Seedance 2.5 — 30-Second Stories in One Pass
ByteDance's next-generation video model generates high-quality 30-second audio-video clips in a single pass, with multi-round extensions for longer narratives. Feed up to 30 images, 10 videos, and 10 audio clips, guide shots with clay-render references, and refine results with timestamp-level editing.
Powered by ByteDance Seed Team
What is Seedance 2.5
Seedance 2.5 is ByteDance Seed Team's new-generation video creation model. Building on Seedance 2.0's unified multimodal audio-video architecture, it focuses on foundational generation and reference-based creation — with breakthroughs in long-form storytelling, multimodal reference, and editing. It generates up to 30-second clips in one pass (up from 15 seconds on 2.0), supports multi-round extensions for multi-minute stories, and accepts up to 30 images, 10 video clips, and 10 audio clips per job. Clay-render referencing helps lock composition and camera paths; timestamp-level editing, green-screen, and camera-perspective tools support film and advertising workflows. Audio and video stay jointly generated so dialogue, effects, and ambience stay locked to picture.
Native 30-Second Single-Pass Generation
Generate a complete high-quality 30-second audio-video clip in one pass — with stronger shot transitions and scene changes for continuous storytelling. Enough length for full ad beats, product demos, and multi-shot narrative arcs that shorter models struggle to deliver in a single generation.
Up to 50 Multimodal References
In one job, combine up to 30 images, 10 video clips, and 10 audio clips — plus stronger clay-render, motion, and creative referencing. Lock character identity, product look, style, and camera language across complex multi-subject scenes.
Multi-Round Extensions
Append follow-up shots while keeping characters, environments, and pacing consistent. Official workflows use this to build multi-minute stories without manually splicing unrelated short clips.
Precise Timestamp Editing
Control narrative, camera, and rhythm for specific time ranges during generation, then make targeted post edits to characters, actions, or plot while preserving continuity. Green-screen, camera-perspective, and reference-based editing support professional film and ad pipelines.
Why Seedance 2.5 Changes Professional AI Video
Seedance 2.5 is built for teams who need complete creative works — not just short novelty clips. These upgrades target storytelling length, reference control, and editable production workflows.
Full Feature Set of Seedance 2.5
Capabilities highlighted in ByteDance Seed's official Seedance 2.5 launch — from one-take storytelling to precise editing.
Text-to-Video at 30 Seconds
Describe scenes, camera moves, and story beats in natural language and receive a full half-minute clip in one generation.
Image & Video Reference Input
Upload up to 30 images and 10 video clips to steer character appearance, environment, motion style, and editing rhythm.
Audio Reference & Joint Sync
Add up to 10 audio clips to guide mood and pacing while the model jointly generates synchronized sound with picture.
Clay-Render Composition Control
Use textureless 3D / clay-render references to lock spatial structure, blocking, motion paths, and camera angles before final rendering.
Timestamp-Level Editing
Target specific time ranges to adjust narrative, actions, or characters while keeping continuity before and after the edit.
Green Screen & Camera Edits
Replace backgrounds or rewrite camera perspective while preserving the main subject and physical interaction with the new scene.
Multi-Round Extension
Continue from an existing clip with consistent subjects, environments, and sound for longer multi-minute stories.
Improved Visual Polish
Official updates emphasize more natural textures, lighting, skin and eye detail, and fewer uncontrolled subtitles or background-music artifacts.
Unified Audio-Video Generation
Dialogue, effects, and ambience are generated with the picture so audiovisual language stays coherent across shots.
Available on SeedDance
Seedance 2.5 is live in the SeedDance video generator alongside Seedance 2.0 — same credits, task history, and workspace.
Frequently Asked Questions
Everything you need to know about Seedance 2.5 and how it compares to earlier Seedance models.
Start Creating with Seedance 2.5 on SeedDance
Generate up to 30-second one-take clips with multimodal references on SeedDance. Seedance 2.5 is live for text-to-video, image-to-video, and reference-to-video — alongside Seedance 2.0.