Seedance 2.5 Goes From 15 to 30 Seconds Per Generation
ByteDance's Seed team has launched Seedance 2.5, and the headline change is length. Single-pass generation goes from 15 seconds to 30 seconds of audio and video produced together, with multiple rounds of extension, so a finished piece can run several minutes with a consistent audiovisual language.
Transcript
ByteDance moved single pass video generation from fifteen seconds to thirty, and rounds of extension build multi minute output.
Seedance two point five generates thirty seconds of audio and video together. Within that pass it organizes connected shots, moving through setup, development, turning points, and resolution.
One pass accepts up to thirty images, ten video clips, and ten audio clips as references. Timestamp level control lets creators edit audio and video at exact moments.
Today it reaches Jimeng AI and Doubao Pro, with API access soon via BytePlus ModelArk. The team says complex motion physics and multi subject scenes still need work.
Inboxsmith helps small businesses handle calls and messages so nothing gets missed. Please like and subscribe for more news.
Sources
Every claim in this video comes from the top ranking coverage of this topic. The claims and where each one came from:
- Seedance 2.5 extends single-pass video generation from 15 to 30 seconds(ByteDance Seed's official announcement)
- supports multiple rounds of extension, users can produce high-quality multi-minute content with a consistent audiovisual language(ByteDance Seed's official announcement)
- the model can organize multiple logically connected shots so that a story unfolds through setup, development, turning points, and resolution(ByteDance Seed's official announcement)
- Users can now input up to 30 images, 10 video clips, and 10 audio clips as reference materials in a single pass(ByteDance Seed's official announcement)
- Seedance 2.5 offers timestamp-level control for targeted editing of audio and video content(ByteDance Seed's official announcement)
- Today, Seedance 2.5 is rolling out on Jimeng AI, Doubao Pro, and other platforms, with API access coming soon via BytePlus ModelArk(ByteDance Seed's official announcement)
- there is still room for improvement, particularly regarding the physical plausibility of complex motions and the stability of scenes involving interactions among multiple subjects(ByteDance Seed's official announcement)