Using Kling 2.6 Motion Control in your workflow

Sorceress brings Kling 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 11 credits per second 720p, 18 1080p; that reference is not a Sorceress quote. This entry cannot currently be invoked through Sorceress.

Inputs and supported options

{
  "type": "object",
  "required": [
    "input_urls",
    "video_urls",
    "mode",
    "character_orientation"
  ],
  "properties": {
    "mode": {
      "enum": [
        "720p",
        "1080p"
      ],
      "type": "string",
      "title": "Mode",
      "description": "Required. Output resolution: \"720p\" or \"1080p\"."
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "maxLength": 2500,
      "description": "A text description of the desired output. Maximum length is 2500 characters. (Max length: 2500 characters)"
    },
    "input_urls": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri"
      },
      "title": "Input URLs",
      "x-media": "image",
      "maxItems": 1,
      "description": "An array containing a single image URL. The photo must clearly show the subject's head, shoulders, and torso. (Accepted types: image/jpeg, image/png, image/jpg; Max size: 10.0MB,size needs to be greater than 300px, aspect ratio 2:5 to 5:2.)"
    },
    "video_urls": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri"
      },
      "title": "Video URLs",
      "x-media": "video",
      "maxItems": 1,
      "description": "An array containing a single video URL. The duration must be between 3 to 30 seconds, and the video must clearly show the subject's head, shoulders, and torso. (Accepted types: video/mp4, video/quicktime; Max size: 100.0MB)"
    },
    "character_orientation": {
      "enum": [
        "image",
        "video"
      ],
      "type": "string",
      "title": "Character orientation",
      "description": "Required. Generate the orientation of the characters in the video. 'image': same orientation as the person in the picture (max 10s video). 'video': consistent with the orientation of the characters in the video (max 30s video)."
    }
  }
}

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.