Animate a Photo or Continue a Short Clip · Alibaba

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "media"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "seed": {
          "type": "integer",
          "maximum": 2147483647,
          "minimum": 0,
          "description": "Optional integer from 0 to 2147483647. Reusing a seed can reuse the random starting point, but does not guarantee identical video, motion or subject details."
        },
        "media": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "type",
              "url"
            ],
            "properties": {
              "url": {
                "type": "string",
                "minLength": 1,
                "description": "Required publicly accessible HTTPS URL for this material. Supply your actual eligible asset; HTTP links, local paths and Base64 input are not accepted."
              },
              "type": {
                "enum": [
                  "first_frame",
                  "last_frame",
                  "driving_audio",
                  "first_clip"
                ],
                "type": "string",
                "description": "Required role: first_frame is the opening image; last_frame is the closing image; driving_audio supplies timing or lip-sync guidance; first_clip is a clip to continue. Images must be JPG/JPEG, PNG without alpha, BMP or WEBP, at most 20 MB, with each side 240–8000 pixels and aspect ratio 1:8–8:1. Audio must be WAV or MP3, 2–30 seconds and at most 15 MB. A starting clip must be MP4 or MOV, 2–10 seconds and at most 100 MB, with each side 240–4096 pixels and aspect ratio 1:8–8:1. Driving audio is only supported with opening-image combinations; accurate synchronization is not guaranteed."
              }
            },
            "additionalProperties": false
          },
          "minItems": 1,
          "description": "Required nonempty array. Each material type may appear once. Use one of six combinations: first_frame; first_frame with driving_audio; first_frame with last_frame; first_frame with last_frame and driving_audio; first_clip; or first_clip with last_frame. A closing image or audio cannot be used alone, and a starting clip cannot be combined with a starting image or driving audio."
        },
        "prompt": {
          "type": "string",
          "maxLength": 5000,
          "minLength": 1,
          "description": "Optional text describing the desired motion, scene or style. If supplied, it must be nonempty and at most 5000 characters. Use specific camera and movement instructions; visual adherence is not guaranteed."
        },
        "duration": {
          "type": "integer",
          "default": 5,
          "maximum": 15,
          "minimum": 2,
          "description": "Optional integer from 2 to 15 seconds, default 5. When continuing a clip, this bounds the total output including the original clip, rather than the added footage. Choose a value longer than the input clip to allow a continuation."
        },
        "watermark": {
          "type": "boolean",
          "default": false,
          "description": "Optional boolean, default false. Set true to request an AI Generated watermark on the video."
        },
        "resolution": {
          "enum": [
            "720P",
            "1080P"
          ],
          "type": "string",
          "default": "720P",
          "description": "Optional 720P or 1080P, default 720P. Framing follows the opening image or starting clip, but resizing and encoding can cause slight aspect-ratio drift. This Tool has no separate aspect-ratio input."
        },
        "prompt_extend": {
          "type": "boolean",
          "default": true,
          "description": "Optional boolean, default true. It lets the model rewrite and expand the description and can add processing time. Expansion does not guarantee improved quality or more accurate details."
        },
        "negative_prompt": {
          "type": "string",
          "maxLength": 500,
          "description": "Optional text of at most 500 characters describing unwanted elements. It guides generation but does not guarantee that every named element will be absent."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}