All models
Seedance

Seedance 2.5

Commercial use
seedance-2.5-text-to-video

Generation input

Text prompt describing the video to generate (max 30000 characters).

Output video resolution.

Video duration from 4 to 30 seconds, or -1 for automatic selection.

Output aspect ratio.

Generate synchronized audio with the video. Disabled by default; enable only when the prompt describes original sound or you provide authorized reference audio.

Reference mediaOptional
Or paste an image URL above

First-frame image URL. The platform uploads it to the virtual asset library before generation. Mutually exclusive with reference_* fields.

Or paste an image URL above

Last-frame image URL. The platform uploads it to the virtual asset library before generation. Requires first_frame_url.

Or paste an image URL above

Reference image URLs (max 30). Mutually exclusive with first/last frame fields.

Reference video URLs (max 10; total duration ≤30s). Each video is uploaded to the virtual asset library before generation.

Reference audio URLs (max 10; total duration ≤30s).

Creative direction

Smart Director Mode

Camera direction
Character performance
Reference optimization

Add an image, first frame, video, or audio reference first.

More technical options

Return the generated video's last frame. Cannot be true when draft=true.

Video output format.

Enable online search for the generation.

Text-to-video

prompt is required. Optionally add reference_image_urls, reference_video_urls, or reference_audio_urls (images and videos enter the virtual asset library; audio stays direct). Or use first_frame_url + last_frame_url instead — but not together with reference_* fields. Playground starts empty by default.