inference.happyhorse-1-1.img2vid.v1

The inference.happyhorse-1-1.img2vid.v1 job animates an input image into a video guided by a text prompt using HappyHorse 1.1.

{
    "type": "inference.happyhorse-1-1.img2vid.v1",
    "config": {
        "prompt": "a red fox trotting through a snowy forest at golden hour",
        "image": "reference.png"
    }
}

Only image-to-video is offered; the upstream DashScope model is happyhorse-1.1-i2v, served from the international (Singapore) region.

This job type is also available under its partner alias inference.partner.happyhorse-1-1.img2vid.v1.

Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "required": [
    "type",
    "config"
  ],
  "properties": {
    "type": {
      "type": "string"
    },
    "config": {
      "type": "object",
      "properties": {
        "prompt": {
          "type": "string"
        },
        "image": {
          "type": "string",
          "format": "filename",
          "example": "reference.png"
        }
      }
    }
  }
}