#提示词

现在各种大模型你追我赶,有的历史对话和上下文需要从一个模型迁移到另外一个模型。Dia 官方提供了一个“导入记忆”的功能,帮助用户把 chatgpt 的记忆导入到 Dia 浏览器,这个本质就是一个提示词,可以用来给自己用的大模型们进行“记忆”同步。 --- I want information about myself and my preferences. First, retrieve and include ALL information you have stored about me from every available source—this includes but is not limited to: User Bio, User Instructions, Assistant Response Preferences, Memory, Notable Past Conversation Topics, Helpful User Insights, Recent Conversation Content, Conversation Style Meta-Notes, and any other stored data, memories, or notes about me. Do not filter or exclude anything. Then organize ALL of this information into the following categories. Create new categories if needed for any information that doesn't fit. If you can't find anything for a given category, skip it. * Response Preferences: How I want my questions answered * Personal Information: Things like my name, where I live, my age range, information about my family, languages I speak, demographic info * Professional: My current employer, job title, role, seniority, team/org, industry, core domain of work, professional affiliations or associations, etc. * Important Relationships: Friends, colleagues, family, etc. * Education: Current school, classes, subjects, teachers, etc. * Projects & Responsibilities: What projects I'm working on (personal or professional), research efforts, initiatives, or responsibilities. Go into detail here with a paragraph per major project. * Goals & Intentions: Personal or professional objectives I'm actively pursuing * Habits & Routines: Behavioral patterns, routines, daily and weekly schedules, etc. * Writing: My preferred writing style, tone, voice, formality vs. informality, clarity vs. complexity, favored vocabulary, typical audiences, length preferences, formatting, etc. * Coding: My development and coding practices—preferred programming languages and tools, coding style, code formatting and commenting practices, commonly used frameworks & libraries, workflows and patterns helpful for collaboration with an LLM coding partner * Interests & Hobbies: My important likes and dislikes, hobbies, intellectual pursuits, activities, subjects of interest, leisure activities, preferred entertainment or recreation, and areas of passionate curiosity or aversion * Media & Content: My favorite media types, genres, books, films, podcasts, TV shows, creators, news sources, favored apps or websites, and content platforms * Lifestyle: My food and other lifestyle preferences * Health & Wellness: My health, fitness, wellness habits and preferences, diet, dietary preferences/restrictions, etc. * Events & Milestones: My major personal or professional life events, achievements, milestones, anniversaries, awards, recognitions, or significant transitions shaping my current identity or trajectory * Notable Conversations: Up to 10 recent notable conversations For each section, provide a bullet list of up to 10 items. Only include known items; if you do not have information for an item, skip it entirely (do not say "not specified"). Be as detailed as possible. Only respond with the sections and content. Do not say anything else—no preamble, no ending, no opt-in prompts to do more tasks for me.
宝玉
2周前
Text to Markdown Prompt 适用于你要把推文、微博这种纯文本内容转成格式良好的博客,可以帮你生成标题、列表,和加粗要点、金句。 亮点: - 借助思维链先提取要点、金句和可选标题,然后选择标题和高亮要点、金句 - 解决了 LLM 在加粗带标点符号的文字时加粗失效的问题(如果你用过 LLM 生成的中文 Markdown 会明白我说什么,参考图4) ---- 提示词开始 ---- # 任务:将文本转换为结构化 Markdown 请你扮演一个专业的编辑,将提供的文本内容转换为一份格式良好、结构清晰、重点突出的 Markdown 文档。 ## A. 内部推理步骤 (请在你的思考过程中执行,无需输出) 在生成最终的 Markdown 之前,请先在内部完成以下思考: 1. **理解与提取**: * 通读全文,准确把握文章的核心主旨和目的。 * 识别并提取文中的**核心论点**、**关键结论**和**重要定义**。 * 找出文中具有高度概括性或特别精辟的**“金句” (Golden Sentences)**。 2. **构思标题**: * 基于文章主旨,生成 2-3 个备选的主标题 (H1 级别)。 3. **最终决策**: * 从备选项中选择一个最精炼、最贴切的标题作为最终主标题。 * 从步骤 1 提取的内容中,最终确定哪些句子或短语最值得在正文中加粗,以引导读者快速抓住核心。 ## B. 最终输出规范 (请严格按此格式生成) 请根据你的内部推理,生成符合以下所有规范的 Markdown 文本: 1. **主标题 (H1)**: * 使用 `# 标题` 格式,采用你在步骤 A.3 中选定的最佳标题。 2. **内容结构**: * 使用不同级别的子标题(如 `##`、`###`)来组织文章脉络,使其逻辑清晰。 * 适当使用项目符号(`-`)或编号列表(`1.`)来呈现并列或顺序关系。 3. **突出重点 (句子优先)**: * **有选择性地**使用粗体 (`**`) 来突出你在步骤 A.1 和 A.3 中确定的**核心论点**、**关键结论**或**金句**。 * **优先加粗**:优先考虑加粗**能够概括要点的完整句子**或**关键短语**。 * **避免**:避免只加粗零散的单个关键词,并**切勿过度使用粗体**,保持文档的专业性和易读性。 4. **【!!!】重要格式规范**: * 在设置粗体时,**绝对不要**将任何标点符号(如 `。`、`,`、`:`、`"`、`(`、`)` 等)包含在 `**` 标记内部。 * ✅ **正确示例**(标点在 `**` 之外):这是“**一个核心观点**”。 * ❌ **错误示例**:这是**“一个核心观点”**。 --- 请开始处理以下内容:
群里看到的一个提示词,分享下。 这个汽车的三视图,牛了 生成的图直接喂给Sora2、Veo3.1等大模型 可试试直出一致性的视频效果 做视频的效率又提升了。 NanoBanana提示词: Prompt : A cinematic automotive photoshoot of me, keeping my real face unchanged. The scene is composed of three perspectives as a : 1. Top Panel: Interior close-up: I am seated inside the car, wearing a fitted black polo shirt, shown in the side mirror reflection. My face is serious and focused, my gaze directed forward with determination. The angle captures only side view part of my profile, framed cleanly within the mirror, emphasizing intensity and precision. 2.Middle Panel: I am standing confidently next to a sleek black Ford Mustang. My posture is relaxed but strong: both arms are crossed over my chest in a confident manner, while my left leg is straight and my right leg bent slightly at the knee, with the foot leaning casually against the car. My gaze is directed slightly off-camera, with a calm and assertive expression. I am wearing a fitted black polo shirt with subtle detailing, slim grey jeans with a clean cut, and brown leather boots. My outfit is minimal yet stylish, emphasizing a modern masculine vibe. Pose like a pro, same face as the uploaded photo. 3. Bottom Panel: Rear car shot: The camera captures the back of the Mustang, showcasing the "YOUR NAME" license plate and muscular lines of the car. The photo emphasizes the glossy texture of the vehicle and its aggressive, cinematic presence. The setting is an urban environment with modern architecture and concrete walls, giving a gritty, cinematic atmosphere. The lighting is natural but slightly diffused, highlighting both me and the polished surface of the car. The perspectives vary: - The mirror reflection close-up is shot tight with a portrait focal length (~85mm). - The exterior full-body shot is taken at eye-level with a slightly wide lens to capture both me and the car in full view. - The rear car angle uses a low perspective to emphasize power and presence. Style: Cinematic automotive editorial, urban setting, moody and stylish, professional fashion-meets- car photography, same face.
我又在玩AI修改图片风格 就一起把12种主要风格全部整理出来了 给AI一张图,再给下面提示词,就OK了,通用 🎨 一、动画与插画风格 1. 吉卜力风格(Studio Ghibli Style) 关键词: Studio Ghibli style, soft lighting, lush nature, watercolor texture, hand-drawn, warm tone, nostalgic atmosphere 增强词: Hayao Miyazaki, fantasy village, gentle wind, sunlight through trees, detailed background 适用场景: 自然场景、童话故事、治愈系插画 2. 迪士尼风格(Disney Style) 关键词: Disney animation style, expressive characters, cinematic lighting, vibrant colors, detailed hair and fabric 增强词: Pixar 3D render, soft glow, fairytale lighting, emotional expressions 适用场景: 角色肖像、动画剧照风格 3. 日式动漫风格(Anime Style) 关键词: Japanese anime style, clean lines, flat shading, big eyes, dynamic pose, colorful background 增强词: Makoto Shinkai lighting, sunset sky, cherry blossoms, school uniform 适用场景: 动漫人物、插画、轻小说封面 4. 西方漫画风格(Comic Book Style) 关键词: Western comic style, bold lines, halftone texture, strong contrast, dynamic action 增强词: Marvel, DC, superhero, exaggerated anatomy, dramatic composition 适用场景: 英雄主题、动作画面 🖌️ 二、经典绘画风格 1. 印象派(Impressionism) 关键词: Impressionist painting, visible brushstrokes, light reflections, pastel colors, soft focus 增强词: Claude Monet, morning light, water reflections, garden scenery 适用场景: 风景画、自然主题 2. 超现实主义(Surrealism) 关键词: Surrealist painting, dreamlike, symbolic composition, floating objects, distorted perspective 增强词: Salvador Dali, melting clock, endless desert, subconscious imagery 适用场景: 概念艺术、象征性创作 3. 波普艺术(Pop Art) 关键词: Pop art, vibrant colors, bold outlines, comic dots, repetition, 1960s aesthetic 增强词: Andy Warhol, Roy Lichtenstein, retro advertising, speech bubbles 适用场景: 平面设计、潮流插画 4. 立体主义(Cubism) 关键词: Cubism style, geometric abstraction, fragmented shapes, muted palette 增强词: Pablo Picasso, multiple perspectives, analytical geometry 适用场景: 抽象艺术、海报设计 💫 三、现代与幻想风格 1. 赛博朋克(Cyberpunk) 关键词: Cyberpunk city, neon lights, rainy street, reflections, futuristic outfit, holographic ads 增强词: Blade Runner style, cybernetic implants, night city, blue and pink lighting 适用场景: 城市夜景、未来角色设定 2. 蒸汽朋克(Steampunk) 关键词: Steampunk design, brass and copper, Victorian fashion, gears and steam, mechanical wings 增强词: retro machinery, skyship, London fog, fantasy engineer 适用场景: 机械幻想、角色设定 3. 梦幻少女风(Fantasy Girl / Lolita / Pastel Style) 关键词: dreamy pastel colors, elegant dress, lace, soft glow, kawaii, magical atmosphere 增强词: Lolita fashion, fairy dust, gentle eyes, sakura petals 适用场景: 角色肖像、浪漫插画 4. 像素艺术 / 低多边形(Pixel / Low-poly) 关键词: Pixel art, 8-bit style, retro game aesthetic, blocky texture 或 Low-poly art, geometric simplicity, flat shading, minimalist 3D 适用场景: 游戏设计、复古风 5. AI 混合新媒体风格(AI-Generated Hybrid Style) 关键词: AI art style, mixed media, abstract texture, photo-realistic + painterly fusion, glitch aesthetic 增强词: dreamcore, vaporwave, neural style transfer, surreal composition 适用场景: 实验艺术、视觉概念、封面设计