curl --request POST \
  --url https://api.aiid.edu.kg/api/v1/services/aigc/video-generation/video-synthesis \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "happyhorse-1.0",
  "mode": "t2v",
  "input": {
    "prompt": "A white horse running through a neon city street, cinematic"
  },
  "parameters": {
    "resolution": "720P",
    "ratio": "16:9",
    "duration": 5
  }
}
'

{
  "id": "task_xxx",
  "output": {
    "task_id": "<string>",
    "task_status": "<string>",
    "video_url": "<string>"
  },
  "usage": {
    "duration": "<string>",
    "SR": "<string>"
  }
}

Video generation HappyHorse

Create video(HappyHorse)

This series supports OpenAI video generation formats (see the link Video generation Sora compatible formats).

HappyHorse Alibaba video generation API, with public paths following the official DashScope protocol.

Supports 5 external models: happyhorse-1.0, happyhorse-1.0-i2v, happyhorse-1.0-t2v, happyhorse-1.0-r2v, and happyhorse-1.0-video-edit. Among them, happyhorse-1.0 is an aggregated model and requires mode to distinguish t2v, i2v, r2v, and video_edit.

The public API keeps the official endpoint format; channel-specific prefixes are only concatenated internally when the gateway requests a specific upstream channel. Clients do not need to pass X-DashScope-Async explicitly; it is handled by the gateway or the official channel adapter layer.

Provides the public request skeleton, task query structure, and recommended validation template for the HappyHorse Alibaba official video generation format; the public paths keep the official endpoint format.

Supported models: happyhorse-1.0, happyhorse-1.0-t2v, happyhorse-1.0-i2v, happyhorse-1.0-r2v, happyhorse-1.0-video-edit

Unified request fields:

model (string, required): HappyHorse external model name. The aggregated model happyhorse-1.0 must be used with mode.
mode (string, optional): Aggregated model mode; common values are t2v, i2v, r2v, and video_edit. You can omit this for fixed submodels.
input.prompt (string, required): Prompt for video generation or editing.
input.media (array[object], optional): Multimedia input. Use first_frame for image-to-video, reference_image for reference-to-video, and video plus optional reference_image for video editing.
parameters.duration (integer, optional): Generation duration, billed by second.
parameters.resolution (string, optional): Output resolution; common values are 720P and 1080P.
parameters.ratio (string, optional): Output aspect ratio, commonly used for text-to-video and reference-to-video.
parameters.watermark (boolean, optional): Whether to add a watermark.
parameters.seed (integer, optional): Random seed.

Common model/mode differences:

HappyHorse 聚合模型: Supports model happyhorse-1.0; the aggregated model uses mode to distinguish the final model.
HappyHorse 文生视频: Supports model happyhorse-1.0-t2v; official-format text-to-video.
HappyHorse 首帧图生视频: Supports model happyhorse-1.0-i2v; official-format first-frame image-to-video.
HappyHorse 参考生视频: Supports model happyhorse-1.0-r2v; official-format multi-reference image-to-video.
HappyHorse 视频编辑: Supports model happyhorse-1.0-video-edit; official-format video editing.

POST

api

services

aigc

video-generation

video-synthesis

curl --request POST \
  --url https://api.aiid.edu.kg/api/v1/services/aigc/video-generation/video-synthesis \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "happyhorse-1.0",
  "mode": "t2v",
  "input": {
    "prompt": "A white horse running through a neon city street, cinematic"
  },
  "parameters": {
    "resolution": "720P",
    "ratio": "16:9",
    "duration": 5
  }
}
'

{
  "id": "task_xxx",
  "output": {
    "task_id": "<string>",
    "task_status": "<string>",
    "video_url": "<string>"
  },
  "usage": {
    "duration": "<string>",
    "SR": "<string>"
  }
}

Authorizations

Authorization

string

header

required

Use Bearer Token authentication. Format: Authorization: Bearer sk-xxxxxx

Body

application/json

model

enum<string>

required

HappyHorse external model name. The aggregate model happyhorse-1.0 must be used with mode.

Available options:

happyhorse-1.0,

happyhorse-1.0-t2v,

happyhorse-1.0-i2v,

happyhorse-1.0-r2v,

happyhorse-1.0-video-edit

Example:

"happyhorse-1.0-t2v"

input

object

required

Hide child attributes

input.prompt

string

required

Prompt for video generation or editing.

Example:

"A white horse running through a neon city street, cinematic"

input.media

object[]

Multimedia input. Image-to-video uses first_frame, reference-to-video uses reference_image, and video editing uses video and optional reference_image.

Hide child attributes

input.media.type

enum<string>

required

Available options:

first_frame,

reference_image,

video

input.media.url

string<uri>

required

mode

enum<string>

Aggregated model mode. Common values are t2v, i2v, r2v, and video_edit. The fixed submodel is optional.

Available options:

t2v,

i2v,

r2v,

video_edit

parameters

object

Hide child attributes

parameters.resolution

enum<string>

Output resolution, common values 720P and 1080P.

Available options:

720P,

1080P

Example:

"720P"

parameters.ratio

string

Output aspect ratio, commonly used for text-to-video and reference-to-video.

Example:

"16:9"

parameters.duration

integer

Generation duration, billed per second.

Example:

5

parameters.watermark

boolean

Whether to add a watermark.

parameters.seed

integer

Random seed.

Response

200 - application/json

Task created successfully

string

required

Example:

"task_xxx"

output

object

Hide child attributes

output.task_id

string

The task ID returned when creating a task, used to query the task.

output.task_status

string

Task status, common values PENDING, RUNNING, SUCCEEDED, FAILED.

output.video_url

string

The URL of the generated video after the task succeeds.

usage

object

Hide child attributes

usage.duration

string

Billable duration, in seconds.

usage.SR

string

Output resolution levels.

Create chat session Query task (HappyHorse)