anti-render
Installation
Summary
Generate "ideal promise vs cruel reality" visual comparisons by analyzing image content across any domain.
- Automatically detects image domain (architecture, portrait, product, food, travel, gaming, fitness, home, tech) and current state (deteriorated, ideal, or normal)
- Outputs three modes: idealized rendering, realistic everyday appearance, or side-by-side comparison with automatic layout (left-right or top-bottom based on aspect ratio)
- Applies five universal contrast dimensions across all domains: lighting, material, color, atmosphere, and composition/detail
- Works with
image-to-promptandprompt-to-imageskills for end-to-end workflow
SKILL.md
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