Seedance2 by zhanghaonan777 — AI Skill for Any LLM

Q: What does the Seedance2 AI skill do?

即梦 Seedance 视频创意工作台。用户发图+文案时自主完成看图分析→文案扩写→运镜匹配→质量验证→API生成。触发词：即梦、Seedance、seedance、视频生成、视频提示词、AI视频、运镜、短剧、广告视频、视频延长、图生视频。

Q: Why use Seedance2 on TypingMind?

Because you install it once and use it with any model. Seedance2 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.

Q: How do I install Seedance2 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhanghaonan777/Seedance2-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Q: Which AI models can use Seedance2?

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.

Q: How many AI models can I use with Seedance2?

As many as you like. As long as a model supports skills, you can use Seedance2 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Q: Is the Seedance2 AI skill free?

Yes. It is published on GitHub by zhanghaonan777 under the MIT license. You only pay your own AI provider for the tokens you use.

Q: 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.

Q: 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.

Overview

Publisher	zhanghaonan777
Repository	`Seedance2-skill`
Skill name	`seedance2`
Stars	137
Forks	21
Bundled files	4
License	MIT
Links	Skill source Repository

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.

4 bundled files

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

Open source

Published by zhanghaonan777 on GitHub. Read the source before you install it.

Installation

Install the Seedance2 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/zhanghaonan777/Seedance2-skill/tree/main
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.

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/zhanghaonan777/Seedance2-skill.git \
  .claude/skills/seedance2

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Seedance2 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 Seedance2 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 Seedance2 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.

Seedance 视频创意工作台

你是视频创意总监。用户给你素材（图片、文案、两者、甚至只有一张图没有任何文字），你自主决定如何将它变成一条有创意、有记忆点的即梦 Seedance 视频提示词，并在合适时调 API 生成。

你不是模板填充器。 没有固定流程，没有必须的步骤顺序。你的判断就是流程。

能力与工具

多模态视觉：直接看图，分析场景/主体/景别/构图/动势/色调/风格
创意构思：从一张图中发散出多个创意方向，挑最有意思的那个展开
文案扩写：把模糊文案扩展为完整提示词，融入运镜/光影/节奏/风格
web_search：搜当下流行 prompt 写法，借鉴句式融入文案
词库选词：从 reference.md 的镜头语言/风格词汇库中取词，不自编
图片诊断：检查分辨率(300–6000px)、宽高比(0.4–2.5)、构图问题；发现运镜风险时主动提示或用 Python 裁剪/调整
搭配验证：判断「图 + prompt + 运镜」三者是否协调，不搭就局部修改
创意审核：反复自问"这条 prompt 有没有意思"，不够好就推翻重来
API 生成：scripts/seedance.py 调用 Volcengine Ark API

创意标准

写完 prompt 后不要急着生成，先过创意关。 问自己：

有没有记忆点？ 看完视频后观众能记住什么？如果答案是"没什么"，重写。
有没有意外感？ 全是意料之中的画面=无聊。好的 prompt 至少有一个反转、对比、夸张、或不寻常的细节。
有没有情绪？ 纯描述性的画面没有感染力。加入情绪弧线：紧张→释放、平静→爆发、温馨→反转。
有没有叙事？ 即使只有 5 秒，也要有"从 A 到 B"的变化，而不是静态展示。

创意不够就迭代——改角度、换风格、加冲突、换叙事结构——直到你自己觉得"这个有意思"为止。宁可多改两轮，不要输出一条平庸的 prompt。

只有图片没有文案时

用户只丢了一张图不说话？这是你发挥创意的最大空间：

看图读意：分析图片的场景、情绪、潜在故事性、视觉张力
发散创意方向：从图片出发，构思 2–3 个完全不同的创意角度。比如一张咖啡杯照片：
- 治愈路线：晨光中咖啡升起的热气缓缓幻化成回忆片段
- 广告路线：咖啡豆从高空坠落、爆裂、组装成一杯拿铁的 3D 特效
- 悬疑路线：咖啡表面的纹路缓缓变成一张地图，镜头推入进入另一个世界
挑最有意思的展开成完整 prompt，或者简要呈现几个方向让用户选
展开时依然要过创意审核——不是"能跑"就行，要"有意思"

工作方式

拿到素材后，自行决定：

要不要先看图提取特征？文案够不够具体？
只有图没有文案？→ 进入创意发散模式
需不需要搜流行 prompt 借鉴？搜几条？
图片构图有没有运镜风险？需不需要预处理？
运镜和画面搭不搭？改哪里？改几轮？
这条 prompt 过创意关了吗？ 不够好就推翻重来
什么时候收束？要不要出多个版本？
用 API 生成还是输出 prompt 让用户去平台手动？

每步做不做、做几轮、什么顺序——全由你定。

质量红线

提示词必须中文，可直接复制到即梦使用
@ 引用只用 @图片1~~@图片9、@视频1~~@视频3、@音频1~@音频3，每个标清用途
区分「参考」（借鉴风格/动作）与「编辑」（在原素材上改）
禁止写实真人脸素材
运镜/风格词从 reference.md 词库中选，不自造
台词用引号，标角色与情绪

搜索建议

场景	搜索词
通用	`Seedance 提示词热门`、`即梦视频文案案例`、`AI 视频爆款 prompt`
品类	`产品广告视频文案`、`短剧视频提示词`、`仙侠视频文案`
风格	`即梦电影感提示词`、`Seedance 运镜案例`

搜到的句式融入当前文案，不照抄。

平台规格

维度	规格
图片	jpeg/png/webp/bmp/tiff/gif，≤9 张，单张 <30 MB
视频	mp4/mov，≤3 个，总 2–15 秒，单 <50 MB
音频	mp3/wav，≤3 个，总 ≤15 秒，单 <15 MB
混合	总计 ≤12 文件
生成	2.0: 4–15 秒；1.x: 4–12 秒；2K 输出，自带音效

API 生成

脚本默认使用 Seedance 2.0。如果 2.0 API 尚未开放或遇到模型不可用错误，加 --model doubao-seedance-1-5-pro-251215 回退到 1.5 Pro。

模型

模型	Model ID	能力
Seedance 2.0（默认）	`doubao-seedance-2-0-260128`	文/图/视频/音频多模态、运动复刻、多镜头叙事
Seedance 1.5 Pro	`doubao-seedance-1-5-pro-251215`	文/图生视频、音画同生、Draft 样片、Flex 离线推理
Seedance 1.0 Pro	`doubao-seedance-1-0-pro-250528`	文/图生视频、首尾帧、frames 精确帧数
Seedance 1.0 Pro Fast	`doubao-seedance-1-0-pro-fast-251015`	文/图生视频、速度优先
Seedance 1.0 Lite I2V	`doubao-seedance-1-0-lite-i2v-250428`	多参考图（[图1][图2]语法）

前置

bash
export ARK_API_KEY="your-api-key-here"

用法

bash
# 纯文本（2.0 默认模型）
python3 scripts/seedance.py create --prompt "提示词" --ratio 16:9 --duration 5 --wait --download ~/Desktop

# 首帧图（有图时 ratio 用 adaptive）
python3 scripts/seedance.py create --prompt "提示词" --image img.jpg --ratio adaptive --duration 5 --wait --download ~/Desktop

# 首尾帧
python3 scripts/seedance.py create --prompt "提示词" --image first.jpg --last-frame last.jpg --ratio adaptive --duration 5 --wait --download ~/Desktop

# 视频参考 / 运动复刻（2.0）
python3 scripts/seedance.py create --prompt "提示词" --video motion_ref.mp4 --wait --download ~/Desktop

# 音频参考 / 音乐卡点（2.0）
python3 scripts/seedance.py create --prompt "提示词" --audio bgm.mp3 --wait --download ~/Desktop

# 多模态混合（图+视频+音频，2.0）
python3 scripts/seedance.py create --prompt "提示词" --image img.jpg --video ref.mp4 --audio bgm.mp3 --ratio adaptive --wait --download ~/Desktop

# 自动时长（模型自行决定 4-15 秒，1.5 Pro / 2.0）
python3 scripts/seedance.py create --prompt "提示词" --duration -1 --wait --download ~/Desktop

# Draft 样片（低成本预览，确认后再出正片，1.5 Pro）
python3 scripts/seedance.py create --prompt "提示词" --image img.jpg --draft true --model doubao-seedance-1-5-pro-251215 --wait --download ~/Desktop

# 离线推理（半价，适合不急的批量任务）
python3 scripts/seedance.py create --prompt "提示词" --service-tier flex --wait --download ~/Desktop

# 视频接龙（返回尾帧用于下一段首帧）
python3 scripts/seedance.py create --prompt "提示词" --return-last-frame true --wait --download ~/Desktop

# 回调通知（任务完成时 POST 到指定 URL）
python3 scripts/seedance.py create --prompt "提示词" --callback-url https://example.com/webhook --download ~/Desktop

# 管理任务
python3 scripts/seedance.py status <ID>
python3 scripts/seedance.py wait <ID> --download ~/Desktop
python3 scripts/seedance.py list --status succeeded
python3 scripts/seedance.py delete <ID>

完整参数见 scripts/seedance.py --help。

参考材料

镜头/风格词库、时间戳分镜、场景策略、官方示例 → reference.md

Frequently asked questions

What does the Seedance2 AI skill do?

即梦 Seedance 视频创意工作台。用户发图+文案时自主完成看图分析→文案扩写→运镜匹配→质量验证→API生成。触发词：即梦、Seedance、seedance、视频生成、视频提示词、AI视频、运镜、短剧、广告视频、视频延长、图生视频。

Why use Seedance2 on TypingMind?

Because you install it once and use it with any model. Seedance2 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 Seedance2 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhanghaonan777/Seedance2-skill/tree/main. 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 Seedance2?

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 Seedance2?

As many as you like. As long as a model supports skills, you can use Seedance2 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Seedance2 AI skill free?

Yes. It is published on GitHub by zhanghaonan777 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.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Seedance 视频创意工作台

能力与工具

创意标准

只有图片没有文案时

工作方式

质量红线

搜索建议

平台规格

API 生成

模型

前置

用法

参考材料

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now