- 📁 genres/
- 📁 modules/
- 📁 references/
- 📄 SKILL.md
Generate images and videos for Douyin (抖音) and Xiaohongshu (小红书) content using AI generation APIs. Use this skill whenever the user wants to generate images, create video clips, produce visual assets, render scenes from a storyboard, or when the pipeline step is "assets". Handles shot-by-shot image and video generation with style consistency, prompt engineering, and quality control.
Generate AI music and songs with Diffrythm, Tencent Song Generation via inference.sh CLI. Models: Diffrythm (fast song generation), Tencent Song Generation (full songs with vocals). Capabilities: text-to-music, song generation, instrumental, lyrics to song, soundtrack creation. Use for: background music, social media content, game soundtracks, podcasts, royalty-free music. Triggers: music generation, ai music, generate song, ai composer, text to music, song generator, create music with ai, suno alternative, udio alternative, ai song, ai soundtrack, generate soundtrack, ai jingle, music ai, beat generator
- 📁 agents/
- 📁 references/
- 📁 scripts/
- 📄 .gitignore
- 📄 LICENSE
- 📄 package-lock.json
Automate JiMeng (即梦AI at jimeng.jianying.com), Seedance video generation, and canvas projects in a real browser with Playwright. Use for Douyin QR login, JiMeng image or video generation, canvas project creation/opening/prompting, record-id based status checks, canceling queued video tasks, and downloading completed results.