Takes a story outline or script and breaks it into 3-5 sequential shots for Seedance 2.0, organizing each by camera movement, character action and expression, spatial position, and audio. Built for the 15-second limit where single-prompt approaches fall apart. The four-dimension structure keeps you from the usual mess of trying to cram narrative arc into one blob of text. Works best when you specify reference materials upfront (character photos, scene images, camera movement samples) and keep it to 4-5 assets max to avoid style conflicts. Includes a checklist to catch the common errors like mixing multiple camera moves in one shot or using vague action verbs instead of specific body movements.

GitHub stars
269
last updated
Jun 1, 2026

Install

$ npx -y skills add cclank/lanshu-awesome-ai-video-kit --skill seedance-storyboard --agent claude-code

Installs into .claude/skills of the current project.

Files

seedance-storyboard

剧情 → 多镜头分镜。Seedance 内部把时间和空间解耦,复杂视频最理想的形态是时间轴化分镜。

何时不用此 skill

  • 单一镜头单一动作 → 用 seedance-prompter
  • 5/10/15 秒紧凑短片(HappyHorse 主战场) → 用 happyhorse-prompter
  • 想做循环视频 → 单镜头 + loop-ready motion with seamless start and end frames

核心规则

详见 methodology/03-分镜时序.md。

  1. 使用 镜头1、镜头2、镜头3 等标识,按事件发生顺序组织(先主后次)
  2. 不强制限制每段时长("00-03s"这种写法不稳定,让模型自然生成节奏)
  3. Seedance 最多 15 秒,所以镜头数控制在 3-5 个最稳
  4. 每个镜头按 4 维度组织:
    • 运镜或镜头切换方式(如 "全景缓慢推近"、"固定机位"、"镜头切至…")
    • 主体动作与表情(核心角色 / 物体的关键动作、神态变化)
    • 位置或空间变化(主体所处的场景、位置或空间关系)
    • 音频信息(音效、人声或背景音乐)

工作流程

步骤 1:解析剧情

把用户给的剧情拆成 3-5 个关键节拍。每个节拍对应一个镜头。问自己:

  • 这一刻最关键的画面是什么?
  • 这一刻的情绪锚点是什么动作/表情?
  • 上下镜头之间怎么承接(动作惯性 / 切场 / 时间跳跃)?

步骤 2:确定素材角色

如果用户提到要用参考图/视频,明确每个素材的"功能角色":

角色作用
角色锚定锁定角色外观(推荐:大头照 + 全身照)
场景定调锁定环境与风格
运镜参考锁定镜头语言与动作节奏
节奏氛围用音频控制情绪、音色

推荐配置:4-5 个素材,不要用满(过多会导致风格冲突)。

步骤 3:用模板拼接

[素材分配 + 主体定义],参考 @视频X 的运镜方式(如有)。

镜头 1:[运镜] + [主体@素材N 的动作与表情] + [位置/空间] + [音频]。
镜头 2:[运镜切换] + [主体@素材N 的动作变化] + [位置变化] + [音频]。
镜头 3:[运镜] + [主体动作] + [位置] + [音频]。

Sponsors

Details

Repository
github.com/cclank/lanshu-awesome-ai-video-kit
Category
AI & Agent Building
License
MIT
First seen
Jun 11, 2026

More from cclank/lanshu-awesome-ai-video-kit

All 7
1cherryhq avatarcherry-assistant-guidecherryhq/cherry-studioCherry Studio 产品知识库、源码路径索引、故障排查和页面导航。当用户询问 Cherry Studio 的功能、配置、报错、使用方法时触发。也适用于用户提到 provider、模型、知识库、Agent、MCP、OpenClaw、PDF、快捷短语等关键词的场景。0skills.sh installs
2cherryhq avatargh-pr-reviewcherryhq/cherry-studioAutomated Cherry Studio code review for local branches, PRs, commits, and files. Use for reviewing code, docs, or pull requests with project-specific checks for0skills.sh installs
3daffy0208 avatarAPI Designerdaffy0208/ai-dev-standardsDesign REST and GraphQL APIs. Use when creating backend APIs, defining API contracts, or integrating third-party services. Covers endpoint design, authenticatio0skills.sh installs
4daffy0208 avatarFrontend Builderdaffy0208/ai-dev-standardsBuild modern React/Next.js frontends. Use when creating web applications, choosing frontend stack, structuring components, or implementing UI/UX designs. Covers0skills.sh installs
5daffy0208 avatarKnowledge Graph Builderdaffy0208/ai-dev-standardsDesign and build knowledge graphs. Use when modeling complex relationships, building semantic search, or creating knowledge bases. Covers schema design, entity 0skills.sh installs
6daffy0208 avatarSecurity Architectdaffy0208/ai-dev-standardsComprehensive security architecture combining threat modeling, security-first design, secure coding review, and compliance validation. Consolidated from threat-0skills.sh installs