Overview
Asynchronous video generation powered by HappyHorse models on Alibaba DashScope. Supports HappyHorse 1.0 and 1.1 for text-to-video, image-to-video, and reference-to-video; video-edit remains on HappyHorse 1.0. HappyHorse 1.1 generation supports 480P, 720P, or 1080P; 1.0 and video-edit support 720P or 1080P.
Primary Endpoint
POST
/api/v1/userHappyhorseVideo/startStart HappyHorse video generation task (T2V / I2V / R2V / Video-Edit)
Request Parameters
| Name | Type | Required | Description |
|---|---|---|---|
| mode | enum: t2v | i2v | r2v | video-edit | Yes | Generation mode |
| name | string | No | Task name |
| model_version | enum: 1.0 | 1.1 | No | Model version for t2v / i2v / r2v. video-edit always uses 1.0. HappyHorse 1.0 keeps the legacy duration/ratio options; 1.1 supports 3-15s, additional aspect ratios, and 480P/720P/1080P. |
| prompt | string | No | Required for t2v / r2v / video-edit; optional for i2v |
| image_url | string | No | First frame image URL (i2v only) |
| reference_image_urls | array<string> | No | Reference images (r2v requires 1-9; video-edit allows 0-5) |
| edit_video_url | string | No | Input video URL (video-edit only) |
| input_video_seconds | number | No | Frontend-detected input video duration in seconds (used to estimate coins for video-edit) |
| duration | enum: 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | No | Output duration (seconds). model_version=1.0 supports 5/10/15; model_version=1.1 supports 3-15. Ignored for video-edit (decided by input video). |
| resolution | enum: 480P | 720P | 1080P | No | Output resolution. 480P is only supported by HappyHorse 1.1 t2v / i2v / r2v; 1.0 and video-edit support 720P / 1080P. |
| ratio | enum: 16:9 | 9:16 | 1:1 | 4:3 | 3:4 | 4:5 | 5:4 | 9:21 | 21:9 | No | Aspect ratio (t2v / r2v only). model_version=1.0 supports 16:9, 9:16, 1:1, 4:3, 3:4; model_version=1.1 also supports 4:5, 5:4, 9:21, 21:9. |
| audio_setting | enum: auto | origin | No | Audio control (video-edit only). auto = model decides; origin = keep input video audio. |
| seed | integer | No | Random seed [0, 2147483647] |
| watermark | boolean | No | DashScope watermark switch |
| minor_suspected_skip | boolean | No | - |
| webhook_url | string | No | HTTPS URL to receive task.completed / task.failed notifications. Best-effort delivery, single attempt, no retries; clients should treat the detail API as the source of truth. |
| webhook_token | string | No | Optional plaintext token returned in the X-A2e-Webhook-Token header so receivers can verify the request originated from a2e. |
Request Example
curl -X POST "https://www.a2e.com.cn/api/v1/userHappyhorseVideo/start" \
-H "Authorization: Bearer YOUR_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"mode": "t2v",
"name": "My generation task",
"model_version": "1.0",
"prompt": "A cinematic scene with natural motion",
"image_url": "https://example.com/reference.jpg",
"reference_image_urls": "https://example.com/reference.jpg",
"edit_video_url": "https://example.com/reference.jpg",
"input_video_seconds": 1,
"duration": "5",
"resolution": "720P",
"ratio": "16:9",
"audio_setting": "auto"
}'Related Endpoints
POST
/api/v1/userHappyhorseVideo/startStart HappyHorse video generation task (T2V / I2V / R2V / Video-Edit)
GET
/api/v1/userHappyhorseVideo/allRecordsList HappyHorse tasks
POST
/api/v1/userHappyhorseVideo/batchDetailBatch query task details
GET
/api/v1/userHappyhorseVideo/{_id}Get HappyHorse task details
DELETE
/api/v1/userHappyhorseVideo/{_id}Delete a HappyHorse task
Responses
200
Task created successfully
401
Unauthorized - Invalid or missing bearer token