Native duration
30 seconds in one pass
Seedance 2.5 generates continuous 30-second clips without stitched segments, holding scene changes and tempo shifts in a single pass.
What changes
Native duration
Seedance 2.5 generates continuous 30-second clips without stitched segments, holding scene changes and tempo shifts in a single pass.
Reference control
The model supports as many as 50 references in one generation, including images, videos, audio, style references, and 3D white models.
Local changes
Instead of regenerating an entire clip, Seedance 2.5 redraws a selected element such as clothing, a prop, or a background region, and keeps the rest of the shot.
Generate a continuous 30-second video in a single pass, leaving room for camera movement, scene rhythm, and multi-beat storytelling, with no extension or stitching workflow needed.
Combine up to 50 reference inputs in a single prompt: images, videos, audio clips, style references, and 3D white-model inputs.
Localized region editing makes targeted changes such as replacing clothing, props, backgrounds, or product details, while preserving the rest of the shot.
Built for production
Seedance 2.5 is built around what production actually needs: references that hold the shot, 30-second clips that stay on track, clean audio and on-screen text, and local edits that save retakes.
Green-screen clips, white-model passes, and reference videos keep blocking, rhythm, and spatial relationships steady, without endless prompt tuning.
Across a longer clip, characters, lighting, camera motion, and scene logic still feel like one continuous take.
Scripts, images, videos, music, and style boards make direction clearer, instead of blending into competing references.
Clean subtitles, lip sync, on-screen text, and background music move a clip straight into editing instead of another pass.
Compared with Seedance 2.0
Final specs will be confirmed on the model page when Seedance 2.5 launches on YouArt.
Potential workflows
Longer single-pass clips make it easier to block a scene before committing to production.
Expanded references help teams hold products, characters, palettes, and visual rules together.
3D white-model conditioning shows product shape and motion from stronger spatial references.
Localized edits shorten review cycles by changing one visible element instead of rebuilding the full clip.
Get access to Seedance 2.5 and all premium AI models with one membership.
For hobbyists and explorers
For creators and pro users
For power users and teams
For teams and studios
For large organizations
FAQ
Track launch access
Use Seedance 2.0 while YouArt prepares Seedance 2.5 access.