MODEL ID alibaba:wan@2.7-image

live

Wan2.7 Image

by Alibaba April 1, 2026

Wan2.7 Image is a unified image generation and editing model from Alibaba that combines generation and interactive editing in a shared latent space. It features virtual avatar face customization with fine bone structure and eye shape control, a color palette system for extracting and applying consistent color schemes, precise marquee selection editing for pixel-level element manipulation, multilingual text rendering supporting up to 3000 tokens in 12 languages, and compositional generation of up to 12 images in a single output.

API Options

Platform-level options for task execution and delivery.

taskType string required value: imageInference: Identifier for the type of task being performed

taskUUID string required UUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType string default: URL: Image output type.

Allowed values 3 values

outputFormat 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.

**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 3 values

outputQuality integer min: 20 max: 99 default: 95: Compression quality of the output. Higher values preserve quality but increase file size.

webhookURL string URI

Specifies a webhook URL where JSON responses will be sent 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
PLATFORM

deliveryMethod string default: sync

Determines how the API delivers task results.

Allowed values 2 values

: Returns complete results directly in the API response.
: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

Learn more 1 resource

Task Polling
PLATFORM

uploadEndpoint string 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.

// 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 object

Content safety checking configuration for image generation.

Properties 2 properties

safety » checkContent checkContent boolean default: false: Enable or disable content safety checking. When enabled, defaults to fast mode.

safety » mode mode string default: none

Safety checking mode for image generation.

Allowed values 2 values

: Disables checking.
: Performs a single check.

ttl integer min: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean default: false: Include task cost in the response.

numberResults 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.

inputs » referenceImages referenceImages array of strings min items: 1max items: 9: List of reference images (UUID, URL, Data URI, or Base64).

Generation Parameters

Core parameters for controlling the generated content.

model string required value: alibaba:wan@2.7-image

Identifier of the model to use for generation.

Learn more 3 resources

positivePrompt string required max: 3000

Text prompt describing elements to include in the generated output.

Learn more 2 resources

width integer required min: 768 max: 2048 step: 16

Width of the generated media in pixels.

Learn more 2 resources

height integer required min: 768 max: 2048 step: 16

Height of the generated media in pixels.

Learn more 2 resources

seed integer min: 0 max: 2147483647

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

Learn more 1 resource

Text To Image: Seed Controlling Randomness Deterministically
GUIDE

Settings

Technical parameters to fine-tune the inference process. These must be nested inside the settings object.

settings » colorPalette colorPalette array of objects min items: 3max items: 10

Color palette to guide the generation. Each entry specifies a hex color and its ratio.

Properties 2 properties

settings » colorPalette » hex hex string required: Hex color code (e.g. '#C2D1E6').

settings » colorPalette » ratio ratio string required: Percentage weight of this color in the palette (e.g. '23.51%').

settings » editRegions editRegions array of arrays: Interactive editing regions. Must match the number of input images. Each entry is an array of bounding boxes in [x1, y1, x2, y2] format using absolute pixel coordinates. Use an empty array for images that don't need editing.

settings » sequential sequential boolean default: false: Enables image set output mode for generating multiple related images.

settings » thinking thinking boolean default: true: Enables thinking mode for improved quality at the cost of increased generation time.

taskType string required value: imageInference: Type of the task.

taskUUID string required UUID v4: UUID of the task.

imageUUID string required UUID v4: UUID of the output image.

imageURL string URI: URL of the output image.

imageBase64Data string: Base64-encoded image data.

imageDataURI string URI: Data URI of the output image.

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

NSFWContent boolean: Flag indicating if NSFW content was detected.

cost float: Task cost in USD. Present when includeCost is set to true in the request.

Image to Image

Art-Deco Glasshouse Masquerade

Request

{
  "taskType": "imageInference",
  "taskUUID": "135b1aef-72c7-41ff-86b5-8948386dcb33",
  "model": "alibaba:wan@2.7-image",
  "positivePrompt": "Create a lavish fantasy masquerade set inside a monumental glasshouse ballroom, combining the costume elegance of the first reference image with the architectural grandeur of the second reference image. A central masked dancer stands on a polished marble floor beneath a vast vaulted glass canopy, surrounded by guests in sculptural eveningwear, cascading tropical foliage, geometric brass details, mirrored surfaces, and floating ribbons of confetti. Emphasize refined Art Deco design, luminous reflections, intricate beadwork, graceful silhouettes, cinematic depth, and ultra-detailed textures. Rich, sophisticated atmosphere with a sense of spectacle and opulence, balanced composition, premium editorial aesthetic.",
  "width": 1024,
  "height": 1024,
  "seed": 22278,
  "settings": {
    "thinking": true,
    "colorPalette": [
      {
        "hex": "#1E2A39",
        "ratio": "34%"
      },
      {
        "hex": "#C6A15B",
        "ratio": "26%"
      },
      {
        "hex": "#E8E1D6",
        "ratio": "22%"
      },
      {
        "hex": "#2F6B5F",
        "ratio": "18%"
      }
    ]
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/83300796-47cf-413a-a2ad-cd1527b9c770.jpg",
      "https://assets.runware.ai/assets/inputs/9e450684-662c-489c-8827-ca3cc5a5b577.jpg"
    ]
  }
}

Response

{
  "taskType": "imageInference",
  "taskUUID": "135b1aef-72c7-41ff-86b5-8948386dcb33",
  "imageUUID": "a18bd5a6-8e90-4356-9824-8c8499c8a74e",
  "imageURL": "https://im.runware.ai/image/os/a09d21/ws/3/ii/a18bd5a6-8e90-4356-9824-8c8499c8a74e.jpg",
  "seed": 22278,
  "cost": 0.03
}

Text to Image

Basalt Library Sky Atrium

Request

{
  "taskType": "imageInference",
  "taskUUID": "dd528c57-4cc9-43c4-a06a-f67b188cf84a",
  "model": "alibaba:wan@2.7-image",
  "positivePrompt": "A vast surreal library carved from dark basalt, with terraced reading galleries, suspended walkways, and an immense open sky atrium above. Floating stone fragments drift beneath a faceted glass canopy, while flocks of white paper birds spiral upward through shafts of pale light. Scholars in tailored coats move among towering shelves, polished black staircases, carved archive tables, and glowing map alcoves. The scene blends monumental geology with refined academic design, featuring crisp perspective lines, intricate textures, elegant scale contrast, and cinematic depth. Ultra-detailed environmental concept art, atmospheric, sophisticated, sharp focus, balanced composition, premium illustration quality.",
  "width": 1536,
  "height": 1024,
  "seed": 84183,
  "settings": {
    "thinking": true,
    "colorPalette": [
      {
        "hex": "#1E2428",
        "ratio": "34%"
      },
      {
        "hex": "#4C5A5D",
        "ratio": "22%"
      },
      {
        "hex": "#C8D2D6",
        "ratio": "18%"
      },
      {
        "hex": "#D8B36A",
        "ratio": "14%"
      },
      {
        "hex": "#7A8F78",
        "ratio": "12%"
      }
    ]
  }
}

Response

{
  "taskType": "imageInference",
  "taskUUID": "dd528c57-4cc9-43c4-a06a-f67b188cf84a",
  "imageUUID": "9d169896-a6b5-476a-a495-cd51a671259f",
  "imageURL": "https://im.runware.ai/image/os/a07d11/ws/3/ii/9d169896-a6b5-476a-a495-cd51a671259f.jpg",
  "seed": 84183,
  "cost": 0.03
}

Image to Image

Iridescent Desert Kite Festival

Request

{
  "taskType": "imageInference",
  "taskUUID": "0fc189c9-38a4-4f48-a286-b4522ba04e64",
  "model": "alibaba:wan@2.7-image",
  "positivePrompt": "Transform the selected regions of the reference image into a spectacular desert sky festival scene: giant geometric kites made of silk, mirrored foil, and painted fabric soaring above the adobe rooftops, long ribbon tails, drifting paper streamers, subtle dust haze glowing in afternoon light, intricate shadows crossing the buildings, joyful cinematic scale, highly detailed realism, preserve the original town architecture and perspective outside the edited areas, harmonious warm earth tones contrasted with vivid cobalt, saffron, coral, and silver accents",
  "width": 1024,
  "height": 1024,
  "seed": 37913,
  "settings": {
    "editRegions": [
      [
        [
          80,
          40,
          944,
          430
        ],
        [
          260,
          430,
          820,
          620
        ]
      ]
    ],
    "thinking": true,
    "colorPalette": [
      {
        "hex": "#C96A3D",
        "ratio": "32%"
      },
      {
        "hex": "#E0B04B",
        "ratio": "19%"
      },
      {
        "hex": "#2E5FA7",
        "ratio": "21%"
      },
      {
        "hex": "#E86F51",
        "ratio": "16%"
      },
      {
        "hex": "#C9C2B8",
        "ratio": "12%"
      }
    ]
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/fe950d09-1b43-4983-9f90-cde1a33831d5.jpg"
    ]
  }
}

Response

{
  "taskType": "imageInference",
  "taskUUID": "0fc189c9-38a4-4f48-a286-b4522ba04e64",
  "imageUUID": "f7112fde-c984-4969-a989-b3fa4c05787d",
  "imageURL": "https://im.runware.ai/image/os/a04d20/ws/3/ii/f7112fde-c984-4969-a989-b3fa4c05787d.jpg",
  "seed": 37913,
  "cost": 0.03
}

Image to Image

Sun-Baked Fossil Carnival Procession

Request

{
  "taskType": "imageInference",
  "taskUUID": "bc3304c4-13af-4681-a62d-63bf09c9f3d6",
  "model": "alibaba:wan@2.7-image",
  "positivePrompt": "Create a grand desert carnival procession at high noon, blending all six references into one original spectacle. A monumental parade advances beneath colossal fossil arches across a sun-baked avenue. The central float is built from carved wood and giant skeletal forms, surrounded by musicians carrying ornate brass instruments and dancers in ceremonial garments layered with shell beads, bone motifs, and flowing ochre fabric. Emphasize swirling dust, radiant heat haze, intricate textures, celebratory movement, and believable material detail. Compose the scene as a richly staged wide cinematic tableau with strong depth, dynamic crowd rhythm, elegant costume silhouette variety, and cohesive design language drawn from the references. Highly detailed, vivid, majestic, tactile, polished image generation.",
  "width": 1536,
  "height": 1024,
  "seed": 66443,
  "settings": {
    "thinking": true,
    "colorPalette": [
      {
        "hex": "#D9B36C",
        "ratio": "28%"
      },
      {
        "hex": "#A65A3A",
        "ratio": "22%"
      },
      {
        "hex": "#E8D9B5",
        "ratio": "20%"
      },
      {
        "hex": "#6F4A2D",
        "ratio": "18%"
      },
      {
        "hex": "#7E8C6A",
        "ratio": "12%"
      }
    ]
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/9588be86-39b0-4eed-b415-138e9b35de2d.jpg",
      "https://assets.runware.ai/assets/inputs/81e53654-60ce-408b-9d12-533e2475899a.jpg",
      "https://assets.runware.ai/assets/inputs/8af5b072-d81a-4d9b-a26f-cbae783da2ba.jpg",
      "https://assets.runware.ai/assets/inputs/458133f1-a320-4a8b-a991-01309c875222.jpg",
      "https://assets.runware.ai/assets/inputs/280e17d1-a317-4d70-8d65-da5d6bdd363e.jpg",
      "https://assets.runware.ai/assets/inputs/a42f0cd7-dde5-4f8a-9574-07bff1ffd94f.jpg"
    ]
  }
}

Response

{
  "taskType": "imageInference",
  "taskUUID": "bc3304c4-13af-4681-a62d-63bf09c9f3d6",
  "imageUUID": "66f87d21-fcb0-43cc-bb2e-0503bcae2245",
  "imageURL": "https://im.runware.ai/image/os/a01d21/ws/3/ii/66f87d21-fcb0-43cc-bb2e-0503bcae2245.jpg",
  "seed": 66443,
  "cost": 0.03
}