seedance-2-0

Generate cinematic video with synced audio via Seedance 2.0 across gateways.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/hanzoai/video --skill seedance-2-0
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: seedance-2-0
Source: https://github.com/hanzoai/video/tree/main/.agents/skills/seedance-2-0
Command: npx skills add https://github.com/hanzoai/video --skill seedance-2-0

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Solves the problem of producing premium cinematic video clips by using Seedance 2.0 across configured gateways.

Core Features & Use Cases

  • Single-pass native synced audio: Speech, SFX, and ambience generated in one pass for cohesive sound design.
  • Multi-shot in a single generation: Create montage-style clips with multiple cuts in one prompt.
  • Reference-conditioned generation & identity consistency: Maintain character identity across shots with up to 9 reference images, 3 video clips, and 3 audio clips.
  • Director-level camera control & lip-sync: Supports camera directions (dolly, tilt, arc) and accurate lip-sync from dialogue text.
  • Use case examples: trailers, teasers, hype edits, or premium cinematic pieces requiring synchronized audio and complex shot choreography.

Quick Start

Generate a cinematic trailer with Seedance 2.0 across gateways using a single prompt, aiming for a 10–15 second piece with 21:9 aspect ratio and synced audio.

Frequently Asked Questions about seedance-2-0

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate cinematic video clips with synced audio in a single pass?

Cinematic video generation with synced audio is achieved by using Seedance 2.0 to render speech, SFX, and ambience natively in one pass, ensuring cohesive sound design without needing separate audio post-processing.

Can I maintain character identity across multiple shots in a generated video?

Yes, character identity consistency across multiple shots is maintained through reference-conditioned generation, allowing you to input up to 9 reference images, 3 video clips, and 3 audio clips to guide the output.

What is the best way to create a multi-shot montage from a single text prompt?

The best way to create a multi-shot montage from a single prompt is using Seedance 2.0 multi-shot generation, which produces montage-style cinematic clips with multiple cuts and director-level camera controls like dolly, tilt, and arc.

Does Seedance 2.0 support lip-sync from dialogue text for cinematic trailers?

Yes, Seedance 2.0 supports accurate lip-sync directly from dialogue text, enabling the production of trailers and teasers with synchronized speech alongside director-level camera control.

How do I route video generation tasks across multiple gateways to manage costs?

Cross-gateway orchestration and preferred-provider routing allow you to manage deployment costs by distributing Seedance 2.0 cinematic video generation tasks across configured gateways within the OpenMontage pipeline.

What are the limitations when using reference videos for hype edits?

Limitations include a maximum input capacity of up to 9 images, 3 video clips, and 3 audio clips for reference-conditioned generation, constraining the total reference material used for a single multi-shot sequence.