Using HappyHorse Video Edit in your workflow

Sorceress brings Alibaba models into a shared API catalog. Select this model explicitly, check its supported inputs, and keep your API key on your server. Model capabilities differ; the schema and options on this page describe this entry rather than every model from the same brand.

Explore motion and scene concepts.
Automate video generation with a saved job that your application can track.

Pricing and availability

Sorceress pricing is awaiting activation. The reference catalog lists 28 credits per second 720p, 48 1080p; that reference is not a Sorceress quote. This entry cannot currently be invoked through Sorceress.

Inputs and supported options

{
  "type": "object",
  "required": [
    "prompt",
    "video_url"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "default": 0,
      "maximum": 2147483647,
      "minimum": 0,
      "description": "Random seed for reproducibility."
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "maxLength": 5000,
      "description": "Required edit instruction describing the intended change (e.g., style transfer / local replacement). Up to 5,000 characters."
    },
    "video_url": {
      "type": "string",
      "title": "Video URL",
      "format": "uri",
      "x-media": "video",
      "description": "URL of the input video (one video). Video requirements: Format: MP4, MOV (H.264 encoding recommended). Duration: 3–60 seconds. Resolution: the longer side must not exceed 2,160 px; the shorter side must be at least 320 px. Aspect ratio: 1:2.5–2.5:1. File size: up to 100 MB. Frame rate: greater than 8 fps."
    },
    "resolution": {
      "enum": [
        "720p",
        "1080p"
      ],
      "type": "string",
      "title": "Resolution",
      "default": "1080p",
      "description": "Output video resolution: 720p or 1080p (default)."
    },
    "audio_setting": {
      "enum": [
        "auto",
        "origin"
      ],
      "type": "string",
      "title": "Audio setting",
      "default": "auto",
      "description": "Audio handling: auto lets the model handle audio; origin keeps the input video's original audio where possible."
    },
    "reference_image": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri"
      },
      "title": "Reference image",
      "x-media": "image",
      "maxItems": 5,
      "minItems": 0,
      "description": "Optional reference image URL list (0–5). Image requirements: Format: JPEG, JPG, PNG, WEBP. Resolution: both width and height must be at least 300 px. Aspect ratio: 1:2.5–2.5:1. File size: up to 10 MB."
    }
  }
}

Completion, results and billing

Save the job identifier returned by asynchronous requests and poll the jobs endpoint until the job succeeds or fails. Do not resubmit a generation just because it is still processing. Chat returns a completed reply and usage details. A multi-step workflow can include separately billed successful steps even if a later step fails. Keep returned asset links with your project, and consult each action for its output format.

Coding agents can discover the current catalog and input requirements from the Sorceress agent instructions. Use a Sorceress key; provider credentials stay on the server.