Dreamina Seedance 2.5
Video modelCard summarizedDesigned for more complex creative workflows
● Re-checked 12 Oct 2026 · 58 facts · 0 corrections · 6 unconfirmedSource: Introducing Seedance 2.5 (ByteDance Seed launch post; no model card published)
Where to call it
- BytePlus ModelArk
dreamina-seedance-2-5-260628
Good for
- Long-form storytelling with coherent shot transitions and scene changes
- Keeping the appearance and voice of multiple characters from references
- Clay-render (textureless 3D) references to set layout, poses, motion paths and camera angles
Overview
ByteDance · 01Seedance, front
Seedance 2.5
Designed for more complex creative workflows
Typical price
$0.231 / sec
720p, 16:9, no video input
- Max resolution
- 1080p
- Max length
- 30 s
- Modes
- text-to-video, image-to-video (first / first-last frame)
- Released
- 6 Aug 2026
ByteDance Seed describes Seedance 2.5 as its new-generation video creation model, built on Seedance 2.0's unified multimodal audio-video joint-generation architecture. It generates 30 s audio-video clips in one pass (up from 15 s), extends videos over multiple rounds, takes up to 30 images, 10 video clips and 10 audio clips as references, and adds timestamp-level, green-screen and camera-perspective editing. Seed publishes no benchmark numbers. launch post
dreamina-seedance-2-5-260628- Typical price
- $0.231 / sec
- Max resolution
- 1080p
- Max length
- 30 s
- Aspect ratios
- 16:9, 4:3, 1:1, 3:4, 9:16, 21:9
- Frame rate
- 24
- Released
- 6 Aug 2026
- text-to-video
- image-to-video (first / first-last frame)
- omni reference-to-video (up to 30 images, 10 videos, 10 audio clips)
- video editing
- video extension (forward/backward)
- draft mode (480p preview → 1080p final)