POST /qwen/api/v1/services/aigc/video-generation/video-synthesis

Method: POSTEndpoint: /qwen/api/v1/services/aigc/video-generation/video-synthesis

Official API Documentation

This section contains endpoint-specific behavior, parameters, or usage notes for this API. This section contains endpoint-specific behavior, parameters, or usage notes for this API.

Request Parameters

Header Parameters

X-DashScope-Async
string
Required
Example:
enable
Content-Type
string
Required
Example:
application/json
Authorization
string
Optional
Default Value:
Bearer {{YOUR_API_KEY}}

Body Parameters application/json Required

model
string
Required
input
object
Required
function
string
Required
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
prompt
string
Required
Prompt used to describe the elements and visual traits expected in the generated video.
Supports both Chinese and English, with a maximum length of 800 characters. Each Chinese character or letter counts as one character. Excess content is truncated automatically.
  // provider-specific example normalized for English documentation
video_url
string
Required
  // provider-specific example normalized for English documentation
The URL must be publicly accessible over HTTP or HTTPS. To get a public URL for a local file, see the temporary file-upload URL guide.
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
The URL must not contain Chinese characters.
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
ref_images_url
array
[string]
Optional
  // provider-specific example normalized for English documentation
The URL must be publicly accessible over HTTP or HTTPS. To get a public URL for a local file, see the temporary file-upload URL guide.
  // provider-specific example normalized for English documentation
Image limits:
Image formats: JPG, JPEG, PNG, BMP, TIFF, WEBP.
Image resolution: width and height must each be in the range [360, 2000] pixels.
Image size: up to 10 MB.
The URL must not contain Chinese characters.
Usage recommendations:
When using subjects from reference images, it is recommended that each image contain only one subject. A solid-color background such as white helps the subject stand out more clearly.
  // provider-specific example normalized for English documentation
mask_image_url
string
Optional
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
Image limits:
Image formats: JPG, JPEG, PNG, BMP, TIFF, WEBP.
  // provider-specific example normalized for English documentation
Image size: up to 10 MB.
The URL must not contain Chinese characters.
mask_frame_id
string
Optional
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
mask_video_url
string
Optional
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
parameters
object
Required
prompt_extend
boolean
Optional
Whether to enable prompt rewriting. When enabled, a large model rewrites the input prompt automatically. This often improves results for short prompts, but it also increases latency.
true (default value): enables smart rewriting.
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
obj_or_bg
array
[string]
Required
size
string
Optional
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
control_condition
string
Optional
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
mask_type
string
Optional
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
expand_ratio
string
Optional
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
expand_mode
string
Optional
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
duration
integer
Optional
Video generation duration in seconds. The value is currently fixed at 5 and cannot be changed. The model always generates a 5-second video.
seed
integer
Optional
  // provider-specific example normalized for English documentation
  // provider-specific example normalized for English documentation
watermark
boolean
Optional
Whether to add a watermark. The watermark appears in the lower-right corner and reads "AI-generated".
  // provider-specific example normalized for English documentation
true: add a watermark.
Example
{
"model"
:
"wanx2.1-vace-plus"
,
"input"
:
{
"function"
:
"image_reference"
,
"prompt"
:
  // provider-specific example normalized for English documentation
,
"ref_images_url"
:
[
"http://wanx.alicdn.com/material/20250318/image_reference_2_5_16.png"
,
"http://wanx.alicdn.com/material/20250318/image_reference_1_5_16.png"
]
}
,
"parameters"
:
{
"prompt_extend"
:
true
,
"obj_or_bg"
:
[
"obj"
,
"bg"
]
,
"size"
:
"1280*720"
}
}

Example Request

Shell

curl --location --request POST '/qwen/api/v1/services/aigc/video-generation/video-synthesis' \
--header 'X-DashScope-Async: enable' \
--header 'Authorization: Bearer {{YOUR_API_KEY}}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "wanx2.1-vace-plus",
    "input": {
        "function": "image_reference",
        "prompt": "In the video, a girl walks gracefully out from the depths of an ancient forest wrapped in morning mist. Her steps are light, and the camera captures each vivid moment. When she stops and looks around at the lush trees, her face blooms into a smile filled with surprise and joy. The scene freezes in an instant of interwoven light and shadow, recording her beautiful encounter with nature.",
        "ref_images_url": [
            "http://wanx.alicdn.com/material/20250318/image_reference_2_5_16.png",
            "http://wanx.alicdn.com/material/20250318/image_reference_1_5_16.png"
        ]
    },
    "parameters": {
        "prompt_extend": true,
        "obj_or_bg": ["obj","bg"],
        "size": "1280*720"
    }
}'

Response

🟢 200 Success

Content Type: application/json

Response Schema

object

Example

{}