This is a full-featured wrapper for Seedance 2.0, the Chinese AI video model that works more like a cinematography instruction set than a typical prompt-to-video tool. It handles text-to-video, image animation, video extension, and some legitimately interesting stuff like first/last frame interpolation and persistent character training through the omni-train mode. The watermark removal function is included, which tells you something about the practical use cases here. With 578 installs and security warnings from Socket and Snyk, you'll want to review the code before dropping this into production. If you're prototyping generative video workflows and want access to Seedance's director-level controls without writing your own API client, it covers the bases.
npx skills add https://github.com/samuraigpt/generative-media-skills --skill muapi-seedance-2