---
title: Qwen-Image-2.1-Turbo | Runware Docs
url: https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo
description: Low-cost image generation and multi-reference editing with LLM prompt rewriting
---
# Qwen-Image-2.1-Turbo

![Qwen-Image-2.1-Turbo](https://assets.runware.ai/covers/alibaba-qwen-image-2-1-turbo.jpg)

Qwen-Image-2.1-Turbo is the lower-cost Turbo tier of Alibaba's Qwen-Image-2.1 family, a unified model for text-to-image generation and prompt-guided image editing. It composes and edits from up to 10 reference images and can rewrite prompts with an LLM before generation, in a direct or agent mode with optional thinking. It outputs from 0.26 to 4.19 megapixels at aspect ratios from 1:8 to 8:1, suited to high-volume product imagery, marketing visuals, and rapid iteration.

- **Status**: live
- **ID**: `alibaba:qwen-image@2.1-turbo`
- Try in Playground
- **Creator**: Alibaba
- **Release Date**: October 9, 2026
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

$0.0141 per run · ~23s per request

**4 example generations**

- [reference-to-image](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo/examples#example-forensic-entomologist-creator-avatar) · 1536×1024: `$0.0141` (~31s)
- [text-to-image](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo/examples#example-geothermal-district-heating-explainer) · 1024×1024: `$0.0141` (~23s)
- [text-to-image](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo/examples#example-vintage-rescue-helicopter-arctic-composite) · 1024×1024: `$0.0141` (~17s)
- [reference-to-image](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo/examples#example-wayang-exhibition-campaign-hero) · 1536×1024: `$0.0141` (~24s)

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

## Compatibility & Validation

When `inputs.referenceImages` is provided, `settings.promptExtendMode` must be `direct`.

---

When `settings.promptExtend` is `false`, `settings.thinking` cannot be used.

---

`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/alibaba-qwen-image-2-1-turbo#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-turbo#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-turbo#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/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-turbo#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-safety-checkcontent)

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

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

### [ttl](https://runware.ai/docs/models/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-turbo#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/alibaba-qwen-image-2-1-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.

### [routing](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-routing)

- **Path**: `routing.preferences`
- **Type**: `object (6 properties)`

Model router options. Only read when `model` is `auto`, and never sent to the model.

#### [preferences](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-routing-preferences)

- **Path**: `routing.preferences`
- **Type**: `object (3 properties)`

Relative importance of each dimension when models are compared. Weights, not thresholds.

##### [quality](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-routing-preferences-quality)

- **Path**: `routing.preferences.quality`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `5`

Importance of one dimension. `0` leaves it out of the decision.

##### [speed](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-routing-preferences-speed)

- **Path**: `routing.preferences.speed`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `5`

Importance of one dimension. `0` leaves it out of the decision.

##### [cost](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-routing-preferences-cost)

- **Path**: `routing.preferences.cost`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `5`

Importance of one dimension. `0` leaves it out of the decision.

#### [maxPrice](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-routing-maxprice)

- **Path**: `routing.maxPrice`
- **Type**: `float`
- **Min**: `0`

Upper bound on what this request may cost, in USD. A model whose cost cannot be bounded is not chosen.

#### [requirements](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-routing-requirements)

- **Path**: `routing.requirements`
- **Type**: `string`
- **Max**: `3000`

Conditions the result has to meet, in plain words. A model that cannot meet them is not chosen.

**Inputs**

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

### [referenceImages](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `10`
- **File size (each)**: `up to 10 MB`

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/alibaba-qwen-image-2-1-turbo#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `alibaba:qwen-image@2.1-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/alibaba-qwen-image-2-1-turbo#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `3000`

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/alibaba-qwen-image-2-1-turbo#request-width)

- **Type**: `integer`
- **Min**: `192`
- **Max**: `4096`

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/alibaba-qwen-image-2-1-turbo#request-height)

- **Type**: `integer`
- **Min**: `192`
- **Max**: `4096`

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/alibaba-qwen-image-2-1-turbo#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.

### [promptExtend](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-settings-promptextend)

- **Path**: `settings.promptExtend`
- **Type**: `boolean`
- **Default**: `true`

Enable LLM-based prompt rewriting to expand and clarify inputs. Affects reproducibility.

### [promptExtendMode](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-settings-promptextendmode)

- **Path**: `settings.promptExtendMode`
- **Type**: `string`
- **Default**: `direct`

Rewriting strategy for `promptExtend`.

**Allowed values**:

- `direct` Direct prompt expansion.
- `agent` Agent-based rewrite.

### [thinking](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-settings-thinking)

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

Enables thinking mode for improved quality at the cost of increased generation time.

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-turbo#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-turbo#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#request-advancedfeatures-watermark-bgcolor)

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

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-turbo#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/alibaba-qwen-image-2-1-turbo#response-imagedatauri)

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

Data URI of the output image.

### [seed](https://runware.ai/docs/models/alibaba-qwen-image-2-1-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/alibaba-qwen-image-2-1-turbo#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/alibaba-qwen-image-2-1-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)

![Geothermal District Heating Explainer](https://assets.runware.ai/examples/alibaba-qwen-image-2-1-turbo/140d7d0e-025b-4bb6-a953-0947135998be.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "cf2d54fe-064a-4b26-bc1a-967b473a90b1",
  "model": "alibaba:qwen-image@2.1-turbo",
  "positivePrompt": "Create a finished square public-education infographic titled “GEOTHERMAL DISTRICT HEATING” with the subtitle “How heat moves from deep rock to city buildings”. Show a precise isometric cutaway of a compact city above layered geology. In the upper half, include a school, apartment block, library, small clinic, streets, trees, and buried district pipes. In the lower half, reveal colorful horizontal rock strata, a deep hot aquifer, one red production well, and one blue reinjection well. Place a clearly visible plate heat exchanger at ground level between the geothermal wells and the city network.\n\nExplain the system as one continuous numbered journey with clean directional arrows and these exact concise labels: “1 HOT AQUIFER”, “2 PRODUCTION WELL”, “3 HEAT EXCHANGER”, “4 INSULATED SUPPLY”, “5 BUILDING LOOP”, “6 RETURN + REINJECTION”. Use coral-red arrows for hot geothermal water rising from the aquifer, golden-yellow arrows for clean heated water traveling to buildings, and teal-blue arrows for cooler water returning and descending through the reinjection well. Make the two closed circuits visually separate at the heat exchanger. Add one prominent callout beside it: “TWO WATER LOOPS. NO MIXING.” Include a small three-swatch legend reading “GEOTHERMAL”, “HOT SUPPLY”, and “COOL RETURN”.\n\nArt direction: sophisticated editorial vector illustration with crisp geometric forms, subtle screen-printed grain, thin navy technical linework, rounded annotation boxes, and restrained cartographic details. Palette of warm ivory paper, midnight navy, volcanic coral, mineral teal, and geothermal yellow. Strong information hierarchy, generous margins, balanced square composition, highly legible uppercase sans-serif typography, accurate arrows, uncluttered spacing. The underground infrastructure must remain the visual focus. No logo, no branding, no extra text, no UI, no website mockup, no photorealism, no decorative fantasy elements.",
  "width": 1024,
  "height": 1024,
  "settings": {
    "thinking": true
  }
}
```

---

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

![Vintage Rescue Helicopter Arctic Composite](https://assets.runware.ai/examples/alibaba-qwen-image-2-1-turbo/de55f3b0-cfd0-465c-a333-815513a0e62f.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "2c473d6b-4aca-4226-82cf-51099178e4c9",
  "model": "alibaba:qwen-image@2.1-turbo",
  "positivePrompt": "Create a finished, photorealistic scene-replacement composite for an aviation museum campaign. The unmistakable hero subject is a restored late-1960s twin-engine search-and-rescue helicopter with a rounded cockpit, boat-shaped fuselage, large side door, stationary five-blade rotor and vivid international-orange paint with cream panels. Show the complete aircraft in a low three-quarter side view, parked securely on a windswept Arctic ice shelf. Preserve crisp structural detail, realistic rivets, windows, landing gear and subtle age in the paint; no logos, insignia, registration numbers or text. Replace any museum or studio context with a vast polar setting: fractured blue-white ice, low snow ridges, a dark steel-blue ocean channel and distant angular mountains beneath a pale cyan twilight sky. Warm amber light glows softly from the cabin windows, contrasting with the cold environment. Add fine windblown snow around the landing gear and physically accurate blue reflections beneath the fuselage, but keep the aircraft unobstructed. Square composition with generous breathing room, rotor fully inside frame, horizon in the upper third, restrained cinematic color grade, crisp editorial realism, seamless contact shadows, natural atmospheric depth. No people, vehicles, buildings, signage, borders or typography.",
  "width": 1024,
  "height": 1024,
  "settings": {
    "thinking": true
  }
}
```

---

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

![Forensic Entomologist Creator Avatar](https://assets.runware.ai/examples/alibaba-qwen-image-2-1-turbo/d64b1c4d-ca90-4693-a254-f3abd982d234.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "e4cf97a6-12b9-4a6f-83ab-a031e4c4e7ba",
  "model": "alibaba:qwen-image@2.1-turbo",
  "positivePrompt": "Transform the referenced scientist into a polished illustrated avatar for a forensic entomology educator’s professional profiles. Preserve her recognizable identity precisely: oval face, warm brown complexion, thick straight brows, small mole below the left eye, round amber glasses, chin-length black bob, distinctive silver streak above the right temple, and calm confident half-smile. Create a centered chest-up portrait with direct eye contact, placing her entire head and shoulders inside the central square safe area so the artwork crops cleanly into a circular profile icon. Replace the plain shirt with a modern ink-navy laboratory jacket featuring subtle celadon piping and no logo. Art direction: sophisticated hand-cut paper collage combined with crisp risograph textures, simplified dimensional shapes, tactile paper grain, clean facial contours, and restrained halftone shadows. Surround her with an orderly radial motif inspired by microscope slides, beetle wing structures, and specimen-drawer geometry; keep these elements abstract, elegant, and secondary to the face rather than creepy. Landscape master composition with balanced decorative space on both sides. Palette of ink navy, oxblood, celadon green, butter yellow, and warm cream. Warm, intelligent, meticulous mood; editorial-quality finish, strong silhouette, excellent small-size readability. No words, letters, logos, watermark, interface, border, or photorealistic background.",
  "width": 1536,
  "height": 1024,
  "settings": {
    "promptExtendMode": "direct"
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/5e36326b-218a-4911-8741-66a4e12598f7.jpg"
    ]
  }
}
```

---

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

![Wayang Exhibition Campaign Hero](https://assets.runware.ai/examples/alibaba-qwen-image-2-1-turbo/b36cba2a-b5da-4a35-8f06-3978ebfc84dc.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "fb6fe31b-e7cc-49df-b7dc-a0b070b894e6",
  "model": "alibaba:qwen-image@2.1-turbo",
  "positivePrompt": "Transform the reference catalog photograph into a finished landscape hero image for a museum exhibition about Javanese puppetry. Preserve the exact wayang golek puppet as the recognizable primary subject: retain its carved ivory-painted face, long pointed nose, facial painting, gold-and-red crown, articulated arms, control rods, proportions, age patina, indigo batik costume, gold embroidery, and fine material details. Keep the puppet fully visible and sharply focused, positioned slightly right of center at approximately the same viewing angle. Replace only the plain studio background with the backstage edge of an intimate traditional Indonesian performance pavilion at blue hour. Behind the puppet, show a large cream cotton shadow-play screen glowing with warm amber lamplight, faint soft-edged silhouettes of other puppets, dark teak beams, a partially visible bronze gamelan instrument, and folded deep-red stage textiles. Create believable contact, scale, and warm rim light along the puppet that matches the illuminated screen, with subtle cool indigo ambient light from the open pavilion. Refined cultural-documentary photography, elegant museum art direction, restrained amber, indigo, teak brown, and muted crimson palette, quiet anticipatory mood, natural depth of field, realistic optics and textures. Leave clean negative space on the left for separate campaign typography, but include no text, logos, labels, borders, display case, or interface elements.",
  "width": 1536,
  "height": 1024,
  "settings": {
    "promptExtendMode": "direct"
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/956f3aea-d890-4681-ae17-8f34194e7392.jpg"
    ]
  }
}
```