Skip to main content
POST
/
wan
/
api
/
v1
/
services
/
aigc
/
video-generation
/
video-synthesis
Reference-to-Video: create a video task with up to 9 reference images to preserve the subject
curl --request POST \
  --url https://api.apiyi.com/wan/api/v1/services/aigc/video-generation/video-synthesis \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'X-DashScope-Async: <x-dashscope-async>' \
  --data '
{
  "model": "happyhorse-1.0-r2v",
  "input": {
    "prompt": "Following the reference image, a girl walking slowly through a garden bathed in sunset light, cinematic lighting",
    "media": [
      {
        "type": "reference_image",
        "url": "https://your-cdn.com/girl.png"
      }
    ]
  }
}
'
{
  "output": {
    "task_id": "hh-...",
    "task_status": "PENDING"
  },
  "request_id": "..."
}

Documentation Index

Fetch the complete documentation index at: https://docs.apiyi.com/llms.txt

Use this file to discover all available pages before exploring further.

You can debug directly in the Playground on the right: fill in Authorization with Bearer sk-your-api-key, set model / input.media / parameters, then send the request. A successful submission returns a task_id; see below for polling and downloading.
This page covers the create endpoint for happyhorse-1.0-r2v (Reference-to-Video): provide reference images, and the model preserves the subjects and scene features in them. HappyHorse-r2v supports up to 9 reference images, giving stronger subject consistency in multi-reference scenarios. For the complete async flow, see the HappyHorse Overview.
  • happyhorse-1.0-r2v supports up to 9 reference_image entries (more than Wan2.7-r2v’s combined ≤5).
  • input.media is required, and the media url must be a public https link that can be fetched directly via GET.
  • The create request goes to /wan/api/v1/... with X-DashScope-Async: enable; do not use /v1/videos.

​
Code Examples

curl -X POST "https://api.apiyi.com/wan/api/v1/services/aigc/video-generation/video-synthesis" \
  -H "X-DashScope-Async: enable" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "happyhorse-1.0-r2v",
    "input": {
      "prompt": "Following the reference image, a girl walking slowly through a garden bathed in sunset light, cinematic lighting",
      "media": [
        {"type": "reference_image", "url": "https://your-cdn.com/girl.png"}
      ]
    },
    "parameters": {"resolution": "720P", "duration": 5, "prompt_extend": true, "watermark": true}
  }'

​
Parameter and Media Quick Reference

ParameterTypeRequiredDefaultNotes
modelstring✓—Fixed to happyhorse-1.0-r2v
input.promptstring✓—Text prompt
input.mediaarray✓—See the media table below
parameters.resolutionstring720P720P / 1080P
parameters.durationint5Integer of 2–15 seconds
parameters.prompt_extendbooltrueSmart rewriting, recommended on
parameters.watermarkboolfalse”AI Generated” watermark

​
media[] Values

typeRequiredCountNotes
reference_image✓1–9Reference image; preserves subject (person/animal/object) and scene features

​
Response Format

{
  "output": { "task_id": "...", "task_status": "PENDING" },
  "request_id": "..."
}
After submission, poll GET /v1/tasks/{task_id} until completed, then download the mp4 from result_url (without the Authorization header, expires in 24 hours). See the full polling loop in HappyHorse 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:happyhorse-1.0-r2v
required

Model ID, fixed to happyhorse-1.0-r2v for Reference-to-Video

Available options:
happyhorse-1.0-r2v
​
input
object
required
​
parameters
object

Response

Task submitted, returns task_id and PENDING status

​
output
object
​
request_id
string

Unique request identifier

Example:

"..."