Model Selector logo

Model Selector

Community
cclank
model-selector

根据用户的视频需求(场景、时长、音频、语言、平台限制、预算、是否需要本地部署/角色一致性等),从 16 个主流 AI 视频模型(12 商业 + 4 开源)中推荐最匹配的 1-3 个,并解释为什么。覆盖商业:Seedance 2.0、HappyHorse 1.0、Kling 3.0、Sora 2、Veo 3.1、**Gemini Omni**(2026-05 新)、Runway Gen-4.5/Aleph、Pika 2.5、Hailuo 02、Hunyuan Video 1.5、Wan 2.7、即梦 AI;开源:LTX-Video 0.9.7、Mochi 1、CogVideoX 5B、Higgsfield Soul。用于"用哪个 AI 视频模型好"、"Sora 还是 Kling"、"国内有什么模型"、"哪个免费"、"哪个支持中文"、"哪个能编辑已有视频"、"哪个能本地部署"、"哪个角色一致性最强"等触发场景。

Overview

Publishercclank
Repositorylanshu-awesome-ai-video-kit
Skill namemodel-selector
Stars
426
Forks
99
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by cclank on GitHub. Read the source before you install it.

Installation

Install the Model Selector 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/cclank/lanshu-awesome-ai-video-kit/tree/main/skills/model-selector
  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/cclank/lanshu-awesome-ai-video-kit.git /tmp/lanshu-awesome-ai-video-kit
mkdir -p .claude/skills
cp -r /tmp/lanshu-awesome-ai-video-kit/skills/model-selector .claude/skills/model-selector
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Model Selector 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 Model Selector 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 Model Selector 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.

model-selector

15 个主流 AI 视频模型(11 商业 + 4 开源)的"购物顾问"。问用户 3-4 个关键问题,给出推荐 + 理由。

何时不用此 skill

  • 用户已经确定要用某个模型 → 用对应的 <model>-prompter skill
  • 用户问"提示词怎么写" → 用 seedance-prompter / kling-prompter / happyhorse-prompter
  • 用户的提示词不工作 → 用 seedance-debugger

11 模型能力速查矩阵

模型中文音频物理编辑时长开源国内可用主战场
Seedance 2.0★★★—★★★—15s—✓电影叙事
HappyHorse 1.0★★★★★★★—15s(默认 5s)—✓ASMR / 短片
Kling 3.0★★★★★★★★★★★★★✓2m—✓中文剧情 / 图生视频
Sora 2★★★★★★★★★★★—25s (Pro)—△电影艺术片
Veo 3.1★★★★★★★★★★—148s chained—△多人对话
Gemini Omni ⭐NEW★★★★★★★★★★★★★待定—△迭代编辑 / 文字渲染 / 跨模态
Runway Gen-4★★★—★★★★★★★★30s—✓视频编辑
Pika 2.5★★★★★—25s—✓创意特效
Hailuo 02★★★—★★★★★—10s—✓物理动作
Hunyuan 1.5★★★★—★★★✓10s★★★★★✓开源 / LoRA
Wan 2.7★★★★★★★★★★★✓15s—✓数字人 lip-sync
即梦 3.0★★★★★★★★★★—15s—✓中文 + 剪映集成

工作流程

步骤 1:问 3-4 个关键问题

不要全部问,挑最影响结果的 3-4 个:

维度问题
时长"需要多长?5 秒 / 10 秒 / 15 秒以上?"
音频"要原生音频吗?只要环境音 / 要对白 / 要 BGM / 不要"
语言"是中文场景还是英文场景?"
编辑性质"全新生成还是编辑已有视频?"
平台限制"国内可用 / 国际可用 / 本地部署?"
用途"短视频爆款 / 影视级 / 商业广告 / 个人创作?"

步骤 2:按决策树推荐

是编辑已有视频?
├── Yes → Runway Aleph(独家)
└── No → 继续
    ├── 要数字人/真人对口型?
    │   └── Yes → Wan 2.7(业界最准)
    ├── 要多人对话+精确配乐?
    │   └── Yes → Veo 3.1
    ├── 中文剧情/中式美学?
    │   └── Yes → 即梦 3.0(创作者) / Kling 3.0(开发者 API)
    ├── 极致物理感(水/火/动作)?
    │   └── Yes → Hailuo 02 > Sora 2
    ├── 创意爆款特效(变身/融化)?
    │   └── Yes → Pika 2.5(Pikaffects)
    ├── 本地部署/开源/LoRA 训练?
    │   └── Yes → Hunyuan 1.5
    ├── 极致电影质感/艺术片?
    │   └── Yes → Sora 2 > Runway Gen-4
    ├── 5/10/15 秒紧凑短片 + 环境音?
    │   └── Yes → HappyHorse 1.0
    └── 复杂多镜头叙事?
        └── Yes → Seedance 2.0 / Kling 智能分镜

步骤 3:输出格式

markdown
## 推荐模型

**最佳选择**:[模型名]
**理由**:[2-3 句话说明为什么]
**对应 skill**:[skills/xxx-prompter] (如果有)
**对应方法论**:[methodology/NN-xxx-公式.md]
**官方平台**:[链接]

**备选**:[模型名]
**为什么备选**:[一句话]

## 你的需求 → 我的判断

| 你的需求 | 对应能力 | 评级 |
|---|---|---|
| [需求 1] | [模型支持情况] | ★★★★★ |
| ... | ... | ... |

实战示例

例 1:用户问"我想做中文短剧"

澄清问题:

  1. 短剧时长?10 秒以内的片段还是 1-2 分钟完整故事?
  2. 要原生音频(角色对话)吗?
  3. 偏向写实 / 古风 / 现代都市哪种?

用户答:单个片段 10 秒,要有对话,现代都市。

输出:

最佳选择:Kling 3.0 理由:中文理解业界并列第一(与即梦),原生音频支持角色定向发声,最长 15 秒单段,5 层进阶公式天然适合剧情。

对应 skill:skills/kling-prompter 对应方法论:methodology/09-kling-公式.md 官方平台:klingai.com

备选:Wan 2.7(如果对话很多且需要数字人感强)/ 即梦 3.0(如果在剪映里直接做后期)


例 2:用户问"我有一段视频想改个风格,比如变水彩动画"

判断:编辑已有视频 → 直接推荐 Runway Aleph。

输出:

最佳选择:Runway Aleph 理由:编辑已有视频是 Aleph 的独家能力(其他 10 个模型都做不到)。re-style 动词专门用于风格转换,能保持原始运动和时序不变。

示例 prompt:

Re-style this clip as a hand-painted watercolor animation. Soft brush textures, flowing edges, warm palette. Preserve all motion and timing exactly.

对应方法论:methodology/13-六大模型公式速查.md#1-runway-gen-4--aleph 官方平台:Runway

备选:没有真正可替代的。如果非要,Hunyuan 视频也能改一些(开源),但不是 native 编辑能力。


例 3:用户问"我自己想搭一个本地视频生成,预算有限"

澄清问题:

  1. GPU 配置如何?(24GB / 12GB / 8GB)
  2. 主要用途?(个人玩 / 自训 LoRA / 商业)

用户答:RTX 4090 24GB,想自训 LoRA。

输出:

最佳选择:Hunyuan Video 1.5(8.3B 版本) 理由:开源最强、24GB 显存可跑、原生支持 LoRA 训练、社区活跃(ComfyUI 完整工作流支持)。

推荐参数:Q5_K_M GGUF + 30 steps + dpmpp_2m_sde + sgm_uniform + cfg 6.0 官方资源:

备选:CogVideoX(智谱开源)/ LTX Video(Lightricks 实时)— 这两个未纳入本仓库主目录,但同属开源阵营。

参考

Frequently asked questions

What does the Model Selector AI skill do?

根据用户的视频需求(场景、时长、音频、语言、平台限制、预算、是否需要本地部署/角色一致性等),从 16 个主流 AI 视频模型(12 商业 + 4 开源)中推荐最匹配的 1-3 个,并解释为什么。覆盖商业:Seedance 2.0、HappyHorse 1.0、Kling 3.0、Sora 2、Veo 3.1、**Gemini Omni**(2026-05 新)、Runway Gen-4.5/Aleph、Pika 2.5、Hailuo 02、Hunyuan Video 1.5、Wan 2.7、即梦 AI;开源:LTX-Video 0.9.7、Mochi 1、CogVideoX 5B、Higgsfield Soul。用于"用哪个 AI 视频模型好"、"Sora 还是 Kling"、"国内有什么模型"、"哪个免费"、"哪个支持中文"、"哪个能编辑已有视频"、"哪个能本地部署"、"哪个角色一致性最强"等触发场景。

Why use Model Selector on TypingMind?

Because you install it once and use it with any model. Model Selector 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 Model Selector in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cclank/lanshu-awesome-ai-video-kit/tree/main/skills/model-selector. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Model Selector?

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 Model Selector?

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

Is the Model Selector AI skill free?

Yes. It is published on GitHub by cclank under the MIT license. 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 👇