Skip to content
prodia

inference.nano-banana.img2img.v1

View markdown

The inference.nano-banana.img2img.v1 job transforms an input image guided by a text prompt using Gemini 2.5 Flash Image (Nano Banana).

{
    "type": "inference.nano-banana.img2img.v1",
    "config": {
        "prompt": "a serene mountain landscape at golden hour",
        "image": "reference.png"
    }
}

Additional configuration:

  • include_messages (boolean; default False)

This job type is also available under its partner alias inference.partner.nano-banana.img2img.v1.

Schema

Section titled “Schema”
{
  "type": "object",
  "required": [
    "type",
    "config"
  ],
  "additionalProperties": false,
  "properties": {
    "type": {
      "type": "string"
    },
    "config": {
      "type": "object",
      "additionalProperties": false,
      "required": [
        "prompt"
      ],
      "properties": {
        "image": {
          "type": "string",
          "format": "filename",
          "example": "input.png",
          "description": "The input image that will be edited."
        },
        "prompt": {
          "type": "string",
          "minLength": 0,
          "maxLength": 2500,
          "examples": [
            "puppies in a cloud, 4k"
          ],
          "description": "A description of the desired output."
        },
        "include_messages": {
          "type": "boolean",
          "default": false,
          "description": "Enable to include the model's messages in the output as message.txt files."
        }
      }
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}