Skip to main content
POST
/
v3
/
async
/
vidu-q2-pro-fast-startend2video
VIDU Q2 Pro Fast Start-End Frame to Video
curl --request POST \
  --url https://api.myrouter.ai/v3/async/vidu-q2-pro-fast-startend2video \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "bgm": true,
  "seed": 123,
  "images": [
    {}
  ],
  "is_rec": true,
  "prompt": "<string>",
  "wm_url": "<string>",
  "payload": "<string>",
  "duration": 123,
  "off_peak": true,
  "meta_data": "<string>",
  "watermark": true,
  "resolution": "<string>",
  "wm_position": 123,
  "movement_amplitude": "<string>"
}
'
{
  "task_id": "<string>",
  "provider_request_id": "<string>"
}
Generate a coherent video from first and last frame images (fast mode). Supports 720p and 1080p resolutions. Fast mode significantly reduces generation time, ideal for speed-sensitive scenarios.
This is an async API that only returns the task_id of the async task. Use the task_id to call the Get Async Task Result API to retrieve the generated result.

​
Request Headers

​
Content-Type
string
required
Enum: application/json
​
Authorization
string
required
Bearer authentication format: Bearer {{API Key}}.

​
Request Body

​
bgm
boolean
default:false
Whether to add background music to the generated video. true: the system will automatically select suitable music from a preset BGM library and add it. false: no BGM is added. BGM has no duration limit; the system automatically adapts to the video duration.
​
seed
integer
Random seed. When not provided or set to 0, a random number is used. When manually set, the specified seed is used.
​
images
array
required
Image array where the first image is treated as the first frame and the second image as the last frame. The model generates a video based on the images provided in this parameter. Supports two images. Note 1: The resolutions of the first and last frame images must be similar, with the first frame resolution / last frame resolution between 0.8 and 1.25. Note 2: Supports Base64-encoded images or image URLs (must be accessible). Note 3: Supported formats: png, jpeg, jpg, webp. Note 4: Image size must not exceed 50 MB. Note 5: Base64 encoding must include the appropriate content type string, e.g., data:image/png;base64,.Array length: 2 - 2
​
is_rec
boolean
default:false
Whether to use recommended prompts. true: the system automatically recommends a prompt and uses it to generate the video (each task consumes 10 additional credits). false: generates the video based on the input prompt.
​
prompt
string
Text prompt describing the video to generate. Note 1: Character length must not exceed 2,000 characters. Note 2: If the is_rec recommended prompt parameter is used, the model will disregard the prompt provided in this parameter.Length limit: 0 - 2000
​
wm_url
string
Watermark content as an image URL. When not provided, the default watermark is used: “Content generated by AI”.
​
payload
string
Pass-through parameter. No processing is performed; data is transmitted as-is. Maximum 1,048,576 characters.Length limit: 0 - 1048576
​
duration
integer
default:5
Video duration (in seconds). Supports 1-8 seconds.Possible values: 1, 2, 3, 4, 5, 6, 7, 8
​
off_peak
boolean
default:false
Off-peak mode. true: generates the video during off-peak hours (lower credit consumption, generated within 48 hours). false: generates the video immediately. Note: Tasks submitted in off-peak mode that are not completed will be automatically canceled and credits refunded. You can also manually cancel off-peak tasks.
​
meta_data
string
Metadata identifier as a JSON-formatted string. Pass-through field. You can customize the format or use the example format. When this parameter is empty, the default metadata identifier generated by Vidu is used.
​
watermark
boolean
default:false
Whether to add a watermark. Default: no watermark. You can use the watermarked_url parameter to retrieve the watermarked video.
​
resolution
string
default:"720p"
Output video resolution. Supports 720p and 1080p. Default: 720p.Possible values: 720p, 1080p
​
wm_position
integer
default:3
Watermark position, indicating where the watermark appears on the image. 1: top-left. 2: top-right. 3: bottom-right (default). 4: bottom-left.Possible values: 1, 2, 3, 4
​
movement_amplitude
string
default:"auto"
Movement amplitude, controlling the intensity of object motion in the video.Possible values: auto, small, medium, large

​
Response

​
task_id
string
required
Use the task_id to call the Get Async Task Result API to retrieve the generated output.
​
provider_request_id
string
Provider request ID (optional)