Skip to main content
POST

Authentication

Authorization
string
required
All endpoints require Bearer Token authenticationGet API Key:Visit the API Key Management Page to get your API KeyAdd to request header:

Request Parameters

model
string
required
Video generation model name, fixed as wan2.6-i2v-flash
image_urls
array<string>
required
Reference image URL array (only 1 first-frame image supported)Supports publicly accessible image URLs or Base64 encoding (data:image/png;base64,...)Example: ["https://example.com/image.jpg"]
Image requirements:
  • Format: JPEG, JPG, PNG (no transparency), BMP, WEBP
  • Resolution: width/height range 240-8000 pixels
  • Size: ≤ 10MB
prompt
string
Video content descriptionOptional but recommended for image-to-video, describes expected actions and effectsClearly specify subject, action, camera and style for better resultsExample: "The person in the image smiles and waves, camera slowly zooms in"
negative_prompt
string
Negative prompt, describes unwanted contentMaximum 500 charactersExample: "blurry, low quality, distorted"
resolution
string
default:"1080p"
Video resolutionOptions:
  • 720p - HD
  • 1080p - FHD (default)
Default: 1080p
Resolution directly affects pricing, 1080p is more expensive than 720p. Aspect ratio is determined by the input image.
duration
integer
default:"5"
Video duration (seconds)Supported range: 2 to 15 seconds (integer)Default: 5
audio
boolean
default:"true"
Whether to generate audioSet to true: automatically generates matching background music/sound effects (default)Set to false: outputs silent videoDefault: true
Not supported when the model is wan2.6-i2v.
audio_url
string
Custom audio URL (wav/mp3, 3-30 seconds, ≤ 15MB)Lower priority than audio: ignored when audio=falseIf audio is longer than video duration, it will be trimmed; if shorter, the remaining part will be silent
Audio file requirements:
  • Format: wav, mp3
  • Duration: 3-30 seconds
  • Size: ≤ 15MB
prompt_extend
boolean
default:"true"
Whether to enable smart prompt rewritingSignificantly improves results for shorter prompts, but increases processing timeDefault: true
shot_type
string
Shot type, requires prompt_extend=trueOptions:
  • single - Single shot (default), outputs a continuous single-shot video
  • multi - Multi-shot, outputs a narrative video with multiple shot transitions
shot_type has higher priority than prompt. Even if the prompt mentions “multi-shot”, setting single will still output a single shot.
seed
integer
Random seed (≥0), specifying the same seed can reproduce similar resultsExample: 12345
watermark
boolean
default:"false"
Whether to add an “AI Generated” watermark (bottom right)Default: false

Audio Control

Response

code
integer
Response status code, 200 on success
data
array
Response data array

Use Cases

Case 1: Minimal Request

Case 2: Full Parameters

Case 3: Custom Audio

Case 4: Silent Video

Case 5: Effect Template

Case 6: Base64 Image

Query Task ResultsVideo generation is an asynchronous task that returns a task_id upon submission. Use the Get Task Status endpoint to query generation progress and results.