Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added LICENSE.txt file to the repository. - Established an explicit license for the seedance-video-generation skill.
What This Skill Does
Generates AI videos from text prompts or images using ByteDance Seedance models via the Volcengine Ark API. Supports text-to-video, image-to-video with first/last frame control, and reference image generation. Includes task management for polling, cancellation, and consecutive video chaining.
The built-in Python CLI handles base64 conversion, polling, retries, and downloading automatically, removing the need to script those steps manually.
When to use it
- Animating a product photo into a short video clip
- Generating a timelapse video from a text description
- Creating a video that transitions between two specific images
- Producing a draft preview before committing to a full-quality render
- Animating a character by referencing multiple photos
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: generate a 5-second video of ocean waves at sunset
- 1Verify ARK_API_KEY is set
- 2Run seedance.py create with the text prompt, default 720p 16:9 settings, and --wait flag
- 3Poll task status every 15 seconds until succeeded
- 4Download the resulting MP4 to the desktop
- 5Display the task ID and local file path to the user
MP4 video file saved to ~/Desktop/seedance_video_20260313_120000.mp4
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.