UNPKG

@huggingface/tasks

Version:
65 lines (64 loc) 2.01 kB
{ "$id": "/inference/schemas/image-to-video/input.json", "$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"] }