Model Settings for Seedance 2.5 Reference-to-Video
Text prompt describing the desired video. Cite reference inputs in submission order with @-syntax: @Image1, @Video1, @Audio1, etc. Prompts phrased as EDITING an input video (e.g. m
Reference Images one of these is requiredReference image URLs, Base64, or asset references (asset://<ASSET_ID>). Up to 30 images for character/style/scene references, video editing, or combined generation. Per-image limit Reference Videos one of these is requiredReference video URLs or asset references for multimodal reference, video editing, or extension. Up to 10 videos. Per-video limits: formats mp4/mov (H.264/H.265 + AAC/MP3), resoluti Reference Audios one of these is requiredReference audio URLs, Base64, or asset references. Formats: wav/mp3, duration [2,30]s per clip, max 15MB each. Up to 10 audios; combined duration of all reference audios must not e Video duration in seconds (4-30), or -1 for the model to choose automatically. Video-EDITING prompts (operating on an input video) accept only -1: the output tracks the input video
Video resolution. 480p, 720p, and 1080p are native Seedance outputs. Every -sr and -esr option first generates the nearest native source, then upscales or enhances it: 720p-sr and
Aspect ratio. 'adaptive' uses the primary media aspect ratio. Explicit ratios apply to reference-to-video generation; video editing and extension force 'adaptive' (the source video
Generate Audio
Whether to generate synchronized audio.
Return Last Frame
Whether to return the last frame as a separate image.
Subtask hint. Omni reference tasks cover three subtasks - reference-to-video, video editing, and video extension. Leave it unset - equivalent to the upstream default 'auto' - to le
Draft first (480p preview)
A quick 480p preview billed at the 480p rate. If you like it, Finish in 1080p from the result: the same shot rendered in full, within seven days.