Wan-2.7-Image

Image generation with unified text-to-image and image editing support, including custom image sizes

POST /api/generate/submit

cURL

wan-2-7-image-text

curl --request POST \
  --url https://api.poyo.ai/api/generate/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "wan-2.7-image",
  "callback_url": "https://your-domain.com/callback",
  "input": {
    "prompt": "A clean product photo of wireless headphones on a soft background",
    "size": "1024x1024",
    "n": 1,
    "seed": 24680
  }
}
'

200

{
  "code": 200,
  "data": {
    "task_id": "task-unified-1757165031-uyujaw3d",
    "status": "not_started",
    "created_time": "2025-11-12T10:30:00"
  }
}

1. After submission, a task_id will be returned. If you provided a callback_url, when the task status becomes finished or failed, a POST request will be sent to the callback_url.
2. Regardless of whether callback_url is provided, you can retrieve the response result through the unified Query Task Status endpoint.

Wan-2.7-Image

wan-2.7-image is an image model with unified text-to-image and image editing support.

It uses a unified request shape:

• If input.image_urls is omitted, the request is handled as text-to-image
• If input.image_urls is provided, the request is handled as edit mode automatically

Available Model

• wan-2.7-image - Unified text-to-image and image editing model

Size Parameter

input.size supports these preset values:

• 512x512
• 1024x1024
• 768x1024
• 1024x768
• 576x1024
• 1024x576

Default value: 1024x1024

Custom Size

For custom image sizes, you can pass width and height as an object:

"size": {
  "width": 1280,
  "height": 720
}

Supported Parameters

• prompt - Required prompt
• size - Preset output size, or a custom { width, height } object
• n - Number of images, 1-4
• seed - Optional random seed
• image_urls - Reference images for editing, 1-4 images required. Order matters: reference them as image 1, image 2, image 3, image 4 in the prompt

How to Call

Use the unified submit endpoint: POST /api/generate/submit

Preset size example:

curl --request POST \
  --url https://api.poyo.ai/api/generate/submit \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "wan-2.7-image",
    "callback_url": "https://your-domain.com/callback",
    "input": {
      "prompt": "A clean product photo of wireless headphones on a soft background",
      "size": "1024x1024",
      "n": 1,
      "seed": 24680
    }
  }'

Edit example:

curl --request POST \
  --url https://api.poyo.ai/api/generate/submit \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "wan-2.7-image",
    "callback_url": "https://your-domain.com/callback",
    "input": {
      "prompt": "Replace the background with a modern neon city street",
      "image_urls": ["https://example.com/reference1.jpg"],
      "size": "1024x576",
      "n": 1
    }
  }'

Custom size example:

{
  "model": "wan-2.7-image",
  "input": {
    "prompt": "A wide editorial fashion scene",
    "size": {
      "width": 1280,
      "height": 720
    },
    "n": 1
  }
}

Authorizations

Authorization · string · header · required

All API endpoints require Bearer Token authentication

Get your API Key:

Visit the API Key Management Page to get your API Key

Add it to the request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json

model · enum<string> · required

Wan-2.7-Image model identifier

Available options: wan-2.7-image

input · object · required

Input parameters for generation. When image_urls is present, the request is routed to edit mode automatically.

Show child attributes

callback_url · string<uri>

Webhook callback URL for result notifications

Example:

"https://your-domain.com/callback"

Response

200

application/json

Task submitted successfully

code · integer · required

HTTP status code

Example:

200

data · object · required

Show child attributes