-sunburst#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `openai:gpt-image@2.5-sunburst`

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/openai-gpt-image-2-5-sunburst#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `32000`

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/openai-gpt-image-2-5-sunburst#request-width)

- **Type**: `integer`
- **Required**: true
- **Min**: `16`
- **Max**: `3840`
- **Step**: `16`

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/openai-gpt-image-2-5-sunburst#request-height)

- **Type**: `integer`
- **Required**: true
- **Min**: `16`
- **Max**: `3840`
- **Step**: `16`

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.

### [background](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#request-settings-background)

- **Path**: `settings.background`
- **Type**: `string`
- **Default**: `auto`

Background handling in generated images.

**Allowed values**:

- `auto` Automatically determines the most appropriate background based on content.
- `opaque` Solid background, no transparency.
- `transparent` Transparent background areas where applicable.

### [moderation](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#request-settings-moderation)

- **Path**: `settings.moderation`
- **Type**: `string`
- **Default**: `auto`

Content moderation level.

**Allowed values**:

- `auto` Standard filtering that limits creating certain categories of potentially age-inappropriate content.
- `low` Less restrictive filtering.

### [quality](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#request-settings-quality)

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

Image quality level.

**Allowed values**: `auto` `max` `xhigh` `high` `medium` `low`

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#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/openai-gpt-image-2-5-sunburst#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#request-advancedfeatures-watermark-image)

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

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

#### [displayPosition](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#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/openai-gpt-image-2-5-sunburst#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/openai-gpt-image-2-5-sunburst#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#request-advancedfeatures-watermark-bgcolor)

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

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#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/openai-gpt-image-2-5-sunburst#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#response-imagedatauri)

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

Data URI of the output image.

### [seed](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/openai-gpt-image-2-5-sunburst#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)

![Industrial Thermal Camera Colorways](https://assets.runware.ai/examples/openai-gpt-image-2-5-sunburst/268dd530-a116-472d-ae9f-1881db70dfea.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "01a344b3-4eb7-48e0-8894-d1eaf7616918",
  "model": "openai:gpt-image@2.5-sunburst",
  "positivePrompt": "Create a premium landscape product-design visualization for a manufacturer of rugged industrial inspection equipment. Show three identical handheld thermal imaging cameras arranged in a disciplined row on individual low concrete plinths. Every camera must have exactly the same industrial design, dimensions, lens assembly, screen placement, controls, grip texture, seams, fasteners, and materials; the only difference between them is the exterior colorway.\n\nColorway 1: deep basalt black body with charcoal rubber grip panels and one restrained cool-gray control ring. Colorway 2: saturated sulfur yellow body with graphite rubber grip panels and black controls. Colorway 3: muted oxidized-copper green body with dark forest rubber grip panels and a small warm-gray control ring. Apply each color consistently to the same corresponding body panels. Keep the lens glass, exposed screws, screen, and black technical components unchanged across all three units.\n\nDesign each product as a credible professional thermal camera used for electrical, mechanical, and building inspections: compact rectangular upper housing, large circular germanium lens, protected recessed display, ergonomic pistol grip, tactile directional controls, durable overmolded corners, subtle ventilation details, precise injection-molded polymer surfaces, realistic part lines, and no unnecessary futuristic decoration. No logos, labels, lettering, symbols, interface graphics, or invented branding.\n\nArt direction: austere industrial design studio with a dark mineral-gray background, matte poured-concrete plinths, faint atmospheric haze, and a clean architectural composition. Three-quarter front views angled consistently toward camera, all products fully visible and equally sized. Use dramatic raking light from the upper left to reveal surface texture and molded geometry, narrow cool rim light from behind, controlled soft reflections on the lenses, and realistic contact shadows. Preserve rich shadow detail and accurate material response: satin polymer shells, soft-touch rubber, anodized metal control rings, coated optical glass, and lightly brushed fasteners. Wide 3:2 composition with generous negative space around the lineup, eye-level product photography, 85mm commercial studio lens aesthetic, sharp focus throughout, restrained contrast, color-accurate finish, photorealistic production quality. The image should read immediately as a professional colorway comparison in which only the selected exterior colors change while the product design remains identical.",
  "width": 1536,
  "height": 1024,
  "settings": {
    "background": "opaque",
    "quality": "max"
  }
}
```

---

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

![Museum Textile Conservator Editorial Portrait](https://assets.runware.ai/examples/openai-gpt-image-2-5-sunburst/61ffa103-6f8c-4475-a6a2-13c9e96e4670.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "b191abf9-2c1f-48e0-bd8a-7d5e2587c94c",
  "model": "openai:gpt-image@2.5-sunburst",
  "positivePrompt": "Create a finished professional environmental portrait for a major museum’s annual report and online expert profile. Use reference image 1 exclusively to define the woman’s identity: preserve her facial structure, age, complexion, eye shape, chin-length black bob, distinctive natural silver streak at the right temple, and subtle smile lines with high fidelity. Do not beautify her into a younger or different person. Use reference image 2 to define the textile-conservation laboratory, material vocabulary, restrained palette, and quiet editorial atmosphere; do not copy any person from that image.\n\nShow the conservator seated at the edge of a pale oak worktable in the museum laboratory, framed from mid-torso upward in a 1280x1024 landscape composition. She faces the camera with relaxed shoulders, intelligent direct eye contact, and a calm, quietly authoritative expression appropriate for a senior specialist. Dress her in a beautifully cut, unbranded deep-indigo work jacket over an undyed linen shirt, professional but connected to her field. Include only a restrained glimpse of her hands near the lower edge of the frame, naturally resting beside an archival sample card.\n\nPlace her slightly left of center, leaving clean, softly detailed negative space on the right for flexible editorial cropping. Behind her, render the laboratory from reference image 2 with pale oak drawers, organized conservation tools, muted indigo and madder textile swatches, a brass task lamp, and a protected woven textile, all subdued and gently out of focus. The setting must feel operational, meticulous, and museum-grade rather than decorative or rustic.\n\nPhotograph with the natural perspective of an 85mm portrait lens at eye level. Soft north-window daylight should shape the face from camera left, with subtle warm fill from the brass lamp and delicate separation along the dark hair. Maintain realistic pores, fine hair, fabric fibers, and age-appropriate detail. Controlled shallow depth of field, crisp focus on both eyes, soft background falloff, balanced highlights, refined tonal range, muted mineral green, dusty indigo, natural linen, and warm oak. Contemporary cultural-institution editorial photography: composed, humane, intelligent, understated, and publication-ready. No text, logos, name badges, watermark, excessive retouching, theatrical costume, clutter, distorted hands, duplicated tools, or artificial-looking skin.",
  "width": 1280,
  "height": 1024,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/4dbcd201-8151-4f3f-9498-63a68197f00b.jpg",
      "https://assets.runware.ai/assets/inputs/9ef6787c-f697-4547-8cb2-c8dff6e46932.jpg"
    ]
  }
}
```

---

### inpaint (inpaint)

![Dance Festival Risograph Portrait](https://assets.runware.ai/examples/openai-gpt-image-2-5-sunburst/8969acfb-d8da-411c-bb5a-761958027b98.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "09b8b2ed-d506-41b6-b7cb-0ed11a1e598f",
  "model": "openai:gpt-image@2.5-sunburst",
  "positivePrompt": "Create a finished square campaign portrait for a contemporary dance festival by editing the supplied photograph. Use the mask to substantially restyle the entire dancer—from hair and face through clothing, hands, legs, and feet—as a handcrafted two-color risograph illustration while preserving her exact identity, facial structure, anatomy, pose, proportions, gesture, and silhouette. Render the dancer with deep indigo ink, fluorescent persimmon-red overlays, cream paper knockouts, visible halftone dots, dry ink texture, subtle paper fibers, chunky graphic shadow shapes, and slight analog color misregistration contained within her silhouette. Keep facial features readable and expressive through economical printmaking marks. The treatment should feel sophisticated and commissioned, like contemporary performing-arts campaign artwork rather than a cartoon. Preserve the unmasked pale mint seamless studio background, floor, lighting gradient, framing, and faint existing floor shadow as clean photography. The contrast between the photographic environment and printed figure should be deliberate and polished. Do not add typography, logos, props, borders, scenery, or additional people.",
  "width": 1024,
  "height": 1024,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/2c2ef088-ad9f-4d06-a4ca-99ff7d2f87a6.jpg"
    ],
    "maskImage": "https://assets.runware.ai/assets/inputs/949221c1-1583-4a2b-a855-1f3d3a7f20cf.png"
  }
}
```

---

### transparent-background (transparent-background)

![Maritime Mystery Streaming Series Poster](https://assets.runware.ai/examples/openai-gpt-image-2-5-sunburst/4a5d9480-25ab-439d-92d1-4f4ff4636d49.png)

```json
{
  "taskType": "imageInference",
  "taskUUID": "485bbf69-49f1-4ada-a67b-7864f33746cf",
  "outputFormat": "PNG",
  "model": "openai:gpt-image@2.5-sunburst",
  "positivePrompt": "Create finished square streaming-series poster art as one isolated, cohesive graphic on a fully transparent background. Center a front-facing antique copper deep-sea diving helmet with an exceptionally clean, production-ready silhouette and generous transparent margin on all sides. The helmet is aged but elegant: burnished copper, dark verdigris seams, rivets, side valves, protective grille, subtle salt corrosion, and controlled cinematic highlights. Inside the circular black glass faceplate, integrate the exact title “THE NINTH BELL” in large condensed ivory capitals, stacked and perfectly legible. Beneath it, in much smaller spaced capitals, add the exact line “A LIMITED SERIES”. A thin ivory sonar-ring motif encircles the title inside the glass, with one small red signal mark at the ninth position. Prestige maritime mystery art direction, ominous and restrained, graphic realism blended with meticulous engraved-poster detail, copper, deep black, oxidized teal, ivory, and one precise signal-red accent. Strong visual hierarchy at thumbnail size. Keep the helmet and its integrated lettering as a single isolated poster emblem with crisp edges. No people, no ocean, no ship, no seafloor, no environmental backdrop, no horizon, no rectangular poster field, no border, no floor, no cast shadow, no glow outside the silhouette, no mockup, no platform branding, and no additional text. All space surrounding the graphic must remain genuinely transparent.",
  "width": 1024,
  "height": 1024,
  "settings": {
    "background": "transparent"
  }
}
```