seedance2-api
Installation
Summary
End-to-end AI video generation from storyboard concept to final output.
- Supports both MCP and standalone Python script modes; automatically detects availability and switches gracefully if MCP is unavailable
- Generates reference images with Seedream 4.5 (text-to-image and image editing), then submits video tasks to Seedance 2.0 with configurable aspect ratios (16:9, 9:16, 1:1, 21:9, 4:3, 3:4) and durations (4–15 seconds)
- Offers two video generation modes: omni reference (up to 9 images, 3 videos, 3 audio files) and first/last frames (keyframe-based generation)
- Includes structured workflow guidance: idea collection, five-dimensional deep dive (content, visuals, camera, motion, audio), storyboard building, and automatic polling with ~10-minute video generation time
SKILL.md
Seedance 2.0 Storyboard & Video Generation
End-to-end workflow from concept to final video: Storyboard → Reference images → Submit video task → Get results.
Step 0: Determine Execution Mode (MCP or Script)
Check MCP availability first:
- Check
xskill-aiMCP service status (readmcps/user-xskill-ai/STATUS.md) - If MCP is available → use
submit_task/get_taskand other MCP tools - If MCP is unavailable or returns errors → switch to Script Mode
Script mode prerequisites: