Skip to main content
POST
/
v1
/
tasks
curl -X POST https://qingbo.dev/v1/tasks \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "viduq3",
    "action": "generate",
    "prompt": "城市夜景延时摄影，霓虹灯光流转",
    "aspect_ratio": "16:9",
    "duration": 5,
    "resolution": "1080p"
  }'

{
  "task_id": "task-wave1775285160b950328499",
  "model": "viduq3",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}
Async processing mode — submit a request and receive a task ID. Use the Query Task Status endpoint to retrieve generation results. Video links are valid for 24 hours. 
curl -X POST https://qingbo.dev/v1/tasks \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "viduq3",
    "action": "generate",
    "prompt": "城市夜景延时摄影，霓虹灯光流转",
    "aspect_ratio": "16:9",
    "duration": 5,
    "resolution": "1080p"
  }'

{
  "task_id": "task-wave1775285160b950328499",
  "model": "viduq3",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

​
Available Models

Model IDDescription
viduq3Vidu Q3, native audio, 16 seconds, 1080p
viduq3-proVidu Q3 Pro, highest quality
viduq3-turboVidu Q3 Turbo, speed-optimized
viduq3-mixVidu Q3 Mix, multi-reference multi-entity consistency
viduq2Vidu Q2
viduq1Vidu Q1

​
Common Parameters

​
model
string
required
Model ID
​
action
string
default:"generate"
Operation type
​
prompt
string
required
Video description text
​
aspect_ratio
string
default:"16:9"
Aspect ratio: 16:9, 9:16, 1:1
​
duration
integer
default:"5"
Video duration (seconds)
​
resolution
string
default:"1080p"
Resolution: 720p, 1080p
​
seed
integer
Random seed, 0 for random
​
watermark
boolean
Whether to add a watermark. Supports custom watermark images and positioning (via extra)
​
image_urls
string[]
Reference image URL array. The number of images determines the generation mode:
  • 1 image: Image-to-video
  • 2 images: First/last frame mode
  • 3+ images: Reference-guided generation (automatically uses viduq2)
​
callback_url
string
Webhook callback URL
​
extra
object
Pass-through parameters

​
Model-Specific Parameters

​
extra.movement_amplitude
string
default:"auto"
Motion amplitude: auto, small, medium, large
​
extra.bgm
boolean
default:"false"
Whether to add background music
​
extra.wm_url
string
Custom watermark image URL (requires watermark: true)
​
extra.wm_position
integer
Watermark position: 1 (top-left), 2 (top-right), 3 (bottom-left), 4 (bottom-right)

​
Generation Modes

ModeParametersDescription
Text-to-videopromptPure text generation
Image-to-videoprompt + image_urls (1 image)Single image reference
First/Last frameimage_urls (2 images)Transition between start and end frames
Reference-guidedimage_urls (3+ images)Multi-image reference (auto-switches to viduq2)

​
Response

​
task_id
string
Task ID
​
model
string
Model ID used
​
action
string
Operation type
​
status
string
Task status: queued
​
created_at
integer
Creation time (Unix millisecond timestamp)
​
progress
integer
Progress, initially 0