Create promo clips in diverse visual styles from identical narration and book covers, delivering locally rendered MP4s and editable sources.
video-illustrator
Turn the user's own voice and real assets (book or course covers, screenshots, logos) plus a chosen visual style into a 20–60 second cinematic promo or concept explainer, or turn a passage, article, idea or script into an animated illustration clip, or (explainer mode) make one passage of an existing narrated video visible as a mechanism insert in 16:9 and 9:16, or (episode mode) make a whole researched, narrated science or tech explainer with real footage. One system where every mode runs the same steps and picks its look from one style atlas (a bright 3D diagram by default for explainers and episodes). Use for 宣传片, 电影感短片, 配视频, 文字转动画, animated explanations, motion graphics, 讲解插入镜头, 机制示意, 整期科普片, 解释手法, or a short video illustration. Produces editable scene source and MP4 rendered locally; optional paid music generation. Not for editing an existing recorded video or managing a production timeline.
ソース情報
- リポジトリ
- axtonliu/video-illustrator
- ソースの最終更新活動
- 2026年10月23日 16:51
- 検出された SKILL.md の言語
- 英語
- スター
- 52
- フォーク
- 6
video-illustrator: Make a promo from your voice
Turn narration, book covers, screenshots or other supplied material into a short promo or animated explainer.
Examples
The author presents the same narration and book cover in several styles. See the editorial-tech example and cinematic 3D example, linked in the repository README. These are author demonstrations.
Prerequisites
Designed for Claude Code with Opus 5.5. Local rendering uses Node.js, Chromium and FFmpeg. Narration and asset folders are optional; text alone is also supported.
How to use
Provide the passage or project folder, choose a style and state the intended duration and audio. Optional inputs go in inputs/voice/, inputs/assets/ and inputs/brand/. The workflow writes brief.md, checks keyframes and a motion preview, then returns the MP4, scene source and required assets.
Limitations
Other hosts are unverified. Supplied assets retain their original appearance. Clips are silent unless audio is requested; generated music uses a paid external service and requires authorization and an API key. This is not for editing recorded footage or managing a production timeline, and samples do not guarantee a finished film in one pass.
インストール方法
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
ソースファイルを確認
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SKILL.md を表示中
| name | video-illustrator |
|---|---|
| description | Turn the user's own voice and real assets (book or course covers, screenshots, logos) plus a chosen visual style into a 20–60 second cinematic promo or concept explainer, or turn a passage, article, idea or script into an animated illustration clip, or (explainer mode) make one passage of an existing narrated video visible as a mechanism insert in 16:9 and 9:16, or (episode mode) make a whole researched, narrated science or tech explainer with real footage. One system where every mode runs the same steps and picks its look from one style atlas (a bright 3D diagram by default for explainers and episodes). Use for 宣传片, 电影感短片, 配视频, 文字转动画, animated explanations, motion graphics, 讲解插入镜头, 机制示意, 整期科普片, 解释手法, or a short video illustration. Produces editable scene source and MP4 rendered locally; optional paid music generation. Not for editing an existing recorded video or managing a production timeline. |