---
title: Wan2.6 Image | Runware Docs
url: https://runware.ai/docs/models/alibaba-wan2-6-image
description: High fidelity image generation built on the Wan2.6 visual stack
---
# Wan2.6 Image

![Wan2.6 Image](https://assets.runware.ai/covers/alibaba-wan2-6-image.jpg)

Wan2.6 Image is a single-frame image generation model derived from the Wan2.6 multimodal video architecture. It focuses on strong prompt adherence, clean spatial structure, and visually coherent results, delivering video-grade image quality for creative, editorial, and product-oriented workflows.

- **Status**: live
- **ID**: `alibaba:wan@2.6-image`
- Try in Playground
- **Creator**: Alibaba
- **Release Date**: December 16, 2025
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

$0.03 per run · ~16s per request

**4 example generations**

- [reference-to-image](https://runware.ai/docs/models/alibaba-wan2-6-image/examples#example-storm-chaser-broadcast-avatar) · 1024×1600: `$0.03` (~17s)
- [text-to-image](https://runware.ai/docs/models/alibaba-wan2-6-image/examples#example-conservas-bar-menu-hero-photograph) · 1600×1024: `$0.03` (~15s)
- [reference-to-image](https://runware.ai/docs/models/alibaba-wan2-6-image/examples#example-paleobotanist-linocut-profile-avatar) · 1024×1600: `$0.03` (~13s)
- [text-to-image](https://runware.ai/docs/models/alibaba-wan2-6-image/examples#example-experimental-folk-album-cover) · 1600×1024: `$0.03` (~17s)

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/alibaba-wan2-6-image#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/alibaba-wan2-6-image#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-wan2-6-image#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/alibaba-wan2-6-image#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-wan2-6-image#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-wan2-6-image#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-wan2-6-image#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-wan2-6-image#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-wan2-6-image#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/alibaba-wan2-6-image#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-wan2-6-image#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-wan2-6-image#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/alibaba-wan2-6-image#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-wan2-6-image#request-inputs-referenceimages)

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

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-wan2-6-image#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `alibaba:wan@2.6-image`

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-wan2-6-image#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `2100`

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-wan2-6-image#request-negativeprompt)

- **Type**: `string`
- **Min**: `1`
- **Max**: `500`

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-wan2-6-image#request-width)

- **Type**: `integer`
- **Required**: true
- **Min**: `1`
- **Max**: `4096`
- **Step**: `1`

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-wan2-6-image#request-height)

- **Type**: `integer`
- **Required**: true
- **Min**: `1`
- **Max**: `4096`
- **Step**: `1`

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)

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/alibaba-wan2-6-image#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-wan2-6-image#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/alibaba-wan2-6-image#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-wan2-6-image#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-wan2-6-image#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-wan2-6-image#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/alibaba-wan2-6-image#request-advancedfeatures-watermark-bgcolor)

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

Background color in hex format.

**Provider Settings**

Parameters specific to this model provider. These must be nested inside the \`providerSettings.alibaba\` object.

### [promptExtend](https://runware.ai/docs/models/alibaba-wan2-6-image#request-providersettings-alibaba-promptextend)

- **Path**: `providerSettings.alibaba.promptExtend`
- **Type**: `boolean`
- **Default**: `true`

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

## Response Parameters

### [taskType](https://runware.ai/docs/models/alibaba-wan2-6-image#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-wan2-6-image#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-wan2-6-image#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/alibaba-wan2-6-image#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/alibaba-wan2-6-image#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/alibaba-wan2-6-image#response-imagedatauri)

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

Data URI of the output image.

### [NSFWContent](https://runware.ai/docs/models/alibaba-wan2-6-image#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/alibaba-wan2-6-image#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)

![Conservas Bar Menu Hero Photograph](https://assets.runware.ai/examples/alibaba-wan2-6-image/0d9a6ef1-989d-42ec-a8ce-3ddd1b25cc61.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "4af83088-5f1e-4553-9f13-db8bb91f170c",
  "model": "alibaba:wan@2.6-image",
  "positivePrompt": "Create a polished commercial food photograph for a contemporary coastal conservas bar menu. A generous Spanish preserved-seafood spread sits on a cobalt-blue glazed tile table in direct Mediterranean midday sunlight. Show three open, unlabeled brushed-aluminum tins arranged in a clean diagonal composition: plump sardines gleaming in olive oil with thin lemon wheels, orange escabeche mussels with translucent shallot and parsley, and tender octopus slices dusted with smoked paprika. Surround them with a small plate of crisp golden potato chips, charred sourdough, green olives, cornichons, a cut lemon, and a chilled stemmed copita of pale fino sherry with realistic condensation. Include a folded vermilion linen napkin and a simple stainless seafood fork. Every item should look edible, fresh, and meticulously styled, with believable oil reflections, crisp bread texture, delicate seafood detail, and restrained crumbs. Photograph from a slightly elevated three-quarter angle using a professional full-frame camera and 50mm lens. Hard sunlight creates graphic striped shadows from an unseen slatted awning, while soft bounce light preserves detail in the tins. Palette: saturated cobalt, tomato orange, silver, lemon yellow, and olive green. Landscape framing, balanced visual hierarchy, sharp hero food with gentle depth falloff, premium editorial menu photography, natural color, photorealistic, no people, no lettering or branding.",
  "negativePrompt": "Text, logos, labels, packaging graphics, menu layout, people, hands, duplicate dishes, warped tins, malformed utensils, floating ingredients, raw-looking seafood, muddy colors, greasy mess, excessive garnish, plastic food, illustration, CGI, oversaturation, harsh clipped highlights, deep crushed shadows, extreme wide-angle distortion, cluttered background, low resolution, blur",
  "width": 1600,
  "height": 1024
}
```

---

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

![Experimental Folk Album Cover](https://assets.runware.ai/examples/alibaba-wan2-6-image/b7e70620-e41f-4429-8dad-d21e77555af7.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "755d17d0-422c-4986-8dbe-f6957d4fc89b",
  "model": "alibaba:wan@2.6-image",
  "positivePrompt": "Finished landscape album cover artwork for an experimental folk-electronic record titled “FIRST LIGHT / LAST PICK” by “NADIA SERRANO”. A cinematic documentary photograph of a nocturnal saffron harvest in rural Spain just before dawn: a vast field of deep violet crocuses receding into low blue fog, five farm workers spaced naturally across the rows, kneeling and carefully gathering flowers into shallow wicker baskets. Their practical dark workwear and small amber headlamps create warm points of light against the cold landscape. In the foreground, dew-covered crocus petals and vivid red saffron threads are rendered with tactile macro detail; the middle distance shows human activity clearly; distant low hills dissolve into mist beneath a charcoal-indigo sky. One old utility vehicle sits far off with soft headlights glowing through the haze. Quiet, patient, grounded mood rather than romantic fantasy. Sophisticated contemporary music photography, restrained analog grain, subtle halation around lamps, rich violet, ink blue, rust red and warm amber palette, deep tonal range, natural faces and hands, coherent agricultural details. Strong panoramic composition with the horizon in the upper third and intentional negative space in the dark sky. Clean condensed ivory typography in the upper left: large exact title “FIRST LIGHT / LAST PICK”; smaller artist name directly beneath: “NADIA SERRANO”. Typography should feel editorial and integrated, with generous tracking and no additional wording. Flat final cover art only, edge-to-edge image, not a physical record mockup.",
  "negativePrompt": "fantasy creatures, magical glow, ornate costumes, oversaturated neon, daytime sunlight, city skyline, staged fashion poses, crowded scene, duplicated workers, distorted hands, illegible lettering, misspelled title, extra text, logos, border, vinyl record, CD case, product mockup, app interface, watermark",
  "width": 1600,
  "height": 1024
}
```

---

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

![Storm Chaser Broadcast Avatar](https://assets.runware.ai/examples/alibaba-wan2-6-image/06682d88-0d5e-4779-8849-2c1c57183df2.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "d2fc25ff-2a87-4751-9d4e-33a60e6a9905",
  "model": "alibaba:wan@2.6-image",
  "positivePrompt": "Create a premium stylized profile avatar for a professional severe-weather livestreamer. Use reference image 1 as the strict identity anchor: preserve the subject’s recognizable facial structure, warm brown complexion, short wavy black hair with its single silver streak, round dark glasses, nose ring, age and calm, capable expression. Use reference image 2 as the environment and lighting anchor: place them inside the storm-chasing command van, with simplified radar screens and radio hardware behind them, and echo the cobalt storm light, safety-orange equipment glow and distant supercell visible through the side window.\n\nRender the final portrait as sophisticated editorial vector art with screen-printed texture: crisp geometric shadow shapes, restrained halftone grain, bold cobalt blue, charcoal, warm cream and signal orange palette. Chest-up, nearly frontal pose, slight three-quarter turn, direct eye contact, face dominant and unobstructed. Give the subject a dark field jacket with one small orange reflective tab and a compact radio microphone clipped near the collar. Frame loosely enough for the full 1024x1600 portrait while keeping the head and shoulders inside a central square and circular avatar-safe area. Strong silhouette, clean separation from the equipment, subtle storm-energy arcs derived from radar contours, confident and analytical rather than heroic or sensational. Polished creator-brand artwork, no lettering, no logo, no watermark.",
  "negativePrompt": "Photorealistic rendering, generic face, changed identity, extra people, duplicated glasses, obscured eyes, exaggerated superhero pose, disaster spectacle, lightning crossing the face, cluttered composition, illegible interface text, typography, logo, watermark, deformed hands, distorted equipment, childish cartoon style, neon rainbow palette.",
  "width": 1024,
  "height": 1600,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/2368c8be-58b7-46fd-9aff-11cf4141152f.jpg",
      "https://assets.runware.ai/assets/inputs/ad179cf0-3a33-4cb6-9f2f-c7d16e84e811.jpg"
    ]
  }
}
```

---

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

![Paleobotanist Linocut Profile Avatar](https://assets.runware.ai/examples/alibaba-wan2-6-image/2750a922-a22f-425e-84f0-66bbd2978c02.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "1c58b435-5ab7-48c6-baa1-98e6aff55727",
  "model": "alibaba:wan@2.6-image",
  "positivePrompt": "Create a finished stylized professional profile avatar for a paleobotany researcher and science communicator. Use reference image 1 strictly as the identity anchor: preserve the person’s recognizable facial structure, skin tone, close-cropped curls, round dark-green glasses, expressive eyes, subtle tooth gap, age, and calm confident presence. Use reference image 2 strictly as the art-direction anchor: translate its hand-carved linocut contours, imperfect ink registration, fibrous paper texture, fern motifs, geological layers, and restrained inky-plum, terracotta, celery-green, charcoal, and cream palette into the portrait. Do not copy a face or composition from reference 2.\n\nHead-and-shoulders three-quarter portrait, subject looking directly toward the viewer with a slight intelligent half-smile, wearing a practical clay-colored field jacket with a small fossil-fern enamel pin. Render the face with flattering graphic simplification while retaining precise likeness and natural skin character. Surround the silhouette with an elegant circular arrangement of fossil fronds and stratigraphic bands, like a contemporary science-editorial emblem. Tall 1024x1600 composition with generous breathing room; keep the face large, centered, and entirely safe within a central square crop for profile-picture use. Crisp silhouette, balanced negative space, tactile printmaking detail, sophisticated museum-publication quality, warm and grounded rather than whimsical. Standalone artwork only, no frame, no mockup, no typography, no logo, no interface elements.",
  "negativePrompt": "Photorealism, generic face, altered ethnicity, changed age, missing glasses, exaggerated caricature, fantasy costume, steampunk elements, laboratory clichés, busy scenery, harsh neon colors, glossy 3D rendering, text, letters, watermark, logo, border, app interface, cropped head, obscured face, distorted features, asymmetrical eyes, extra accessories.",
  "width": 1024,
  "height": 1600,
  "providerSettings": {
    "alibaba": {
      "promptExtend": false
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/6f3e4738-1286-46e5-9219-f5d81acf750c.jpg",
      "https://assets.runware.ai/assets/inputs/35122f95-26d3-42f0-be29-db1256926ad3.jpg"
    ]
  }
}
```