# inference.wan2-1.img2img.v1

Source: https://docs.prodia.com/job-types/inference-wan2-1-img2img-v1/

## Schema

```json
{
	"type": "object",
	"required": [
		"type",
		"config"
	],
	"additionalProperties": false,
	"properties": {
		"type": {
			"type": "string",
			"enum": [
				"inference.wan2-1.img2img.v1"
			]
		},
		"config": {
			"type": "object",
			"required": [
				"prompt"
			],
			"additionalProperties": false,
			"properties": {
				"prompt": {
					"type": "string",
					"minLength": 1,
					"maxLength": 2500,
					"examples": [
						"Same scene with morning sunlight and rising mist."
					],
					"description": "Text description guiding the image transformation."
				},
				"images": {
					"type": "array",
					"minItems": 1,
					"maxItems": 1,
					"items": {
						"type": "string"
					},
					"description": "Filename of the conditioning image in the request body. If omitted, the first uploaded blob is used."
				},
				"seed": {
					"type": "integer",
					"examples": [
						42,
						531286735183442
					],
					"description": "A randomness initializer for image reproducibility."
				},
				"width": {
					"type": "integer",
					"minimum": 256,
					"maximum": 2048,
					"examples": [
						1024,
						1280,
						1536
					],
					"description": "Requested output width in pixels. Defaults to the input image's width. Inference runs at the closest pre-compiled production resolution; the output is then resampled to the requested size."
				},
				"height": {
					"type": "integer",
					"minimum": 256,
					"maximum": 2048,
					"examples": [
						1024,
						720,
						1920
					],
					"description": "Requested output height in pixels. Defaults to the input image's height."
				},
				"steps": {
					"type": "integer",
					"default": 20,
					"minimum": 1,
					"maximum": 50,
					"description": "Number of denoising steps. The BF16 I2V teacher quality plateaus around 20 steps."
				},
				"guidance_scale": {
					"type": "number",
					"default": 5,
					"minimum": 1,
					"maximum": 12,
					"description": "Classifier-free guidance scale. Higher = stricter prompt adherence."
				}
			}
		}
	}
}
```