This is a forensic debugger for when your Seedance 2.0 video generation goes wrong. You paste in your broken prompt and describe what happened (duplicate characters, random subtitles, face drift, style switching mid-video), and it walks through a decision tree of 12 common failure modes to diagnose root cause. Then it hands back a fixed prompt with a diff table explaining each change. The methodology is extremely specific: it knows that three-view reference images cause twin cloning, that café scenes trigger storefront text, that extending videos more than a few times degrades faces into blotchy messes. Most fixes are prompt rewrites, but for things like splice jumpcuts it tells you to drop 6 frames in one clip and 1 in the other because that's the frame offset issue. Honest and procedural.

GitHub stars
269
last updated
Jun 1, 2026

Install

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

Installs into .claude/skills of the current project.

Files

seedance-debugger

输入:有问题的提示词 + 用户描述的症状(或视频截图)。 输出:诊断(根因) + 修复后的提示词 + 解释为什么这样改。

何时不用此 skill

12 类问题诊断手册

详见 methodology/08-避坑12问.md。这里给出快速决策树。

症状识别 → 跳转

用户说的症状跳转
"人脸不像 / 中途换脸 / 撞脸明星"#1 人物-id-漂移
"莫名出现字幕 / 视频里有文字"#2 字幕
"有水印 / 有 Logo"#3 logo-水印
"动漫风格变成真人了 / 风格变了"#4 风格漂移
"拼接处跳帧 / 衔接不流畅"#5 延长跳变
"出现两个一模一样的人"#6 双胞胎
"延长后画质变糊 / 人脸有斑驳色块"#7 画质劣化
"特效不对 / 倒计时乱跳"#8 特效不对
"人物多了/少了"#9 参考人物过多
"结尾有咔哒声"#10 结尾噪音
"中文读错字了"#11 中文发音
"音色不像参考音频"#12 音色不准

1. 人物 ID 漂移

根因:参考图混用(人脸 + 全身 + 服装在一张图) OR 人脸占比过小。

修复策略:

  1. 让用户额外准备一张大头照(只包含面部,无表情最佳)
  2. 提示词中明确区分:<主体1> 的面部特征参考图片1(大头照),妆造参考图片2(全身照)
  3. 重要素材前置

反例:将图1中的人物作为主角... 正例:将@图片1(大头照)的面部特征作为主角面部锚点,@图片2(全身照)作为整体妆造参考。主角...


2. 字幕

根因:参考图/视频中包含文字;竖屏更易触发。

Sponsors

Details

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

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

All 7
1cclank avatarseedance-storyboardcclank/lanshu-awesome-ai-video-kit把复杂剧情/故事大纲拆分为 Seedance 2.0 的"镜头1/镜头2/镜头3"多分镜结构。每个分镜按 4 维度组织(运镜 + 主体动作与表情 + 位置/空间变化 + 音频)。用于"帮我把这个故事写成 Seedance 提示词"、"分镜脚本"、"多镜头视频"、"剧情复杂的视频"、"剧本转分镜"等触发场景。0skills.sh installs
2cherryhq 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
3cherryhq 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
4daffy0208 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
5daffy0208 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
6daffy0208 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