Wan2.6
Wan2.6 Video Generation
- Alibaba Cloud Wanxiang video generation model
- Supports Text-to-Video and Image-to-Video
- Supports 720p/1080p resolution, 5/10/15 seconds duration
- Supports automatic prompt extension and audio generation
POST
Authorization
string
required
All API endpoints require Bearer Token authenticationGet your API Key:Visit the API Key Management Page to get your API KeyAdd it to the request header:
Request Parameters
string
required
Video generation model name, fixed as
wan2.6boolean
default:"false"
Whether to run content moderation before submitting the video task.
true: useomni-moderation-latestto review prompts and input imagesfalseor omitted: do not send a moderation request, adding no moderation cost or latency (default)
string
required
Video content descriptionRequired for text-to-video mode. Describe scenes, actions, and styles in detail for better resultsExample:
"A cute cat stretching in the sunlight"array<url>
Reference image URL array (only 1 image supported)Required for image-to-video mode. Supports publicly accessible image URLsExample:
["https://example.com/image.jpg"]The system automatically selects text-to-video or image-to-video mode based on whether
image_urls is includedstring
Negative prompt describing unwanted contentExample:
"blurry, low quality, distorted"string
default:"16:9"
Video aspect ratioOptions:
16:9- Landscape (default)9:16- Portrait1:1- Square4:3- Landscape3:4- Portrait
16:9string
default:"720p"
Video resolutionOptions:
720p- Standard (default)1080p- High definition
720pBilled per second. Pricing varies by resolution. Please refer to the model marketplace for specific pricing
integer
default:"5"
Video duration (seconds)Supported values:
5, 10, 15 seconds onlyDefault: 5integer
Random seed for reproducible resultsExample:
12345boolean
Whether to automatically extend the promptWhen enabled, the system will automatically optimize and enrich your prompt
boolean
Whether to automatically add audioWhen enabled, the system will generate matching audio for the video
string
Specified audio URLTakes priority over the
audio parameterstring
Shot typeOptions:
single- Single shotmulti- Multiple shots
boolean
Whether to add watermark
string
Effect template name for image-to-video special effects modeGeneral Effects:
When using effects mode:
- Only one image is required (passed via
image_urls) - No prompt is needed (model ignores the
promptfield)
squish- Squish & Squeezerotation- Rotationpoke- Pokeinflate- Balloon Inflatedissolve- Molecular Dissolvemelt- Heat Wave Melticecream- Ice Cream Planetflying- Magic Levitation
carousel- Time Carouselsingleheart- Love Youdance1- Swing Momentdance2- Dance Move
Resolution and Aspect Ratio Combinations
Response
integer
Response status code, 200 on success
array
Response data array
Use Cases
Case 1: Text-to-Video (Simple Request)
Case 2: Text-to-Video (Full Parameters)
Case 3: Image-to-Video
Case 4: Image-to-Video (Base64 Image)
Mode Description
Text-to-Video
promptparameter is requiredimage_urlsparameter is not needed
Image-to-Video
image_urlsparameter is required (only 1 image supported)promptparameter is optional, used to describe expected actions
The system automatically selects the mode based on whether
image_urls is included in the requestQuery Task ResultsVideo generation is an async task that returns a
task_id upon submission. Use the Get Task Status endpoint to query generation progress and results.