Seedance 2.5 is live on Seedances. Generate clips up to 30 seconds at 480p, 720p, or 1080p. Add up to 30 images, 10 video clips, and 10 audio clips, or edit and extend a source video.
Text, image, reference, video edit, or video extend — generate up to 30s at 480p, 720p, or 1080p. Jobs use credits.
Latest — up to 30s, 480p/720p/1080p, plus video edit and extend
Tip: Press Ctrl+Enter to generate. Put dialogue in quotes for lip-synced audio.
0 / 10000
Sign in to generate with Seedance 2.5. Jobs use credits — creating an account does not include free generations.
Your preview will appear here
Write a prompt, choose settings, and hit Generate — your cinematic clip renders in this panel.
Longer clips than Seedance 2.0, more reference files, and video edit or extend. Output is 480p, 720p, or 1080p.
Earlier AI video models stitched shorter segments, which caused character drift, lighting shifts, and visible seams at cuts. Seedance 2.5 uses a sparse diffusion transformer to maintain scene state across the full timeline in one inference pass — scene changes and tempo shifts included.
In the generator, Seedance 2.5 outputs 480p, 720p, or 1080p.
A reference job accepts up to 30 images, 10 video clips, and 10 audio clips.
Edit a source clip, or extend it forward or backward. This works on the whole clip.
Visual and audio signals share a unified latent space, so dialogue, ambient sound, and effects stay synchronized with on-screen action. Wrap spoken lines in double quotes for clearer lip-sync timing.
Built by ByteDance's Doubao team, the sparse attention architecture extends temporal context so the model tracks identity, physics, and camera continuity across long clips — the technical foundation behind single-pass 30-second output.
Whether you start from a script, a product photo, or a full reference board, Seedance 2.5 supports the same production routes teams already use on Seedance 2.0 — with room to scale references and duration.
Describe subject, environment, camera verbs, pacing, and mood in natural language. Seedance 2.5 is tuned for longer narrative beats — up to 30 seconds with internal scene transitions — and ByteDance reports roughly 20% stronger prompt adherence versus the previous generation.
Upload hero frames or first-and-last-frame pairs to animate catalog photography, key art, and storyboards. Image-to-video keeps labels, materials, and composition faithful while Seedance 2.5 adds camera motion, physics, and native audio in the same render.
Attach up to 30 images, 10 video clips, and 10 audio clips, then describe how each asset should be used.
Seedance 2.5 is live on Seedances. It generates clips up to 30 seconds at 480p, 720p, or 1080p — for teams who outgrew 10–15 second generators and manual stitching.
For most of 2024 and 2025, AI video meant short loops: five seconds here, ten seconds there, then an editor hid the seams. Seedance 2.5 attacks the duration problem at the architecture level. ByteDance claims the model produces an unbroken 30-second timeline in a single generation call — including deliberate scene changes and tempo shifts — without post-stitching shorter segments. That matters for performance marketing hooks, vertical stories, education explainers, and pre-visualization where narrative pacing cannot break every twelve seconds.
On Seedances, Seedance 2.5 outputs 480p, 720p, or 1080p. Preview at 720p, then re-run at 1080p when the motion looks right.
Reference jobs on Seedance 2.5 accept up to 30 images, 10 video clips, and 10 audio clips. Seedance 2.0 reference mode is smaller: up to 9 images, 3 video clips, and 3 audio clips.
Video edit and video extend change an existing clip instead of starting over. Edit follows the source length. Extend continues the clip forward or backward for a length you choose.
Seedances wraps Seedance 2.5 in a production-ready web stack: authenticated accounts, credit-based billing with automatic refunds on failure, subscription tiers, and a unified generation history. Generate Seedance 2.5 now in the AI Video Generator — text, image, and reference routes with native audio — or continue with the Seedance 2.0 family on /ai-video.
Seedance 2.5 is live: up to 30s · 480p/720p/1080p · up to 30 images, 10 videos, and 10 audio clips · video edit and extend · generator at seedances.ai/seedance-2-5.
Longer native clips and richer controls unlock workflows that short-loop generators could not support without heavy manual editing.
Ship paid social spots and campaign variants up to 30 seconds. Reference images, video, and audio keep product look consistent. Video edit changes an existing clip instead of regenerating the whole job.
Turn product photos into lifestyle motion without a physical set. Draft at 720p, then export at 1080p.
Build half-minute concept explainers with synchronized narration — dialogue in quotes drives lip-sync on presenter-style shots. Scene changes inside one clip support chapter-like pacing for LMS modules and YouTube explainers.
Directors block camera moves and lighting across 30-second beats before live action. Agencies pitch storyboards as motion with native audio temp tracks. Sparse attention helps maintain character continuity across longer beats than earlier models allowed.
Common questions about Seedance 2.5 and generating on Seedances.
Seedance 2.5 is live on Seedances. Generate from text, image, or references, or edit and extend a source video. Output is up to 1080p. Jobs use credits.
Open AI Video Generator
