Skip to main content
POST
Image-to-video: create a video generation task from a first frame (+ optional driving audio)
The Playground on the right lets you debug directly: put Bearer sk-your-api-key in Authorization, fill in model / input.media / parameters, and send the request. A successful submission returns a task_id; see below for polling and download.
This page is the creation endpoint for wan2.7-i2v (image-to-video): give a first frame + prompt to bring the image to life, and optionally pass driving_audio to make the portrait follow the audio’s mouth movements and rhythm. For the full async flow, see the Wan Overview.
  • Audio drive is exclusive to wan2.7-i2v: HappyHorse i2v does not support driving_audio, so lip-sync / rap must use wan2.7-i2v.
  • input.media is required, otherwise the upstream returns image-to-video model ... must provide an image. Each media url must be a public https link that can be fetched directly with GET.
  • Creation requests go to /wan/api/v1/... with X-DashScope-Async: enable; do not use /v1/videos.

Code examples

Parameter and media quick reference

media[] values

Response format

Check status and download

Once you have the task_id, follow these three steps to poll status and download the mp4:
  • Poll GET /v1/tasks/{task_id} (with Authorization; the query does not need the X-DashScope-Async header), every 5-10 seconds (not < 3 seconds), until status becomes completed.
  • Status values: submitted (queued) / in_progress (generating; progress often sitting at 30% is normal) / completed (success) / failed (check error).
  • Download: GET the result_url from the response directly, without the Authorization header (it is an OSS signed direct link — sending Auth returns 403); result_url expires in 24 hours by default, so save it promptly.
The above is the quick check/download path for “already have a task_id”. For the full polling loop (with timeout fallback) and Python client, see Wan Overview · Async call flow.

Authorizations

Authorization
string
header
required

The API Key obtained from the APIYI console

Headers

X-DashScope-Async
enum<string>
default:enable
required

Async processing switch; must be set to enable

Available options:
enable

Body

application/json
model
enum<string>
default:wan2.7-i2v
required

Model ID; for image-to-video, fixed wan2.7-i2v (legacy version wan2.6-i2v)

Available options:
wan2.7-i2v,
wan2.6-i2v
input
object
required
parameters
object

Response

Task submitted; returns task_id and PENDING status

output
object
request_id
string

Unique request identifier

Example:

"..."