POST
/
v3
/
async
/
vidu-q1-startend2video
Vidu Q1 Start End to Video
curl --request POST \
  --url https://api.novita.ai/v3/async/vidu-q1-startend2video \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '{
  "images": [
    "<string>"
  ],
  "prompt": "<string>",
  "duration": 123,
  "seed": 123,
  "resolution": "<string>",
  "movement_amplitude": "<string>",
  "bgm": true
}'
{
  "task_id": "<string>"
}
Vidu Q1 Start End to Video transforms static images into dynamic videos, incorporating creative storytelling and animations.
This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the Task Result API to retrieve the video generation results.

​
Request Headers

​
Content-Type
string
required
Supports: application/json
​
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

​
Request Body

​
images
string[]
required
Two images: first is start frame, second is end frame.Notes:
  1. Public URL or Base64
  2. Aspect ratios must be close: ratio between start/end frame must be in 0.8~1.25
  3. Format: png, jpeg, jpg, webp
  4. Max size: 50MB
  5. The length of the base64 decode must be under 10MB, and it must include an appropriate content type string. For instance:
data:image/png;base64,{base64_encode}
​
prompt
string
Prompt description, max 1500 characters.
​
duration
integer
Video duration in seconds. The default is 5 seconds, with 5 being the only available option.
​
seed
integer
Random seed for video generation.
  • Defaults to a random seed number
  • Manually set values will override the default random seed
​
resolution
string
Output video resolution. Default is 1080p, with 1080p as the only option available.
​
movement_amplitude
string
The movement amplitude of objects in the frame. Default: auto
Accepted values: auto, small, medium, large
​
bgm
boolean
Whether to add background music to the generated video. Default: false
Acceptable values: true, falseWhen true, the system will automatically add a suitable BGM. BGM has no time limit and the system automatically adapts.

​
Response

​
task_id
string
required
Use the task_id to request the Task Result API to retrieve the generated outputs.