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

Source: https://docs.prodia.com/job-types/inference-partner-seedream-4-img2img-v2/

The `inference.partner.seedream-4.img2img.v2` job transforms an input image guided by a text prompt using Seedream 4.0.

```json
{
  "type": "inference.partner.seedream-4.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`)

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

```json
{
	"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": [
						"1K",
						"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
				},
				"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"
}
```