{
	"$id": "/inference/schemas/text-to-video/input.json",
	"$schema": "http://json-schema.org/draft-06/schema#",
	"description": "Inputs for Text To Video inference",
	"title": "TextToVideoInput",
	"type": "object",
	"properties": {
		"inputs": {
			"description": "The input text data (sometimes called \"prompt\")",
			"type": "string"
		},
		"parameters": {
			"description": "Additional inference parameters for Text To Video",
			"$ref": "#/$defs/TextToVideoParameters"
		}
	},
	"$defs": {
		"TextToVideoParameters": {
			"title": "TextToVideoParameters",
			"type": "object",
			"properties": {
				"num_frames": {
					"type": "number",
					"description": "The num_frames parameter determines how many video frames are generated."
				},
				"guidance_scale": {
					"type": "number",
					"description": "A higher guidance scale value encourages the model to generate videos closely linked to the text prompt, but values too high may cause saturation and other artifacts."
				},
				"negative_prompt": {
					"type": "array",
					"items": {
						"type": "string"
					},
					"description": "One or several 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."
				},
				"seed": {
					"type": "integer",
					"description": "Seed for the random number generator."
				}
			}
		}
	},
	"required": ["inputs"]
}