New model

Seedance 2.0

New multi‑shot video model with strong consistency.

Next‑gen video model focused on multi‑shot storytelling with multimodal reference inputs, audio‑visual sync, and strong character consistency.

Best for: Cinematic previews

Inputs: Text/Audio

Outputs: Video

What this model is best at

Short answer: Next‑gen video model focused on multi‑shot storytelling with multimodal reference inputs, audio‑visual sync, and strong character consistency.

Use this workspace to preview the model, compare example output, and start creating with the recommended workflow for this model.

Highlight 1

Multi‑shot narrative generation with consistent characters.

Highlight 2

Multimodal references (image, video, text, and audio).

Highlight 3

Audio‑visual beat matching for timing and rhythm.

New

Seedance 2.0 workspace

Start from the built-in workflow below, then tune the model inside the standard LipsyncX creation surface.

New model

Cinematic previews · Multi‑scene storytelling

Photo Parlante Doublage Vidéo Vidéo Longue Animaux et Anime

1. Upload photo

1. Choisir un visage

Choisir un modèle ou téléchargerGlissez et déposez une vidéo ou une photoou cliquez pour télécharger

2. Choose Model

3. Add Script

Instant script templates

One-click copy for greetings, celebrations, and announcements.

—

Unité de facturation10 credits / 5s

Unités de facturation—

Durée estimée—

Est. total—

Utilise la durée audio réelle lorsqu'elle est disponible.

Voix

Speech speed (0.90x)

0 / 1000

—

Étape 1/4

Choisir un visage

Suivez l'étape suivante pour continuer à construire votre vidéo.

—

Temps de rendu moyen

7 min

Langues prises en charge

50+

Créateurs intégrés

3 200+

Approuvé par les équipes

StudioBlendAudioNovaCourseWaveMintlyVisionSpark

Multi‑shot teaser

Generate a cinematic multi‑scene preview.

Concept

Generated

Popular use cases

Use case 1

Cinematic previews

Showcase multi‑shot narratives.

Use case 2

Brand storytelling

Create multi‑scene launch teasers.

Use case 3

Concept videos

Prototype full sequences fast.

Quick specs

Image inputs

Up to 9 images

Video inputs

Up to 3 videos (max 15s total)

Audio inputs

Up to 3 MP3 files (max 15s total)

Text input

Natural‑language prompts

Best practices

Be explicit about what each reference controls (style, motion, camera, character).

Prioritize the most important assets within the 12‑file limit.

Double‑check @‑mentions to avoid swapping files.

Specify edit vs reference when using an existing video.

Align generation duration with intended extension length.

Write prompts like you are briefing a human editor.

FAQ

What makes it different from single‑shot models?

Seedance 2.0 focuses on multi‑shot storytelling with consistent characters across scenes.

What reference inputs are supported?

It supports multimodal references such as text, images, video, and audio.

What resolution does it target?

High‑resolution outputs up to 2K are supported.

Ready to try Seedance 2.0?

Use the built-in workspace to test prompts, compare outputs, and see how this model fits your content workflow.