Wan 2.5 Image-to-Image Preview

wan25_i2i_preview

Wan 2.5 Image-to-Image Preview edits and transforms input images from text prompts through the China mainland (Beijing) node.

Endpoints

POST /v1/queue/wan25_i2i_preview # Create task

GET /v1/queue/wan25_i2i_preview/requests/{request_id}/status # Check status

GET /v1/queue/wan25_i2i_preview/requests/{request_id}/response # Get result

PUT /v1/queue/wan25_i2i_preview/requests/{request_id}/cancel # Cancel task

Request parameters

curl --location "https://cloud.seaart.ai/model/v1/queue/wan25_i2i_preview" \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "prompt": "Turn the reference image into a clean product poster with a white studio background.",
    "images": [
      "https://image.cdn.vtrix.top/2026-04-17/d7h0ad5e8787vbqk6k6g_0/9b65c5d087e41c146d46a5bcf09e2010.webp"
    ],
    "negative_prompt": "low quality, blurry",
    "size": "1024*768",
    "n": 1,
    "prompt_extend": true,
    "watermark": false,
    "seed": 12345
  }'

prompt string required

Positive prompt describing the expected elements and visual characteristics in the generated image.

Chinese and English are supported. Maximum length: 2000 characters. Extra content is automatically truncated.

Example: 一只坐着的橘黄色的猫, 表情愉悦, 活泼可爱, 逼真准确.

images string[] required

Array of image URLs or Base64-encoded strings. Supports single-image editing and multi-image fusion.

Maximum array length: 3 images. For multi-image input, image order follows the array order.

Image formats: JPEG, JPG, PNG, BMP, WEBP. PNG images do not support transparent channels.

Image width and height: 384 - 5000 pixels.

File size: no more than 10MB.

negative_prompt string

Negative prompt describing content that should not appear in the image. It can be used to constrain the image.

Chinese and English are supported. Maximum length: 500 characters. Extra content is automatically truncated.

size string

Output image resolution in width*height format. Total pixels must be between 768*768 and 1280*1280, and the aspect ratio must be between 1:4 and 4:1. If size is not specified, the system generates an image with total pixels of 1280*1280 by default and approximately preserves aspect ratio as follows: for single-image input, it follows the input image aspect ratio; for multi-image input, it follows the last input image aspect ratio.

Default: 1280*1280

n int

Number of images to generate. This parameter directly affects cost; explicitly set it to 1 during testing to control cost.

Range: 1 - 4

Default: 4

prompt_extend bool

Whether to enable intelligent prompt rewriting. When enabled, a large model rewrites the input prompt to improve overall results, but request latency increases.

Default: true

watermark bool

Whether to add a watermark in the lower-right corner of the image. The fixed watermark text is AI生成.

Options: false, true

Default: false

seed int

Random seed. If omitted, the algorithm automatically generates a random seed. When n=4, the algorithm uses seed, seed+1, seed+2, and seed+3 respectively.

Range: 0 - 2147483647

Response parameters

{
  "request_id": "mmsu_01hxyz...",
  "response_url": "https://cloud.seaart.ai/model/v1/queue/wan25_i2i_preview/requests/mmsu_01hxyz.../response",
  "status_url": "https://cloud.seaart.ai/model/v1/queue/wan25_i2i_preview/requests/mmsu_01hxyz.../status",
  "cancel_url": "https://cloud.seaart.ai/model/v1/queue/wan25_i2i_preview/requests/mmsu_01hxyz.../cancel",
  "queue_position": 0
}

Field	Type	Description
`request_id`	string	Task ID used for all follow-up operations.
`response_url`	string	URL to fetch the final result.
`status_url`	string	URL to query task status.
`cancel_url`	string	URL to cancel the task.
`queue_position`	int	Current queue position.

Follow-up operations

Check status

Get result

Cancel task

Error handling