---
title: Krea 2 Turbo | Runware Docs
url: https://runware.ai/docs/models/krea-2-turbo
description: Fast open-source Krea image model for low-cost text-to-image generation and LoRA-friendly workflows
---
# Krea 2 Turbo

![Krea 2 Turbo](https://assets.runware.ai/covers/krea-2-turbo.jpg)

Krea 2 Turbo is the open-source Krea image endpoint exposed on Runware for fast, low-cost text-to-image generation. It focuses on prompt-driven generation rather than the richer Krea 2 reference workflow, making it a better fit for simple production pipelines, accelerated runtimes, and workflows that benefit from open-model compatibility such as LoRA-based customization.

- **Status**: live
- **ID**: `krea:krea@2-turbo`
- Try in Playground
- **Creator**: Krea
- **Release Date**: July 14, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Image, Image to Image, Checkpoint

## Pricing

$0.0015 from, per run · ~4s per request

**Measured runs**

- 512×512 · steps 8: `$0.0015` (~1s)
- 1024×1024 · steps 8: `$0.0045` (~4s)
- 2048×2048 · steps 8: `$0.0179` (~13s)

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/krea-2-turbo/examples#example-coastal-engineering-book-cover): `$0.015` (~4s)
- [text-to-image](https://runware.ai/docs/models/krea-2-turbo/examples#example-converted-water-tower-living-room): `$0.015` (~4s)
- [text-to-image](https://runware.ai/docs/models/krea-2-turbo/examples#example-mine-water-heating-explainer): `$0.015` (~4s)
- [text-to-image](https://runware.ai/docs/models/krea-2-turbo/examples#example-nitrate-film-preservation-blog-hero): `$0.015` (~5s)

billed by compute time, so a request costs what it took · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

`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/krea-2-turbo#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/krea-2-turbo#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/krea-2-turbo#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/krea-2-turbo#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/krea-2-turbo#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/krea-2-turbo#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/krea-2-turbo#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/krea-2-turbo#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/krea-2-turbo#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/krea-2-turbo#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/krea-2-turbo#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/krea-2-turbo#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/krea-2-turbo#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.

### [acceleration](https://runware.ai/docs/models/krea-2-turbo#request-acceleration)

- **Type**: `string`
- **Default**: `medium`

Optimization level.

**Allowed values**: `none` `low` `medium` `high`

**Inputs**

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

### [referenceImages](https://runware.ai/docs/models/krea-2-turbo#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `4`

Style reference images for guiding generation. Each item can be a plain image input (UUID, URL, DataURI, or Base64) or an object with an image and a per-image strength.

**Examples**:

**Shorthand format:** When you don't need to specify a custom strength, you can pass a plain image input directly. It will use the default influence strength.

```json
"referenceImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to control the exact influence of the reference image, use an object with `image` and `strength`. Positive values guide the output toward the reference; negative values guide away from it.

```json
"referenceImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "strength": 0.7
  }
]
```

**Multiple images:** You can provide multiple reference images and even mix both formats.

```json
"referenceImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "strength": 1.2
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/krea-2-turbo#request-inputs-referenceimages-format-2-image)

- **Path**: `inputs.referenceImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [strength](https://runware.ai/docs/models/krea-2-turbo#request-inputs-referenceimages-format-2-strength)

- **Path**: `inputs.referenceImages.strength`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Default**: `0.5`

Influence strength of the reference image on the generated output.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/krea-2-turbo#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `krea:krea@2-turbo`

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/krea-2-turbo#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **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/krea-2-turbo#request-width)

- **Type**: `integer`
- **Required**: true
- **Min**: `64`
- **Max**: `2048`
- **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/krea-2-turbo#request-height)

- **Type**: `integer`
- **Required**: true
- **Min**: `64`
- **Max**: `2048`
- **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)

### [seed](https://runware.ai/docs/models/krea-2-turbo#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `9223372036854776000`

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

**Learn more** (1 resource):

- [Seed](https://runware.ai/docs/learn/seed) (learn)

### [steps](https://runware.ai/docs/models/krea-2-turbo#request-steps)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `100`
- **Default**: `8`

Total number of denoising steps. Higher values generally produce more detailed results but take longer.

**Learn more** (1 resource):

- [Steps](https://runware.ai/docs/learn/steps) (learn)

### [lora](https://runware.ai/docs/models/krea-2-turbo#request-lora)

- **Path**: `lora.model`
- **Type**: `array of objects (2 properties)`
- **Min items**: `1`

With LoRA (Low-Rank Adaptation), you can adapt a model to specific styles or features by emphasizing particular aspects of the data. This technique enhances the quality and relevance of generated content and can be especially useful when the output needs to adhere to a specific artistic style or follow particular guidelines.

Multiple LoRA models can be used simultaneously to achieve different adaptation goals.

**Examples**:

```json
"lora": [
  {
    "model": "<lora-model-air>",
    "weight": 0.8
  }
]
```

**Learn more** (1 resource):

- [Loras](https://runware.ai/docs/learn/loras) (learn)

#### [model](https://runware.ai/docs/models/krea-2-turbo#request-lora-model)

- **Path**: `lora.model`
- **Type**: `string`
- **Required**: true

LoRA model identifier.

#### [weight](https://runware.ai/docs/models/krea-2-turbo#request-lora-weight)

- **Path**: `lora.weight`
- **Type**: `float`
- **Min**: `-4`
- **Max**: `4`
- **Step**: `0.01`
- **Default**: `1`

Strength of the LoRA influence. A value of 0 means no influence. Higher values increase the influence, and negative values can be used to steer away from the LoRA's style.

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/krea-2-turbo#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/krea-2-turbo#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/krea-2-turbo#request-advancedfeatures-watermark-image)

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

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

#### [displayPosition](https://runware.ai/docs/models/krea-2-turbo#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/krea-2-turbo#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/krea-2-turbo#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/krea-2-turbo#request-advancedfeatures-watermark-bgcolor)

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

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/krea-2-turbo#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/krea-2-turbo#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/krea-2-turbo#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/krea-2-turbo#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/krea-2-turbo#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/krea-2-turbo#response-imagedatauri)

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

Data URI of the output image.

### [seed](https://runware.ai/docs/models/krea-2-turbo#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/krea-2-turbo#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/krea-2-turbo#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)

![Coastal Engineering Book Cover](https://assets.runware.ai/examples/krea-2-turbo/0c4f3d5c-f10e-4713-82aa-e54296c8cd02.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "e15dd9e3-9658-4d10-8577-4f310113f048",
  "model": "krea:krea@2-turbo",
  "positivePrompt": "Create a finished landscape-format front cover for a premium coastal engineering and landscape architecture book titled “THE LIVING BREAKWATER,” with the subtitle “Oyster Reefs for Resilient Cities.” Show a visually rich cutaway panorama where sea and shoreline meet: above the waterline, low wind-driven waves approach a distant contemporary harbor city; below the waterline, a thriving constructed oyster reef forms a protective barrier, with layered oyster shells, juvenile fish, eelgrass roots, crabs, sediment, and concrete reef modules clearly visible. Make the reef the central hero, stretching diagonally across the composition and visibly dissipating wave energy before it reaches shore. Art direction: sophisticated editorial scientific illustration combining crisp screen-printed shapes, fine engraved natural-history detail, subtle paper grain, and restrained technical-diagram precision. Palette of deep Atlantic navy, oxidized turquoise, warm shell ivory, muted coral orange, and small accents of acid yellow. Dramatic side lighting filters through the water in broad rays; the underwater habitat feels alive, intricate, and optimistic rather than fantastical. Strong depth, coherent ecology, accurate oyster anatomy, elegant negative space for typography. Place the exact title “THE LIVING BREAKWATER” in large condensed uppercase ivory lettering across the upper left, clean and highly legible. Place the exact subtitle “Oyster Reefs for Resilient Cities” beneath it in smaller coral-orange sans serif. Add the author line “MARA VELASQUEZ” at lower left in small uppercase letters. Preserve generous margins and professional publishing hierarchy. Flat standalone cover artwork only, edge-to-edge composition, no physical book mockup, no spine, no dust-jacket folds, no hands, no table, no extra logos, no badges, no additional text.",
  "width": 1536,
  "height": 1024
}
```

---

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

![Converted Water Tower Living Room](https://assets.runware.ai/examples/krea-2-turbo/eb8bf4e7-cac6-4d90-9ee4-8afb41ac1188.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "253e21f0-1bef-4410-b54f-6ae4f2d47e45",
  "model": "krea:krea@2-turbo",
  "positivePrompt": "High-end real-estate interior photography of a decommissioned 1960s concrete water tower converted into an extraordinary circular residence. Show the main living room occupying the full round tank: honest curved board-formed concrete walls, a shallow ribbed concrete ceiling, and a continuous band of slim panoramic windows overlooking a dense European city at blue hour. Compose from the edge of the room with a wide but natural architectural perspective, emphasizing the sweeping curve of the space while keeping vertical lines straight. A low crescent-shaped rust velvet sofa faces a sculptural blackened-steel fireplace; cobalt lounge chairs, a round travertine coffee table, a large hand-knotted cream rug, walnut cabinetry, and restrained contemporary art create a sophisticated warm interior. Include a compact reading nook integrated beneath the windows and subtle evidence of the original industrial structure, including restored steel braces and one sealed pipe connection used as a display niche. Soft amber concealed lighting grazes the textured concrete, balanced with cool indigo dusk through the glazing; practical lamps are gently illuminated, with realistic reflections and nuanced shadow detail. Immaculately staged but believable, quiet and inviting, tactile materials, editorial architectural photography, photorealistic, crisp natural detail, broad dynamic range, no people, no signs, no lettering, no fisheye distortion, no duplicated furniture. Finished standalone property-marketing image in 3:2 landscape composition.",
  "width": 1536,
  "height": 1024
}
```

---

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

![Mine Water Heating Explainer](https://assets.runware.ai/examples/krea-2-turbo/b2e69290-2942-4f1f-ba0a-f1fab52c43b9.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "00c2aa6b-ef62-4cde-a190-c75b44a886e5",
  "model": "krea:krea@2-turbo",
  "positivePrompt": "Create a finished landscape educational infographic for a municipal energy visitor center explaining how warm water in an abandoned coal mine becomes useful district heating. Use a visually rich axonometric cutaway illustration with a coherent left-to-right process. Across the lower half, reveal underground geology in cross-section: layered rock, old mine shafts and galleries filled with turquoise water. On the left, show a production borehole lifting naturally warmed mine water to the surface. In the center, show a compact energy center in cutaway with a plate heat exchanger and large electric heat pump. On the right, show an insulated district heating loop serving a library, apartment block, school, and greenhouse, followed by a separate reinjection borehole returning cooled mine water underground. Make the two water circuits unmistakably separate: turquoise arrows for the mine-water loop and coral-orange arrows for the clean heating loop. Add large numbered stages 1 through 5 and concise, clearly legible labels: “1 WARM MINE WATER”, “2 HEAT EXCHANGER”, “3 HEAT PUMP”, “4 DISTRICT HEATING”, “5 COOL WATER RETURNS”. Include the main heading at top left: “HEAT FROM THE MINE BELOW”. Add a small subheading: “A closed-loop journey from flooded workings to warm buildings”. Include a compact legend reading “MINE WATER” beside a turquoise line and “HEATING WATER” beside an orange line. Art direction: premium mid-century scientific diagram blended with contemporary editorial infographics, crisp geometric vector forms, subtle screen-printed grain, precise technical details, confident flat shapes, warm cream background, deep charcoal outlines, turquoise, coral orange, mustard yellow, and muted brick red. Strong information hierarchy, generous margins, balanced negative space, readable typography, clean arrows, no logos, no interface elements, no mockup, no photorealism. The image should feel authoritative, accessible, optimistic, and suitable for a professionally commissioned public exhibition panel.",
  "width": 1536,
  "height": 1024
}
```

---

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

![Nitrate Film Preservation Blog Hero](https://assets.runware.ai/examples/krea-2-turbo/fea55e7b-fbc1-44ab-826e-1f92cf1c8ee1.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "d9a858c7-6d2c-45af-a0e5-fa6a3ec1a7f6",
  "model": "krea:krea@2-turbo",
  "positivePrompt": "Cinematic editorial photograph for a long-form magazine article about nitrate film preservation. Inside a dark, climate-controlled film archive, a professional conservator wearing a charcoal lab coat and pale nitrile gloves carefully examines a curling strip of damaged 35mm motion-picture film above a softly illuminated inspection bench. Frame the conservator on the right third in three-quarter profile, with an intent expression and sharply rendered hands; the translucent film arcs through the foreground as the visual focal point, revealing tiny monochrome frames, amber edges, scratches, buckling, and delicate decay. Behind them, orderly shelves of unbranded metal film canisters recede into cool shadow. A narrow projector beam passes through faint suspended dust, creating a dramatic diagonal of warm honey light against deep petrol-blue and graphite surroundings. Authentic conservation tools sit subtly on the bench: loupe, cotton swabs, archival leader, small hand-cranked film viewer. Rich tactile detail, restrained teal-and-amber palette, gentle analog grain, realistic skin and materials, atmospheric documentary photography, sophisticated museum-publication art direction. Wide landscape composition with uncluttered dark negative space across the upper left for an editorial headline overlay. Strong subject separation and immediate thumbnail readability. No flames, no fantasy elements, no logos, no captions, no visible brand names, no interface, no border, no embedded typography.",
  "width": 1536,
  "height": 1024
}
```