Skip to main content
POST
/
v3
/
async
/
vidu-q3-turbo-f2v
Vidu Q3 Turbo Start-End Frame to Video
curl --request POST \
  --url https://api.myrouter.ai/v3/async/vidu-q3-turbo-f2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "audio": true,
  "images": [
    {}
  ],
  "is_rec": true,
  "prompt": "<string>",
  "duration": 123,
  "off_peak": true,
  "resolution": "<string>"
}
'
{
  "task_id": "<string>"
}
Vidu Q3 Turbo Start-End Frame to Video generates high-quality videos from start and end frame images, with text-guided motion interpolation, supporting up to 1080p resolution.
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

​
seed
integer
Random seed for reproducible results. Set to 0 for random.
​
audio
boolean
default:true
Whether to enable audio-video generation. Default: true. false outputs a silent video; true outputs a video with synchronized audio (including dialogue and sound effects). Only supported by Q3 series models.
​
images
array
required
Two image URLs or Base64-encoded images. The first is the start frame, the second is the end frame. Supported formats: png, jpeg, jpg, webp. Maximum 50MB per image. The resolutions of the start and end frame images must be similar (start/end ratio between 0.8 and 1.25). Aspect ratio must be less than 1:4 or greater than 4:1.Array length: 2 - 2
​
is_rec
boolean
Whether to use a recommended prompt. When enabled, the system automatically generates a prompt.
​
prompt
string
Text describing the desired video motion between the start and end frames, up to 1500 characters.Length limit: 0 - 1500
​
duration
integer
default:5
Video duration (seconds). Range: 1-16.Range: [1, 16]
​
off_peak
boolean
default:false
Whether to use off-peak mode. Tasks will be processed within 48 hours at a lower cost.
​
resolution
string
default:"720p"
Output video resolution.Possible values: 540p, 720p, 1080p

​
Response

​
task_id
string
required
Use the task_id to call the Get Async Task Result API to retrieve the generated output.