Skill

Pass

Audit score 90

anti-render

lionad-morotar/anti-render-skill

Generate ideal-vs-reality visual comparisons by analyzing images and creating side-by-side contrasts.

What is anti-render?

Anti-Render intelligently identifies image content and generates "ideal promise vs. harsh reality" style visual comparisons across any domain. Use it when you want to reveal the gap between marketing renderings and actual everyday conditions—whether for architecture, portraits, products, food, travel, games, fitness, home décor, or tech.

Analyzes uploaded images to detect domain (architecture, portraits, products, food, travel, gaming, fitness, home, tech) and current state (deteriorated, ideal, or normal)
Generates idealized renderings showing perfect lighting, pristine materials, saturated colors, and polished atmospheres
Creates realistic versions showing natural lighting, authentic wear, true colors, and unfiltered environments
Produces side-by-side comparison images with automatic layout (left-right or top-bottom) based on original aspect ratio
Maps five universal contrast dimensions (lighting, material, color, atmosphere, composition) to domain-specific expressions

How to install anti-render

npx skills add https://github.com/lionad-morotar/anti-render-skill --skill anti-render

Prerequisites

Image file to analyze (jpg, png, or similar format)
Works best with companion skills: image-to-prompt and prompt-to-image

Claude Code

Cursor

Windsurf

Cline

How to use anti-render

1.Upload or reference an image you want to analyze
2.The skill will detect the domain (architecture, food, product, etc.) and assess the image's current state
3.Specify your desired output: idealized rendering only, realistic version only, or side-by-side comparison
4.The skill generates the target image(s) with appropriate contrast across lighting, materials, color, atmosphere, and composition dimensions
5.For comparisons, images are automatically arranged left-right (if original is landscape) or top-bottom (if original is portrait)

Use cases

Good for

Compare architectural renderings with actual building conditions to highlight construction quality gaps
Contrast product marketing photos with real-world user experiences for honest product reviews
Show the difference between restaurant menu photography and actual plated dishes served
Reveal the gap between fitness influencer transformations and realistic workout results
Compare hotel booking images with actual room conditions guests receive

Who it's for

Content creators and reviewers seeking authentic before-after comparisons
Marketing professionals wanting to understand perception gaps in their campaigns
Architects and designers analyzing rendering accuracy versus built reality
Social media creators making humorous or critical content about expectation vs. reality
Educators demonstrating the effects of professional photography and post-processing

anti-render FAQ

What happens if the image state is unclear?

The skill will ask you to clarify your intended direction—whether you want an idealized version, realistic version, or comparison.

Can I use this for any type of image?

Yes. The skill adapts to nine core domains (architecture, portraits, products, food, travel, gaming, fitness, home, tech) and applies universal contrast principles to each.

How does the skill decide layout for comparison images?

It analyzes the original image's aspect ratio: landscape images get left-right comparison with vertical divider; portrait images get top-bottom comparison with horizontal divider.

Will text labels appear on the comparison images?

No. By default, the skill keeps comparison images visually clean without added text, letting the visual contrast speak for itself.

What are the five core contrast dimensions?

Lighting (perfect vs. natural), Material (flawless vs. worn), Color (saturated vs. muted), Atmosphere (polished vs. authentic), and Composition (idealized vs. unretouched).

Full instructions (SKILL.md)

Source of truth, from lionad-morotar/anti-render-skill.

name: anti-render description: 智能识别图像内容并生成"理想承诺 vs 残酷现实"风格的视觉对比。触发词："anti-render"、"理想vs现实"、"对比图"、"渲染vs真实"。适用于任何领域：建筑、人像、产品、食物、旅游、游戏、健身、家居、科技等。 disable-model-invocation: true

Anti-Render 理想vs现实视觉对比生成器

核心理念

通过并置(juxtaposition)手法，揭示任何领域中"承诺与交付之间巨大落差"的普遍困境。左侧呈现理想化的完美渲染，右侧揭示真实的日常面貌。

执行流程

接收图像 → 分析内容，识别所属领域为 $domain，计算图片宽高比为 $ratio
状态判断 → 确定当前状态（破败/普通/理想）
意图识别 → 根据用户指令确定输出模式
参数映射 → 将通用五维度映射到领域专属表达
构建提示词 → 构建基于领域专属表达的提示词
生成图像 → 生成目标图像

works well with skills: image-to-prompt, prompt-to-image

工作模式

1. 图像状态识别

用户上传图片后，分析其当前状态：

状态	特征	输出目标
破败	质量问题、使用痕迹、维护不良	生成理想化渲染图（即 step 2.1）
理想	用户上传了营销图片、广告图片等精修后照片	生成轻微破败渲染图片（即 step 2.2）
普通/正常	无明显破损、日常使用状态	生成理想化渲染和轻微破败的对比图（即 step 2.3）

如状态模糊，无法判断意图，主动询问用户期望方向

2. 三种输出模式

2.1 理想化渲染 (Ideal)

目标：输出对应领域的宣传级别完美呈现
特征：高饱和度、完美光影、无瑕疵、精心构图

2.2 真实面貌 (Reality)

目标：输出对应领域日常的真实状态（非破败）
特征：自然光线（“死亡打光”）、真实质感、日常氛围、未经修饰

2.3 对比图 (Comparison)

目标：输出理想化渲染和真实面貌并置的对比图
排列：根据原图宽高比自动选择左右或上下排列

领域识别与适配

领域检测

基于图像内容关键词匹配：

建筑领域: 建筑外观、城市景观、室内空间、建筑效果图、楼盘、住宅、商业空间
人像领域: 人像写真、Cosplay、自拍、证件照、活动拍摄、肖像
产品领域: 电商产品、商品展示、包装设计、电子产品、服饰
食物领域: 美食摄影、菜品展示、烘焙、饮品、餐厅菜单
旅游领域: 风景照、景点打卡、酒店房间、度假胜地
游戏领域: 游戏截图、游戏宣传、UI界面、角色设计
健身领域: 健身照、运动场景、瑜伽、健身房
家居领域: 室内装修、家具展示、样板间、智能家居
科技领域: 产品发布会、概念设计、VR/AR、智能汽车

核心对比维度（通用框架）

所有领域共享以下五个核心对比维度：

1. 光影 (Lighting)

理想侧	现实侧
精心计算的完美光照	自然/现场实际光线
黄金时刻或柔和补光	硬光、顶光或平淡漫射光
明暗层次丰富、无死黑/过曝	曝光妥协、阴影浓重
方向性明确、立体感强	低对比度、缺乏层次

2. 材质 (Material)

理想侧	现实侧
完美无瑕的表面	真实使用痕迹
色彩饱和、质感强化	褪色、污渍、磨损
无灰尘、无水痕、无瑕疵	自然老化、环境痕迹
CG般的精确反射/折射	混浊、不完美的反射

3. 色彩 (Color)

理想侧	现实侧
高饱和度、鲜艳夺目	低饱和度、略显平淡
色温精准、统一协调	色温偏移、白平衡未校正
后期精修的色彩增强	相机原生色彩还原
广告级别的视觉吸引力	日常感、朴素感

4. 氛围 (Atmosphere)

理想侧	现实侧
充满活力、生机勃勃	冷清、平凡或略显尴尬
精心布置的场景元素	杂乱的现场环境
梦幻、理想化的背景	真实、暴露现场的环境
情绪饱满、引人入胜	纪实感、冷峻客观

5. 构图/细节 (Composition)

理想侧	现实侧
完美的透视与比例	自然的镜头畸变
瑕疵移除、穿帮修复	保留所有现场细节
精心安排的元素布局	随机、不规则的真实分布
后期添加的特效/光效	无后期加持的原始状态

对比图技术规范

排列规则

如生成对比图，需根据原图宽高比 $ratio 判断新的排列规则：

原图横向（宽 > 高）：对比图上下排列，水平分割线
原图纵向（高 > 宽）：对比图左右排列，垂直分割线

分割线规范

位置：画面正中
宽度：2-5像素
颜色：纯白或极浅灰
边缘：锐利清晰，无羽化

内容规则

对比图左或上（根据排列规则）：理想化渲染
对比图右或下（根据排列规则）：普通现实主义（默认）或破败状态（用户明确要求强烈对比效果）
默认不要添加标题文字，保持画面纯净，让视觉对比本身说话

Related skills

More from lionad-morotar/anti-render-skill and the wider catalog.

douyin-video-summary

liu-wei-ai/douyin-video-summary

Summarize Douyin videos by extracting audio, transcribing locally, and generating structured summaries.

1.8k installs

browser-bridge

liuzhengdongfortest/codestable

通过 Chrome 扩展控制真实浏览器。需要访问网页、抽取网页数据、点击按钮、填写表单、执行浏览器自动化、提取渲染后的组件证据，或以程序方式操作页面时使用。通过 DOM diff、简化 HTML 和 component evidence pack 返回节省 token 的结构化结果。适用于 browser control、web automation、page scraping、web data extraction、execute JS in browser、web_scan、web_execute_js、open browser、navigate to URL、get page content、fill form、click button、extract component、rendered DOM、computed styles、component evidence。

635 installs