模板仓库

[中文] 平面插画，东方幻想风格高端城市海报设计，竖版9:16构图，整体采用对角线+S型流动构图，从左下向右上延展，画面以深邃黑色为背景，自上而下渐变至浓烈暗红色，形成强烈冷暖对比与空间纵深，背景带微弱星尘与颗粒质感。画面中央一条金色流动能量线条如火焰般蜿蜒贯穿，自底部向上延伸，具有流体质感、粒子光效与渐变高光，局部带细微能量碎屑与体积光。 金色流光中逐层浮现广州城市地标建筑群：广州塔为视觉核心，比例突出，周围融合珠江新城高楼群、猎德大桥及现代与岭南建筑元素，建筑采用“精细线描 + 金色发光体块”表现，轮廓清晰、细节丰富，在金色光晕映衬下仿佛悬浮于虚空，形成超现实空间层次，远景轻微雾化增强纵深感。 画面底部为一位东方白发女性形象，长发飘逸，如烟似雾，与金色流光自然衔接并逐渐融合，发丝半透明带渐变光感，姿态柔美，双目微闭，神情宁静，怀抱一束多彩鲜花，花间点缀微光粒子与星点效果，象征人与城市能量的精神连接，人物细节适度简化以突出整体设计感。 光影集中于金色流线、建筑与人物轮廓，形成强烈明暗对比与视觉聚焦，整体氛围宏大、神秘、具有东方神话意境且略带治愈感。色彩以黑与暗红为基底，高亮鎏金为主视觉强调，金色具备丰富明暗层次，辅以小面积高饱和花束色彩点缀，整体高级克制。 页面文字与画面融合排版：顶部居中宋体大字“广州·中国”，下方小字“2026/04/20”，再下方小字“LIYUE”，文字采用淡金色或柔和暖白色，与整体光影统一。高品质细节，电影级光影表现，体积光与粒子细节丰富，画面干净无噪点，超高清8K分辨率，商业级海报质感。 [English] Flat illustration, Oriental fantasy style high-end city poster design, vertical 9:16 composition, the overall adopts a diagonal + S-shaped flowing composition, extending from the bottom left to the top right, the picture uses deep black as the background, gradually changing from top to bottom to intense dark red, forming a strong cold-warm contrast and spatial depth, the background has a faint stardust and grainy texture. In the center of the picture, a golden flowing energy line winds through like a flame, extending from the bottom to the top, having a fluid texture, particle light effects and gradient highlights, with subtle energy debris and volumetric light in some areas. Guangzhou city landmark building complexes emerge layer by layer in the golden flowing light: Canton Tower is the visual core, with a prominent proportion, surrounded by the integration of Zhujiang New Town high-rise buildings, Liede Bridge and modern and Lingnan architectural elements, the buildings are expressed using "fine line drawing + golden glowing blocks", clear outlines and rich details, set off by the golden halo, they seem to float in the void, forming a surreal spatial hierarchy, the distant view is slightly fogged to enhance the sense of depth. At the bottom of the picture is an oriental white-haired female figure, long hair fluttering, like smoke and mist, naturally connecting and gradually blending with the golden flowing light, the hair is translucent with a gradient light sense, graceful posture, eyes slightly closed, serene expression, holding a bunch of colorful fresh flowers in her arms, interspersed with faint light particles and starlight effects among the flowers, symbolizing the spiritual connection between human and urban energy, character details are moderately simplified to highlight the overall sense of design. Light and shadow are focused on the golden streamlines, buildings and character outlines, forming a strong light-dark contrast and visual focus, the overall atmosphere is grand, mysterious, with an Oriental mythological artistic conception and a slight healing sense. The color uses black and dark red as the base, highlighted gilded gold as the main visual emphasis, the gold has rich light and dark layers, supplemented by small areas of high-saturation bouquet color embellishments, the overall is advanced and restrained. Page text and picture integrated typography: large Song typeface characters "Guangzhou·China" centered at the top, small characters "2026/04/20" below, small characters "LIYUE" further below, the text uses light gold or soft warm white, unifying with the overall light and shadow. High-quality details, cinematic light and shadow performance, rich volumetric light and particle details, clean picture without noise, ultra-high definition 8K resolution, commercial-grade poster texture.

[中文] 9:16 竖版 — 一个 3x3 网格拼贴（九张图片）形成一系列韩国偶像肖像摄影。每一帧都呈现同一位年轻的韩国女性偶像，在所有九张镜头中保持 100% 一致的面部特征、比例、发型和身份。自然、超逼真的皮肤纹理，无修图，无磨皮。干净的偶像风格极简妆容，柔和的光泽，微妙的瑕疵。发型：长发、蓬松的黑发，微乱，在所有帧中保持一致（自然松散的垂落，轻微的动感）。服装：连贯的韩国偶像摄影造型 — 白色衬衫 + 短款下装（或简单的中性色调服装），青春、干净、略带休闲但有造型感。所有帧中穿着相同的服装。场景：极简的工作室或简单的室内环境（白墙，柔和的窗光，干净的背景）。聚焦于主体，而不是环境。光照：柔和漫反射的自然光，温柔的高光，低对比度，略带通透感的色调，微妙的胶片般柔和感。相机风格：亲密的肖像摄影，略带手持感，微妙的瑕疵（轻微的颗粒感，动态帧中的轻微模糊，不完美的构图）。帧分解（3x3 网格）：顶行：- 左上：自然站立，视线略微偏向一侧，表情放松 - 中上：面对镜头，随意的中间动作（头发或身体轻微移动） - 右上：轻微的侧面角度，柔和的注视，自然的抓拍感 中间行：- 中左：微微向上看，柔和的沉思表情 - 正中：特写肖像，直接的眼神接触，温柔的偶像微笑 - 中右：身体微微转动，中间动作的抓拍帧 底行：- 左下：随意坐着或倚靠着，放松的姿势 - 中下：背部部分转向，越过肩膀看向镜头 - 右下：靠近画框站立，略带俏皮或柔和的表情 氛围：韩国偶像写真集 / 小卡美学，亲密、柔和、自然、日常的魅力。质量：超写实，8K 细节，微妙的模拟胶片颗粒感，自然的瑕疵，柔和梦幻的色调 [English] 9:16 vertical — a 3x3 grid collage (nine images) forming a Korean idol portrait photoshoot series. Each frame features the same young Korean female idol, maintaining 100% consistency in facial features, proportions, hairstyle, and identity across all nine shots. Natural, ultra-realistic skin texture, no retouching, no smoothing. Clean idol-style minimal makeup, soft glow, subtle imperfections. Hair: long, voluminous dark hair, slightly tousled, consistent across all frames (natural loose flow, slight movement). Outfit: cohesive Korean idol photoshoot styling — white shirt + short bottoms (or simple neutral-toned outfit), youthful, clean, slightly casual but styled. Same outfit across all frames. Setting: minimal studio or simple indoor environment (plain wall, soft window light, clean background). Focus on subject, not environment. Lighting: soft diffused natural light, gentle highlights, low contrast, slightly airy tones, subtle film-like softness. Camera style: intimate portrait photography, slightly handheld feel, subtle imperfections (minor grain, slight blur in motion frames, imperfect framing). Frame breakdown (3x3 grid): Top row: - Top left: standing naturally, looking slightly away, relaxed expression - Top center: facing camera, casual mid-motion (hair or body slight movement) - Top right: slight side angle, soft gaze, natural candid feel Middle row: - Center left: looking slightly upward, soft thoughtful expression - Center: close-up portrait, direct eye contact, gentle idol smile - Center right: turning body slightly, mid-motion candid frame Bottom row: - Bottom left: seated or leaning casually, relaxed posture - Bottom center: back partially turned, looking over shoulder toward camera - Bottom right: standing close to frame, slightly playful or soft expression Mood: Korean idol photobook / photocard aesthetic, intimate, soft, natural, everyday charm. Quality: ultra-realistic, 8K detail, subtle analog film grain, natural imperfections, soft dreamy tone

[中文] 角色：世界级科学百科插画师兼知识图谱架构师 任务：以经典、无品牌标识（无任何 Logo）的科学百科风格，创作一幅细节极致丰富、结构极其精巧、视觉效果惊艳的「环球图解百科科学信息图」。 题材选择：从【人物、植物、动物】中任选其一。 具体对象：【例如：大王乌贼 / 列奥纳多・达・芬奇 / 红杉树】 风格：采用复古泛黄米色纸张背景，绘制精细工整的科学插画；线条细腻精致，整体繁复专业、严谨考究。 核心视觉要求 主体逼真 3D 效果 位于画面视觉中心（C 位）的主体形象，需具备极致的写实感与动态张力。营造强烈的空间纵深感，让人物、植物或动物仿佛突破画框，从平面纸张中跃出、冲向观者（效果类似变形 3D 或动态弹出效果，高精度写实呈现）。 版式布局与留白设计 主体位置：占据画面中心，周围刻意设置规划式留白，强化立体弹出效果，使其成为绝对视觉焦点。 周边模块：根据所选题材，在画面四周（上下左右及四角）排布 6–8 个独立且规整有序的知识模块。整体呈现规整的信息密度感，而非杂乱堆砌。每个模块需带有清晰边框、标题栏与详尽丰富的内容。 关联结构 运用纤细的指示线、箭头、括号、虚线与小型连接点，构建复杂且逻辑清晰的网络，将中心主体与所有周边模块相连，并使各模块之间相互关联，形成完整统一的知识体系。 文字与标注（硬性要求：必须为清晰中文） 主标题：以醒目大气、笔法优美的中文书法字体呈现具体对象名称【例如：大王乌贼】。 书法点缀：在主体画面与模块标题中，对关键术语使用工整美观的中文书法字体标注。 标准中文文本：其余所有说明文字、大量清晰中文手写注释、模块内容及注解均使用清晰可辨的简体汉字，不得出现乱码或无法识别符号，优先保证文字可读性。 指示线标注：模块内所有细小结构、细节、子模块、图表与插画，均需搭配详尽的指示线标注（仿解剖图形式），直接指向对应部位，最大化体现专业性与科普价值，做到每一处结构均有标注。 分题材模块结构（参考示例） A. 人物类 模块 1：解剖结构与骨骼系统（含放大剖面图示） 模块 2：生理运作机制（如循环系统、神经系统） 模块 3：生平背景与时间线（核心成就） 模块 4：主要贡献图解（详细拆解） 模块 5：认知模式与心理特征 模块 6：基因特征与演化溯源 模块 7：全球影响力与文化冲击 模块 8：艺术形象与后世传承 B. 动物类 模块 1：整体外形草图与解剖结构（含显微镜级圆形放大细节） 模块 2：行为模式与生命周期（如交配、迁徙，流程图形式） 模块 3：消化系统与骨骼系统 模块 4：栖息环境与分布地图（含环境细节） 模块 5：独特适应性特征（如伪装、捕食器官） 模块 6：演化历史与亲缘物种 模块 7：共生关系与生态位作用 模块 8：保护现状与人类互动 C. 植物类 模块 1：植株整体草图与解剖结构（含叶片、根部放大细节） 模块 2：光合作用与生命周期流程（搭配环境示意图标） 模块 3：细胞结构（圆形放大视图） 模块 4：药用价值与实际应用 模块 5：环境适应性与独有特征 模块 6：分布地图与生长环境 模块 7：基因变异与培育方式 模块 8：历史用途与民间传说 整体构图要求 信息密度极高，规整划分为 6–8 个结构化模块，同时通过中心区域的规划留白突出超写实主体的立体弹出效果。风格硬核、专业、学术化，凭借动态 3D 主体实现极强视觉吸引力。 无任何百科品牌标识（如 DK 等 Logo）。 所有标注清晰可辨，所有手写注释工整可读。 主标题采用中文书法字体。 画面比例：3:4。 【主题内容】 [English] Role: World-class Scientific Encyclopedia Illustrator & Knowledge Graph Architect. Task: Generate a highly detailed, extremely intricate, and visually stunning "Universal Illustrated Encyclopedia Science Infographic" in a classic, unbranded (NO logos) scientific encyclopedia style. Subject Matter: Choose one from [People, Plants, or Animals]. Specific Subject: [e.g., The Giant Squid / Leonardo da Vinci / The Sequoia Tree]. Style: Fine, detailed scientific illustration on a retro, aged beige paper background. Delicate linework. Intricately complex and professional. Key Visual Requirements: 1. Lifelike 3D Effect (The Central Subject): The central subject in the "C position" must be rendered with extraordinary realism and dynamism. Create a dramatic sense of depth where the character, plant, or animal appears to break the frame, leaping or bursting out of the flat paper towards the viewer (an effect similar to anamorphic 3D or dynamic pop-out, with high-precision realism). 2. Layout & Strategic White Space: * Central Subject: Dominates the center, with intentional "strategic white space" around it to enhance the popping-out effect and make the figure the clear focal point. * Surrounding Modules: The surrounding area (left, right, top, bottom, and corners) must be filled with 6-8 distinct, highly organized knowledge modules, depending on the subject. There should be a sense of organized density, not random clutter. The modules themselves must have clear borders, headers, and extensive, detailed content. 3. Connections: Use a complex, logical network of fine leader lines, arrows, brackets, dotted lines, and small connection points to link the central figure to all surrounding modules, and interconnect the modules themselves into a cohesive knowledge web. 4. Text & Annotation (Hard Requirement - Must be CLEAR Chinese): * Main Title: A large, prominent, beautifully executed **Chinese calligraphy** (书法体) of the specific subject's name [e.g., "大王乌贼"]. * Calligraphic Accents: Scattered throughout the main content and module titles, use beautiful, clear Chinese calligraphy for important terms. * Standard Chinese Text: All other descriptive text, handwritten notes (大量清晰中文手写注释), module content, and annotations must be clear, legible Chinese characters (简体中文), not gibberish or unreadable symbols. Ensure text clarity is prioritized. * Leader Line Annotations: Every single small component, detail, submodule, diagram, or illustration within the modules must have detailed leader line annotations (拟解剖图) pointing directly to it for maximum professionalism and educational value. Every part should be labeled. Subject-Specific Module Structure (Example for general reference): A. For Humans [People]: - Module 1: Anatomy & Skeletal Structure (w/ magnified cross-sections) - Module 2: Physiological Processes (e.g., Circulatory/Nervous System) - Module 3: Historical Context & Timeline (Key Achievements) - Module 4: Major Contribution Diagram (Detailed breakdown) - Module 5: Cognitive Process / Psychological Insight - Module 6: Genetic Profile / Evolution - Module 7: Global Influence & Cultural Impact - Module 8: Cultural Representations / Legacy B. For Animals: - Module 1: Full External Sketch & Anatomy (w/ microscope magnified detail circular windows) - Module 2: Behavioral Patterns & Lifecycle (e.g., Mating/Migration, Flowchart style) - Module 3: Digestive & Skeletal System - Module 4: Habitats & Distribution Map (with environmental details) - Module 5: Unique Adaptations (e.g., camouflage, hunting tools) - Module 6: Evolutionary History & Relatives - Module 7: Symbiotic Relationships / Ecosystem Role - Module 8: Conservation Status & Human Interaction C. For Plants: - Module 1: Full Plant Sketch & Anatomy (w/ magnified leaf/root details) - Module 2: Photosynthesis & Lifecycle Flow (w/ icons for environment) - Module 3: Cellular Structure (Magnified circular views) - Module 4: Medicinal Properties / Practical Applications (as in original original prompt) - Module 5: Environmental Adaptations / Unique Features - Module 6: Distribution Map & Environmental Context - Module 7: Genetic Variations & Cultivation - Module 8: Historical Usage & Folklore Overall Composition: Extremely dense with information, organized into 6-8 structured modules, but balanced with strategic empty space around the center to allow the main, hyper-realistic figure to pop. Hard-core, professional, academic, but visually engaging due to the dynamic 3D central figure. No branding from any specific encyclopedia (e.g., no "DK" logos). All annotations must be legible. All handwritten notes must be clear. Main titles in Chinese calligraphy. Aspect Ratio: 3:4. [主题内容]

[中文] { "prompt": { "style_and_tech": "手机照片，老式CCD相机美学，刺眼的闪光灯，颗粒感，昏暗杂乱的室内光线，抓拍快照感觉，轻微的运动模糊", "subject": "年轻的韩国女偶像，温柔纯真的外表", "pose": "动作进行中，微微转头看向镜头，仿佛刚刚注意到正在被拍照，肩膀微微耸起", "expression": "眼睛微微睁大，因惊讶而微微张开的嘴唇，害羞且猝不及防的表情", "clothing": "宽松柔软的居家服（薄开衫+内搭上衣），一侧肩膀微微滑落但没有暴露", "vibe": "毫无防备，亲密，意外的瞬间，唤起好奇心与保护欲", "aspect ratio": "9:16" } } [English] { "prompt": { "style_and_tech": "mobile phone photo, old CCD camera aesthetic, harsh flash, grainy, dim messy indoor lighting, candid snapshot feeling, slight motion blur", "subject": "young Korean female idol, soft innocent look", "pose": "mid-action, slightly turning head toward camera as if just noticed being photographed, shoulders slightly raised", "expression": "eyes widened slightly, lips parted in surprise, shy and caught-off-guard expression", "clothing": "loose soft homewear (thin cardigan + inner top), slightly slipping off one shoulder but not revealing", "vibe": "unprepared, intimate, accidental moment, evokes curiosity and protectiveness"， "aspect ratio":"9:16" } }

[中文] 使用附图中的图案，由专业设计师打造 4 款时尚单品，采用不同的色彩搭配与排版设计，附带穿搭效果图。以雅致的构图凸显图案的美感。格式为 2:3，希望将图像生成模型从 duct-tape-1 指定为 duct-tape-2、3。 [English] Use the patterns in the attached image, crafted by professional designers to create 4 fashion items, using different color schemes and layout designs, accompanied by outfit effect pictures. Highlight the beauty of the patterns with an elegant composition. The format is 2:3, hoping to specify the image generation model from duct-tape-1 to duct-tape-2, 3.

[中文] 创作一张超高细节等距像素艺术时间线插画（3:4，4K），融合细节密度、象征性与隐喻。用户指定的主题为【Western Art Development】。 首先，围绕Western Art Development进行推理，确定：主题的中英文标题、涵盖的最早与最近历史时期、起始阶段标签与结束阶段标签，以及3-5个关键演进阶段及其各自的象征性元素与色彩方案。 然后构建一个以"Western Art Development"为主题的等距"演进博物馆"，每个展馆区域代表一个演进阶段，空间推进即代表时间演变。采用标准等距视角（2:1），丰富的层次深度与流畅过渡。每个阶段分配3-5个与主题强烈关联的象征元素，并用差异化色彩暗示时间流动。在场景中融入双语像素字体标题：中文"[主题中文]演进史"与英文"EVOLUTION OF Western Art Development"，加上起止阶段的双语副标题及关键时间节点标记。整体风格专业且具视觉张力，适合学术分析与对比可视化，直接出图。 [English] Create an ultra-high-detail isometric pixel art timeline illustration (3:4, 4K), integrating detail density, symbolism, and metaphor. The user-specified theme is [Western Art Development]. First, reason around Western Art Development to determine: the Chinese and English titles of the theme, the earliest and most recent historical periods covered, the starting stage label and the ending stage label, as well as 3-5 key evolution stages and their respective symbolic elements and color schemes. Then build an isometric "Evolution Museum" themed "Western Art Development", where each exhibition hall area represents an evolution stage, and spatial progression represents time evolution. Adopt a standard isometric perspective (2:1), rich layer depth, and smooth transitions. Allocate 3-5 symbolic elements strongly associated with the theme to each stage, and use differentiated colors to imply the flow of time. Integrate bilingual pixel font titles in the scene: Chinese "[Theme Chinese] Evolution History" and English "EVOLUTION OF Western Art Development", plus bilingual subtitles for the starting and ending stages and key time node markers. The overall style is professional and visually tense, suitable for academic analysis and comparative visualization, direct image output.

Role: World-class Scientific Encyclopedia Illustrator & Knowledge Graph Architect. Task: Generate a highly detailed, extremely intricate, and visually stunning "Universal Illustrated Encyclopedia Science Infographic" in a classic, unbranded (NO logos) scientific encyclopedia style. Subject Matter: Choose one from [People, Plants, or Animals]. Specific Subject: [e.g., The Giant Squid / Leonardo da Vinci / The Sequoia Tree]. Style: Fine, detailed scientific illustration on a retro, aged beige paper background. Delicate linework. Intricately complex and professional. Key Visual Requirements: 1. Lifelike 3D Effect (The Central Subject): The central subject in the "C position" must be rendered with extraordinary realism and dynamism. Create a dramatic sense of depth where the character, plant, or animal appears to break the frame, leaping or bursting out of the flat paper towards the viewer (an effect similar to anamorphic 3D or dynamic pop-out, with high-precision realism). 2. Layout & Strategic White Space: * Central Subject: Dominates the center, with intentional "strategic white space" around it to enhance the popping-out effect and make the figure the clear focal point. * Surrounding Modules: The surrounding area (left, right, top, bottom, and corners) must be filled with 6-8 distinct, highly organized knowledge modules, depending on the subject. There should be a sense of organized density, not random clutter. The modules themselves must have clear borders, headers, and extensive, detailed content. 3. Connections: Use a complex, logical network of fine leader lines, arrows, brackets, dotted lines, and small connection points to link the central figure to all surrounding modules, and interconnect the modules themselves into a cohesive knowledge web. 4. Text & Annotation (Hard Requirement - Must be CLEAR Chinese): * Main Title: A large, prominent, beautifully executed **Chinese calligraphy** (书法体) of the specific subject's name [e.g., "大王乌贼"]. * Calligraphic Accents: Scattered throughout the main content and module titles, use beautiful, clear Chinese calligraphy for important terms. * Standard Chinese Text: All other descriptive text, handwritten notes (大量清晰中文手写注释), module content, and annotations must be clear, legible Chinese characters (简体中文), not gibberish or unreadable symbols. Ensure text clarity is prioritized. * Leader Line Annotations: Every single small component, detail, submodule, diagram, or illustration within the modules must have detailed leader line annotations (拟解剖图) pointing directly to it for maximum professionalism and educational value. Every part should be labeled. Subject-Specific Module Structure (Example for general reference): A. For Humans [People]: - Module 1: Anatomy & Skeletal Structure (w/ magnified cross-sections) - Module 2: Physiological Processes (e.g., Circulatory/Nervous System) - Module 3: Historical Context & Timeline (Key Achievements) - Module 4: Major Contribution Diagram (Detailed breakdown) - Module 5: Cognitive Process / Psychological Insight - Module 6: Genetic Profile / Evolution - Module 7: Global Influence & Cultural Impact - Module 8: Cultural Representations / Legacy B. For Animals: - Module 1: Full External Sketch & Anatomy (w/ microscope magnified detail circular windows) - Module 2: Behavioral Patterns & Lifecycle (e.g., Mating/Migration, Flowchart style) - Module 3: Digestive & Skeletal System - Module 4: Habitats & Distribution Map (with environmental details) - Module 5: Unique Adaptations (e.g., camouflage, hunting tools) - Module 6: Evolutionary History & Relatives - Module 7: Symbiotic Relationships / Ecosystem Role - Module 8: Conservation Status & Human Interaction C. For Plants: - Module 1: Full Plant Sketch & Anatomy (w/ magnified leaf/root details) - Module 2: Photosynthesis & Lifecycle Flow (w/ icons for environment) - Module 3: Cellular Structure (Magnified circular views) - Module 4: Medicinal Properties / Practical Applications (as in original original prompt) - Module 5: Environmental Adaptations / Unique Features - Module 6: Distribution Map & Environmental Context - Module 7: Genetic Variations & Cultivation - Module 8: Historical Usage & Folklore Overall Composition: Extremely dense with information, organized into 6-8 structured modules, but balanced with strategic empty space around the center to allow the main, hyper-realistic figure to pop. Hard-core, professional, academic, but visually engaging due to the dynamic 3D central figure. No branding from any specific encyclopedia (e.g., no "DK" logos). All annotations must be legible. All handwritten notes must be clear. Main titles in Chinese calligraphy. Aspect Ratio: 3:4. 主题内容：潘金莲

[中文] 帮我生成一个以《金瓶梅》为主题的古代 ARPG MMO 开放世界游戏的截图 [English] Help me generate a screenshot of an ancient ARPG MMO open-world game themed around Jin Ping Mei.

[中文] 请用这个角色制作一本专业设计师打造的照片集。语言为日语。 根据喜好加入提示词会让它更丰富多彩… ・丰富的场景 ・信息量较多 [English] Please use this character to create a photo book crafted by a professional designer. The language should be Japanese. Adding prompts according to your preferences will make it more colorful and rich ・Rich scenes ・Large amount of information

[中文] 生成一个天坛的建筑拆解图，有详细的说明，中式美学风格 [English] Generate an architectural exploded view of the Temple of Heaven, with detailed annotations, Chinese aesthetic style

[中文] 可爱地解释一下大语言模型训练过程 [English] Cute explanation of the large language model training process

[中文] 模仿《无畏契约》的风格，生成一个三国神话的 FPS 游戏 [English] Imitating the style of Valorant, generate a Three Kingdoms mythological FPS game

[中文] 生成一张高质量二次元美少女图片。 角色设定： - 年龄：17岁 - 发型：双马尾，颜色：樱花粉，发梢带点渐变紫色 - 眼睛：大而明亮，紫色瞳孔，有星星高光 - 服装：JK制服，白色衬衫，深蓝色格子裙，红色领结 - 配饰：白色过膝袜，棕色小皮鞋，头上戴一个粉色蝴蝶结 风格要求： - 日系动画风格，线条清晰 - 色彩鲜艳，对比度高 - 光影柔和，有层次感 - 背景：樱花树下，花瓣飘落，远处是学校教学楼 表情：微笑，有点害羞 姿势：站姿，双手放在身后，身体微微前倾 比例：16:9（手机壁纸） 质量：8K，超精细，细节丰富 [English] Generate a high-quality anime beautiful girl image. Character setting: - Age: 17 years old - Hairstyle: twin tails, color: cherry blossom pink, hair tips with a bit of gradient purple - Eyes: large and bright, purple pupils, with star highlights - Clothing: JK uniform, white shirt, dark blue plaid skirt, red bow tie - Accessories: white over-the-knee socks, brown leather shoes, wearing a pink bow on the head Style requirements: - Japanese animation style, clear lines - bright colors, high contrast - soft light and shadow, with a sense of layering - Background: under the cherry blossom tree, petals falling, school teaching building in the distance Expression: smiling, a bit shy Pose: standing posture, hands placed behind the back, body slightly leaning forward Proportion: 16:9 (mobile wallpaper) Quality: 8K, ultra-fine, rich in details

[中文] 生成一张黑神话·潘金莲的游戏介绍画面，人物十分的迷人 [English] Generate a game introduction screen for Black Myth: Pan Jinlian, the character is extremely charming.

[中文] （国风卷轴插画师）你是一位顶尖的中国传统工笔人物画师，擅长将经典人物群像绘制成长卷式百科海报。根据用户指定的【eight immortals】，生成一张 “中国传统人物群像长卷海报”：画面为横向长卷式构图，所有人物排成一条队列，从左至右依次展开；每个人物都有鲜明的传统服饰、标志性道具和神态，下方配有竖排名牌标注姓名；卷轴顶部有醒目的书法标题；背景为符合主题的场景元素（如祥云、海浪、山水、亭台等）。整体为高质量国风工笔插画：细腻线稿 + 雅致上色，浅米色 / 宣纸质感背景；注释为清晰的中文书法字体；横向 4K 长卷海报，构图均衡，人物分明，氛围贴合主题（如仙气、豪迈、温婉等）。直接出图，人物群像为【eight immortals】。 [English] (Guofeng scroll illustrator) You are a top Chinese traditional Gongbi figure painter, skilled in painting classic character group portraits into long-scroll-style encyclopedia posters. According to the user-specified [eight immortals], generate a "Chinese traditional character group portrait long scroll poster": The picture is a horizontal long-scroll composition, all characters are arranged in a queue, unfolding sequentially from left to right; each character has distinct traditional clothing, iconic props, and expressions, below is a vertical nameplate annotating the name; the top of the scroll has a striking calligraphy title; the background is scene elements fitting the theme (such as auspicious clouds, ocean waves, mountains and rivers, pavilions). The overall style is high-quality Guofeng Gongbi illustration: delicate line art + elegant coloring, light beige / Xuan paper texture background; annotations are in clear Chinese calligraphy fonts; horizontal 4K long scroll poster, balanced composition, distinct characters, atmosphere fitting the theme (such as fairy-like, heroic, gentle). Output the image directly, the character group portrait is [eight immortals].

[中文] 生成一张古代皇宫 × 快递驿站 [English] Generate an ancient imperial palace × express delivery station

[中文] 生成一张动画分镜生成器 [English] Generate an animation storyboard generator

[中文] 杠精视角文案 + GPT Image 2 [English] Troll perspective copywriting + GPT Image 2

[中文] 生成高质量美女（宅男必备） [English] Generate high-quality beautiful girl (otaku must-have)

[中文] 一张三甲医院的门诊处方笺，医生潦草的手写字，包含真实合理的 诊断、药品名、剂量，右下角有医生签名和科室章。 [English] An outpatient prescription sheet from a Grade 3A hospital, doctor's illegible handwriting, containing realistic and reasonable diagnosis, drug names, dosages, with a doctor's signature and department stamp in the bottom right corner.

[中文] 生成一个抖音直播的截图 里面是一个美女在直播，在卖丝袜和内衣，她的在线人数是99996，热度是18+，有个叫小互的大哥，给她刷了一个飞机礼物 [English] Generate a screenshot of a Douyin live stream featuring a beautiful woman live streaming, selling pantyhose and underwear, her online viewer count is 99996, the popularity rating is 18+, a big brother named Xiao Hu sent her an airplane gift

[中文] { 超写实iPhone 15 Pro前置摄像头自拍，一位成年女性在明亮的沙滩上， 从举臂高角度自拍视角拍摄。手机略微举在脸部上方， 营造出自然的前置摄像头几何形态，带有轻微的等效24mm广角畸变， 写实的面部比例， 以及智能手机的深景深。她向上抬起下巴，一只手遮挡刺眼的阳光，同时直视手机镜头。她的表情中性， 面无表情， 且略带疏离感， 眼睛大而专注，但在解剖学上具有真实的眼部尺寸和自然面部比例。\n\n她有着极浅的铂金色头发，梳成两条紧紧的辫子， 苍白的皮肤带有真实摄影的皮肤纹理， 可见的毛孔， 细微的绒毛， 淡淡的眼下纹理， 自然的唇部纹理， 以及柔和的阳光光泽，而不是磨皮后的完美无瑕。她的嘴唇是自然色调且略丰满， 她的鼻子小巧精致但很写实。她的指甲是鲜艳的蓝色。她穿着一件浅蓝色紧身弹力棉上衣，领口非常深且宽，以自然、 非风格化的方式露出突出的锁骨和上胸结构。\n\n背景是宽阔的海岸沙滩，在强烈的上午晚些时候的阳光下， 背景中有一条柔和模糊的地平线。光线明亮， 色温约5500K的高调海岸日光， 强烈的白色沙子反光从下方和脸部周围均匀地填充阴影。皮肤被直射阳光加上海滩宽阔柔和的反射补光照亮， 产生清脆但写实的高光，没有生硬的对比。明亮沙子的细小颗粒微妙地捕捉光线。整体图像应该感觉像是在强烈的海边光线下在户外拍摄的真正高曝光智能手机自拍。\n\n色彩渲染应该是柔和、 干净、 且现代的， 带有中性至柔和的色调， 写实的iPhone计算摄影， 略微提高的曝光， 受控的高光过渡， 自然的肤色， 没有电影级调色。优先考虑写实性、 物理准确性、 可信的解剖结构， 以及真实的智能手机图像表现，而不是美化风格化。", "negative_prompt": "动漫， 洋娃娃脸， 瓷器皮肤， 无毛孔皮肤， 塑料皮肤， CGI， 3D渲染， 超现实眼睛， 过大的眼睛， 奇幻美， 磨皮精修， 浓妆， 魅力光， 戏剧性阴影， 胶片颗粒， 雪， 冬装， 黑色上衣， 红指甲， 保守领口， 影棚背景， 人造模糊， 扭曲的手， 变形的手指， 畸形的脸， 对称完美， 美颜滤镜， 惊悚的皮肤平滑" } [English] { Ultra-realistic iPhone 15 Pro front-camera selfie of an adult woman on a bright beach, photographed from a raised-arm high-angle selfie perspective. The phone is held slightly above her face, creating natural front-camera geometry with mild 24mm equivalent wide-angle distortion, realistic facial proportions, and deep smartphone depth of field. She tilts her chin upward and looks directly toward the phone lens while shielding harsh sunlight with one hand. Her expression is neutral, blank, and slightly distant, with wide attentive eyes but anatomically realistic eye size and natural facial proportions.\n\nShe has very light platinum-blonde hair styled in two tight braids, pale skin with real photographic skin texture, visible pores, subtle peach fuzz, faint under-eye texture, natural lip texture, and a soft sunlit sheen rather than airbrushed perfection. Her lips are naturally toned and slightly full, her nose is small and refined but realistic. Her nails are vivid blue. She wears a light blue fitted stretch-cotton top with a very deep wide neckline that reveals pronounced collarbones and upper chest structure in a natural, non-stylized way.\n\nThe setting is a wide coastal beach under strong late-morning sunlight, with a softly blurred horizon line in the background. The lighting is bright, high-key coastal daylight around 5500K, with strong white sand bounce filling the shadows evenly from below and around the face. Skin is illuminated by direct sun plus broad soft reflected fill from the beach, producing crisp but realistic highlights without harsh contrast. Fine grains of bright sand catch light subtly. The overall image should feel like a real high-exposure smartphone selfie taken outdoors in intense seaside light.\n\nColor rendering should be soft, clean, and modern, with neutral-to-pastel tones, realistic iPhone computational photography, slightly elevated exposure, controlled highlight rolloff, natural skin color, and no cinematic grading. Prioritize realism, physical accuracy, believable anatomy, and true smartphone image behavior over beauty stylization.", "negative_prompt": "anime, doll face, porcelain skin, poreless skin, plastic skin, CGI, 3D render, surreal eyes, oversized eyes, fantasy beauty, airbrushed retouching, heavy makeup, glamour lighting, dramatic shadows, film grain, snow, winter clothing, black top, red nails, conservative neckline, studio backdrop, artificial blur, warped hands, deformed fingers, malformed face, symmetry perfection, beauty filter, uncanny skin smoothing" }

[中文] { "相机参数": { "设备类型": "iPhone 15 Pro 前置自拍", "镜头": "24mm", "构图": "高角度 POV（第一人称视角）", "后期处理": "计算摄影风格，清晰的数字读出，深景深" }, "主体描述": { "特征": "陶瓷娃娃审美，无瑕的苍白皮肤，巨大的冰蓝色眼睛，小巧的鼻子，翘起的自然色嘴唇", "表情": "面无表情，空洞，瞪大眼睛注视", "造型": "白金色的双紧辫发型，鲜艳的蓝色美甲", "服装": "浅蓝色紧身弹力棉上衣，极深超宽 V 领，深邃锁骨与领口线", "动作": "抬头仰视镜头，用一只手遮挡刺眼的阳光" }, "环境与灯光": { "场景": "广阔的沙滩，背景中模糊的海平线", "灯光": "高调明亮的沿海日光，5500K 色温，强烈的白沙反光填充，均匀照明", "质感": "微带露水的无孔皮肤，细腻的反光白沙颗粒" }, "技术约束": { "色彩科学": "柔和的粉彩色调，线性中性色，高曝光", "负面提示词": [ "重阴影", "雪", "冬装", "红指甲", "黑色上衣", "保守的领口", "胶片颗粒感" ] } } [English] { "cameraParameters": { "deviceType": "iPhone 15 Pro front selfie", "lens": "24mm", "composition": "High angle POV (first-person perspective)", "postProcessing": "Computational photography style, clear digital readout, deep depth of field" }, "subjectDescription": { "features": "Porcelain doll aesthetic, flawless pale skin, huge ice-blue eyes, small nose, slightly upturned natural-colored lips", "expression": "Expressionless, hollow, wide-eyed staring", "styling": "Platinum blonde tight double braids hairstyle, vibrant blue nail polish", "clothing": "Light blue tight stretch cotton top, extremely deep ultra-wide V-neck, deep collarbone and neckline", "action": "Looking up at the camera, blocking the glaring sunlight with one hand" }, "environmentAndLighting": { "scene": "Vast sandy beach, blurry horizon in the background", "lighting": "High-key bright coastal daylight, 5500K color temperature, strong white sand reflection fill, even lighting", "texture": "Slightly dewy poreless skin, fine reflective white sand particles" }, "technicalConstraints": { "colorScience": "Soft pastel tones, linear neutral colors, high exposure", "negativePrompts": [ "Heavy shadows", "Snow", "Winter clothing", "Red nails", "Black top", "Conservative neckline", "Film grain" ] } }

[中文] 帮我生成一张特朗普对战哈梅内伊在英雄联盟中路对线的截图。 [English] Help me generate a screenshot of Trump versus Khamenei in the mid lane in League of Legends.