Dreamina Seedance 2.5 from @BytePlusGlobal is now available on OpenRouter.
A joint audio-video model for long-form storytelling, multimodal reference, and precise editing. Generate up to 30 seconds in one pass, then extend across multiple rounds, supporting up to 50 references.
One request can support up to 30 images, 10 video clips, and 10 audio clips as reference inputs.
Edit the visuals or audio of the original video, such as replacing the video subject, adding, deleting, or modifying objects.
https://t.co/EeprHsEION
Get started with our API docs below.
https://t.co/l9UzyOyWKy
Joint audio and video generation with reference conditioning and object-level editing covers the stages of a video pipeline that usually require several models stitched together.
