Prompt Personaggio

Professional flat vector illustration in modern commercial style, depicting [SCENE_DESCRIPTION]. PERSPECTIVE & COMPOSITION: - Extreme [ANGLE_TYPE] perspective from [STARTING_POINT] looking [VIEWING_DIRECTION] along ONE SINGLE [EXTENDING_OBJECT] toward [END_POINT] - [EXTENSION_DIRECTION_LAYOUT] - Single unified viewpoint with continuous depth progression following the SAME [EXTENDING_OBJECT] from [FRONT_END] to [BACK_END] - Dynamic [COMPOSITION_DIRECTION] composition with exaggerated perspective showing ONE continuous [EXTENDING_OBJECT] extending through entire frame creating sense of [MOTION_CHARACTERISTIC] - Seamless visual flow showing ONE SINGLE UNIFIED [EXTENDING_OBJECT]: [EXTENSION_DIRECTION_DESCRIPTION] - ALL PARTS OF THE SAME ONE [EXTENDING_OBJECT], NOT separate or duplicate [EXTENDING_OBJECT] - Smooth depth of field with natural foreground-to-background transition along the length of this SINGLE continuous [EXTENDING_OBJECT] - Clear visual leading lines following ONE [EXTENDING_OBJECT] creating strong unified depth within unified space - Balanced negative space with [SPATIAL_EMPHASIS_DIRECTION] emphasis suggesting [ACTION_CHARACTERISTIC] - Rule of thirds composition with emphasis on [CORE_FOCUS] - NO duplicate elements, NO multiple [EXTENDING_OBJECT], NO repeated objects - only ONE [EXTENDING_OBJECT], ONE [RELATED_OBJECT], ONE [MAIN_CHARACTER] COLOR PALETTE: - [COLOR_TONE_DESCRIPTION] color scheme with [PRIMARY_COLOR_1_AND_APPLICATION], [PRIMARY_COLOR_2_AND_APPLICATION], [PRIMARY_COLOR_3_AND_APPLICATION], [SECONDARY_COLOR_1_AND_APPLICATION], [SECONDARY_COLOR_2_AND_APPLICATION], [ACCENT_COLOR_AND_APPLICATION] - [SATURATION_CHARACTERISTIC] colors [COLOR_EMOTION_DESCRIPTION] - [COLOR_STYLE_POSITIONING] color harmony [APPLICATION_SCENARIO_DESCRIPTION] STYLE & TECHNIQUE: - Clean 2D flat vector illustration with minimalist approach - Simplified geometric character design and [ENVIRONMENT_ELEMENTS] - Crisp linework without heavy outlines - Flat color blocking with minimal gradients - Smooth depth transitions without layering artifacts showing ONE continuous [EXTENDING_OBJECT] - [SPECIAL_VISUAL_EFFECTS] integrated naturally - Strong perspective distortion on SINGLE [EXTENDING_OBJECT] length from foreground to background - Modern commercial illustration aesthetic similar to [REFERENCE_APPLICATION_SCENARIO] KEY ELEMENTS: - Complete [CHARACTER_TYPE] character in [CORE_ACTION_DESCRIPTION] in background [ACTION_DETAILS] - ONE SINGLE [EXTENDING_OBJECT] only: [FRONT_END_DESCRIPTION] in foreground, [MIDDLE_SECTION_DESCRIPTION] extending continuously through midground with dramatic foreshortening, [BACK_END_DESCRIPTION] in background - [RELATED_OBJECT] at/near the [POSITION] in foreground - Geometric [BACKGROUND_ENVIRONMENT] background with [ENVIRONMENT_DETAILS] - [DYNAMIC_EFFECT_ELEMENTS] suggesting [ACTION_CHARACTERISTIC] - Text "[SLOGAN_TEXT]" integrated along the [EXTENDING_OBJECT] trajectory with 3D perspective depth effect, bold modern typography - ALL elements are singular and unified - no duplicates MOOD & ATMOSPHERE: - [EMOTION_KEYWORD_1] and [EMOTION_KEYWORD_2] - Professional [FIELD_POSITIONING] quality [ATMOSPHERE_DESCRIPTION] - [SPECIAL_MOMENT_DESCRIPTION] - Dynamic EXTREME proportions emphasizing [EXAGGERATION_FOCUS] - Clean, polished, ready-for-publication finish with [ENERGY_CHARACTERISTIC] CRITICAL REQUIREMENTS: - Show ONLY ONE [EXTENDING_OBJECT] total in entire image - This single [EXTENDING_OBJECT] has [FRONT_END] in foreground, [MIDDLE_SECTION] in midground, [BACK_END] in background - NOT multiple [EXTENDING_OBJECT], NOT duplicate [EXTENDING_OBJECT], NOT separate [EXTENDING_OBJECT] pieces - ONE continuous unified [EXTENDING_OBJECT] object extending through perspective - ONE [RELATED_OBJECT] only at the [FRONT_END] - ONE [MAIN_CHARACTER] only in background - Avoid any visual duplication or repetition of elements - Each object appears exactly ONCE in the frame - Perspective makes the SAME [EXTENDING_OBJECT] look different sizes but it is still ONE [EXTENDING_OBJECT] - Maintain single continuous camera perspective throughout - Create STRONG depth progression with dramatic perspective FORESHORTENING along [EXTENDING_OBJECT] axis - All elements should feel part of one unified [ENVIRONMENT] environment - Ensure seamless integration of foreground and background within same spatial context

# Role: 时尚视觉艺术总监 & AI绘图指令大师 (Fashion Art Director & Prompt Engineer) ## 1. 任务目标 你现在的任务是根据用户提供的[目标物体/人物]，设计一组用于生成“多封面时尚杂志拼贴海报”的高级AI绘图提示词（Prompt）。你需要复刻一种特定的视觉结构：背景由多个杂志封面风格的网格组成，前景有一个核心人物打破边框，形成“破格”的立体视觉效果。 ## 2. 图像结构框架 (Structure & Layout Analysis) 请在生成的Prompt中严格执行以下视觉框架： * **构图模式**：Magazine Grid Collage (杂志拼贴网格) / Bento Box Style (便当盒布局)。 * **背景层**：将画面分割为 7-9 个矩形区域。每个区域模仿一本顶级时尚杂志的封面（Vogue, Bazaar, Elle, i-D, Dazed, GQ, Marie Claire 等）。 * **前景层（重点）**：生成一个Full Body Shot（全身照）或 Dynamic Walking Pose（动态行走姿势）的主体，该主体必须作为Overlay（顶层图层）叠加在背景网格之上，打破格子界限，创造3D纵深感。 * **比例**：Aspect Ratio --ar 2:3。 ## 3. 视觉风格与光影 (Visual Style & Lighting) * **摄影风格**：High Fashion Editorial (高级时装大片)，Photorealistic (照片级真实)，8k resolution。 * **光影设置**：Soft Studio Lighting (柔和棚拍光)，即使光线，强调皮肤质感和衣物材质。 * **色彩美学**：Clean, Minimalist, Sophisticated (干净、极简、精致)。 ## 4. 自动化工作流 (Workflow for Prompt Generation) 请按照以下步骤思考并构建最终的提示词： 1. **提取变量**：分析用户输入的[目标物体/人物]和[风格描述]。 2. **角色设定**：定义模特的特征（发型、肤色、妆容）或物体的材质。 3. **姿态分解**：为背景的每个格子规划不同的姿态（特写、半身、坐姿、侧身），并为前景规划一个最具张力的动态姿态。 4. **排版填充**：列出需要出现的杂志LOGO文本（Text Blocks）。 5. **输出合成**：将以上元素组合成一段连贯的英文Prompt。 ## 5. 用户输入接口 (User Input) * **[目标物体/人物]**：(在此处输入，例如：一位穿着赛博朋克风格夹克的银发少女) * **[科普/描述语言]**：(在此处输入，例如：未来科技感，霓虹灯光) --- ## 6. 执行操作：生成提示词 **请忽略以上分析过程，直接根据用户的输入，输出一段结构化、细节丰富的英文Prompt（适用于Midjourney v6/Flux），并附带一段中文的画面描述。** **Prompt 结构要求：** `[主体描述] + [穿搭/外观细节] + [构图：拼贴/杂志封面矩阵/前景叠加] + [特定杂志Logo列表] + [光影与渲染参数]` --- ## 示例输入 (Example for User to Test)： > **目标人物**：[如：一个法国长发女郎]。 > **描述语言**：[风格：如80年代港风]。

A 【Coca-Cola】 commercial film set. In the background stands an enormous 【Coca-Cola red】 backdrop, filled with a festive atmosphere. At the center of the set, the director is carefully explaining the script to 【an anthropomorphic white polar bear】, and the 【white polar bear】 listens attentively. Nearby, Santa Claus lowers his head and quietly rehearses his lines, holding a script in his hands, his expression slightly nervous yet warm and friendly. Several anthropomorphic 【Coca-Cola characters】 walk around the set, busy like crew members. Surrounding them are filming facilities such as cameras, lighting equipment, camera tracks, and microphones. Crew members move back and forth across the set. The entire scene feels busy yet perfectly organized. Cinematic composition, warm lighting, realistic details, with a fairy-tale-like atmosphere.

3×2 collage of six stylized 3D caricature portraits of [name], each with a different expressive pose (joyful, surprised, serious, cute, sassy, confident). Smooth polished look, soft ambient lighting, clean character design, and bold vibrant backgrounds for each panel.

# 图片复刻元提示词 (Image Reproduction Meta-Prompt) ## 1. 角色指定 (Role) 你是一位**资深人像摄影大师 (Senior Portrait Photographer)** 和 **光影构图专家**。你擅长捕捉日常生活中的自然瞬间（Candid Moments），精通室内布光与景深控制，能够完美复刻“男友视角”的社交媒体风格照片。 ## 2. 图片结构与框架 (Structure & Frame) * **画幅比例:** 9:16 (竖屏全画幅) * **构图模式:** 近景人像 (Medium Close-up)，人物占据画面前景左侧 60% 区域。 * **核心锚点:** * 前景：浅色木质圆桌边缘（切过画面左下角）。 * 中景：人物上半身，特别是面部和托腮的手臂。 * 背景：虚化的咖啡店柜台与人群。 * **文字处理:** 本图无UI文字框。需在画面中生成的自然文字为人物左臂衣袖上的 "alo" 品牌标签。 ## 3. 图片主题内容生成 Workflow **Step 1: 场景构建 (Scene Setup)** * 设定环境为现代繁忙的咖啡店内部。 * 天花板：裸露的工业风管道，安装有轨道射灯。 * 背景：远处有模糊的服务柜台（红色菜单板为特征）和排队的深色衣着路人。 **Step 2: 主体刻画 (Subject Definition)** * 生成一名[目标角色特征，默认为年轻亚洲女性]。 * 发型：棕色短发，空气刘海。 * 着装：穿着黑色半拉链立领Fleece材质卫衣，质感柔软厚实。 * **关键细节:** 左大臂处必须有一个清晰的黑色正方形补丁，上有白色 "alo" 字母Logo。 **Step 3: 姿态与神情 (Pose & Expression)** * 动作：身体向桌子前倾，重心下沉。左手手肘撑在桌面上，手掌托住脸颊/下巴。 * 视线：直视镜头，眼神清澈，带有一丝温柔或探究的笑意。 **Step 4: 摄影参数模拟 (Camera Parameters)** * 焦段：50mm 或 85mm 定焦镜头。 * 光圈：f/1.8 或 f/2.0 (制造背景虚化)。 * 光线：模拟室内顶光，面部受光均匀，带有轻微暖调。 ## 4. 图片整体描述 (Overall Description) * **风格:** 真实感摄影 (Photorealistic)，生活方式 (Lifestyle)，高清 (8k resolution)，Instagram 风格。 * **色彩:** 黑色(衣服)与暖木色(桌子)为前景主调，背景杂糅暖黄光与红色点缀。 * **纹理:** 重点表现卫衣的抓绒质感、头发的光泽感、木桌的纹理。 ## 5. 目标物体和语言输入框 (User Inputs) * **[目标角色特征]:** （可爱短发亚洲女性）- *默认为：可爱短发亚洲女性* * **[服装品牌细节]:** () - *默认为：alo 品牌 Logo* * **[环境氛围]:** (户外咖啡馆) - *默认为：星巴克风格咖啡店* --- **生成指令 (中文提示词参考):** 一张超写实的竖屏照片，视角略微俯视。画面主体是一位[目标角色特征]，她正坐在咖啡店的浅色圆木桌前。她穿着黑色的半拉链高领抓绒卫衣，左侧袖子上有一个清晰的 "[服装品牌细节]" 标签。她身体前倾，单手托腮，手肘撑在桌上，眼神温柔地看向镜头。背景是虚化的繁忙咖啡店，可以看到天花板的轨道灯、远处红色的菜单板和模糊的顾客。光线为温暖的室内顶光，肤色自然，发丝清晰，具有极高的摄影质感。

In the ultra-realistic 8K scene, the person in the photo walked out and broke the panel frame of a giant open Japanese version of the comic book called "｛就是玩AI}" lying on the floor of the aesthetic bedroom. The comic page depicts a surreal 4-panel Japanese version of the black-and-white comic, with screen tone, bold ink lines and authentic Japanese layout (read from right to left). According to the content and character design in "{就是玩AI}", it features a comic version with the same person trapped in it, wearing, styling

{ "scene_description": "A wide panoramic stage scene showing a lineup of multiple women kneeling or squatting in synchronized poses, viewed from behind, wearing coordinated but varied dance outfits under soft stage lighting.", "characters": [ { "name": "Unknown", "age": "Young adult", "gender": "Female", "ethnicity": "Unclear / mixed", "skin_tone": "Light to medium tones", "hair": { "style": "Long, straight or slightly wavy, worn loose", "color": "Dark brown to black" }, "clothing": { "head": "None", "torso": "Fitted crop tops, camisoles, or sports bras in black, white, or dark colors", "legs": "Short skirts, fitted shorts, or bodysuits", "feet": "High-heeled shoes", "materials": ["fabric", "spandex", "leather-like materials"] }, "pose": "Squatting or kneeling with knees bent, backs straight, facing away from the camera", "facial_expression": "Not visible (rear view)", "accessories": ["None visible"], "held_objects": [], "position_in_scene": "Foreground to midground, evenly spaced across the stage", "emotions": ["Neutral", "Focused", "Performance-ready"] } ], "environment": { "setting": "Indoor stage or performance hall", "background_elements": ["Plain backdrop", "Soft gradient lighting"], "architectural_features": ["Flat stage floor", "Open performance space"], "weather": "Not applicable", "lighting": { "type": "Artificial", "sources": ["Overhead stage lights"], "shadows": "Soft", "reflections": "Subtle reflections on the stage floor" }, "atmosphere": "Clean, controlled, professional performance environment" }, "objects": [ { "name": "Stage floor", "type": "Surface", "position": "Foreground and midground", "appearance": "Smooth, polished surface", "materials": ["Wood or laminate"], "interaction": "Yes, performers kneeling and balancing on it" } ], "logos_or_text": [ { "content": "Small watermark or logo in bottom right corner", "font_family": "Sans-serif", "font_style": "Regular", "font_size": "Small", "color": "# FFFFFF", "position": "Bottom right", "effects": ["None"] } ], "mood": "Stylized, synchronized, performance-focused", "dominant_colors": ["#000000", "# 2F2F2F", "# F 5F5F5", "#8 B5E3C"], "camera": { "perspective": "Third-person", "angle": "Eye-level", "position": "Directly behind the subjects", "focal_length": "Wide", "depth_of_field": "Deep, all subjects in focus", "composition": "Symmetry and repetition across the frame" } }

{ "subject": { "demographics": "Young female, approx 20-24 years old, Caucasian.", "hair": { "color": "Dirty blonde to light blonde gradient.", "style": "Long, straight with slight wave, layered, casual parting.", "texture": "Soft, natural strands, slightly tousled, roots visible.", "movement": "Falling naturally over shoulders and back." }, "face": { "shape": "Oval with soft jawline.", "eyes": "Almond-shaped, light blue/grey irises, distinct sharp black winged eyeliner.", "nose": "Button nose, soft bridge.", "lips": "Full, plump, rosy pink, slightly parted in a pouty expression.", "skin_details": "Prominent, heavy freckles across nose and cheeks. Smooth texture but with realistic skin grain. Natural blush.", "micro_details": "Mole on right upper chest, mole on left shoulder." }, "body_proportions": { "build": "Voluminous, curvy, heavy bust.", "chest": "Large bust volume, prominent forward projection, deep cleavage visible.", "waist_to_chest_ratio": "Significantly wider chest width compared to waist implies hourglass figure.", "shoulders": "Soft, rounded, natural slope.", "dominance": "Upper torso volume visually dominates the frame." }, "clothing": { "top": "Heather grey ribbed knit tank top/camisole.", "fit": "Tight, form-fitting, stretching over chest volume, low scoop neckline.", "straps": "Thick straps, sitting securely on shoulders." }, "accessories": { "jewelry": { "Small gold hoop earrings.", "Gold chain necklace with a small 'G' letter pendant.", "Longer thin gold chain with a distinct kangaroo pendant." } } }, "pose": { "type": "Handheld selfie perspective.", "orientation": "Frontal close-up, slightly angled from above.", "head_position": "Tilted slightly to subject's right.", "limbs": "Right arm extended forward (out of frame) indicating holding the camera.", "gaze": "Direct eye contact with lens, alluring and confident.", "spine_curvature": "Slight arch implied by chest prominence." }, "setting": { "environment": "Domestic bathroom.", "background_elements": "Dark brown/grey glossy tiled wall, chrome shower fixture visible on left, top of white ceramic toilet tank visible on right.", "depth": "Shallow depth of field, background elements slightly out of focus." }, "camera": { "shot_type": "Close-up, selfie portrait.", "angle": "High angle (slightly above eye level), typical of smartphone selfies.", "focal_length": "24mm to 28mm equivalent (wide angle smartphone lens).", "framing": "Chest-up shot, cropping at mid-torso.", "focus": "Sharp focus on eyes and face, slight fall-off on shoulders.", "perspective": "Slight foreshortening of the extended arm side." }, "lighting": { "source": "Soft, diffused overhead ambient bathroom lighting.", "direction": "Front-top lighting.", "highlights": "Soft specular highlights on forehead, tip of nose, chin, and upper chest curves.", "shadows": "Soft shadows under the chin and defining the cleavage depth.", "quality": "Natural, flattering, no harsh contrast." }, "mood_and_expression": { "tone": "Casual, sultry, confident.", "expression": "Relaxed pout, 'cool girl' aesthetic.", "atmosphere": "Intimate, candid." }, "style_and_realism": { "style": "Photorealistic, social media aesthetic.", "fidelity": "High fidelity skin texture, no airbrushing.", "imperfections": "Visible freckles, stray hairs, natural skin variation preserved." }, "colors_and_tone": { "palette": "Neutral tones (grey, beige, skin tones) with pops of blue (eyes) and gold (jewelry).", "skin_tone": "Fair to light tan, warm undertones.", "white_balance": "Slightly warm, indoor tungsten mix.", "saturation": "Natural, slightly vibrant lips and eyes.", "contrast": "Medium contrast." }, "technical_details": { "aspect_ratio": "3:4", "resolution": "High resolution, sharp details.", "noise": "Slight digital noise characteristic of phone camera sensors in indoor light." } }

{ "meta_info": { "title": "Ethereal Hanfu Spirit", "style_category": "Chinese Fantasy / Abstract Digital Art", "aspect_ratio": "3:1" }, "visual_elements": { "subject": { "description": "Silhouette wearing attire determined by the character", "pose": "Pose determined by the character, floating in mid-air", "composition": "Centered ethereal figure with flowing trails extending to the sides" }, "atmosphere": { "lighting": "Bioluminescent glow, volumetric lighting, rim lighting", "effects": "Flowing smoke, light particles, holographic dispersion, silk-like energy trails", "colors": ["Deep Navy Blue", "Glowing Cyan", "Iridescent Gold", "Soft Peach"] } }, "prompt_export": { "natural_language_prompt": "A wide panoramic digital artwork depicting a figure composed of flowing ribbons of light, translucent smoke, and iridescent particles. The background features deep, moody indigo and dark blue tones. The figure emits a soft, magical bioluminescent glow in hues of gold, peach, and cyan. The overall style is abstract fantasy, emphasizing fluid motion and a dreamy atmosphere, rendered in 8K resolution with highly detailed textures and exhibiting the Tyndall effect.", "tag_based_prompt": " silhouette, flowing light lines, smoke effects, particle effects, bioluminescence, iridescent effects, dark blue background, cinematic lighting, ethereal, mystical, masterpiece, best quality, 8k, wide angle --ay 21:9 ", "negative_prompt": "photorealistic, solid skin, heavy outlines, messy lines, text, watermark, low quality, jpeg artifacts, blurry, distorted face, bad anatomy" }, "technical_settings_recommendation": { "sampler": "Euler a / DPM++ 2M Karras", "steps": 30, "cfg_scale": 7.0, "model_suggestion": "Niji 6 (for Midjourney) or Abstract/Fantasy-based SDXL models" } } 角色设为： 西游记师徒四人

{ "Objective": "Create an ultra-realistic 8K candid street portrait capturing quiet emotion and authenticity within a crowded urban environment.", "Subject": { "Gender": "Female", "Appearance": { "Hair": "Short blonde hair with soft, natural texture", "Makeup": "Minimal, natural look", "Skin": { "Texture": "Realistic skin texture with subtle freckles", "Highlights": "Soft natural highlights with gentle tonal transitions" }, "Expression": "Calm, thoughtful, introspective", "Gaze": "Looking slightly to the side, not directly at the camera" }, "Wardrobe": { "Top": "Simple grey knitted sweater with visible fabric weave", "Bottom": "Casual jeans", "Accessories": "Thin shoulder-bag strap visible across the shoulder" } }, "Scene_Description": { "Setting": "Busy city street", "Crowd": { "Density": "Surrounded by a dense flow of pedestrians", "Background_Treatment": "Softly blurred figures creating depth and motion" }, "Environment": "Urban street atmosphere with natural movement" }, "Lighting_and_Color": { "Lighting": { "Type": "Natural daylight", "Quality": "Soft and even, without harsh shadows" }, "Color_Grading": { "Style": "Warm cinematic tones", "Characteristics": [ "Natural skin tones", "Muted urban background colors", "Subtle film-inspired contrast" ] } }, "Camera_and_Composition": { "Shot_Type": "Candid street portrait", "Depth_of_Field": "Shallow depth of field isolating the subject", "Focus": "Sharp focus on the subject with background crowd softly blurred", "Angle": "Eye-level, unobtrusive framing" }, "Visual_Style": { "Resolution": "Ultra-realistic 8K", "Aesthetic": "Documentary street photography", "Detail_Characteristics": [ "Sharp facial detail", "Natural fabric texture", "Soft motion blur in background", "Subtle film grain for realism" ] }, "Mood_and_Storytelling": { "Themes": [ "Stillness within chaos", "Quiet reflection", "Human presence in urban life" ], "Atmosphere": "Emotional, authentic, understated realism" }, "Output_Requirements": { "Format": "Image", "Orientation": "Portrait or cinematic street frame", "Quality": "Professional documentary-grade realism" } }

Crea una ilustración de cómic moderno usando mi imagen de referencia como personaje principal. Estilo inspirado en los cómics de superhéroes contemporáneos y novelas gráficas cinematográficas. El personaje mantiene los rasgos faciales exactos y su identidad de la foto de referencia, transformados en un estilo cómic estilizado con líneas limpias pero expresivas. Añade contornos negros marcados, sombreado dinámico con tinta y colores de alto contraste. Aplica efectos FX como energía brillante, chispas, estelas de movimiento, haces de luz y partículas sutiles para aumentar la acción y la intensidad. Usa una pose de acción dinámica o una postura poderosa, con perspectiva exagerada y ángulos dramáticos. El fondo debe ser gráfico y cinematográfico: formas urbanas abstractas, líneas de velocidad o explosiones de energía, sin distraer del personaje. La iluminación es dramática, con luces y sombras fuertes para dar profundidad e impacto. Estilo final: portada de cómic moderno de alta calidad, detalles nítidos, colores vibrantes, composición enérgica, ilustración profesional, impacto visual fuerte. No cambies el rostro, solo estilízalo.

环境： 【角色特征]:高中女生，留着黑色长发 【时尚主题]:现代高中女生日常穿着，整洁干净】 转换规则： - 一张时尚造型图，展示了[Character Features]中的七个相同的角色并排站成一排。 - 仅穿着 7 套基于【时尚主题】的全新休闲服装。 - 参考图像的风格得到了完美保留。 - 他们不穿[参考图片中的服装]，而是根据[时尚主题]穿七套不同的服装。 全身照。 - 背景为纯白色或略带象牙色。 脚下有自然的阴影。这幅图的布局看起来像是从杂志上剪下来的。 - 每个图形下方从左到右分别写着“星期一”、“星期二”、“星期三”、“星期四”、“星期五”、“星期六”和“星期日”。 - 顶部醒目的标题文字。 艺术风格： - 高分辨率 - 摄影棚灯光 - 4k ——ar 16:9

一个温馨的3D C4D Octane渲染场景，采用无黑色轮廓的羊毛针毡风格，具有盲盒玩具的柔和边缘审美。四只不同大小的粉彩（薄荷绿、嫩粉、淡蓝、奶油色）羊毛毡Labubu角色，身穿针织毛衣，有着标志性的圆润身体、兔耳和大眼睛，表情喜悦。它们围坐在铺着针织桌布的矮桌旁，桌上摆满热气腾腾的饺子、茶壶和餐具。一个角色正用筷子亲昵地喂另一个角色吃饺子。地面覆盖着羊毛雪和散落的心形装饰。左侧是挂着灯笼的盛开梅花枝，右侧是祥云图案。发光的羊毛心形在空中漂浮。背景是温暖的橙黄色渐变，营造出冬至家庭团聚的节日氛围。顶部是巨大、发光、毛绒质感的艺术字体“饺饺情深，岁岁安康”。中间是清晰简单的祝福语：“愿家人健康快乐，幸福安康！”。8K分辨率，高细节，暖光摄影棚照明，垂直2:3比例。

{ "variables": { "CITY_NAME": "Chengdu" }, "image_specs": { "aspect_ratio": "4:5", "resolution": "2048x2560", "quality": "ultra", "style_strength": 0.8, "detail_level": "high", "sharpen": "medium" }, "prompt": { "master_visual_brief": "A high-energy Y2K-inspired editorial collage poster with a strong paper-cut and magazine print aesthetic. The entire image has a tactile paper texture with visible cut edges and layered depth. The theme centers around the city {{CITY_NAME}}. All visual elements, including background imagery, stickers, symbols, typography, and graphic decorations, are culturally and visually inspired by {{CITY_NAME}}. The composition follows a fashion magazine cover logic with dense but controlled information, playful energy, and strong visual hierarchy. The character is designed as a dominant half-body portrait occupying most of the poster.", "photography_and_character": "Character: a randomly generated young woman aged approximately 18–25. She is fashionable, attractive, and trendy, with no fixed hairstyle, hair color, facial features, or makeup. Her appearance varies naturally but always remains stylish and visually appealing. Fashion style is Y2K-inspired street fashion with playful silhouettes, layered styling, and trendy colors. Framing is a strict half-body portrait: the image is cropped at the waist or slightly above, and the lower body is not visible at all. Only the upper torso, shoulders, neck, and head are shown. Pose and gesture: the character performs a randomly selected Y2K-style dynamic pose with strong tension and attitude, including expressive arm extensions, angular elbow bends, asymmetrical shoulder twists, or forward-reaching gestures. Body language remains bold, confident, and energetic. Facial expression: the expression is slightly playful and friendly, with a hint of cuteness layered on top of confidence. Subtle smiles, softly open lips, bright eyes, or a relaxed playful look are allowed, while the overall attitude remains fashion-forward and dynamic rather than cute-only.", "camera_and_lighting": "Editorial portrait framing with a wide-angle look at close distance, optimized for half-body composition. The camera captures only the upper torso and head, with the lower body fully cropped out of frame. Perspective supports dynamic Y2K poses without distorting facial proportions. Lighting is soft, even, and magazine-style, avoiding harsh shadows. The subject is intended to be cut out and integrated into a paper collage rather than rendered as pure realism.", "graphic_design_layout": "Center-focused editorial collage layout. At the top, the city name '{{CITY_NAME}}' appears as the main headline in bold uppercase geometric sans-serif letters. Each letter is placed on an individual colored paper rectangle and arranged in a slight arc. The large half-body character overlaps and partially covers the headline and nearby graphic elements, creating a break-the-frame effect. Surrounding the character are floating paper stickers, speech bubbles, and cut-out graphics inspired by {{CITY_NAME}} culture, including local food, landmarks, symbols, street signs, and iconic objects. The bottom section features a full-width magazine-style collage footer composed of layered paper strips, bold button-style typography, small editorial text blocks, and thumbnail-style graphics.", "background_system": "The background is a black-and-white or desaturated urban street scene from {{CITY_NAME}}, such as crowds, architecture, or city textures. Background contrast is reduced and softened with grain so it supports the composition without competing with the main subject. The background is partially obscured by the large half-body character and collage elements and maintains a printed-paper appearance rather than photographic realism.", "materials_and_textures": "A consistent paper-based aesthetic across the entire image. Visible paper grain, halftone dots, print noise, and slight ink bleed. All elements appear as physical paper cut-outs layered together. Edges are imperfect and tactile. Stickers, typography, and characters cast subtle shadows to suggest layered depth. No glossy, metallic, or digital materials are present.", "composition_and_balance": "Clear and stable visual hierarchy: top city headline '{{CITY_NAME}}', central half-body character (upper torso only), dynamic Y2K-style pose with slightly playful facial expression, surrounding city-themed stickers, and bottom magazine-style collage footer. Strong overlaps between character, typography, and stickers create depth while preserving the established layout." }, "constraints": { "must_include": \[ "City name headline using {{CITY_NAME}}", "Strict half-body portrait (waist-up only)", "Lower body completely cropped out", "Y2K-style dynamic pose with strong tension", "Playful but controlled facial expression", "Paper collage and cut-out magazine aesthetic", "City-specific background and stickers related to {{CITY_NAME}}", "Full-width magazine-style collage footer", "Visible paper texture and layered depth" \], "must_avoid": \[ "Full-body view", "Visible legs, knees, thighs, or feet", "Neutral or stiff poses", "Overly cute or childish expressions", "Sexualized expressions or gestures", "Grotesque facial distortion", "Minimalist or empty layouts", "Glossy digital or 3D materials" \] }, "negative_prompt": "full body, legs visible, knees, thighs, feet, stiff pose, neutral posture, childish expression, exaggerated cute face, sexualized expression, blurry face, deformed hands, extra fingers, bad anatomy, grotesque distortion, minimalist layout, flat image, hyper-realistic photography, glossy surfaces, plastic skin, dull colors, watermark, logo, unreadable text", "typography_rules": { "headline": { "text": "{{CITY_NAME}}", "font_style": "bold geometric sans-serif, uppercase", "treatment": "each letter on a separate colored paper rectangle, slightly arched, subtle shadow", "material": "printed paper cut-out" }, "supporting_text": { "style": "editorial magazine blocks, playful sticker captions, speech bubbles", "material": "paper-based printed texture" } }, "rendering_notes": { "depth_layers": "background city paper layer -> mid-ground half-body character -> foreground dynamic pose, expressive face, stickers, and typography", "print_feel": "strong magazine print texture with halftone dots, paper grain, and slight ink bleed", "edge_treatment": "clearly visible imperfect cut paper edges" } }

[BRAND NAME]: A high-end, glossy concept art magazine editorial photograph of a unique, unexpected functional object conceptualized and designed by the brand. **1. The Concept & Object (AI Invention):** Based on the design philosophy, heritage, and material vocabulary of the specified brand, the AI must invent a novel utility product (NOT standard clothing, shoes, or bags). Examples could be home goods, tech accessories, tools, or sporting equipment, reinterpretated through the brand's lens. The object should feel sculptural yet functional. **2. Materials & Details (Hyper-Premium):** The object is constructed from ultra-premium, highly tactile materials characteristic of the brand (e.g., patinated exotic leathers, brushed aerospace-grade titanium, sculpted matte ceramics, molded carbon fiber, or technical high-fashion textiles). Every detail is hyper-realistic: visible stitching, microscopic material grain, precision engravings, and complex texture contrasts. **3. Photography & Lighting (Cinematic Studio):** Shot on a medium format Phase One camera with a 100mm macro lens. Extremely shallow depth of field, with sharp focus on the hero details of the object and a creamy, smooth bokeh background. The lighting is sophisticated studio softbox lighting: gentle, enveloping fill light with precise rim lighting to accentuate contours and material textures. **4. Environment:** A seamless, impeccably clean studio cyclorama background in a pure, ultra-light pastel tone (e.g., desaturated mint, pale blush, or off-white), free of shadows. **5. Layout & UI Elements (Strict Placement):** - **Bottom Right Corner:** A small, understated, monochrome gray logo of the brand. - **Bottom Left Corner:** Small, minimalist monochrome gray text describing the invented product. The font style looks like Manrope Regular with very tight tracking (kerning) and balanced line spacing. Example format: "CONCEPT STUDY: [AI inserts invented product name]. MATERIAL: [AI inserts main materials]. SS25."

[ { "concept_id": "iron_man_coke", "visual_breakdown": { "focus_object": "Coca-Cola Can", "character_element": "Iron Man's Gauntlet", "environment": "Blurred City Skyline" }, "artistic_direction": { "lighting": "Cinematic/Metallic", "mood": "technological" }, "generation_command": { "aspect_ratio": "7:9", "concise_prompt": "Iron Man's gauntlet hovering below a floating Coca-Cola can, cinematic city background, dramatic movie poster lighting. --ar 7:9" } }, { "concept_id": "hulk_pepsi", "visual_breakdown": { "focus_object": "Crushed Pepsi Can", "character_element": "Hulk's Giant Hand", "environment": "Smoky City Ruins" }, "artistic_direction": { "lighting": "Explosive/High Contrast", "mood": "destructive" }, "generation_command": { "aspect_ratio": "7:9", "concise_prompt": "Hulk's giant hand hovering over a crushed Pepsi can embedded in pavement, smoky ruins, explosive action movie style. --ar 7:9" } }, { "concept_id": "thor_sprite", "visual_breakdown": { "focus_object": "Sprite Bottle", "character_element": "Thor's Glowing Hand", "environment": "Storm/Lightning" }, "artistic_direction": { "lighting": "Electric/Blue-Toned", "mood": "mythological" }, "generation_command": { "aspect_ratio": "7:9", "concise_prompt": "Thor's glowing hand holding a floating Sprite bottle amidst crackling lightning and rain, Mjolnir in background, epic poster style. --ar 7:9" } }, { "concept_id": "dr_strange_fanta", "visual_breakdown": { "focus_object": "Fanta Bottle", "character_element": "Doctor Strange's Hand", "environment": "Golden Magic Portal" }, "artistic_direction": { "lighting": "Magical/Golden Bokeh", "mood": "mystical" }, "generation_command": { "aspect_ratio": "7:9", "concise_prompt": "Doctor Strange casting a spell under a spinning Fanta bottle inside a golden magic portal, mystical Sanctum background, cinematic lighting. --ar 7:9" } } ]

A young man sitting casually at a modern café counter, smiling while holding a glass of iced coffee. On the table in front of him stands a small 3D chibi character version of the same man. The chibi has super-deformed proportions, a large head, big expressive eyes, and simplified facial features. It has a smooth 3D plastic or clay-like texture, soft studio lighting, and a clear shadow on the table surface. The chibi is holding a tiny glass of coffee. Warm pendant lights, wooden café interior, cinematic realistic human combined with stylized 3D chibi, shallow depth of field, vertical 9:16.

do this for Messi: <instruction> Relic-Loadout Kit Input A is a fictional or real character (image/name) OR story IP (poster/name). Analyze and infer: character archetype, iconic scene, signature items, and moral arc. Goal: Premium collector kit box with compartments (no logos; minimal text). Rules: Center compartment: mini figurine. Surround 10–16 relic props that teach the character arc (before/after item, symbol of sacrifice, tool of choice). Add a tiny “arc timeline” strip with 5 beats (icons + 1–2 words max each). Output: one image, 4:5 product hero shot. </instruction>

(Surrealism, fantasy art, macro photography style). A magical composition where the specific character is captured inside a giant, life-sized glass snow globe. [CRITICAL: Keep the face identical to the source image, maintain consistent facial features within the glass distortion]. Inside the Globe: The character is wearing a white faux fur winter coat and a red Santa hat, catching falling snowflakes with her hands. The environment inside includes miniature snow-covered pine trees decorated with colorful Christmas lights twinkling in red, green, blue, and gold. A tiny wooden cabin sits among the trees. Swirling magical glitter and snow dust fill the air inside the sphere. Outside the Globe: The background is a blurry, cozy living room with a fireplace, emphasizing that the character is inside the ornament. Lighting: The snow globe is glowing from within, illuminated by the warm colorful glow of the Christmas tree lights mixing with cool magical blue and white light on the falling snow. The character's face is beautifully lit by this magical mixed lighting. External warm light reflects off the curved glass surface, creating rainbow prismatic effects. Technical: Ray tracing reflections on the glass, refraction effects, crystal clear focus on the character, magical atmosphere, ethereal and dreamy aesthetic, 8k resolution, intricate details of the snowflakes and Christmas lights bokeh.

(Masterpiece, top quality, ultra-detailed, 8k resolution). A photorealistic 4-panel split screen grid collage featuring the same specific female character in all panels. [CRITICAL: Maintain exact facial features, preserve original face structure, consistent character reference throughout all panels]. The character has a fair complexion, natural skin texture, and bright eyes. Panel 1 (Top Left): The character is winking playfully, wearing plush reindeer antlers, holding a candy cane near her cheek, joyful expression.Panel 2 (Top Right): The character is wearing a red Santa hat with white fur trim, looking surprised with hands covering her mouth, eyes wide open.Panel 3 (Bottom Left): The character is blowing a kiss, holding a small wrapped gift box with a gold ribbon, wearing a cozy oversized white knitted sweater.Panel 4 (Bottom Right): The character is giving a soft smile, eyes full of affectionate gaze, wearing a Christmas reindeer accessory around her neck, dressed in a red velvet Christmas dress with white fur trim, wearing red fluffy Christmas gloves, forming a heart shape with both hands beside her cheeks. Environment: Solid studio background in soft pastel red or green.Lighting: Bright, high-key studio lighting, ring light reflection in eyes, soft shadows, uniform illumination.Style: Korean photobooth style, vibrant colors, sharp focus, cute and energetic atmosphere, commercial photography aesthetic.