The Wan text-to-video model accepts text, images, and audio as input and generates videos up to 15 seconds long at 1080P resolution.
- Core capabilities: Integer video durations (2–15 seconds), custom resolutions (480P, 720P, 1080P), prompt rewriting, and watermarking.
- Audio capabilities: Automatic dubbing or custom audio files for audio-video sync. (Supported by wan2.5 and wan2.6)
- Multi-shot narrative: Multiple shots with consistent main subject across transitions. (Supported only by wan2.6)
Authorizations
string
header
required
DashScope API Key. Get one from the QwenCloud console.
Header Parameters
enum<string>
required
Must be set to enable for asynchronous task submission.
enable
Body
application/jsonenum<string>
required
Model name. See the model table in the endpoint description for supported models and their capabilities. For Wan 2.1 in China North 2 (Beijing) (cn-beijing), use the wanx2.1-* form: wanx2.1-t2v-plus and wanx2.1-t2v-turbo.
wan2.6-t2v,wan2.5-t2v-preview,wan2.2-t2v-plus,wan2.1-t2v-turbo,wan2.1-t2v-plus,wanx2.1-t2v-plus,wanx2.1-t2v-turbo
wan2.6-t2v
object
required
Input data for video generation.
object
Video generation parameters.