skills.rest
brillianodhiya
brillianodhiyaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

seedance-v2

Generate short-form video with ByteDance Seedance 2.0 Pro via the RunComfy CLI.

Updated Jun 11, 2026
Search Tags:#video generation#text-to-video#AI video#lip-sync#seedance#bytedance#runcomfy
One-click install
npx skills add https://github.com/brillianodhiya/VisionScript --skill seedance-v2-brillianodhiya
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: seedance-v2
Source: https://github.com/brillianodhiya/VisionScript/tree/main/.agents/skills/seedance-v2
Command: npx skills add https://github.com/brillianodhiya/VisionScript --skill seedance-v2-brillianodhiya

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @runcomfy/cli.

What problem does it solve? Creating cinematic short-form video with synchronized audio and lip-sync normally requires stitching together separate generation, TTS, and editing tools. This Skill routes video generation requests to ByteDance Seedance 2.0 Pro on the RunComfy Model API, handling multi-modal references (images, videos, audio) in a single call. ## Core Features & Use Cases - Multi-modal video generation: Combine up to 9 image references, 3 video clips, and 3 audio references with a text prompt to produce 4–15 second videos at 480p or 720p. - Native lip-synced audio: Generate in-pass synchronized speech, SFX, and music with tone direction, ideal for spokesperson ads and dialogue content. - Model routing guidance: Built-in decision table for when to use Seedance 2.0 Pro versus HappyHorse 1.0, Wan 2.7, Kling, or LTX 2. - Use Case: A marketer needs a vertical 9:16 lip-synced ad where a barista explains today's special. Provide a headshot image reference plus a prompt describing camera movement and tone, and the Skill invokes runcomfy run bytedance/seedance-v2/pro to produce the clip. ## Quick Start Ask the AI to generate a video with Seedance 2.0 Pro, for example: "Use Seedance to generate an 8-second 9:16 video of a barista explaining today's special with natural lip-sync, using this headshot as the image reference."

Frequently Asked Questions about seedance-v2

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

FAQPage Schema
How do I generate a video with Seedance 2.0 Pro?▼

Run `runcomfy run bytedance/seedance-v2/pro --input '{"prompt": "your prompt"}' --output-dir <path>` after installing the RunComfy CLI and logging in. The CLI submits the request, polls for completion, and downloads the result video to your output directory.

Seedance 2.0 Pro vs Wan 2.7 vs Kling for video generation?▼

Seedance 2.0 Pro is best for multi-modal references and native lip-synced dialogue. Wan 2.7 fits audio-driven lip-sync from your own track via audio_url, Kling Video O1 handles motion editing on existing footage, and HappyHorse 1.0 leads blind-vote quality rankings.

What reference media does Seedance 2.0 Pro support?▼

It accepts up to 9 images (JPEG/PNG/WebP/BMP/TIFF/GIF), 3 video clips (MP4/MOV, 2–15 seconds each), and 3 audio files (WAV/MP3, 2–15 seconds, under 15MB each). Out-of-range files are rejected by the API.

What are the duration and resolution limits of Seedance 2.0 Pro?▼

Videos must be 4–15 whole seconds; longer requests return a 422 error, so segment into multiple calls. Resolution is capped at 480p or 720p on this endpoint, with aspect ratios including 16:9, 9:16, 1:1, and adaptive.

Why does my Seedance video have identity drift from the prompt?▼

Describing stable identity (face, costume, logo) verbally in the prompt causes drift. Put stable identity in image_url references and reserve the prompt for evolving narrative elements like action, mood, lighting, and camera movement.

How do I authenticate the RunComfy CLI in CI environments?▼

Set the RUNCOMFY_TOKEN environment variable instead of running `runcomfy login`, which uses a browser device-code flow. Locally, the token is stored at ~/.config/runcomfy/token.json with owner-only 0600 permissions.

Related Skills

Explore More Design & Creative Skills→
genmedia-labsgenmedia-labs
12

wan-3-0-prime-reference-to-video

Generate videos from numbered image, video, and audio references via the RunComfy CLI.

Official
Intermediate
Peter-Swain-IncPeter-Swain-Inc
1

ad-creative-brief-generator

Generate ICA-informed ad creative briefs with platform specifications and measurement frameworks.

Official
Advanced
labs21-devlabs21-dev
28

media

Generate images, videos, speech, and transcriptions via harness CLI commands.

Official
Intermediate
runcomfy-comruncomfy-com
12

wan-2-7

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

Official
Intermediate