---
title: Qwen-Image-3.0-Pro | Runware Docs
url: https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro
description: High-control image generation and editing for dense layouts, small text rendering, and multilingual visual design
---
# Qwen-Image-3.0-Pro

![Qwen-Image-3.0-Pro](https://assets.runware.ai/covers/alibaba-qwen-image-3-0-pro.jpg)

Qwen-Image-3.0-Pro is Alibaba's higher-capability Qwen Image 3.0 model for both text-to-image generation and prompt-guided image editing. It is built for visually dense and instruction-heavy work, with stronger support for complex layouts, image-within-image compositions, multilingual typography, and precise small-text rendering while preserving high photorealistic detail in faces, skin, hair, and materials. It is especially well suited to posters, menus, storyboards, interface mockups, branded graphics, and other production workflows where layout fidelity and text quality matter as much as raw image quality.

- **Status**: live
- **ID**: `alibaba:qwen-image@3.0-pro`
- Try in Playground
- **Creator**: Alibaba
- **Release Date**: August 4, 2026
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

$0.04 from, per run · ~1m 10s per request

**Rates**

- 1K output image · per run: `$0.04`
- 2K output image · per run: `$0.075`
- Input image · per input image: `$0.003`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro/examples#example-colorized-cable-ship-archive-photograph) · 1536×1024: `$0.04` (~11s)
- [text-to-image](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro/examples#example-municipal-geothermal-campaign-key-visual) · 1536×1024: `$0.04` (~12s)
- [reference-to-image](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro/examples#example-museum-pest-investigation-blog-hero) · 1024×1536: `$0.046` (~2m 34s)
- [reference-to-image](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro/examples#example-atlantic-dulse-carton-packaging) · 1024×1536: `$0.046` (~2m 7s)

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.promptExtendMode` 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-3-0-pro#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-3-0-pro#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-3-0-pro#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro#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-3-0-pro#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-3-0-pro#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-3-0-pro#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/alibaba-qwen-image-3-0-pro#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-3-0-pro#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-3-0-pro#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/alibaba-qwen-image-3-0-pro#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-3-0-pro#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro#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/alibaba-qwen-image-3-0-pro#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`
- **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-3-0-pro#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `alibaba:qwen-image@3.0-pro`

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-3-0-pro#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `32000`

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/alibaba-qwen-image-3-0-pro#request-negativeprompt)

- **Type**: `string`
- **Min**: `2`
- **Max**: `16000`

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/alibaba-qwen-image-3-0-pro#request-width)

- **Type**: `integer`
- **Min**: `1`
- **Default**: `1024`

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-3-0-pro#request-height)

- **Type**: `integer`
- **Min**: `1`
- **Default**: `1024`

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-3-0-pro#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-3-0-pro#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-3-0-pro#request-settings-promptextendmode)

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

Rewriting strategy for `promptExtend`.

**Allowed values**:

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

**Features**

Standalone addons and post-processing features.

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

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro#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-3-0-pro#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-3-0-pro#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-3-0-pro#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro#response-imagedatauri)

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

Data URI of the output image.

### [seed](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro#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-3-0-pro#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/alibaba-qwen-image-3-0-pro#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)

![Colorized Cable Ship Archive Photograph](https://assets.runware.ai/examples/alibaba-qwen-image-3-0-pro/962dd576-c6e3-406a-912d-e92286c58513.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "5a3892b0-ed8a-46b2-8db0-2876c0afb0fa",
  "model": "alibaba:qwen-image@3.0-pro",
  "positivePrompt": "Create the finished restored and colorized archival photograph for a maritime communications museum collection. Reconstruct a historically plausible 1928 documentary photograph taken on the open deck of a British transatlantic cable-repair ship in the North Atlantic. Six weathered cable engineers and deckhands stand and crouch around a freshly hauled submarine telegraph cable as two men carefully inspect its exposed copper core on a heavy wooden workbench. Include a vast iron cable drum, wet hemp rope, riveted steel fittings, capstan machinery, canvas oilskins, knitted watch caps, wool trousers, salt-stained leather boots, hand tools and a low ship rail. Beyond the rail, show a cold steel-blue sea with modest swells and a hazy horizon beneath an overcast sky. Arrange the crew in a natural working tableau rather than a formal pose: one older foreman studies the splice, two workers guide the thick cable, another wipes his hands, and two figures watch from beside the drum. Preserve distinct, realistic faces, working hands and period-correct clothing.\n\nCompose as a 3:2 landscape press photograph made with a late-1920s large-format camera: eye-level viewpoint, slightly wide framing, crew concentrated across the lower middle, cable drum anchoring the left side, workbench and exposed cable forming a strong diagonal toward the right, open sea providing breathing room above the rail. Soft diffused maritime daylight, damp surfaces, subdued contrast and believable depth. Apply expert museum-grade restoration: missing emulsion and torn areas seamlessly reconstructed, scratches, dust, chemical stains, fold marks and silvering removed, facial detail and machinery recovered without making them unnaturally sharp. Retain subtle period lens softness, gentle corner falloff and a fine, authentic monochrome-film grain structure beneath the color.\n\nUse conservative hand-colorization appropriate to a professionally restored archive print: muted navy and charcoal workwear, faded ochre oilskins, dark brown leather, weathered reddish-brown wood, gunmetal machinery, dull copper strands, pale wind-reddened skin, cool gray-blue sea and cloud cover. Colors should feel researched, restrained and slightly desaturated, never modern, glossy or cinematic. The result must be one seamless full-frame historical photograph, not a before-and-after comparison, not a collage, not a framed print, and not a museum display mockup. No captions, dates, logos, borders or visible writing.",
  "width": 1536,
  "height": 1024,
  "providerSettings": {
    "alibaba": {
      "promptExtend": false
    }
  }
}
```

---

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

![Municipal Geothermal Campaign Key Visual](https://assets.runware.ai/examples/alibaba-qwen-image-3-0-pro/32c1b2ce-c21a-47b2-afad-73977c38beb9.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "ea26aa9a-d335-4a26-9c67-ebfc6288c3c9",
  "model": "alibaba:qwen-image@3.0-pro",
  "positivePrompt": "Create a finished landscape brand campaign key visual for CIVIC GROUND, a municipal geothermal utility. Use a sophisticated editorial cutaway composition that reveals an entire city block above and below ground. Across the upper third, show a calm winter neighborhood at blue hour: three contemporary brick apartment buildings, a small public library, bare street trees, pedestrians in coats, bicycles, and softly illuminated windows. A light dusting of snow covers roofs and pavement. The street is shown in precise architectural side elevation, while the earth beneath it occupies the lower two-thirds of the image as a dramatic geological cross-section. Render layered bands of clay, sandstone, granite, and deep bedrock in rich mineral colors. Two slender geothermal boreholes descend vertically through the strata, connected by elegant vermilion-red and pale-cyan flow lines that loop back toward a compact neighborhood energy station. Show subtle heat movement as clean graphic gradients and fine contour lines rather than flames or science-fiction effects.\n\nArt direction: premium European public-infrastructure campaign, combining mid-century screen-print geometry, contemporary architectural illustration, and scientific atlas clarity. Slightly tactile paper grain, crisp vector-like edges, restrained halftone shading, carefully simplified human figures, credible engineering details. Palette of midnight cobalt, warm brick red, mineral ochre, chalk cream, muted teal, and one vivid vermilion accent. The contrast between the quiet snowy city above and the warm geological layers below should communicate dependable hidden energy. Mood: intelligent, civic-minded, optimistic, calm, trustworthy, not corporate stock imagery.\n\nReserve a clean field of midnight cobalt in the upper-left sky for campaign typography. Set the following exact text, with correct spelling and no additional words: a small uppercase brand line “CIVIC GROUND” and beneath it a large bold headline on two lines, “HEAT, FROM HERE.” Use a modern condensed sans-serif in warm cream, left aligned, with excellent kerning and generous spacing. Integrate a simple circular brand mark beside CIVIC GROUND: three concentric contour rings with a single vertical line descending through them. Keep all typography fully legible and comfortably inside safe margins. Balance the buildings toward the upper-right so the headline has ample negative space. Wide 3:2 composition, polished advertising finish, suitable as the master image for outdoor media, transit placements, a campaign landing page, and press materials.",
  "negativePrompt": "photorealistic stock photography, generic smart-city imagery, solar panels, wind turbines, flames, lava, fantasy caverns, futuristic holograms, app interface, website mockup, buttons, illegible lettering, misspelled words, extra copy, crowded layout, cartoon style, childish characters, distorted architecture, broken pipes, disaster scene, gloomy dystopian mood, watermark",
  "width": 1536,
  "height": 1024,
  "providerSettings": {
    "alibaba": {
      "promptExtend": false
    }
  }
}
```

---

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

![Museum Pest Investigation Blog Hero](https://assets.runware.ai/examples/alibaba-qwen-image-3-0-pro/b5bd4d4a-cf4e-4f78-90f8-1bb9222536e8.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "754862c2-9b22-4b69-a980-e4cba32503cc",
  "model": "alibaba:qwen-image@3.0-pro",
  "positivePrompt": "Create a finished portrait-format blog hero for a serious museum conservation feature. Use reference image 1 to preserve the conservator’s recognizable face, navy work coat, gloves, rolled tapestry, and authentic collection-storage environment. Use reference image 2 to preserve the exact appearance, striped bristles, anatomy, and crimson wool setting of the carpet beetle larva. Combine both references into one coherent editorial photomontage: the conservator occupies the lower-right half, inspecting the tapestry beneath a focused task lamp, while an enlarged macro view of the beetle larva emerges across the upper-left as if revealed through a circular inspection lens. Make the scale shift intentional and scientifically legible, not a giant insect physically present in the room. Add subtle archival pest-monitoring details—small specimen pins, a paper inspection grid, fiber fragments, and restrained diagram lines—integrated around the macro inset.\n\nArt direction: sophisticated 1970s scientific-journal collage updated with crisp contemporary photographic detail; deep ultramarine shadows, acid-chartreuse annotation accents, warm ivory paper texture, and controlled crimson from the damaged wool. Investigative, intelligent, slightly tense, never horror or sensationalist. Strong depth, precise skin and textile texture, clean cut-paper transitions, restrained halftone grain, premium cultural-institution editorial design.\n\nReserve a calm ivory title field across the upper third without covering the larva’s head. Set the exact text “COLLECTIONS CARE” as a small uppercase kicker, “THE TINY THREAT” as the large two-line headline, and “Inside the quiet war against museum pests” as a smaller deck. Typography must be crisp, correctly spelled, highly legible, and limited to those three text elements. Use a condensed bold grotesque for the headline and a clean modern sans serif for the supporting text. Maintain generous margins and a clear reading hierarchy suitable for a museum journal blog hero and vertical social preview. One finished standalone editorial image, full bleed, no website interface, no browser frame, no logo, no buttons, no mockup.",
  "negativePrompt": "Horror imagery, monstrous insect, giant insect physically attacking a person, gore, damaged face, extra fingers, distorted hands, incorrect beetle anatomy, duplicate person, duplicate larva, cluttered layout, illegible lettering, misspelled text, extra words, fake logo, website interface, browser window, navigation bar, social media UI, button, device mockup, low resolution, plastic skin, oversaturated colors, whimsical fantasy",
  "width": 1024,
  "height": 1536,
  "providerSettings": {
    "alibaba": {
      "promptExtend": true,
      "promptExtendMode": "direct"
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/9a8f6fd3-d850-4d4d-8391-753bd131d740.jpg",
      "https://assets.runware.ai/assets/inputs/37a79aaf-684f-48f3-a0ca-512fe7289267.jpg"
    ]
  }
}
```

---

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

![Atlantic Dulse Carton Packaging](https://assets.runware.ai/examples/alibaba-qwen-image-3-0-pro/d1089fce-83b7-48f3-acd7-d140f315ba62.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "df553d60-d1d5-4122-a26a-e5473503335f",
  "model": "alibaba:qwen-image@3.0-pro",
  "positivePrompt": "Create a finished photorealistic packaging visualization for an upscale smoked dulse seaweed product. Show one tall, slim folding-paper carton standing upright on a seamless warm gray studio surface, front panel facing the viewer with a narrow portion of the right side visible. Compose vertically so the carton fills most of the 1024x1536 portrait frame, with a subtle grounding shadow and ample neutral breathing room.\n\nUse reference image 1 as the direct botanical guide for the central dulse illustration: preserve the specimen's recognizable branching silhouette, delicate translucent fronds, burgundy-red coloration and organic imperfections. Render it as a refined archival herbarium image printed into the carton design, not as loose seaweed sitting in front of the package.\n\nUse reference image 2 as the guide for the supporting graphic system: adapt its coastline contours, sounding lines, coordinate grid and navigational marks into a restrained background pattern wrapping from the front onto the right side. Borrow the chart's visual rhythm and cartographic line quality, but do not copy any place names or existing text from the reference. Both references must feel deliberately integrated into one coherent label system: botanical specimen in the foreground, nautical survey geometry behind it.\n\nArt direction: a 1960s oceanographic field report reinterpreted as contemporary premium pantry packaging. Uncoated warm parchment board with visible paper fibers, deep oxblood botanical tones, marine navy linework, muted kelp green accents and one small flash of mineral orange. Precise editorial grid, generous margins, thin rules, compact sans-serif typography paired with a dignified high-contrast serif. Sophisticated, scientific, coastal and understated rather than rustic.\n\nRender the following front-panel wording clearly and exactly, with strong hierarchy:\nPELAGIC\nNO. 04\nSMOKED DULSE\nPalmaria palmata\nHAND-HARVESTED SEA VEGETABLE\nNORTH ATLANTIC COAST\nNET WT 40 g / 1.4 oz\n\nPlace “PELAGIC” at the top in spaced uppercase letters. Make “SMOKED DULSE” the dominant product name. Set the Latin name in small italic serif type directly beneath it. Include “NO. 04” inside a small mineral-orange survey-style index box. Keep the remaining copy legible but secondary. On the visible right side panel, add a narrow vertical label reading “SEA VEGETABLES” and continue the nautical coordinate grid around the fold.\n\nShow realistic print production details: crisp ink registration, subtle debossing on the word PELAGIC, matte uncoated stock, clean folded edges and believable carton thickness. Soft directional studio light from upper left, natural paper texture, restrained highlights, premium commercial product-render quality. The result must be a single complete package visualization, not a dieline, mood board, webpage, poster or collection of alternate concepts.",
  "negativePrompt": "Illegible typography, misspelled text, extra wording, copied chart place names, multiple packages, cans, bottles, plastic pouch, loose seaweed obscuring the carton, rustic craft aesthetic, bright tropical colors, glossy laminate, excessive gold foil, cluttered layout, barcode on front, website interface, mockup template labels, hands, people, dramatic scenery, warped carton, bent typography, low-resolution print, blurry details",
  "width": 1024,
  "height": 1536,
  "providerSettings": {
    "alibaba": {
      "promptExtend": true,
      "promptExtendMode": "direct"
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/5cff7cc9-7f2c-43b7-99bb-c1908527e447.jpg",
      "https://assets.runware.ai/assets/inputs/c2755f11-4cda-4d73-bdf0-2f3893c556db.jpg"
    ]
  }
}
```