skills.rest
prime-skills
prime-skillsOFFICIAL
Explore all skills by this author →
GitHub

seedance-v2

Generate cinematic short-form videos with synchronized audio via RunComfy.

31|9|Updated Apr 30, 2026
Search Tags:#video generation#seedance#lip sync#cinematic video#runcomfy#multimodal references
One-click install
npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill seedance-v2-prime-skills
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: seedance-v2
Source: https://github.com/prime-skills/runcomfy-agent-skills/tree/main/seedance-v2
Command: npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill seedance-v2-prime-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps creators produce polished short-form cinematic videos without stitching together separate video, voice, lip-sync, and sound-design workflows. It preserves the identity and visual details of reference media while generating coherent motion, dialogue, and synchronized audio through RunComfy.

Core Features & Use Cases

  • Multimodal Reference Generation: Combine up to nine images, three videos, and three audio references to guide characters, environments, movement, voice tone, and scene continuity.
  • Native Synchronized Audio: Generate dialogue, natural lip-sync, sound effects, music, and ambient sound in the same video pass.
  • Cinematic Creative Control: Specify camera shots, motion, lighting, aspect ratio, duration, resolution, and reproducible seeds for short-form video production.
  • Model Routing Guidance: Choose Seedance 2.0 Pro for reference-driven cinematic clips, while routing motion editing, audio-driven lip-sync, ultra-fast iteration, or maximum blind-vote quality to more suitable sibling models.
  • Use Case: Create an eight-second vertical spokesperson advertisement using a character image, a conversational script, warm cafe lighting, and synchronized spoken audio.

Quick Start

Ask the AI to generate a five-second cinematic video from your prompt with synchronized audio using Seedance 2.0 Pro on RunComfy.

Frequently Asked Questions about seedance-v2

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

FAQPage Schema
How do I generate cinematic video with native lip-sync audio from text prompts?▼

You can generate cinematic video with native lip-sync audio by submitting validated text prompts, optional image, video, and audio URLs to the bytedance/seedance-v2/pro endpoint via RunComfy CLI for clips between four and fifteen seconds.

Can I use multiple images and audio references to guide video generation?▼

Yes, multimodal reference generation allows combining up to nine images, three videos, and three audio references to guide characters, environments, movement, voice tone, and scene continuity for your cinematic video.

Do I need the RunComfy CLI to produce synchronized dialogue and sound effects?▼

Yes, RunComfy CLI is required to execute the endpoint and generate synchronized dialogue, natural lip-sync, sound effects, music, and ambient sound in the same video pass.

What aspect ratios and resolutions are supported for short-form video production?▼

Short-form video production supports validated aspect ratios with 480p or 720p resolution options, alongside reproducible seeds, camera shots, motion, and lighting controls.

When should I choose Seedance 2.0 Pro over sibling models for video creation?▼

Choose Seedance 2.0 Pro for reference-driven cinematic clips, while routing motion editing, audio-driven lip-sync, ultra-fast iteration, or maximum blind-vote quality to more suitable sibling models.

What are the limitations when creating spokesperson advertisements with this workflow?▼

Limitations include clip durations restricted to four to fifteen seconds, supported resolutions capped at 720p, and strict dependency on multimodal references, validated prompts, and RunComfy CLI.

Related Skills

Explore More Design & Creative Skills→
runcomfy-comruncomfy-com
12

image-to-video

Route still images to RunComfy image-to-video models for animated video output.

Official
Intermediate
CoachSteffCoachSteff
1

videoeditor

Automates video editing tasks such as trimming, merging, and formatting with FFmpeg and NLP.

Community
Advanced
delorenjdelorenj
14

fal-text-to-image

Generate images from text prompts using fal.ai models with style transfer.

Community
Advanced
runcomfy-comruncomfy-com
12

wan-2-7

Generate text-to-video clips with optional audio-driven lip-sync via RunComfy.

Official
Intermediate