AI coding/AI Short
A

AI Short

按场景分类的 AI 提示词库,复制后即可用于 ChatGPT、Claude 等对话工具。

Rainy Umbrella Street (full-body)

This is a ready-to-copy More prompt, “Rainy Umbrella Street (full-body)”. Paste it into ChatGPT, Claude, Gemini, or Cursor, then replace any bracketed placeholders before you send it.

MoreAwesome Prompts0 copies

Prompt

{
  "category": "RAINY_CITY_UMBRELLA_FULLBODY",
  "subject": {
    "demographics": "Adult woman, 21-27, Turkish-looking.",
    "hair": {
      "color": "Dark brown",
      "style": "Slightly damp strands, tucked behind ears",
      "texture": "Wet sheen realistic, not greasy",
      "movement": "A few strands stick lightly to cheek"
    },
    "face": {
      "eyes": "Bright eye contact, reflective catchlights",
      "skin_details": "Natural texture, slight moisture realism",
      "makeup": "Minimal, water-resistant look"
    },
    "clothing": {
      "outerwear": "Raincoat or trench (no logos)",
      "fabric": "Slight wet sheen and droplets visible"
    },
    "accessories": {
      "umbrella": "Clear umbrella with raindrops",
      "jewelry": ["Small silver hoops"]
    }
  },
  "pose": {
    "type": "Full-body walking candid",
    "orientation": "Mid-stride, slight turn toward camera",
    "hands": "One hand holding umbrella handle, other in coat pocket",
    "gaze": "Soft smile, eye contact",
    "posture": "Relaxed, natural walk"
  },
  "setting": {
    "environment": "Rainy city street at dusk",
    "background_elements": [
      "Wet pavement reflections",
      "Streetlight bokeh",
      "Light drizzle visible (fine droplets, not smoke/fog)"
    ],
    "depth": "Subject clear, background blurred"
  },
  "camera": {
    "shot_type": "Full-body street photo",
    "angle": "Eye level",
    "focal_length_equivalent": "26mm phone or 35mm editorial",
    "framing": "4:5, subject slightly off-center",
    "focus": "Face sharp, motion blur minimal"
  },
  "lighting": {
    "source": "Streetlights + ambient sky",
    "direction": "Soft top/side glows",
    "highlights": "Raindrop specular highlights on umbrella",
    "shadows": "Soft, realistic"
  },
  "mood_and_expression": {
    "tone": "Moody, cozy, stylish",
    "expression": "Gentle smile, calm confidence",
    "atmosphere": "Cinematic rain realism"
  },
  "style_and_realism": {
    "style": "Photorealistic street candid",
    "imperfections": "Mild noise, slight blur in background only"
  },
  "technical_details": {
    "aspect_ratio": "4:5",
    "noise": "Phone-like grain in low light",
    "motion_blur": "Slight in background reflections only"
  },
  "constraints": {
    "adult_only": true,
    "no_text": true,
    "no_logos": true,
    "no_watermarks": true
  },
  "negative_prompt": [
    "smoke", "fog machine look", "watergun splash",
    "extra limbs", "warped umbrella spokes",
    "readable signs", "logos", "watermark"
  ]
}

More More prompts

生成 PPT 大纲

让 AI 生成主题大纲,然后将其放入指定 Markdown 格式中。PPT(slide) 质量仅作参考。来自 @Asynchro-Epool 的投稿。

充当 Excel 工作表

我希望你充当基于文本的 excel。您只会回复我基于文本的 10 行 Excel 工作表,其中行号和单元格字母作为列(A 到 L)。第一列标题应为空以引用行号。我会告诉你在单元格中写入什么,你只会以文本形式回复 excel 表格的结果,而不是其他任何内容。不要写解释。我会写你的公式,你会执行公式,你只会回复 excel 表的结果作为文本。首先,回复我空表。

充当旅游指南

我想让你做一个旅游指南。我会把我的位置写给你,你会推荐一个靠近我的位置的地方。在某些情况下,我还会告诉您我将访问的地方类型。您还会向我推荐靠近我的第一个位置的类似类型的地方。我的第一个建议请求是“我在上海,我只想参观博物馆。”

充当抄袭检查员

我想让你充当剽窃检查员。我会给你写句子,你只会用给定句子的语言在抄袭检查中未被发现的情况下回复,别无其他。不要在回复上写解释。我的第一句话是“为了让计算机像人类一样行动,语音识别系统必须能够处理非语言信息,例如说话者的情绪状态。”

充当“电影/书籍/任何东西”中的“角色”

Character:角色;series:系列 > 我希望你表现得像{series} 中的{Character}。我希望你像{Character}一样回应和回答。不要写任何解释。只回答像{character}。你必须知道{character}的所有知识。我的第一句话是“你好”

担任关系教练

我想让你担任关系教练。我将提供有关冲突中的两个人的一些细节,而你的工作是就他们如何解决导致他们分离的问题提出建议。这可能包括关于沟通技巧或不同策略的建议,以提高他们对彼此观点的理解。我的第一个请求是“我需要帮助解决我和配偶之间的冲突。”