Handdrawn Live Video Generator Local logo

Handdrawn Live Video Generator Local

Community
swan7-py
handdrawn-live-video-generator-local

本地版(逐步确认式 · 纯提示词)。手绘发光动画+实拍融合 15s 16:9 视频:同语言组织提示词(接触→连续变形→逃脱→手机延迟追随),确认后调用 h3-video-prompt-cn skill 输出完整 H3 文生视频提示词(T2VA,无参考图)+设置建议,由用户自行在 H3 节点执行。无生图步骤;语音音乐先问云端否;删除自动剪辑。不依赖 MiniMax Hub。

Overview

Publisherswan7-py
RepositoryMiniMax-H3-Skills-Local
Skill namehanddrawn-live-video-generator-local
Stars
66
Forks
5
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by swan7-py on GitHub. Read the source before you install it.

Installation

Install the Handdrawn Live Video Generator Local AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/swan7-py/MiniMax-H3-Skills-Local/tree/main/old/handdrawn-live-video-generator-local
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/swan7-py/MiniMax-H3-Skills-Local.git /tmp/MiniMax-H3-Skills-Local
mkdir -p .claude/skills
cp -r /tmp/MiniMax-H3-Skills-Local/old/handdrawn-live-video-generator-local .claude/skills/handdrawn-live-video-generator-local
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Handdrawn Live Video Generator Local in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Handdrawn Live Video Generator Local on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Handdrawn Live Video Generator Local is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Handdrawn Live-Action Fusion Video Generator(本地版 · 逐步确认式)

本文件由原始 skill handdrawn-live-video-generator 改造为「本地版 · 逐步确认式」。 本地化改造总则 v2(纯提示词 · 逐步确认 · 交付物门)

⏹ 门控硬规则(真停顿 · 已生效):本 skill 中每个 ⏸ 确认门 与 ⏸ 交付物门 均为硬性停止点,不是建议。固定执行顺序:① 仅输出当前步骤交付物(提示词 / 文本计划 / 分镜脚本等);② 立即调用 AskUserQuestion 工具,给三选项「✅ 确认,继续下一步」「✏️ 修改当前步」「⏸ 暂停 / 停止或换方向」;③ 等待用户回复,本回复内绝不可预生成任何后续步骤(即使你觉得能一次写完)。任一 ⏸ 门不得跳过 / 合并,也不得仅用一句"请确认"文字代替——必须用 AskUserQuestion 真正阻塞。

  1. 本 skill 无生图步骤(纯文生视频);如未来需静帧,只给文生图提示词、用户自行生图并返回地址,不硬编码任何 ComfyUI 路径。
  2. 每一步都确认 + 交付物门(核心规则):每个步骤产出后我都会暂停,等你「确认 / 修改」。视频步骤生成后,等你**返回视频地址(可选)**或确认后再继续。
  3. 视频提示词调用 h3-video-prompt-cn skill:视频提示词调用用户级 h3-video-prompt-cn skill(纯文本、无需 API)来写;本 skill 为纯文生视频(T2VA),无参考图,按其 T2VA 结构输出完整 H3 视频提示词,并附设置建议,由你在本地 H3 节点自行执行。 H3 特殊占位符 <d>/</d>、<|lyrics_start|>/<|lyrics_end|>、<|caption_start|>/<|caption_end|>、<|cutoff|> 及其固定 id 见 h3-video-prompt-cn 的「特殊标记」节,写对白/歌词/字幕时严格照用。
  4. 语音 / 音乐先询问(已升级为「音频模式门」):进入流程第一步(方向/简报锁定)时,必须先用 AskUserQuestion 问你音频方案,二选一:
  5. 批次时长上限先问(贯穿分镜设计):同样在进入流程第一步(方向/简报锁定)时,用 AskUserQuestion 问你「本次一次生成几秒?」可选 5s / 10s / 15s(或自定),记为批次时长上限,并贯穿到本 skill 的分镜 / 镜头表设计步骤,使分镜在设计期就 ≤ 批次、无需事后强切。
    • A) 统一 H3 音频:旁白 + 对白 + BGM 全部由 H3 原生音频驱动生成(最省事,音色/配乐与画面同步,无需外部文件)。
    • B) 分离生成:旁白/对白只给提示词(你用任意 TTS 工具,推荐用「参考/音色克隆」模式保证跨镜头一致;不绑定 MOSS-TTS)、BGM 用 ACE-Step 1.5 本地生成(调用 ace-step-1.5-prompt-writer skill)、对白分别生成,后期合成。
    • 记录你的选择,后续「视频提示词步骤」与「音频步骤」依此分支执行。
  6. 旁白/对白一致性(分离模式必做):若选 B 且含旁白/对白,提醒你把【音色参考文件】(.wav/.mp3,代表目标音色)放到当前项目文件夹(你运行本 skill 的工作目录),并在调用 TTS 时使用「参考模式 / 音色克隆」,确保多镜头音色统一;若你未提供该文件,先暂停请其提供,禁止无参考直接生成(否则各镜头音色漂移)。
  7. BGM 分离 -> 视频提示词只规划视觉(重要):若选 B,BGM 由 ACE-Step 1.5 单独生成,因此调用 h3-video-prompt-cn 写视频提示词时不可规划 BGM/旁白/对白的音频出现(如"音乐渐强""旁白响起""对话切入"等),只规划镜头/动作/画面;音频在后期合成。若选 A,视频提示词可正常包含音频驱动指令,无需单独生成音频。
  8. 删除自动剪辑 / 拼接:本 skill 为单条视频,无剪辑;若有拼接需求改为剪辑思路。
  9. 规划 / 分镜 / 排版等文本方法论沿用原 skill。
  10. 删除"表情图"相关提示词(本 skill 不涉及)。

Step 1:同语言理解用户意图

同原 skill(中文输入→中文提示词,英文→英文,日文→日文;保留影像结构:实拍空间出现平面手绘发光动画、与真实手/物接触、同一实体连续变形并逃跑、相机慢半拍追赶;蜡笔/粉笔/彩铅/粉彩质感;禁 3DCG/毛绒/均匀矢量/平滑霓虹/恐怖/巨眼/裂口/牙/威吓/跳吓;0–3s 必现接触;全片同一相邻空间连续;13–15s 空间级变形+可爱余韵)。

  • ⏸ 确认门:意图理解呈现后暂停,等你确认。

Step 2:全新创意内容

同原 skill:每轮新组合,不复用参考 prompt 的暗房/PC/冰箱/星/心/蓝涡/蝶/蛇/章鱼/汉堡/巨眼/牙/暗结尾;新值:实拍空间、手绘初态、中心色、变形链、接触方式、追逐路线、拍摄者反应、空间级变形笑点。

  • ⏸ 确认门:创意呈现后暂停,等你确认。

Step 3:必需输出格式

同原 skill:开头句 + 实拍空间与手机质感 + 0–3s + 3–6s + 6–10s + 10–13s + 13–15s + 手绘质感 + 相机追随 + 禁止事项 + 环境音。

Step 4:提示词写作规则

同原 skill:可执行视频提示词而非散文;除非你要解释,先给提示词再给一句下一步建议;你明确确认 H3 生成前不生任何视频/图/音频/分镜。

Step 5:交付 + 视频提示词(调用 h3-video-prompt-cn + 设置建议 + 交付物门)

你确认后,不再由本 skill 直接写 H.3 提示词,改为调用 h3-video-prompt-cn skill:

  • 调用用户级 h3-video-prompt-cn skill(纯文本、无需 API),以 STEP1–4 的同语言创意材料为输入,按其 T2VA 结构输出完整 H3 视频生成提示词(纯文生视频,无参考图)。
    • ⚠️ 分镜 / 批次(严格遵循 h3-video-prompt-cn 约定):① 沿用起始门(简报)已确定的批次时长上限(批次时长由设备定,已在分镜设计前问过,本步不再重问);② 把分镜按批次时长分组,每批次产出一份独立 .md 文件(命名 batch_01.md、batch_02.md…),文件内含该批次全部分镜的 H3 提示词 + 端口/顺序/时长/分辨率建议。(本 skill 为纯文生视频 T2VA,无参考图,故不涉 <Picture N> 占位符。)
    • 🔒 批次打包(不重切分镜):把本 skill 分镜设计步骤产出并确认的分镜按时长累加打包为批次——同批次各镜时长之和 ≤ 批次时长上限(已在起始门确定),一个批次 = 一次 H3 生成 = 一份 batch_XX.md。不重新切分已设计的分镜,分镜的创意与音频时序在打包中保持不变。仅当某分镜本身 > 批次时长上限(设计期偶发)时,在生成层做机械分段(如 Shot 3 → 3a / 3b,该分镜音频跨子段连续),不改其创意内容。motion-context 在连续批次的衔接边界问(见 h3-video-prompt-cn 规则⑤:跨段连续时启用,第 2 段起 22 帧重复 + 时间标注后延 0.917s、第 1 段不变)。
  • 并附设置建议:
    • 本 skill 为纯文生视频(T2VA):不接参考图;音频依总则「音频模式门」——模式=分离 时本视频提示词仅规划视觉,环境音/配乐后期合成(除非你自备环境音接端口)。
    • 时长 = 15s;分辨率 = 16:9(1920×1080);其余你自定
    • 模型标注 MiniMax-H3;本地用 Wan/Animate2 文生视频亦可
    • 生成后自检:接触明显、连续变形、延迟追随、非恐怖手绘质感是否保留
  • 本步骤产出:完整 H3 视频提示词(T2VA)+ 设置建议。
  • ⏸ 交付物门(可选):你确认提示词后自行在本地 H3 节点生成视频;返回成片地址(可选)。未返回也可直接结束。

下一步建议(同语言一句话):示例「下一步建议:若确认此 prompt,可在本地 ComfyUI 的 H3 节点生成 15s 16:9 视频。」

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Handdrawn Live Video Generator Local AI skill do?

本地版(逐步确认式 · 纯提示词)。手绘发光动画+实拍融合 15s 16:9 视频:同语言组织提示词(接触→连续变形→逃脱→手机延迟追随),确认后调用 h3-video-prompt-cn skill 输出完整 H3 文生视频提示词(T2VA,无参考图)+设置建议,由用户自行在 H3 节点执行。无生图步骤;语音音乐先问云端否;删除自动剪辑。不依赖 MiniMax Hub。

Why use Handdrawn Live Video Generator Local on TypingMind?

Because you install it once and use it with any model. Handdrawn Live Video Generator Local is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Handdrawn Live Video Generator Local in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/swan7-py/MiniMax-H3-Skills-Local/tree/main/old/handdrawn-live-video-generator-local. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Handdrawn Live Video Generator Local?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Handdrawn Live Video Generator Local?

As many as you like. As long as a model supports skills, you can use Handdrawn Live Video Generator Local with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Handdrawn Live Video Generator Local AI skill free?

It is published on GitHub by swan7-py. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇