{
	"$id": "/inference/schemas/image-to-video/input.json",
	"$schema": "http://json-schema.org/draft-06/schema#",
	"description": "Inputs for Image To Video inference",
	"title": "ImageToVideoInput",
	"type": "object",
	"properties": {
		"inputs": {
			"type": "string",
			"description": "The input image data as a base64-encoded string. If no `parameters` are provided, you can also provide the image data as a raw bytes payload.",
			"comment": "type=binary"
		},
		"parameters": {
			"description": "Additional inference parameters for Image To Video",
			"$ref": "#/$defs/ImageToVideoParameters"
		}
	},
	"$defs": {
		"ImageToVideoParameters": {
			"title": "ImageToVideoParameters",
			"type": "object",
			"properties": {
				"prompt": {
					"type": "string",
					"description": "The text prompt to guide the video generation."
				},
				"guidance_scale": {
					"type": "number",
					"description": "For diffusion models. A higher guidance scale value encourages the model to generate videos closely linked to the text prompt at the expense of lower image quality."
				},
				"negative_prompt": {
					"type": "string",
					"description": "One prompt to guide what NOT to include in video generation."
				},
				"num_inference_steps": {
					"type": "integer",
					"description": "The number of denoising steps. More denoising steps usually lead to a higher quality video at the expense of slower inference."
				},
				"num_frames": {
					"type": "number",
					"description": "The num_frames parameter determines how many video frames are generated."
				},
				"target_size": {
					"type": "object",
					"description": "The size in pixel of the output video frames.",
					"properties": {
						"width": {
							"type": "integer"
						},
						"height": {
							"type": "integer"
						}
					},
					"required": ["width", "height"]
				},
				"seed": {
					"type": "integer",
					"description": "Seed for the random number generator."
				}
			}
		}
	},
	"required": ["inputs"]
}