Skip to content
prodia

inference.partner.seedream-4-5.img2img.v2

View markdown

The inference.partner.seedream-4-5.img2img.v2 job transforms an input image guided by a text prompt using Seedream 4.5.

{
  "type": "inference.partner.seedream-4-5.img2img.v2",
  "config": {
    "image": "reference.png",
    "prompt": "a serene mountain landscape at golden hour"
  }
}

Additional configuration:

  • width (number; default 2048)
  • height (number; default 2048)
  • watermark (boolean; default False)
  • seed (integer)

Supports resolution tiers instead of width/height, sequential generation with sequential_image_generation: "auto", and max_images. Image-to-image jobs accept an explicit images filename array. All successfully generated images are returned. Input and generated image counts together cannot exceed 15.

Schema

Section titled “Schema”
{
  "type": "object",
  "required": [
    "type",
    "config"
  ],
  "additionalProperties": false,
  "properties": {
    "type": {
      "type": "string"
    },
    "config": {
      "type": "object",
      "required": [
        "prompt"
      ],
      "additionalProperties": false,
      "properties": {
        "image": {
          "description": "Set image to edit.",
          "type": "string",
          "format": "filename",
          "example": "image.png"
        },
        "images": {
          "type": "array",
          "minItems": 1,
          "maxItems": 14,
          "items": {
            "type": "string",
            "format": "filename"
          }
        },
        "prompt": {
          "description": "Description of desired output.",
          "type": "string",
          "default": "a dancing cat under moonlight",
          "minLength": 3,
          "maxLength": 4096
        },
        "resolution": {
          "description": "Output resolution tier; use instead of width/height.",
          "type": "string",
          "enum": [
            "2K",
            "4K"
          ]
        },
        "width": {
          "description": "Pixel dimension; combined pixel count and aspect ratio must satisfy upstream limits.",
          "type": "integer",
          "default": 2048,
          "minimum": 1,
          "maximum": 16384
        },
        "height": {
          "description": "Pixel dimension; combined pixel count and aspect ratio must satisfy upstream limits.",
          "type": "integer",
          "default": 2048,
          "minimum": 1,
          "maximum": 16384
        },
        "watermark": {
          "description": "When set to true a watermark is added indicating the output is AI generated.",
          "type": "boolean",
          "default": false
        },
        "seed": {
          "description": "A randomness initializer for image reproducability.",
          "type": "integer",
          "minimum": 0,
          "maximum": 2147483647
        },
        "sequential_image_generation": {
          "description": "Generate a single image or a related sequence.",
          "type": "string",
          "default": "disabled",
          "enum": [
            "disabled",
            "auto"
          ]
        },
        "max_images": {
          "description": "Maximum outputs; input and output image counts together cannot exceed 15.",
          "type": "integer",
          "minimum": 1,
          "maximum": 15
        }
      },
      "allOf": [
        {
          "not": {
            "required": [
              "resolution",
              "width"
            ]
          }
        },
        {
          "not": {
            "required": [
              "resolution",
              "height"
            ]
          }
        }
      ]
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}