Seedance 2.5 generates 30 seconds of video with audio in one pass
- Source
- x.com
- Date
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
Context
Dreamina Seedance 2.5 can use reference pictures, video and sound together to guide a generated clip, according to OpenRouter's release thread. The announced limits allow up to 30 seconds of audio-video output in one pass, with further extension rounds available afterward. A request can contain up to 30 images, 10 video clips and 10 audio clips. That makes the input a collection of visual and audio references as well as written instructions, giving creators a way to specify what a scene should draw from before generating or editing it.
Checking sign-in…
Loading comments…