{"info":{"title":"Seedance 2.5 Reference to Video","version":"1.0.0"},"openapi":"3.1.0","components":{"schemas":{"Input":{"type":"object","title":"Input","required":["prompt","reference_images"],"properties":{"prompt":{"type":"string","title":"Prompt","x-order":0,"description":"Describe the shot, the action, the camera move, and the sound. Address the reference images positionally as @Image1, @Image2 and so on, numbered by their order in reference_images: with a product photo first and a room photo second, '@Image1 rests on the counter in @Image2, steam rising as the camera pushes in' places the product from the first reference inside the room from the second. A reference the prompt never names is usually ignored or blended into the others, so name every one you send."},"duration":{"type":"integer","oneOf":[{"const":-1},{"maximum":30,"minimum":4}],"title":"Duration","default":-1,"x-order":4,"description":"Clip length in seconds, from 4 to 30. Leave at -1 (the default) to let the model choose an appropriate whole-second length inside that range. Billing is per second of finished video, so -1 makes the cost of a run variable."},"resolution":{"allOf":[{"$ref":"#/components/schemas/resolution"}],"title":"resolution","default":"720p","x-order":2,"description":"Output resolution of the clip. 720p costs more per second of video than 480p."},"aspect_ratio":{"allOf":[{"$ref":"#/components/schemas/aspect_ratio"}],"title":"aspect_ratio","default":"16:9","x-order":3,"description":"Frame shape of the clip. Reference images do not dictate the framing on this variant, so pick the shape you want - a 16:9 request against 3:2 references returns a 16:9 clip. Use adaptive to let the model choose the framing instead."},"generate_audio":{"type":"boolean","title":"Generate Audio","default":true,"x-order":5,"description":"Generate a synchronized soundtrack (dialogue, ambience and sound effects) together with the picture. Set false for a silent clip; the price is the same either way."},"reference_audios":{"type":"array","items":{"type":"string","format":"uri"},"title":"Reference Audios","x-order":6,"maxItems":10,"description":"Experimental: up to 10 short audio references for the generated soundtrack, addressed as @Audio1, @Audio2 and so on. Each clip 2-30 seconds, 30 seconds combined at most; WAV or MP3, under 15 MB each. The clips are accepted and add nothing to the price, but their effect on the finished soundtrack has not been verified - treat the field as experimental. They cannot be sent on their own: at least one reference image is always required."},"reference_images":{"type":"array","items":{"type":"string","format":"uri"},"title":"Reference Images","x-order":1,"maxItems":30,"minItems":1,"description":"1 to 30 reference images that steer identity, wardrobe, product, location or style. The first entry is @Image1 in the prompt, the second @Image2, and so on. JPEG, PNG, WebP, BMP, TIFF or GIF; 300-6000 px on a side, aspect ratio between 1:2.5 and 2.5:1, under 30 MB each. The references do not fix the framing - set aspect_ratio for that."}}},"Output":{"type":"string","title":"Output","format":"uri","description":"URL of the generated MP4 video clip."},"resolution":{"enum":["480p","720p"],"type":"string","title":"resolution","description":"An enumeration."},"aspect_ratio":{"enum":["16:9","4:3","1:1","3:4","9:16","21:9","adaptive"],"type":"string","title":"aspect_ratio","description":"An enumeration."}}}}