Use Seedance 2.0 for fluid multi-shot clips, text-to-video prompts, image references, and controllable video settings.
ByteDance's flagship tops blind preference leaderboards with director-level reference control: up to multiple images, video clips, and audio inputs steering one coherent generation.
Seedance 2.0 generates cohesive multi-shot sequences — consistent characters, lighting, and world across cuts — the failure point of most video models and the reason this one leads human-preference rankings. Narrative clips stop feeling like stitched-together gachas.
Steer a generation with multiple reference images, video clips, and audio tracks at once — a control surface communities describe as unavailable anywhere else. Lock a character, a location, and a motion style, then direct the scene in plain language.
Dialogue and ambience generate inside the same pass with believable lip-sync — no post-production audio layering. For talking pieces and atmospheric scenes, the clip arrives finished.
Modify specific elements of a generated scene or extend it with follow-up shots instead of regenerating from scratch. Iteration becomes editing, which is where real projects live.
Generated here on 15 August 2026, first take, exact prompts and settings shown. Each clip targets one of the capabilities claimed further down this page.
A potter shaping a tall vase on a wheel, clay slipping through wet hands, warm workshop light, camera slowly orbiting the wheel.
A busy morning market street: vendors arranging fruit, steam from a food cart, people walking past, consistent lighting and depth, slow dolly forward.
Compare Seedance 2.0 with other video models — same workspace, one click to switch.
Three steps from a blank prompt box to a finished clip.
Open the model picker and choose Seedance 2.0. The panel shows its credit cost, resolution options, and duration limits before you spend anything.
Write the subject, the action, and how the camera behaves. Attach a first frame if you want the clip to start from a specific image.
Download the clip, extend it, or send it through further editing. Prompt, model, and settings stay attached in your history.
One account, the full image and video generation workflow.
Run Seedance 2.0 on the free tier's daily credits, or upgrade for premium models, faster generation, and 4K output.
Perfect for getting started
Billed annually · $240/year
Billed annually · $300/year
It currently leads blind human-preference leaderboards for AI video, with multi-shot consistency, multi-reference control (images, clips, and audio), and native lip-synced audio.
Multiple reference images plus video and audio inputs in reference-to-video mode — lock characters, locations, motion styles, and soundtrack direction simultaneously.
Per second of output, varying with resolution — four tiers from 480p up to true 4K — and audio. The exact cost shows before generation, and failed runs are automatically refunded.
Yes — Seedance 2.0 offers 480p, 720p, 1080p, and 4K output. Higher resolutions bill at a higher per-second rate, so most creators draft at 480p and re-render the winning take at 1080p or 4K for delivery.
Configurable duration up to 15 seconds per generation, with scene extension available to continue a sequence.
Seedance leads on multi-shot consistency and reference control; Veo is strong on single-shot cinematic polish. For narrative sequences, Seedance is the community pick.
Yes — animate a still faithfully, or combine it with other references for a directed scene.
One-click tools for everything around generation — polish, restyle, and share.
