{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"prompt":{"description":"Text prompt describing the video to generate. Optional when at least one reference image, video, or audio clip is provided (Seedance 2.5 supports audio-only input).","type":"string","maxLength":2000},"image":{"description":"First-frame reference image (HTTP(S) URL or base64 data URI) for image-to-video","type":"string"},"last_frame_image":{"description":"Last-frame reference image (HTTP(S) URL or base64 data URI). Requires a first-frame image to also be given.","type":"string"},"reference_images":{"description":"Reference images (0-30, HTTP(S) URLs or base64 data URIs) to guide multimodal video generation, editing, or extension.","maxItems":30,"type":"array","items":{"type":"string"}},"reference_videos":{"description":"Reference videos (0-10, HTTP(S) URLs or base64 data URIs) for style/motion guidance, video editing, or video extension. Total duration of all reference videos must not exceed 30 seconds.","maxItems":10,"type":"array","items":{"type":"string"}},"reference_audios":{"description":"Reference audio clips (0-10, HTTP(S) URLs or base64 data:audio/... URIs). Supports audio-only input (no image or video required). Total duration of all audio clips must not exceed 30 seconds.","maxItems":10,"type":"array","items":{"type":"string"}},"duration":{"description":"Generated video duration in seconds. Supported range: 4-30, or -1 for automatic selection. For multimodal reference-to-video requests that edit an input reference video, only -1 is supported and the output duration is kept close to the input.","default":5,"anyOf":[{"type":"number","const":-1},{"type":"integer","minimum":4,"maximum":30}]},"resolution":{"description":"Video resolution","default":"720p","type":"string","enum":["480p","720p"]},"aspect_ratio":{"description":"Video aspect ratio. \"adaptive\" automatically matches the aspect ratio of the provided reference image or video when applicable. First/last-frame generation always uses \"adaptive\"; any supplied value is overridden.","default":"adaptive","type":"string","enum":["16:9","4:3","1:1","3:4","9:16","21:9","adaptive"]},"fps":{"description":"Frame rate (frames per second)","default":24,"type":"number","const":24},"camera_fixed":{"description":"Whether to fix camera position. Not currently supported by the provider; has no effect.","default":false,"type":"boolean"},"generate_audio":{"description":"Whether to generate audio with the video","type":"boolean"},"watermark":{"description":"Whether to add a watermark to the output video","default":false,"type":"boolean"},"seed":{"description":"Random seed. Passing this does not error, but reproducibility is not guaranteed and is not documented by the provider.","type":"integer","minimum":-9007199254740991,"maximum":9007199254740991},"output_format":{"description":"Output video container format. \"mp4\" offers the best compatibility and smaller file size; \"mov\" preserves higher color fidelity for professional post-production workflows at the cost of a larger file.","default":"mp4","type":"string","enum":["mp4","mov"]},"use_virtual_avatar":{"description":"Route image reference inputs (image, reference_images, last_frame_image) through ByteDance's trusted virtual avatar asset library before generation. Intended for AI-generated/virtual character avatars that would otherwise be blocked by face or deepfake detection","default":false,"type":"boolean"}},"required":["duration","resolution","aspect_ratio","fps","camera_fixed","watermark","output_format","use_virtual_avatar"],"additionalProperties":false}