Cinematography Hard Soft Light logo

Cinematography Hard Soft Light

Community
geegl
cinematography-hard-soft-light

用户提到硬光、软光、柔光、阴影清晰/模糊、光源大小

Overview

Publishergeegl
Repositorydirectorskills
Skill namecinematography-hard-soft-light
Stars
68
Forks
7
Bundled files
1
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.

  • 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 geegl on GitHub. Read the source before you install it.

Installation

Install the Cinematography Hard Soft Light 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/geegl/directorskills/tree/main/output/books/cinematography-brown/cinematography-hard-soft-light
  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/geegl/directorskills.git /tmp/directorskills
mkdir -p .claude/skills
cp -r /tmp/directorskills/output/books/cinematography-brown/cinematography-hard-soft-light .claude/skills/cinematography-hard-soft-light
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cinematography Hard Soft Light 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 Cinematography Hard Soft Light 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 Cinematography Hard Soft Light 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.

硬光/软光二元框架

R — 原文 (Reading)

归根结底布光中其实只有两种光线(就光线的品质而言):硬光和软光。光线的硬和软取决于光源的大小。光源越小,光线就越硬,这是至关重要的一点。 — Brown, 第7章, p.g_0035

I — 方法论骨架 (Interpretation)

灯光品质的二元分类是所有布光决策的第一步判断:

硬光(镜面反射光):

  • 特征:清晰、尖锐的阴影
  • 原因:光线是平行的(如激光)
  • 光源:小光源(太阳虽大但远→天空中显得小→硬光)
  • 效果:冷硬、戏剧性、揭示质感和轮廓

软光(漫反射光):

  • 特征:模糊、不明显甚至没有阴影
  • 原因:光线从多个方向到达
  • 光源:大光源(阴天整片天空→巨大光源→软光)
  • 效果:柔和、美化、减少瑕疵

片场制造软光的两种方法:

  1. 反射法:让硬光在大面积白色物体上反射(泡沫板、白墙、伞)。反射板面积越大,光线越软。
  2. 透射法:让硬光通过柔光布(描图纸、丝绸、专用柔光布)。布越厚,光线越软。

关键认知:硬光/软光不是灯的属性,而是光源相对大小的属性。同一盏灯,不加柔光布是硬光,加上大面积柔光布就变成软光。

A1 — 书中的应用 (Past Application)

案例:《艺伎回忆录》的超大面积柔光

  • 问题:需要为整个场景创造极其柔和的光线效果。
  • 方法论的使用:导演用非常大的丝绸向整个场景反射光,使用的丝绸有"几英亩那么大"。丝绸面积越大,光源相对越大,光线越软。
  • 结论:柔光的极致追求需要极致的光源面积。这不是技术限制,而是物理定律。

案例:日间外景的阳光控制

  • 问题:直射阳光是硬光,产生粗糙的阴影,如何在白天外景中控制?
  • 方法论的使用:三种方法——1)用大型丝绸罩住场景柔化阳光;2)用反光板反射阳光作补光;3)用日光白平衡的HMI灯补光平衡阴影。
  • 结论:即使是太阳这样的硬光源,也可以通过改变"有效光源大小"来柔化。

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

  1. 用户在选择灯光器材——"应该用聚光灯还是柔光灯?"
  2. 用户想要特定的阴影效果——"我想要清晰的阴影"或"阴影太硬了怎么柔化?"
  3. 用户为AI画面选择灯光品质——"硬光还是软光?"

语言信号

  • "硬光"、"软光"、"柔光"、"散射光"
  • "阴影太硬"、"阴影太明显"、"想要柔和的效果"
  • "用什么灯"、"要不要加柔光布"、"反射板"
  • "阳光太刺眼"、"阴天拍摄"

与相邻 skill 的区分

  • 与 three-point-lighting 的区别:三点布光是"有哪些灯"的结构,硬光/软光是"每盏灯什么品质"的判断。
  • 与 light-direction-mood 的区别:方向决定情绪的"方向性",品质决定情绪的"质感"。

E — 可执行步骤 (Execution)

  1. 判断场景需要硬光还是软光

    • 硬光适合:戏剧性、黑色电影、揭示质感、硬朗风格
    • 软光适合:美化人物、柔情场景、时尚/美容、减少瑕疵
    • 完成标准:能回答"这个场景需要清晰阴影还是柔和阴影?"
  2. 选择制造所需光质的方法

    • 硬光:直接使用小光源(聚光灯、裸灯泡、直射阳光)
    • 软光反射法:光源→大面积白色反射面→主体
    • 软光透射法:光源→柔光布→主体
    • 完成标准:选择的器材和方法能产生目标光质
  3. 调整光源有效面积

    • 需要更软?增大反射板或柔光布面积

    • 需要更硬?缩小光源面积或移除柔光材料

    • 完成标准:阴影的清晰度符合预期

    • 🔴 判停条件: 若演员面部阴影边缘过于生硬(硬光)或过于平淡失去立体感(软光),说明光质选择不当——调整光源大小或柔光布距离,重新测试光比

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

  • 用户在讨论色彩问题而非灯光品质问题
  • 用户已经确定了灯光品质,需要讨论方向(使用 light-direction-mood)
  • 用户在讨论自然光摄影且无法控制光源

作者在书中警告的失败模式

  • 混淆光源大小与灯的功率:一盏大功率灯加上大面积柔光布仍然是软光。功率影响亮度,不影响光质。
  • 忽略相对大小:同一盏灯在近距离是相对较大的光源(较软),在远距离是相对较小的光源(较硬)。
  • 柔光布距离错误:柔光布应尽量靠近主体而非靠近光源,这样有效光源面积最大。

反模式与常见错误

  • 混淆光源功率与光质:高功率灯+大面积柔光布=软光,功率只影响亮度不影响光质,不要以为大功率灯就是硬光
  • 忽略相对大小原理:同一盏灯在近距离是相对大光源(较软),远距离是相对小光源(较硬),不要以为灯本身决定光质
  • 柔光布紧贴灯头而非靠近主体:柔光布应尽量靠近主体以最大化有效光源面积,紧贴灯头反而缩小了有效光源

作者的盲点 / 时代局限

Blain Brown 的分析框架源自传统胶片摄影,对数字传感器的特性(如动态范围、高光滚降、暗部噪声)讨论不足。他假设摄影团队有充足的设备和时间,独立制作或低预算场景的应对策略覆盖较少。案例库以好莱坞和欧洲艺术片为主,对亚洲、拉美等非西方电影传统的摄影风格涉及有限。

此外,硬光/软光的讨论基于传统灯具,对 LED 面板、RGB 棒灯等新型光源的特性(如色温一致性、频闪问题)涉及较少。他假设灯光师有充足的灯光设备,对用自然光或单灯实现硬/软效果的实操技巧讨论不足。

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 Cinematography Hard Soft Light AI skill do?

用户提到硬光、软光、柔光、阴影清晰/模糊、光源大小

Why use Cinematography Hard Soft Light on TypingMind?

Because you install it once and use it with any model. Cinematography Hard Soft Light 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 Cinematography Hard Soft Light in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/geegl/directorskills/tree/main/output/books/cinematography-brown/cinematography-hard-soft-light. 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 Cinematography Hard Soft Light?

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 Cinematography Hard Soft Light?

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

Is the Cinematography Hard Soft Light AI skill free?

Yes. It is published on GitHub by geegl 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 👇