Using Ideogram Character Base in your workflow

Sorceress brings Ideogram 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.

Create visual concepts and iterate on art direction.
Build images into an asset pipeline using the supported inputs below.

Pricing and availability

Sorceress pricing is awaiting activation. The reference catalog lists 12 credits per image TURBO, 18 BALANCED, 24 QUALITY; that reference is not a Sorceress quote. This entry cannot currently be invoked through Sorceress.

Inputs and supported options

{
  "type": "object",
  "required": [
    "prompt",
    "reference_image_urls"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "description": "Seed for the random number generator"
    },
    "style": {
      "enum": [
        "AUTO",
        "REALISTIC",
        "FICTION"
      ],
      "type": "string",
      "title": "Style",
      "default": "AUTO",
      "description": "The style type to generate with. Default value: \"AUTO\""
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "maxLength": 5000,
      "description": "The prompt describing the scene to generate with the referenced character. (Max length: 5000 characters)"
    },
    "image_size": {
      "enum": [
        "square",
        "square_hd",
        "portrait_4_3",
        "portrait_16_9",
        "landscape_4_3",
        "landscape_16_9"
      ],
      "type": "string",
      "title": "Image size",
      "default": "square_hd",
      "description": "The resolution of the generated image Default value: square_hd"
    },
    "num_images": {
      "enum": [
        "1",
        "2",
        "3",
        "4"
      ],
      "type": "string",
      "title": "Num images",
      "default": "1",
      "description": "Number of images to generate."
    },
    "expand_prompt": {
      "type": "boolean",
      "title": "Expand prompt",
      "description": "Determine if MagicPrompt should be used in generating the request or not. Default value: true (Boolean value (true/false))"
    },
    "negative_prompt": {
      "type": "string",
      "title": "Negative prompt",
      "maxLength": 5000,
      "description": "Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. Default value: \"\" (Max length: 5000 characters)"
    },
    "rendering_speed": {
      "enum": [
        "TURBO",
        "BALANCED",
        "QUALITY"
      ],
      "type": "string",
      "title": "Rendering speed",
      "default": "BALANCED",
      "description": "The rendering speed to use. Default value: \"BALANCED\""
    },
    "reference_image_urls": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri"
      },
      "title": "Reference image URLs",
      "x-media": "image",
      "description": "A set of images to use as character references. Currently only 1 image is supported, rest will be ignored. (maximum total size 10MB across all character references). The images should be in JPEG, PNG or WebP format (Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)"
    }
  }
}

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.