#63 · Primary category: Video & Animation
seedance-2.0
Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0
Project last updated:08/06/26
GitHub Stars
7.0K
Forks
1.0K
Contributors
4
License
MIT
Why we included this project
Seedance 2.0 users who keep getting generic 'cinematic' output are the audience for this skill package. It treats prompt writing as directing: before you draft anything, an agent reads what the scene is actually doing, then works out camera, light, blocking, performance, and sound as one coherent setup instead of piling on adjectives. The repo is a modular agent-skill system built around a mandatory Director's Read and a deeper directing engine, with 33 worked derivations covering product, music video, horror, anime, action, comedy, and documentary work end to end. It also handles the unglamorous production side: separating reference assets by role, source-dating platform and model claims so nobody guesses at API details, and post-generation take triage with retake budgets and cost-aware drafting. Chinese, Japanese, and Korean readers get first-class entry points with language-specific prompt guidance, and anyone who wants repeatable, auditable Seedance workflows instead of one-off prompts will find a concrete operating system here.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
yt-dlp
A feature-rich command-line audio/video downloader
MoneyPrinterTurbo
Generate HD short videos from a topic or keyword with an automated AI workflow.
Deep-Live-Cam
real time face swap and one-click video deepfake with only a single image
manim
Animation engine for explanatory math videos
anime
JavaScript animation engine