Skip to main content
POST
https://api.novita.ai
/
v3
/
async
/
vidu-q3-pro-i2v
Vidu Q3 Pro Image-to-Video
curl --request POST \
  --url https://api.novita.ai/v3/async/vidu-q3-pro-i2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "audio": "<string>",
  "style": "<string>",
  "images": [
    {}
  ],
  "is_rec": true,
  "prompt": "<string>",
  "wm_url": "<string>",
  "duration": 123,
  "off_peak": true,
  "watermark": true,
  "resolution": "<string>",
  "wm_position": "<string>",
  "aspect_ratio": "<string>"
}
'
{
  "task_id": "<string>"
}
Vidu Q3 Pro Image-to-Video transforms static images into dynamic videos with natural motion and smoother scene dynamics while maintaining subject consistency.
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

​
seed
integer
Random seed for reproducibility; 0 or omit for random generationValue range: [0, 2147483647]
​
audio
string
Custom audio URL for video background music; supports mp3, wav, m4a, flac; max 20MB
​
style
string
default:"general"
Visual style of output; general for realistic, anime for animated styleOptional values: general, anime
​
images
array
required
Reference image URLs for video generation; supports .jpg, .jpeg, .png, .webp. Max file size 50MB per image; aspect ratio must be between 1:4 and 4:1. only support one image input now.
​
is_rec
boolean
default:false
Enable audio scene matching; when true, matches audio rhythm to video motion
​
prompt
string
Motion description for video generation; describes scene motion, actions, and dynamics.Length limit: 0 - 1500
​
wm_url
string
Custom watermark image URL; supports png, jpeg, jpg, webp; max 10MB
​
duration
integer
default:5
Video length in secondsValue range: [1, 16]
​
off_peak
boolean
default:false
Use off-peak pricing; when true, task is queued for off-peak processing at reduced cost
​
watermark
boolean
default:false
Enable watermark on output video
​
resolution
string
default:"720p"
Output video resolutionOptional values: 540p, 720p, 1080p
​
wm_position
string
Watermark position on videoOptional values: top-left, top-right, bottom-left, bottom-right
​
aspect_ratio
string
default:"16:9"
Output video aspect ratioOptional values: 16:9, 9:16, 4:3, 3:4, 1:1

​
Response

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