agentleFS
Sign inStart free
Anil-matchaAnil-matcha/Seedance-2.0-API/skills/seedance-v2/SKILL.md

seedance-v2

Skill352 starsChanged 7 months agoMITView on GitHub

Generate cinematic, high-fidelity AI videos from text prompts and static images using Seedance 2.0 (by ByteDance).

  • Reads credentials

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. prime-skills/runcomfy-agent-skills★ 41same name
    2. genmedia-labs/skills★ 26same name
    3. runcomfy-com/skills★ 16same name
    4. agentspace-so/runcomfy-skills★ 4same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a reusable character sheet for consistent generation.

    line 54
  2. Distinctive:

    Remove MuAPI watermarks from generated videos.

    line 60
  3. Very specific:

    Wait for Completion: Use the --wait flag to receive the final video URL directly.

    line 74
  4. Very specific:

    Aspect Ratios: Use 16:9 for horizontal videos and 9:16 for vertical content (like TikTok or Reels).

    line 75
  5. Very specific:

    Quality: Use --quality high for 2K resolution.

    line 76

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Seedance V2

Seedance 2.0 is a state-of-the-art video generation model developed by ByteDance. This skill allows you to generate videos from text, animate images, and edit existing videos using natural language commands.

Prerequisites

  • MUAPI_API_KEY: You must have an API key from muapi.ai. Set it as an environment variable.

Usage Guide

You can use Seedance 2.0 to create videos in various aspect ratios (16:9, 9:16, 4:3, 3:4) and durations.

Text-to-Video (T2V)

Generate a video from a descriptive text prompt.

python3.11 skills/seedance-v2/seedance_cli.py t2v --prompt "A cinematic slow-motion shot of a cyberpunk city in the rain" --wait

Image-to-Video (I2V)

Animate one or more static images.

python3.11 skills/seedance-v2/seedance_cli.py i2v --images "https://example.com/image.jpg" --prompt "Make the clouds move slowly" --wait

Video Rendering & Editing

Edit an existing video or apply styles.

python3.11 skills/seedance-v2/seedance_cli.py edit --videos "https://example.com/video.mp4" --prompt "Add a sunset filter" --wait

Omni-Reference Generation

Condition videos on any combination of images, videos, and audio.

python3.11 skills/seedance-v2/seedance_cli.py omni --prompt "The character @character:ID dances in the rain" --images "https://example.com/bg.jpg" --videos "https://example.com/motion.mp4" --wait

Character Consistency

Create a reusable character sheet for consistent generation.

python3.11 skills/seedance-v2/seedance_cli.py character --images "https://example.com/face.jpg" --outfit "Cyberpunk neon jacket" --name "Neo" --wait

Watermark Removal

Remove MuAPI watermarks from generated videos.

python3.11 skills/seedance-v2/seedance_cli.py watermark-remover --video_url "https://api.muapi.ai/..." --wait

Extending Videos

Extend a previously generated video segment.

python3.11 skills/seedance-v2/seedance_cli.py extend --request_id "YOUR_REQUEST_ID" --duration 5 --wait

Tips for Best Results

  • Be Descriptive: Detailed prompts result in better video quality and more accurate motion.
  • Wait for Completion: Use the --wait flag to receive the final video URL directly. Without it, you will receive a request_id which you can check later using the status command.
  • Aspect Ratios: Use 16:9 for horizontal videos and 9:16 for vertical content (like TikTok or Reels).
  • Quality: Use --quality high for 2K resolution.
  • Watermarks: Most v2.0 generation commands now support a --remove_watermark flag.

Commands Reference

CommandArgumentsDescription
t2v--prompt, --aspect_ratio, --duration, --quality, --remove_watermark, --waitText to Video
i2v--images, --prompt, --aspect_ratio, --duration, --quality, --remove_watermark, --waitImage to Video
omni--prompt, --images, --videos, --audios, --aspect_ratio, --quality, --waitOmni-Reference
character--images, --outfit, --name, --waitCreate Character Sheet
edit--prompt, --videos, --images, --aspect_ratio, --quality, --remove_watermark, --waitVideo Editing
watermark-remover--video_url, --waitRemove Watermark
t2v-480p--prompt, --aspect_ratio, --duration, --quality, --waitText to Video (480p)
i2v-480p--images, --prompt, --aspect_ratio, --duration, --quality, --waitImage to Video (480p)
extend--request_id, --prompt, --duration, --quality, --waitExtend Video
status--request_idCheck Task Status

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free