ByteDance / Video
seedance-2.5
Generate videos from text or reference images.
https://orux.top/api/v1/tasksRequest body
model: seedance-2.5. Place model parameters inside input.
Examples use configured defaults. Replace placeholders in angle brackets with actual values.
Parameters
Fields accepted in the request body for this model.
prompttextfirst_frame_urlimage URLUse first/last frames or reference media as separate modes.
last_frame_urlimage URLUse first/last frames or reference media as separate modes.
resolutionenumdurationintegerChoose an exact output duration. Automatic duration and video references are not available yet.
aspect_ratioenumgenerate_audiobooleanreference_image_urlsimage URL[]reference_audio_urlsaudio URL[]2–30 seconds per audio; total at most 30 seconds.
web_searchbooleanUse online search when generating.
output_formatenumreturn_last_framebooleannsfw_checkerbooleandraftbooleanGenerate a 480p draft. Upgrading a saved draft is not available yet.
Response examples
Illustrative response structures. Actual content depends on the request.
Retrieve the result
Save task_id and poll the task endpoint. An accepted task has not yet finished generating.