Seedance 2.5

About

ByteDance's flagship multimodal video model with native audio, native 30-second generation, and large multimodal reference sets.

Settings

Seed- Random seed. Set for reproducible generation. Reproducibility is not guaranteed.

Image- First-frame image for image-to-video or first/last-frame generation. Cannot be combined with reference images, videos, or audios.

Duration- Video duration in seconds. Set to -1 for intelligent duration (the model picks the best length). Editing mode requires -1.

Watermark- Add a watermark to the generated video.

resolution- Video resolution.

aspect_ratio- Video aspect ratio.

output_format- Output video container format.

Generate Audio- Generate synchronized audio with the video.

Last Frame Image- Last-frame image. Requires a first-frame image.

Reference Audios- Reference audio files (up to 10) for audio-driven generation and lip-sync.

Reference Images- Reference images (up to 30) for character consistency, style guidance, and scene composition.

Reference Videos- Reference videos (up to 10) for motion transfer, style reference, editing, and extension.