---
title: Qwen-Image-3.0 | Runware Docs
url: https://runware.ai/docs/models/alibaba-qwen-image-3-0
description: Unified image generation and editing that balances visual quality, layout fidelity, and response speed
---
# Qwen-Image-3.0

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

Qwen-Image-3.0 is the standard model in Alibaba's Qwen Image 3.0 family, supporting both text-to-image generation and prompt-guided image editing in a single endpoint. It keeps the family’s strengths in structured visual composition, typography-heavy generation, multilingual text rendering, and multi-image editing, but is positioned as the quality-speed balanced option rather than the highest-fidelity Pro tier. It is a strong fit for everyday creative production where teams want one model for generation and editing, support for one to three reference images, and reliable handling of layout-sensitive prompts without always reaching for the heavier model.

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

## Pricing

$0.03 per run · ~1m 23s per request

**Rates**

- Per run · per run: `$0.03`
- Input image · per input image: `$0.003`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/alibaba-qwen-image-3-0/examples#example-adaptive-beach-wheelchair-lifestyle-hero) · 1536×1024: `$0.03` (~1m 19s)
- [text-to-image](https://runware.ai/docs/models/alibaba-qwen-image-3-0/examples#example-tidal-turbine-linocut-wall-art) · 1536×1024: `$0.03` (~1m 27s)
- [reference-to-image](https://runware.ai/docs/models/alibaba-qwen-image-3-0/examples#example-horseshoe-crab-volunteer-social-post) · 1024×1536: `$0.036` (~1m 29s)
- [reference-to-image](https://runware.ai/docs/models/alibaba-qwen-image-3-0/examples#example-curbside-compost-pickup-pinterest-ad) · 1024×1536: `$0.036` (~1m 17s)

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#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#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#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#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#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#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#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#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#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#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#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#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

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

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

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#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#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#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#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#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#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#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#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#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#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#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#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#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#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#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#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#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#response-imageurl)

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

URL of the output image.

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

- **Type**: `string`

Base64-encoded image data.

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

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

Data URI of the output image.

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

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

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

![Adaptive Beach Wheelchair Lifestyle Hero](https://assets.runware.ai/examples/alibaba-qwen-image-3-0/01e16b1d-1561-400a-a6d6-6691f478bfe0.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "6854ed5a-47ef-4bbb-a018-f8f2c074e7be",
  "model": "alibaba:qwen-image@3.0",
  "positivePrompt": "Commercial lifestyle hero photograph for an adaptive recreation equipment campaign. Feature one premium all-terrain beach wheelchair as the unmistakable hero product: lightweight matte cobalt-blue tubular frame, supportive charcoal mesh seat, footrest, push handles, safety belt, and three oversized pale-gray balloon tires designed for soft sand. Place it at the end of an accessible timber boardwalk where it meets a broad windswept beach, angled three-quarters toward the ocean so the complete product and wheel construction are clearly visible. Low coastal grasses bend in the breeze, shallow tidal pools reflect the sky, and distant white surf creates layered depth. Fresh late-afternoon light after rain, luminous turquoise, cobalt, sand, and soft coral palette, crisp natural textures, subtle wet highlights on the tires, premium outdoor editorial photography, realistic engineering and proportions. Wide landscape composition with the wheelchair occupying the right-center foreground and open shoreline extending left, generous breathing room, low camera height, 35mm lens character, polished but believable, no people, no logos, no text.",
  "negativePrompt": "multiple wheelchairs, standard hospital wheelchair, bicycle, missing wheels, extra wheels, warped frame, impossible mechanics, buried product, cropped product, studio backdrop, interior scene, people, hands, logos, labels, typography, watermark, UI elements, oversaturated fantasy colors, illustration, CGI appearance",
  "width": 1536,
  "height": 1024,
  "providerSettings": {
    "alibaba": {
      "promptExtend": true,
      "promptExtendMode": "agent"
    }
  }
}
```

---

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

![Tidal Turbine Linocut Wall Art](https://assets.runware.ai/examples/alibaba-qwen-image-3-0/08eca4f7-1d06-4623-8519-e110a49d323e.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "e36c74df-aa08-41c8-b5e7-c5829736c66e",
  "model": "alibaba:qwen-image@3.0",
  "positivePrompt": "Finished landscape wall artwork, not a framed mockup: a dramatic cutaway view through a tidal strait where the world above and below the waterline appears in one continuous composition. Above water, low wind-shaped islands, a tiny lighthouse, distant working boats, and wheeling seabirds beneath a broad dawn sky. Below water, three elegant tidal turbines stand on the rocky seabed as powerful currents sweep through their blades; schools of silver fish curve around the machinery, kelp forests cling to the rocks, and layered current lines reveal the flow of the sea. Render as a sophisticated hand-carved reduction linocut with bold simplified forms, visible carved marks, tactile ink grain, and slight handmade registration variation. Restrained palette of deep indigo, oxidized teal, warm bone, coral red, and muted mustard. Strong panoramic rhythm, turbine silhouettes concentrated across the lower middle, generous sky for visual calm, balanced asymmetry, crisp printable edges, refined contemporary maritime art suitable for an architect's office or museum design shop. No lettering, labels, border, frame, room interior, or signature.",
  "negativePrompt": "photorealism, glossy 3D rendering, generic fantasy seascape, steampunk machinery, text, captions, logos, watermark, signature, decorative frame, wall mockup, furniture, people in foreground, cluttered composition, neon colors",
  "width": 1536,
  "height": 1024,
  "providerSettings": {
    "alibaba": {
      "promptExtend": true,
      "promptExtendMode": "agent"
    }
  }
}
```

---

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

![Horseshoe Crab Volunteer Social Post](https://assets.runware.ai/examples/alibaba-qwen-image-3-0/275f1b83-166a-4d70-84d1-aed5859b5c14.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "5eb2f3f9-2b5c-480d-bda8-1a67be216d11",
  "model": "alibaba:qwen-image@3.0",
  "positivePrompt": "Create a finished 1024x1536 portrait social media recruitment post for a nonprofit horseshoe crab monitoring event. Use the horseshoe crab from reference image 1 as the dominant subject, preserving its recognizable anatomy, shell markings, and long telson. Integrate the gloved volunteer hands and measuring activity from reference image 2 into the lower portion as a secondary documentary detail. Art direction: contemporary marine-science editorial design with the tactile energy of a two-color risograph print, deep cobalt blue, fluorescent safety orange, warm uncoated-paper cream, coarse halftone dots, subtle ink misregistration, torn paper edges, measurement ticks, tide-chart curves, and small scientific annotation marks. Strong asymmetric composition with the crab crossing diagonally through the center and generous clear space for typography. Include only this exact, clearly legible text: large headline “NIGHT TIDE COUNT”; supporting line “MAY 18 · DELAWARE BAY”; footer “VOLUNTEERS NEEDED”. Use bold condensed sans-serif lettering, disciplined hierarchy, and excellent contrast. Make it feel urgent, practical, ecological, and credible rather than whimsical. Standalone social graphic, edge-to-edge artwork, no device frame, no interface, no logo, no CTA button.",
  "negativePrompt": "Misspelled words, additional text, fake logos, app interface, website mockup, phone frame, fantasy creature, incorrect horseshoe crab anatomy, extra tails, duplicated hands, distorted gloves, glossy corporate stock-photo aesthetic, photorealistic gore, cluttered typography, weak contrast, illegible lettering.",
  "width": 1024,
  "height": 1536,
  "providerSettings": {
    "alibaba": {
      "promptExtend": true,
      "promptExtendMode": "direct"
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/43cfbdaf-cff9-4c15-a201-10ca57290e25.jpg",
      "https://assets.runware.ai/assets/inputs/fc26813f-0af4-4df6-bea9-d50c0e70a434.jpg"
    ]
  }
}
```

---

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

![Curbside Compost Pickup Pinterest Ad](https://assets.runware.ai/examples/alibaba-qwen-image-3-0/2bc45d5a-2b74-4eca-a434-5318af0306f3.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "408a6d24-86a2-4c19-ac85-ffd220cc603f",
  "model": "alibaba:qwen-image@3.0",
  "positivePrompt": "Create a finished 2:3 portrait Pinterest advertisement for a modern weekly curbside food-scrap pickup service. Use reference image 1 as the exact product guide: preserve the compact teal compost caddy's recognizable proportions, lid, handle and color. Place it prominently in the lower center, rendered as a crisp photoreal product cutout. Use the specific scraps from reference image 2 as subject guidance, transforming them into a dynamic upward spiral that transitions into rich dark soil, seedlings and fresh herb leaves. Surround the photography with tactile cut-paper shapes and coarse risograph textures in chartreuse, persimmon orange, deep plum and warm cream. Optimistic, clever, design-forward environmental campaign rather than rustic farm imagery. Strong editorial hierarchy with generous negative space. At the top, render the exact large headline: \"SCRAPS, MEET SOIL.\" Under it, render the exact smaller line: \"WEEKLY FOOD-SCRAP PICKUP\". Along the bottom, render the exact compact footer: \"CLEAN BINS • LOCAL COMPOST\". Bold condensed sans-serif typography, perfectly legible spelling, flat front-facing finished artwork, no interface, no mockup, no invented logo, no CTA button.",
  "negativePrompt": "Illegible text, misspelled words, extra copy, invented brand names, logos, app interface, browser frame, CTA button, rustic farmhouse styling, dirty bin, plastic trash bags, landfill imagery, gloomy mood, distorted product, duplicated handle, malformed food, cluttered composition, watermark.",
  "width": 1024,
  "height": 1536,
  "providerSettings": {
    "alibaba": {
      "promptExtend": true,
      "promptExtendMode": "direct"
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/23b6934b-aeaa-4f8c-8f66-4a7d903e1f91.jpg",
      "https://assets.runware.ai/assets/inputs/9633c121-4809-46f4-99e8-07ce91ebeeda.jpg"
    ]
  }
}
```