Исследуйте
Промпты

A simple black-and-white illustration of a [subject] in [outfit], [doing action], with a [facial expression] expression, in a Notion-style minimalist editorial aesthetic, clean line art, flat monochrome design, simple shapes, subtle hand-drawn feel, minimal detail, expressive posture, clean white background, neat modern layout, soft playful character style

[BRAND NAME] | [HEADLINE] | [SUB-TEXT] | [CTA]. Act as a Senior Art Director. PHASE 1: INTEGRATED COMPOSITION & OVERLAP. - Layout: Seamless fusion of 2D graphics and 3D photography. - Overlap Logic: The subject and their primary "Product Prop" (e.g., a car, a device) must physically overlap the graphic panel to break the "wall" between design and photo. - Unity: Geometric shapes from the graphic side must bleed into the photographic sky area. PHASE 2: BRAND & CATEGORY SIMULATION. Autonomously analyze the [BRAND NAME] and its industry category: - INDUSTRY CONTEXT: * If Automotive: Include the vehicle and a person interacting with it. * If Tech: Include flagship devices/gadgets. * If Fashion/Lifestyle: Focus on editorial poses and premium accessories. - SHAPE SIMULATION: Match shapes to brand identity (e.g., Sharp/Speed for Auto, Minimalist/Grid for Tech). - COLOR SIMULATION: Use the brand's primary signature hue for both the graphic pattern and the subject's outfit/accents. PHASE 3: TYPOGRAPHY & CUSTOM CONTENT. - Headline: Display "[HEADLINE]" in a bold, modern Sans-Serif font. (If [HEADLINE] is empty, generate a high-energy slogan for [BRAND NAME]). - Sub-headline: Display "[SUB-TEXT]" below the headline. - Button: Create a minimalist pill-shaped CTA button with the text: "[CTA]". - Interaction: Text layers should have 3D depth, sitting partially behind the subject or product prop. PHASE 4: PHOTOGRAPHY & SUBJECT. - Perspective: Extreme low-angle (worm’s eye view) looking up. - Subject: A diverse persona reflecting the brand's audience. - Environment: Massive, clear blue sky as the backdrop. - Visual Link: Subject's styling must incorporate the Brand's primary color. PHASE 5: FINAL VISUAL STYLE. High-end commercial aesthetic. Crisp, saturated, professional fusion of flat vector art and realistic photography.

Luxury extreme close-up portrait, magazine cover style, title "SIGHT", featuring an elegant asian woman with calm and powerful gaze, extreme close-up framing, face fills the frame, focus on eyes and skin texture, slightly cropped composition for tension, ultra realistic skin texture, visible pores, natural glow, sharp eyes with catchlight, subtle glossy lips, cinematic beauty lighting, soft diffused key light, controlled highlights, soft shadows, dark background, black and gold tone, cinematic luxury mood, minimal styling, clean high-fashion makeup, elegant serif typography, modern magazine layout, macro lens detail, shallow depth of field, photorealistic, ultra high resolution, glossy finish, 8k --ar 2:3 --v 6 --style raw ---

生成一张《纸上成真 · 神话绮装》风格图片，4:5 竖版。 画面是高级东方神话高定服饰设定稿：米白色手稿纸夹在木质画板上，放在温暖木色设计工作台。桌面有布料小样、配色色卡、铅笔、针管笔、陶瓷茶杯、玉饰、金属配件和小型服饰结构草图。 主体是一位成年中国神话女性人物[Character Name]，从纸面服饰设定稿中苏醒。人物非常写实，像真实人物摄影，皮肤白皙自然，有真实皮肤纹理，不要动漫感、硅胶感、塑料皮肤。 人物眼神要和画面有互动，可以看向镜头、看向创作者，或看向右下角正在绘制的铅笔区域。上半身必须明显从纸面立起来，有真实体积、空间高度 and 自然投影，一只手轻撑纸面，形成“纸上成真”的错觉。 人物比例修长但自然，约 7–7.5 头身，上半身清楚可见，胸腔、腰部、胯部和腿部比例协调。腿部偏写实呈现，修长自然，不要小腿过粗，不要下半身过短或过长。 服饰为东方神话高定风格，主色调为[Color Palette]。服装要有连续统一的颜色层次，不要斑驳杂乱。 从上到下呈现：写实人物与服装主体 → 腿部和中段裙装偏写实 → 裙角、披帛尾端、飘带末端逐渐变成淡彩手绘 → 右下角铅笔正在画的区域保留未完成铅笔素描。 纸面加入少量手稿标注：LOOK 01、silhouette、ribbon flow、skirt movement、ornament detail，也可加入中文：裙摆走势、发饰位置、披帛结构、金饰位置。 真实摄影感，高级东方审美，神话人物高定设定稿，纸张纹理清晰，阴影真实，构图干净。避免卡通、动漫脸、硅胶皮肤、文字乱码、人体比例错误、上半身太小、腿部畸形、全身过度手绘、颜色斑驳、低清晰度。

一张高分辨率的3x3网格照片拼贴，包含九个不同的动态姿势，以上传的女性面部照片为参考，背景是充满活力的蔚蓝天空，点缀着朵朵白云，强烈的明暗自然阳光照射下，形成清晰的阴影。人物身穿针织衫，搭配一条裙子，并佩戴一条纤细的银项链。摄影运用了多种焦距，从35mm广角全身镜头到85mm特写人像镜头，画面切换自如。姿势丰富多样，包括：双腿分开、双手抱头的有力姿势；手掌直指镜头的透视效果；透过一只眼睛上方“OK”手势的俏皮特写；双手托腮的欢快中景；以及用手遮住半张脸的忧郁姿势。图像质量高达 8K 分辨率，呈现出超逼真的效果，展现了细腻的肌肤纹理、次表面散射、逼真的衣物褶皱以及根根分明的发丝，呈现出高端商业时尚画册或生活方式宣传片的精致美感。

Dark Bedroom Hosiery Editorial, vertical 9:16. Create a realistic fashion editorial portrait of an adult female model seated on the bed, not on the bed edge. Grey bedding, white pillows, soft wrinkled sheets, low-saturation cool grey tones, soft window light. Consistent composition: model placed slightly to the right, body forming a natural diagonal line, legs as the main visual focus, clean bedding space on the left. She looks slightly downward, one hand gently adjusting her hair, the other hand resting naturally. Calm, elegant, unforced pose, no direct eye contact. All-black styling: black top, black hosiery, black closed-toe heels. Hosiery direction: [Hosiery Style]. The hosiery should look realistic: medium-black tone, subtle transparency, smooth texture, soft light reflection, natural stretch and elegant leg shaping. Shoes must fully cover the toes. Feet and ankles should look natural, elongated and relaxed. Avoid twisted ankles, floating feet, exposed toes or broken shoe structure. High clarity, realistic skin texture, clear facial features, clear hands, clear hosiery details, clear shoe structure, detailed bedding folds. Avoid low resolution, blurry subject, plastic skin, distorted hands, twisted feet, messy hosiery pattern, unrealistic body proportions, cartoon or illustration style.

Create a branded technical infographic of a [SNACK], combining a realistic photograph or photoreal render of the product with technical annotation overlays placed directly on top. Use black ink–style line drawings with strategic [BRAND COLOR] accents (architectural sketch look) on a pure white studio background, including: • Key component labels • Internal cross-section showing structure, layering, or internal design • Measurements, dimensions, and specifications • Material callouts with composition and quantities • Arrows indicating function for primary features and structural integrity • Simple schematic or sectional diagram showing key mechanical or design elements • Sustainability callouts Title placement: Inside a hand-drawn technical annotation box with accent border reading the product name in bold font, positioned in upper corner. Style & layout rules: • The realistic product remains clearly visible • Annotations feel sketched, technical, and architectural • Accents used for highlight (20-30% of linework), black for primary technical lines (70-80%) • Clean composition with balanced negative space • Educational, food-engineering vibe with premium branding • Include subtle brand logo mark in corner Visual style: Minimal technical illustration aesthetic, black linework with accents over realistic imagery, precise but slightly hand-drawn feel. Color palette: White background, black annotation lines/text, [BRAND COLOR] for accents and key callouts only. Output: 1080×1080, ultra-crisp, social-feed optimized, no watermark

{ "objective": "Create a split architectural visualization where the top is a detailed dark-themed blueprint and the bottom is a photorealistic house that matches the blueprint EXACTLY", "aspect_ratio": "3:4", "composition": { "layout": "vertical split", "top_section": "blueprint", "bottom_section": "realistic render", "alignment": "perfect structural correspondence between both sections" }, "top_section": { "type": "architectural blueprint", "style": "dark luxury blueprint (similar to reference image 2)", "visual_style": { "background": "deep navy / charcoal blue", "lines": "thin glowing beige/gold lines", "walls": "slightly extruded 3D effect", "labels": "clean modern sans-serif", "lighting": "soft ambient glow" }, "content": { "rooms": [ "3 bedrooms (left, right, bottom-right)", "central living room", "kitchen + dining (top center)", "2 bathrooms", "garage (left side connected)", "front porch", "backyard pool with deck" ], "details": [ "furniture outlines (beds, sofa, dining table)", "door swings and openings", "window placements", "circulation paths", "exact proportions and spacing" ] } }, "bottom_section": { "type": "photorealistic house render", "constraint": "MUST MATCH THE BLUEPRINT EXACTLY — no added, removed, or shifted rooms", "architecture": { "style": "modern single-story house", "roof": "flat layered roof", "materials": [ "smooth concrete walls", "wood panel accents", "large glass windows" ] }, "layout_mapping_rules": [ "garage must be on the left side exactly as blueprint", "main entrance aligned with living room", "pool positioned in backyard matching blueprint dimensions", "window placements correspond to each room location", "bedroom volumes visible externally in correct positions" ], "environment": { "setting": "suburban neighborhood", "elements": [ "green lawn", "minimal landscaping", "clean driveway leading to garage", "pool deck matching blueprint footprint" ] }, "lighting": { "time": "golden hour", "style": "soft natural light with realistic shadows" }, "camera": { "angle": "slightly elevated front perspective", "lens": "35mm architectural view" } }, "consistency_rules": [ "room positions must be identical between blueprint and render", "no extra structures added in render", "all doors and windows must align logically", "pool size and placement must match exactly", "garage placement must match blueprint" ], "style": { "top": "architectural visualization (dark premium)", "bottom": "photorealistic modern house", "overall": "clean, high-end architectural presentation" }, "negative_constraints": [ "no mismatch between blueprint and render", "no extra rooms", "no fantasy elements", "no unrealistic proportions", "no cluttered environment" ] }

[BRAND NAME]. Act as a Senior Editorial Designer and Typographer. PHASE 1: TYPOGRAPHIC MASK (THE "WINDOW" EFFECT). - Core Element: Use the most iconic slogan or the name of [BRAND NAME] as a massive, ultra-bold, heavy sans-serif typographic mask. - Layout: The letters must be giant, filling the entire vertical frame from edge to edge with tight kerning. - Concept: The text acts as a "cut-out" window. The background is solid white, and the photographic subject is visible ONLY through the letterforms. PHASE 2: DYNAMIC SUBJECT LOGIC. - Subject Selection: - Detail: Ensure a high-contrast element (like a red shoe or a glowing headlight) is visible through one of the letters as a focal point. PHASE 3: SOPHISTICATED MUTED PALETTE. - Atmosphere: Use a "Refined Muted" color scheme. - Tones: Soft slate blues, charcoal greys, and creamy off-whites for the photography inside the mask. - Accent: Identify one sharp, saturated accent color belonging to [BRAND NAME] and apply it to a single key object visible through the text. PHASE 4: PHOTOGRAPHY & LIGHTING. - Lighting: Soft-box studio lighting. Diffused shadows and gentle highlights to create a cinematic, high-end editorial feel. - Finish: Clean, matte texture with zero visual noise. High-definition photographic quality. PHASE 5: MINIMALIST BRANDING. - Accents: Add a tiny minimalist logo and a small vertical tagline in a clean, microscopic sans-serif font near the corners. - Year: Include the year "2026" in a subtle, elegant font to mimic a limited-edition look.

(cobalt blue knit swimsuit), bikini, (multi-harness bikini:1.2), (blue harness-like swimwear construction:1.2), choker with halter neck harness strap, diagonal chest strap, wraparound waist straps, non-matching strap tension, fashion experimental swimwear, (tube top)

高端日系时装杂志封面感插画，主体为[韩国女孩]，极简现代时装数字插画风，精致赛璐璐上色，干净锐利的大色块塑形，几乎无线稿，边缘优雅清晰。画面保持蓝白骨架配色，同时加入少量珊瑚红、雾紫、浅黄、灰粉、鼠尾草绿、银灰等辅助色，整体仍然简约、高级、统一，不花哨。背景干净，可为钴蓝、皇家蓝、雾蓝等纯净大色块，并保留大面积负空间。强烈阳光从左上方照射，白色区域明亮接近过曝，阴影使用冷蓝、灰蓝、蓝紫色硬边块面表现。主体轮廓修长，姿态安静冷淡，细节简化但造型准确，整体清透、冷艳、时尚，像高级杂志封面海报。无文字，无水印，无复杂背景，无写实摄影，无 3D，无厚涂，无低幼卡通，无杂乱装饰。

入力されたキャラクター画像をもとに、 そのキャラクターの「魅力解剖図」を1枚のビジュアルとして作成してください。 これは通常のキャラクター設定資料、三面図、プロフィールシートではありません。 目的は、キャラクターの情報を説明することではなく、 「この子のどこが可愛いのか」「なぜ目を惹かれるのか」「どの部分に好きになる理由があるのか」を、 デザイン的・感情的に分解して見せることです。 入力画像からキャラクターの以下の魅力要素を丁寧に読み取ってください。 ・目の形、瞳の色、目線の印象 ・髪の流れ、前髪、毛先、シルエットの可愛さ ・表情のクセ、微笑み方、照れ、無表情の中の感情 ・手の仕草、指先、袖口との関係 ・衣装の好きポイント、リボン、フリル、装飾、小物 ・首元、肩、袖、スカート、靴などの見せ場 ・そのキャラクターが一番かわいく見える角度 ・全体から感じる性格、雰囲気、守りたくなるポイント、惹かれる理由 中央にはキャラクターを大きく配置してください。 キャラクターはただ立たせるのではなく、 その子の魅力が最も伝わる角度、ポーズ、表情で描いてください。 正面すぎる証明写真のような構図は禁止。 少し振り向く、手を口元に添える、袖をつまむ、髪を軽く押さえる、視線を少し外すなど、 “好きになる瞬間”を切り取ったような自然で魅力的なポーズにしてください。 周囲には、キャラクターの魅力ポイントを分解した小さなクローズアップパネルを配置してください。 ただし機械的な設定資料のように並べるのではなく、 雑誌の特集ページ、デザイン解剖図、ファンが作った愛のある分析ボードのように、 美しく、可愛く、少し偏愛を感じるレイアウトにしてください。 配置するパネル例： ・瞳のアップ：この子らしさが宿る目元 ・髪の流れ：シルエットを決める毛束 ・手元：仕草に出る性格 ・表情差分：微笑み、照れ、少し不機嫌、無防備な顔 ・衣装の推しポイント：リボン、袖、襟、装飾、素材感 ・一番かわいい角度：顔の向き、視線、首の傾き ・小物やモチーフ：その子の世界観を象徴する要素 各パネルは、キャラクターの魅力を強調するための拡大カットとして描いてください。 パーツだけを無機質に切り抜くのではなく、 「ここが好き」と思わせるような温度感のある見せ方にしてください。 画面内には短い注釈風のラベルを入れてもよいですが、 長文説明ではなく、短い見出しや記号的なデザインにしてください。 例： “eyes” “hair flow” “gesture” “best angle” “favorite detail” “charm point” “soft expression” “tiny habit” 文字は主役にしすぎず、あくまでデザイン要素として扱ってください。 読ませる資料ではなく、見た瞬間に「この子、可愛い」と伝わるビジュアルにしてください。 デザイン全体は、可愛い研究ノート、キャラクター愛の解剖図、ファッション誌の分析ページ、公式アートブックの特集ページを合わせたような雰囲気。 背景はシンプルで清潔感があり、キャラクターの色に合わせた淡いグラデーション、紙面風の余白、細い罫線、半透明のパネル、手書き風の丸囲み、矢印、ハート、小さな装飾を使ってください。 重要： キャラクターを単に説明しないこと。 身長、年齢、能力、所属、武器説明などの設定資料的な情報は不要です。 描くべきなのはスペックではなく、 “好きになる理由”です。 キャラクター本人の魅力が最優先。 パネルや注釈が多すぎて主役が埋もれないようにしてください。 中央のキャラクターは必ず最も可愛く、最も完成度高く描いてください。 全体の印象： cute character charm analysis sheet, visual breakdown of cuteness, not a character profile, not a model sheet, aesthetic design board, fan-favorite details, emotional attraction map, soft editorial layout, official artbook style, clean anime illustration, beautiful eyes, expressive hands, flowing hair, adorable pose, best angle, lovable expression, fashion detail close-ups, delicate annotations, soft pastel panels, refined graphic design, high-quality anime illustration, commercial-level finish.

Rework the given image into a crayon-style illustration, transforming the entire scene into something that feels hand-drawn by a 10-year-old. Keep the forms simple and slightly imperfect, like a child’s drawing. Avoid using the original color palette—replace it with bright, playful crayon colors on a clean white paper background. Aim for a soft, cute, and innocent aesthetic. Incorporate fun, childlike details such as castles or towers, candy, stars, clouds, and other whimsical decorations to amplify the playful vibe. The final result should feel charming, colorful, and full of childlike imagination.

[BRAND NAME] + [HERO COLOR] Act as a Mixed-Media Campaign Art Director. Your specialty: combining studio photography cutouts with hand-drawn 2D illustration where the real human and the drawn object physically interact — touching, holding, standing on, leaning against, or using the illustrated element as if it truly exists in their space. PHASE 1: CANVAS & COLOR SYSTEM Format: 1:1 square canvas. Base: single flat saturated color [HERO COLOR]. No gradients. No texture. Pure chromatic field. Overlay: 3–4 organic amoeba blob shapes in the same [HERO COLOR] but 20% darker in value. Smooth edges, irregular silhouettes, scattered asymmetrically. Some bleeding off-frame. Hand-painted feel, clean execution. PHASE 2: AUTONOMOUS OBJECT SELECTION BEFORE staging the scene, the AI must first make two autonomous decisions: DECISION 1 — SELECT THE OBJECT: Analyze [BRAND NAME] and identify ONE iconic physical object from this framework: — What is the single most recognizable product or artifact this brand has ever made? — What object do fans of this brand collect, use daily, or photograph? — What prop has defined this brand's visual identity across decades? Do NOT choose animals. Do NOT choose logos. Choose a real, large, tangible object that can physically occupy space next to a person. DECISION 2 — SELECT THE INTERACTION: Based on the chosen object, determine the most natural and visually dynamic way the real model can directly interact with the drawn object. Interaction must be: ✓ Physical and direct — hands touching, feet on, body leaning, arms around ✓ Immediately readable — the relationship between person and object is understood in under 2 seconds ✓ Scaled correctly — the object must be large enough to interact with at human scale ✓ Active, not passive — the model is DOING something with the object, not just standing next to it INTERACTION TYPE EXAMPLES (AI selects the most brand-appropriate): · HOLDING: model's real hands grip the illustrated object — cup, camera, trophy, bottle, bag · WEARING/USING: model's real body wears or uses the object — sitting on a chair, wearing an illustrated hat, holding an illustrated product to their face · STANDING ON: model's real feet are planted on top of the illustrated object — skateboard, surfboard, podium, giant sneaker · RIDING/LEANING: model's real body leans against or drapes over the illustrated object — car hood, shopping cart, giant product silhouette · EMERGING FROM: model appears to step out of or through the illustrated object — bursting through a giant sneaker box, rising from an illustrated cup PHASE 3: STAGING THE SCENE Once object and interaction are selected, stage the full scene: MODEL: Single model age 18–26, clean cutout, zero fringing. Pose is determined by the chosen interaction — the body position must make the interaction feel natural and physically believable. Wardrobe: [BRAND NAME]'s most iconic apparel in [HERO COLOR] monochromatic palette. ILLUSTRATED OBJECT: Pure white (#FFFFFF) flat 2D illustration. Brush-pen marker line quality, 3–5px weight. Slightly imperfect organic edges — hand-drawn feel, not vector-perfect. NO shading. NO gradients. Flat white fill only. SCALE RULE — CRITICAL: The illustrated object must be LARGE. Minimum size: 40% of canvas height. The object should feel monumental — oversized relative to real-world scale is acceptable and encouraged. A coffee cup can be waist-height. A sneaker can be as tall as the model. Large scale = better readability = stronger visual impact. DEPTH LAYERING — CRITICAL:The object must exist on multiple z-layers: — Parts of the object sit BEHIND the model — Parts of the object come IN FRONT of the model — The model's real hands/feet make contact at the intersection point This layering is what makes the scene feel integrated rather than collaged. BRAND STAMP: One small [BRAND NAME] logo mark appears on the object's surface — naturally embedded as if printed, engraved, or stitched. Rendered in [HERO COLOR] darker variant. Subtle, not dominant. PHASE 4: SUPPORTING ILLUSTRATION SYSTEM All supporting elements: white, flat, brush-pen line style. Same visual language as the hero object. LOGO MARKS: [BRAND NAME] primary icon in white: — Large (upper-left corner, ~15% canvas width) — Medium (opposite corner, ~10% canvas width) IMPACT MARKERS: 2–3 manga-style exclamation dash clusters near the point of interaction between model and object — where hands grip, where feet land, where bodies touch. This emphasizes the physical connection. MOTION LINES: 2–4 curved speed lines radiating from the object or the model's most active body part. Taper at ends. Cross behind and in front of the model for depth. GROUND EFFECT: At the base of the scene: white illustrated ground interaction — sparkle stars, short speed dashes, or object-specific effect (splash if cup, dust clouds if sneaker landing, wheel tracks if skateboard). AMBIENT SQUIGGLES: 1–2 loose organic white lines floating near the model's torso — visual rhythm connecting the photographic and illustrated layers. PHASE 5: LIGHTING Studio strobe, high-key, even and clean. 5500K neutral. No dramatic shadows on model. Soft contact shadow at model's feet (opacity 15%). The photography reads as natural and real against the graphic illustrated environment. TECH SPECS Aesthetic: mixed media — real photograph integrated with hand-drawn 2D illustration. Color count: 3 maximum — [HERO COLOR] light, [HERO COLOR] dark blobs, white illustration. Photography skin tones and fabric colors are the only additional color exception. Illustration style: Y2K comic energy, Japanese streetwear magazine, brush marker. Composition: asymmetric and dynamic. The interaction point between model and object is the visual center of gravity — everything else orbits around it. No text. No wordmarks. Logo icon only. Mood: the model is not posing WITH the object — the model is IN THE MIDDLE of using it. Caught mid-action. Alive.

{ "global_settings": { "resolution": "8K ultra high definition", "aspect_ratio": "3:4", "camera_style": "studio food photography with cinematic lighting", "depth_of_field": "shallow depth of field, sharp subject, soft background", "lighting": "soft directional key light, subtle rim light, controlled highlights", "style": "hyper-realistic food illustration with editorial infographic overlays", "composition_rules": [ "no zoom", "no crop", "center-weighted vertical composition", "floating elements frozen in motion" ], "text_design": { "ingredient_name_color": "metallic gold", "ingredient_description_color": "pure white", "font_style": "elegant serif for titles, clean sans-serif for descriptions", "indicator_lines": "long, thin, smooth golden lines with rounded corners" } }, "module_1_image_1_style": { "scene_description": "A vertical stack of assorted cake slices floating above a white ceramic plate against a soft pink gradient background.", "background": { "color": "soft pastel pink", "texture": "smooth gradient", "lighting": "even, studio-lit, no harsh shadows" }, "main_subjects": [ "multiple layered sponge cake slices", "white whipped cream layers", "raspberry cream layer", "chocolate cream topping" ], "visible_ingredients": [ "vanilla sponge cake", "whipped cream", "raspberries", "blueberries", "strawberries", "macarons (vanilla and chocolate)", "chocolate bar pieces", "mint leaves", "small nut fragments" ], "motion_elements": [ "floating fruits", "floating macarons", "crumbs suspended in air" ], "text_labels": [ "Vanilla Cake – soft, fluffy sponge cake layered with white cream filling", "Macaron – creamy filling between almond meringue shells", "Raspberries – juicy, fresh raspberries", "Chocolate Bar – chunks of smooth milk chocolate", "Raspberry Cream – soft sponge cake layered with creamy, fruity raspberry cream" ] }, "module_2_image_2_style": { "scene_description": "Rolled Syrian dessert presented vertically with syrup pouring from above, placed in a warm, rustic kitchen environment.", "background": { "environment": "traditional kitchen", "elements": [ "warm lantern light", "wooden surfaces", "brass and copper utensils" ], "lighting": "warm ambient lighting with soft highlights" }, "main_subjects": [ "rolled white dessert dough", "cream filling spilling out", "golden syrup stream" ], "visible_ingredients": [ "white cheese dough", "cream filling", "pistachios", "sugar syrup" ], "motion_elements": [ "syrup dripping vertically", "pistachio crumbs falling" ], "text_labels": [ "White Cheese Dough – soft outer layer made from cheese and semolina", "Cream Filling – creamy filling inside the roll", "Pistachios – crushed pistachios sprinkled over and inside the rolls" ] }

[BRAND NAME]. Act as a World-Class Editorial Designer. PHASE 1: DYNAMIC SUBJECT LOGIC. - Subject Selection: Autonomously analyze [BRAND NAME]. - Layering (The Sandwich Effect): Interweave the subject with background shapes. Some parts of the car/person must be hidden behind geometric blocks, while other parts (wheels, limbs, props) must overlap them to create 3D depth. PHASE 2: GRID & GEOMETRY. - Layout: A clean 2x2 grid composition. - Overlays: Superimpose large, bold geometric arcs and circles over the grid. - Visual Balance: Place one iconic product prop (e.g., a floating key fob for cars or a ball for sports) in a separate quadrant to balance the subject. PHASE 3: SOPHISTICATED MUTED PALETTE. - Color Direction: DO NOT use aggressive neon or oversaturated colors. - Palette: Identify the core colors of [BRAND NAME] and shift them to a "Sophisticated Muted" spectrum. - Tones: Use desaturated, earthy, or "dusty" versions of the brand colors (e.g., instead of hot pink, use dusty rose; instead of bright mint, use sage green; instead of royal blue, use slate blue). - Finish: Matte, flat color blocks with zero gradients. PHASE 4: PHOTOGRAPHY & LIGHTING. - Subject Style: High-end commercial studio photography. - Lighting: Soft, diffused studio lighting with gentle highlights. No harsh shadows. - Integration: The subject must feel physically embedded into the graphic grid. PHASE 5: MINIMALIST BRANDING. - Logo: Place a clean, single-color [BRAND NAME] logo in the center of one background block. No taglines, just the iconic symbol.

[BRAND NAME]. Act as a Creative Director and Still Life Photographer for a hypebeast fashion publication. THE TASK: Create a high-end "Showroom Still Life" photograph announcing a limited merchandise drop for [BRAND NAME]. PHASE 1: AUTONOMOUS CURATION (STRATEGY) Analyze [BRAND NAME]: Identify the industry and the core physical product (e.g., if "Spalding" -> Basketballs; if "McDonald's" -> Burger Boxes; if "Visa" -> Metal Cards). Determine the Palette: Background Color: A deep, rich, textured tone derived from the brand's secondary palette (e.g., Teal, Navy, Burgundy, Slate Grey). Merch Color: A contrasting warm or neutral tone (Camel, Orange, Cream) to pop against the background. Select the "Merch Item": Choose a high-quality apparel piece relevant to the brand's vibe (e.g., a Varsity Letterman Jacket, a Heavyweight Hoodie, a Canvas Tote, or a Wool Scarf). PHASE 2: SET DESIGN (THE RACK) The Prop: A simple, modern White Powder-Coated Metal Rack or Shelf unit. It stands cleanly in the frame. The Arrangement: Hanging Item: The chosen "Merch Item" (e.g., the Jacket) is draped casually over the rack or hanging on a hanger, showing off the texture (wool/felt). Stacked Items: On the shelves of the rack, stack multiple units of the brand's Core Product (e.g., a stack of basketballs, a pyramid of cans, a row of boxes). The Background: A Hand-Painted Canvas Backdrop in the chosen Deep Background Color. Visible texture/brushstrokes are essential for that "studio" look. PHASE 3: PHYSICAL BRANDING (TEXTURE) On the Merch: The hanging apparel must feature High-Quality Physical Branding. Use "Chenille Patches", "Embroidered Logos", or "Screen Print" running down the sleeve or on the back. It must look like a real, expensive garment. On the Products: Ensure the stacked core products have the correct [BRAND NAME] logo visible. PHASE 4: PHOTOGRAPHY & LIGHTING Lighting: Soft, directional window light from the side. Creates realistic, soft shadows on the rack and rich highlights on the textures. Lens: 50mm or 85mm. Sharp focus on the merch, slight fall-off in the background. PHASE 5: UI OVERLAY (THE "DROP" LAYOUT) Left Side Alignment: Large, clean White Logo of [BRAND NAME] floating in the negative space on the left. Under the logo, small white text with the brand's official slogan.

Create a complete visual worldbuilding set for a futuristic desert civilization powered by solar technology, multiple images including architecture, characters, clothing, vehicles, and maps, cohesive design language, cinematic realism, ultra detailed.

Preserve the face, proportions, and external features of the model as in the reference. A minimalist monochrome fashion editorial triptych featuring three stacked cinematic frames. The subject is a young man with short dark hair and a groomed beard. Frame 1: Emotional and introspective, looking downward with a hand near the collarbone, highlighting bone structure with Rembrandt lighting. Frame 2: A crisp profile shot with a focus on the nose, lips, and masculine jawline, gaze directed slightly upward. Frame 3: A frontal, thoughtful portrait with shoulders relaxed and direct eye contact. The composition is clean and modern, using a white T-shirt and gold necklace for visual continuity. Commercial magazine quality, high-end mirrorless camera, authentic skin pores, soft bokeh, and elegant masculinity.

Create a hyper-realistic Forbes “30 Under 30” magazine-style portrait of the same woman from the reference image (preserve her exact facial features, identity, and expression 100%). She is sitting confidently on a modern luxury sofa in a high-end office or studio environment. She has a radiant, glowing skin tone with soft, natural makeup, subtle highlights on cheekbones, and bright, sharp eyes behind elegant glasses. Her expression is calm, confident, and successful. Outfit: smart professional attire (minimalist black or neutral tones), clean and modern.

日本語の架空広告をテーマに、SNSでバズることを目的としたインパクトの強いビジュアルを作成してください。 1:1の正方形キャンバスに、4種類の広告を「2×2グリッド」で配置してください。 ジャンル： ①テック（AI・アプリ） ②美容・コスメ ③飲食 ④フィットネス すべて日本語コピー入り・架空ブランドで作成。 【バズるための演出要件】 ・一瞬で目を引く強烈なキャッチコピー ・感情を動かす要素（驚き・共感・焦り・欲望） ・コントラストの強い配色（ネオン、ビビッドカラー、黒×蛍光など） ・大胆なレイアウト（はみ出し・斜め配置・大きすぎる文字） ・サムネ映えする構図（中央強調・顔アップ・視線誘導） ・SNS広告っぽい“あざとさ”（矢印・強調枠・吹き出し） 【デザインスタイル】 ・2025年トレンドのSNS広告風 ・TikTok / Instagram広告風 ・視認性最優先（スマホで見ても読める） ・写真風 or 高品質イラスト ・CTA入り（例：今だけ無料・限定・残り3日など） 【ランダムバズ要素】 以下の①〜③から、それぞれ1つずつランダムに選び、必ずキャッチコピーに反映すること。 ①禁断ワード系（いずれか1つ） ・知らないと損 ・99%が間違ってる ・今すぐやめて ②ギャップ演出（いずれか1つ） ・見た目かわいいのに中身がヤバい ・普通に見えて実は… ・これ、○○じゃありません ③数字・限定（いずれか1つ） ・3日限定 ・残り1枠 ・無料→0円 【重要】 ・4つそれぞれ明確に違う雰囲気にする ・グリッドは崩さない ・文字は読みやすく配置する ・“スクロールを止める違和感”を意図的に入れる 出力：4広告が1枚にまとまった高インパクトビジュアル

生成一张[餐饮品牌触点矩阵]系列视觉图，用于展示一个完整的餐饮品牌视觉系统与包装应用方案。 这是一个面向餐饮行业的品牌VI样机展示板 / 包装系统陈列图 / 品牌提案页。画面不是单张宣传海报，而是将品牌主视觉、主打产品、包装物料、菜单信息、促销内容与小型延展物料整合成一张系统化品牌展示图。 【用户输入信息】 - 品牌名：[品牌名] - 经营类目：[经营类目] 【可选补充信息】 - 主打产品：[主打产品] - 品牌口号：[品牌口号] - 风格方向：[风格方向] - 主色调：[主色调] - 辅助色：[辅助色] - 客群定位：[客群定位] - 价格定位：[价格定位] - 地域风格：[地域风格] - 画幅比例：[画幅比例] 【自动补全规则】 如果用户没有提供完整品牌信息，请根据【品牌名】与【经营类目】自动推导并完成最优组合，包括： 1. 判断品牌调性（年轻、亲和、国潮、复古、清新、治愈、精致、快餐感等） 2. 匹配适合该类目的视觉风格 3. 自动设定合理的主色、辅助色与点缀色 4. 自动补全主打产品与辅助产品 5. 自动生成适合餐饮传播的品牌口号、卖点文案、价格信息与推荐标签 6. 自动匹配合适的餐饮物料类型与展示内容 【画面内容要求】 画面中应围绕【品牌名】构建一整套餐饮品牌物料系统，包含但不限于以下内容： - 核心包装：手提袋、外卖袋、包装盒、打包盒、纸袋、塑料袋 - 饮品 / 食品容器：纸杯、杯套、碗、餐盒、封口贴、标签 - 信息传播物料：菜单、促销海报、价格牌、桌牌、立牌、小卡片 - 小型品牌延展：贴纸、徽章、纸巾、餐具、包装封条、吊牌 - 产品表现：主打餐品照片、单品主视觉、食物特写、切面图、推荐组合图 【构图与版式要求】 采用竖版【画幅比例】构图，整体为白色、米白色或浅灰色背景，以品牌提案板 / 样机矩阵板的方式组织画面。 通过大中小物料混排形成视觉层级： - 大型包装和主视觉物料作为视觉锚点 - 中型菜单、海报和价格模块负责信息传达 - 小型贴纸、餐具、标签与周边物料增强系统完整度 整体构图应具有明确秩序感，接近品牌方案展示页、作品集陈列页、包装提案页的视觉效果。元素要排列整齐但不呆板，丰富但不杂乱，具有模块化与可阅读性。 【风格与质感要求】 整体风格应符合【经营类目】与【品牌名】气质，具有明显的餐饮品牌感、商业传播感、样机展示感与系统设计感。 可融合以下风格倾向：现代简洁、国潮趣味、轻复古、生活方式感、快消感、温暖治愈感、年轻化传播感。 材质真实，包含纸张、塑料、布袋、包装盒、杯体、贴纸、餐具等真实物料质感；光影柔和统一，像在干净摄影棚环境中拍摄的品牌物料合集。 【文字与图形要求】 所有物料上应统一出现品牌名、Logo、品牌符号、主色块、口号或卖点文案。 文案可为中文或中英混排，但要符合餐饮传播表达，简洁直接，具备商品售卖感。 图形系统可以根据品牌调性选择简洁插画、几何图形、卡通吉祥物、符号化图标或辅助纹样，用于增强品牌记忆点。 【输出目标】 最终生成一张完整的【品牌名】餐饮品牌视觉系统展示图，像设计团队为该餐饮品牌制作的整套品牌提案样机板。 要求画面统一、精致、具备商业落地感与作品集展示质量，并能清楚体现品牌风格、主打类目与多触点包装延展能力。 Make the aspect ratio 9:16

A minimalist cinematic colored poster featuring a [Character Name]’s portrait from shoulders to the top of the head. The face is reconstructed using a small number of large, square-cut paper fragments arranged in a simple grid [around 4x5 or 5x6 pieces]. Each paper fragment contains a disjointed part of the face which together reconstruct the portrait. The internal paper fragments constituting the face are not perfectly flat; many have slightly curled edges and lifted corners, casting tiny, realistic shadows that give them a three-dimensional, tacked-down appearance. 4 of these squares have subtle black handwritten [text1, text2, text3, text4] directly on the skin/image. Scattered irregularly around the outer perimeter of this central grid in various randomly placed positions (not confined to the corners), several [Sticky Note Color] sticky notes are attached to the [Color] wall, containing handwritten [External Text Content, e.g., iconic quotes]. The overall layout is slightly irregular with visible gaps between the pieces showing [Color] concrete wall background. Realistic paper texture throughout, high-end studio lighting emphasizing the lifted edges, sharp focus on ink and paper grain.

[BRAND NAME] Act as a Macro Product Photographer and Textile Art Director shooting a close-up editorial campaign of a premium embroidered garment. References: Loro Piana fabric campaigns, Brunello Cucinelli texture photography, A.P.C. garment detail shoots, Japanese boro textile documentation. PHASE 0: BRAND LOGO INTELLIGENCE Retrieve the canonical logotype or primary mark of [BRAND NAME] from training data. Identify the core geometric essence of the logo — its fundamental shapes, stroke relationships, and compositional balance. Translate this identity into an embroidery-native form language: sharp geometric elements become satin stitch bars and needle-point spikes, circular elements become dense satin stitch ovals or French knot clusters, complex letterforms are simplified into their most essential strokes while remaining recognizable. The embroidery interpretation must feel like a deliberate premium interpretation of the brand mark — as if [BRAND NAME]'s design team commissioned an embroidery artist to translate their logo into thread. Autonomously determine the thread color most iconic to [BRAND NAME] — this becomes the primary embroidery thread color. If [BRAND NAME] has no dominant single color, default to deep navy #1A2332. PHASE 1: TEXTILE BACKGROUND The background is a premium waffle-knit cotton fabric — the weave structure is a precise geometric grid of raised square cells, each cell approximately 2×2mm equivalent, separated by thin recessed channels running both horizontally and vertically. The raised nodes of each cell are flat-topped, not rounded — creating a regular orthogonal relief pattern across the entire surface. The fabric color is cold off-white — #F0F0EE to #EBEBEA range, with a very slight cool gray bias, not warm ecru or cream. The weave is consistent and uniform across the entire frame — machine precision, no tension variation, no distortion. Microscopic fiber fuzz is visible on the flat tops of the raised nodes — individual cotton fibers catching the diffused overhead light as a very fine surface bloom. The recessed channels between cells are in soft shadow — not deep shadow, just slightly darker than the raised nodes, consistent with flat overhead illumination. PHASE 2: EMBROIDERY CONSTRUCTION SYSTEM The logo mark of [BRAND NAME] rendered as machine or hand embroidery using these specific stitch techniques. Satin stitch: the primary technique for all filled areas and stroke elements — dense parallel threads laid side by side with zero gap, creating a smooth glossy surface. Thread direction follows the long axis of each stroke element — horizontal strokes have horizontal threads, diagonal strokes have diagonal threads. The characteristic sheen of satin stitch is critical: threads catch light along their length creating bright reflective zones on thread-parallel surfaces and darker zones on thread-perpendicular surfaces, creating a directional shimmer across the embroidery surface. Stem stitch or outline stitch: used for any curved linear elements — thin continuous line of overlapping thread segments following curves with natural flexibility. French knots: small circular dot elements rendered as tightly wound thread knots — each knot has a visible spiral wind pattern at macro distance. Spike elements: long tapering needle-like forms executed in satin stitch that tapers from full width to a single thread point — gradual and precise, ending in a razor-sharp thread tip. Edge treatment: every embroidered element has a thin visible backing outline — 1 to 2 thread widths of the base fabric visible between the embroidery and the surrounding textile. This underlay/backing edge is slightly lighter than the main embroidery thread — it outlines every form and confirms the physical layering of embroidery over fabric. Physical relief: the embroidery sits 1 to 3mm above the fabric surface — confirmed by a very subtle shadow halo directly underneath each embroidered element. The shadow is symmetrical around the embroidery perimeter, soft-edged, 1 to 2mm wide — consistent with flat overhead illumination, not directional raking light. PHASE 3: THREAD MATERIAL Primary thread color: autonomously determined brand color from PHASE 0. Thread material: mercerized cotton or silk embroidery thread — high sheen, smooth filament surface. The thread color is never flat — it shifts in value along its length based on light angle. Directly lit zones approach a lighter more luminous version of the base color. Shadow zones approach a deeper more saturated version. The overall embroidery reads as one unified color but contains a full tonal range within that color family. Secondary thread: the backing/underlay edge thread is 2 to 3 shades lighter than the primary thread — creating the characteristic light outline visible around all embroidered elements. PHASE 4: COMPOSITION & CAMERA Camera body: Canon EOS R5 or Nikon Z8 — full frame, 45 megapixel minimum for fabric texture resolution. Lens: Canon RF 100mm f/2.8L Macro IS USM or Nikon Z MC 105mm f/2.8 VR S — used at moderate close-up distance, not at maximum 1:1 magnification. Focus distance: 40 to 55cm — the embroidery fills approximately 30 to 40% of the frame height, leaving generous fabric context on all sides. This is a moderate close-up, not extreme macro — the full embroidery composition is visible with substantial textile surround. Aperture: f/8 to f/11 — deep depth of field, the entire embroidery and all surrounding fabric texture are in crisp simultaneous focus from corner to corner. No visible bokeh anywhere in the frame. Shutter speed: 1/200s with continuous light source. ISO: 100 — base ISO, zero noise, maximum tonal resolution in the subtle gray shadows of the waffle recesses. White balance: 5600K — neutral daylight, renders the cold off-white fabric accurately without warm or cool shift. Exposure: slightly bright ETTR — the off-white fabric renders as a luminous near-white, embroidery thread reads as deep rich dark against the bright ground. Aspect ratio: 4:5 portrait. Camera perpendicular to fabric plane — zero perspective distortion, embroidery geometry rendered faithfully. PHASE 5: LIGHTING Primary light: large diffused overhead source — a 120×120cm softbox or diffusion panel positioned directly above the fabric at 60 to 80cm distance. The light is as close to flat and directionless as possible. No raking angle — the light comes from directly above at 85 to 90° to the fabric plane. This flat overhead lighting creates: uniform brightness across the entire fabric field with no hot spots or falloff. Very short soft shadows in the recessed channels of the waffle grid — 1 to 2mm wide, soft-edged, falling straight down. Soft symmetrical micro-shadow halo directly beneath the embroidery — the 1 to 3mm relief creates a subtle darker zone immediately surrounding the embroidery perimeter, equal on all sides. No directional shadow — the shadow is not cast to one side. Secondary light: none. No fill, no rim, no accent. The single large overhead diffused source is the complete lighting setup. Overall mood: clinical, precise, bright — consistent with product documentation or high-end textile editorial photography where the subject must be seen with maximum clarity and zero atmospheric distraction. PHASE 6: TECH SPECS Render: Octane Render or Redshift with fiber/textile displacement geometry. Thread geometry: actual 3D cylindrical thread strands — each thread strand is a real geometric object casting real shadows on adjacent threads, not texture maps. Fabric weave: real geometric displacement mesh for waffle structure — not normal map. Ray tracing: on — for accurate micro-shadow casting between individual thread strands and between embroidery and fabric surface. Subsurface scattering: subtle on thread material — mercerized cotton and silk have slight translucency. Depth of field: physically accurate — f/8 to f/11 at 100mm at 40 to 55cm focus distance, full frame sharp corner to corner. Anti-aliasing: maximum. Sampling: minimum 2048 samples — zero noise in shadow zones, full tonal resolution in the off-white fabric field. Output feel: this image should be indistinguishable from a photograph taken with a Canon 100mm macro in a textile documentation studio. The viewer must feel the urge to touch the fabric.

Ultra-realistic Gen Z selfie photo collage, three vertical smartphone flash selfies of a young woman with long wavy black hair, soft dewy glass skin, rosy blush, glossy peach lips, natural makeup, wearing a faded blue-gray sleeveless Nirvana tank top, silver chain necklace, black nail polish with nail art, posing with hand under chin, playful wink with tongue out, and warm smiling expression. Direct front-facing flash photography, clean light gray wall background, high contrast shadows, candid Instagram aesthetic, sharp facial details, shallow depth of field, Y2K vibe, soft skin texture, photorealistic, 35mm lens, high resolution. Prompt : Ultra-realistic late-night flash selfie collage, three stacked smartphone photos of a young woman with shoulder-length dark hair, luminous skin, subtle blush, glossy pink lips, natural Korean-inspired makeup, wearing a blue-gray sleeveless tank top, silver chain necklace, resting face on hand, playful wink, looking sideways, and kissing-face expression. Direct camera flash creating bright highlights and deep shadows, dim indoor bedroom background, casual candid selfie aesthetic, soft messy hair, photorealistic skin texture, high detail eyes and lips, Instagram/Tumblr vibe, 35mm photography, realistic lighting, ultra-sharp focus, high resolution.

Minimalist ultra-high-resolution travel sketch poster of Omotesando, Tokyo, on clean white sketchbook paper with subtle paper grain texture. Style: refined pen drawing + loose watercolor sketch. Delicate black ink linework, airy watercolor washes, elegant urban details. Show a calm everyday Omotesando street scene — the iconic zelkova tree-lined avenue, chic boutiques and flagship stores, small stylish cafés, people walking with shopping bags, bicycles, crosswalks, low-rise modern architecture mixed with traditional touches, subtle Japanese signage (Japanese characters on shop signs), fashionable Tokyo pedestrians, soft morning light filtering through the trees. Spacious editorial composition with generous negative space. Mood: calm, modern, sophisticated, poetic. Typography: "[OMOTESANDO]" "Everyday Urban Rhythm" Premium travel sketch aesthetic, minimal and stylish, ultra-realistic watercolor + ink travel journal style, ultra-high-resolution, 9:16.

Create a typographic art portrait using the uploaded photo of a person as reference. Display a left-facing side profile portrait. The entire image--including the face. hair. and facial features--must be formed exclusively from repeated white calligraphic text using the words: "[PUT WHATEVER WORDS YOU WANT HERE]" The text should follow the natural contours of the face and hair, clearly shaping the person's profile silhouette. Use a deep navy blue background with high contrast The stvle should be clean vector art with sharp edges. Output in high-resolution 8K quality. Do not alter the person's facial identity. No additional colors. no textures. and no watermark. Dimension 4:5

{ "project_settings": { "task_type": "九宫格新年祝福肖像（男生版）", "aspect_ratio": "1:1", "grid_layout": "3x3", "batch_size": 1 }, "overall_style": { "整体风格": "极简新年祝福风", "视觉基调": "干净、温和、克制的节日感", "背景": "纯色白墙面，无装饰", "光线": "自然柔光，均匀无强阴影", "色彩重点": "中国红（服装 + 文字）" }, "subject_base": { "人物一致性": "九宫格内为同一位人物", "人物类型": "亚洲男性", "性别气质": "干净、阳光、自然，不油腻", "发型": "黑色短发，自然蓬松，简洁利落", "服装": "红色针织毛衣或卫衣，简洁无图案", "妆容": "无明显妆感，真实自然肤质", "表情气质": "开心，克制的微笑，不夸张" }, "pose_variations": { "grid_1": "食指竖于嘴前，轻松安静手势", "grid_2": "单手比 V 手势靠近脸部", "grid_3": "单手做 OK 或三指手势", "grid_4": "双手举起做轻松俏皮手势（不过度卖萌）", "grid_5": "单手张开遮住半边脸", "grid_6": "单手做电话手势靠近脸侧", "grid_7": "单手轻点脸颊或下巴", "grid_8": "单手托下巴，轻微思考姿势", "grid_9": "双手指向脸部或克制比心变体" }, "text_overlays": { "字体风格": "传统中文新年书法字体", "文字颜色": "中国红", "年份颜色": "深蓝色", "文字位置": "每一格顶部居中", "文字结构": "四字祝福语 + 年份" }, "text_content": [ { "position": "grid_1", "text": "一帆风顺", "year": "2026" }, { "position": "grid_2", "text": "双喜临门", "year": "2026" }, { "position": "grid_3", "text": "三阳开泰", "year": "2026" }, { "position": "grid_4", "text": "四季发财", "year": "2026" }, { "position": "grid_5", "text": "五福临门", "year": "2026" }, { "position": "grid_6", "text": "六六大顺", "year": "2026" }, { "position": "grid_7", "text": "七星高照", "year": "2026" }, { "position": "grid_8", "text": "八方来财", "year": "2026" }, { "position": "grid_9", "text": "九九同心", "year": "2026" } ], "constraints": { "禁止项": [ "不改变人物身份", "不夸张表情", "不女性化姿态", "不使用复杂背景", "不添加节日道具", "不风格化面部" ], "一致性要求": [ "人物脸型五官保持完全一致", "服装颜色与材质一致", "拍摄角度与距离基本一致" ] }, "use_cases": [ "男生新年纪念照", "个人春节祝福九宫格", "社交平台头像矩阵", "品牌新年男生模板" ] }

View from under a plane of completely transparent plexiglass. We are looking straight up. Many people are walking on the plexiglass. In the background is a pure blue sky. No buildings visible. No edges or separations in the plexiglass. It’s as if the plexiglass isn’t even there. We are very close to the people. The people are in the process of walking. The people are walking generally from left to right. The soles of their shoes are very close to the foreground.

Ultra-realistic candid smartphone photograph, 9:16 vertical. Use the attached image only as a strong visual inspiration for general facial proportions and vibe, while ensuring the generated subject remains fully original, non-identifiable, and not a face copy. Scene Nighttime on a quiet Tokyo city sidewalk beside a building with white ceramic tile walls. The subject is walking past the camera, partially side-on, captured mid-step in a rushed, accidental moment. Poses & Gestures (combined naturally) The subject reacts instinctively to being photographed: turning her head back mid-walk as if surprised, raising one hand close to the lens to partially block the camera, shy, restrained smile forming as she suppresses laughter, body angled in half-profile while continuing to walk forward, motion carries her slightly out of frame, imperfect framing. Expressions are subtle and spontaneous — embarrassed, playful, fleeting — never posed. Camera & Motion Shot on a modern smartphone, handheld, rushed capture. Strong uncontrolled camera shake. Heavy directional motion blur across the raised hand, hair, and face. Facial features appear smeared and streaked by movement, faintly recognizable but distorted. Partial ghosting around the body. Imperfect framing, subject nearly leaving the frame. Lighting Flash-only lighting fired mid-motion. Harsh flash highlights on skin and hand. Deep surrounding darkness. Uneven exposure, blown highlights, hard shadows typical of hurried night phone photography. Background White ceramic tile wall stretches into streaked light bands due to motion blur. Street surroundings fade into darkness with minimal readable detail. Mood Candid, shy, slightly playful. Feels intrusive, raw, imperfect, and authentic — like a fleeting memory accidentally captured and never meant to be perfect. Image Quality Extremely noisy. Heavily blurred. Raw smartphone look. Not cinematic. Not editorial. Not polished. Negative Prompt anime, illustration, painting, stylized, studio lighting, beauty lighting, soft portrait, sharp focus, clean face, perfect anatomy, smooth skin, fashion editorial, posed portrait, cinematic grading, film still, tripod shot, professional photography, identity match, face copy, real person replication

请根据【主题】生成一张高质量竖版「科普百科图」。 这张图不是普通海报，也不是单纯插画，而是一张兼具“图鉴感、百科感、信息结构感、收藏感”的模块化科普信息图。整体风格参考高级博物图鉴、现代百科书页、生活方式知识卡和社交媒体高传播信息图的结合。 请让画面包含： - 一个清晰漂亮的主题主视觉 - 若干局部特征放大细节 - 多个圆角模块化信息分区 - 清楚的标题层级与重点标签 - 简洁但丰富的百科内容 - 可视化评分、要点总结或Top 5模块 内容栏目请根据主题自动适配，优先从这些方向中选择并合理组合： 基础档案、分类信息、外观特征、习性/生态、形成机制/结构组成、生长或使用条件、养护或维护建议、风险与注意事项、适合人群或适用场景、优缺点对比、快速评分卡。 视觉要求： 浅色干净背景，柔和配色，轻阴影，精致小图标，圆角信息框，整洁排版，信息密度高但不拥挤，阅读体验好。整体必须像真正可以发布、阅读、收藏、系列化生产的科普百科卡，而不是广告图。 请不要做成普通商业宣传海报。要突出“知识整理 + 模块信息 + 图鉴式展示”的特征。

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

生成一张适合小红书发布的 3:4 竖版九宫格海报，整体为 3列 × 3行 排版，九个宫格边界清晰，方便后期直接切割成 9 张单图发布。整体风格干净、高级、统一，适合女性向健康生活方式内容，具有小红书爆款封面气质。画面要求 信息排版清晰、文字大、可读性强、留白舒服、配色温柔治愈。 整体视觉风格： 奶油白、浅米色、淡燕麦色、浅焦糖色为主色调，搭配少量深棕色文字，ins风、治愈感、睡眠疗愈主题，简约排版，轻拟物插画点缀，可加入枕头、月亮、星星、热牛奶、香薰、书本、眼罩、窗帘、床铺等元素。整体像专业新媒体设计图，字体工整，适合做知识科普类小红书九宫格。 排版要求： 整张图必须是标准九宫格构图，切分后每一格都能独立成图 每个宫格内容完整居中，不要把标题或正文压在分割线附近 每个格子之间保留明显间隔或细边框，保证裁切后不影响阅读 所有文字使用中文，清晰易读，不要乱码，不要英文 每个宫格都像独立的小红书图文卡片，但视觉风格保持统一 画面精致、真实、自然，不要廉价营销感，不要过度花哨 九宫格具体内容： 第1格（封面） 大标题：让你倒头就睡的8个 tips 副标题：失眠党、熬夜党一定要收藏 封面视觉最吸睛，适合做首图，加入柔软床铺、月亮、枕头、眼罩等治愈睡眠元素，标题突出，排版高级。 第2格 标题：1. 睡前1小时别玩手机 正文：蓝光会让大脑更清醒，越刷越睡不着。 配图元素：手机、月亮、困倦表情的小插画 第3格 标题：2. 睡前把灯光调暗 正文：暖光环境能帮助身体进入“准备睡觉”的状态。 配图元素：床头灯、暖黄色灯光、窗帘 第4格 标题：3. 房间温度别太高 正文：稍微凉一点，更容易快速入睡。 配图元素：空调、温度计、被子 第5格 标题：4. 晚上别喝浓茶咖啡 正文：咖啡因会延迟困意，让你躺很久还睡不着。 配图元素：咖啡杯、茶杯、禁止符号 第6格 标题：5. 睡前洗个热水澡 正文：能让身体放松下来，入睡速度更快。 配图元素：浴室蒸汽、毛巾、热水 第7格 标题：6. 脑子停不下来就写下来 正文：把烦心事和待办清单写下，大脑会更容易放松。 配图元素：笔记本、钢笔、小台灯 第8格 标题：7. 固定上床时间 正文：每天差不多时间睡，生物钟会越来越稳定。 配图元素：时钟、月亮、床 第9格 标题：8. 试试深呼吸放松法 正文：吸气4秒，停4秒，呼气6秒，慢慢就有困意了。 底部小字：收藏这组，今晚试试看 配图元素：呼吸线条、闭眼人物、星星 画质要求： 高清，高级排版，杂志感，真实可发布，新媒体运营审美，小红书爆款图文风格，文字布局规整，适合直接切图。

{ "subject": { "description": "the prettiest (G)I-DLE Yuqi taking a high-angle selfie.", "mirror_rules": "Left arm extended holding camera.", "age": "Early 20s", "expression": { "eyes": { "look": "upward at lens", "energy": "alluring", "direction": "direct" }, "mouth": { "position": "slightly parted", "energy": "soft" }, "overall": "seductive and innocent" }, "face": { "preserve_original": true, "features": "Yuqi's irresistibly cute yet alluring round-yet-sharp face, bright expressive eyes, charming smile lines, and vibrant fair aesthetic.", "makeup": "Asian influencer aesthetic, heavy under-eye blush, light contacts, glossy lips." } }, "hair": { "color": "Warm light brown", "style": "Long, loose waves, voluminous.", "effect": "Top backlit halo, strands falling over chest." }, "body": { "frame": "Slim with pronounced curves.", "waist": "Narrow", "chest": "Full, deep cleavage.", "legs": "Upper thighs visible.", "skin": { "visible_areas": "Chest, shoulders, left arm, upper hips.", "tone": "Fair, pale luminous.", "texture": "Smooth, soft, slightly dewy.", "lighting_effect": "Harsh warm sunlight hitting cleavage and left shoulder, casting sharp shadows." } }, "pose": { "position": "Angled torso, hips pushed back, playful high-angle pose with slight hip cock and energetic lean.", "base": "Standing/leaning.", "overall": "Leaning forward into the high-angle lens with flirty body language." }, "clothing": { "top": { "type": "Tight shiny latex bodysuit with detached left sleeve.", "color": "Glossy Purple", "details": "Deep scoop neck, thin straps.", "effect": "Stretching tightly over chest." }, "bottom": { "type": "Latex bodysuit bottom", "color": "Glossy Purple", "details": "Extremely high cut exposing hips." } }, "accessories": { "jewelry": "Delicate silver pendant necklace." }, "photography": { "camera_style": "Smartphone selfie", "angle": "High angle, looking down.", "shot_type": "Medium close-up.", "aspect_ratio": "9:16", "texture": "Digital, slight wide-angle distortion on left arm.", "lighting": "Strong directional warm light, high contrast.", "depth_of_field": "Shallow, blurry dark background." }, "background": { "setting": "Dark interior room.", "wall_color": "Dark/black.", "elements": [ "Lit door edge on left" ], "atmosphere": "Intimate, private.", "lighting": "Mostly dark with one sharp shaft of warm light." }, "the_vibe": { "energy": "Captivating", "mood": "Sensual", "aesthetic": "Soft-core, golden hour selfie.", "authenticity": "Casual smartphone snapshot.", "intimacy": "High, direct eye contact.", "story": "Catching the golden hour light in a bedroom.", "caption_energy": "Effortless glow." }, "constraints": { "must_keep": [ "High angle perspective", "Harsh warm directional light", "Bodysuit cut" ], "avoid": [ "Flat studio lighting", "Professional posture", "Over-bright background" ] }, "negative_prompt": [ "ugly", "flat light", "studio lighting", "professional camera", "overexposed", "extra limbs", "stiff" ] }

Untitled work

[product], centered top down flat lay, surrounded by [ingredients], fresh slices and whole pieces, glossy wet look, water splash frozen mid motion around the product, dewy droplets on label and surface, warm beige seamless background, soft directional sunlight, crisp realistic shadow, high end skincare advertising, ultra realistic macro product photography, 100mm lens look, f/8 sharp focus, clean composition, no extra text, 8k, 1:1

生成完整高端的品牌运营图 ，产品是老干妈和星巴克的联名款：老干妈美式，中间是主图，下面放一些联名的设计，包装袋、杯套以及吉祥物。

[product setup], minimalist product photo, clean warm studio scene, textured beige wall background, soft directional sunlight creating long shadows, simple tabletop surface, product arranged in a playful concept composition, hand drawn white line doodle overlay of [character] interacting with the product, mixed media look combining real photography and sketch illustration, high end branding feel, shallow depth of field, ultra realistic, no extra text, no watermark

Create a technical infographic of [OBJECT] with a 45-degree isometric 3D perspective showing the device slightly tilted to reveal depth and dimension. Combine a realistic photoreal render with black ink technical annotations on pure white background. Include: Key component labels with color-coded callout boxes Internal component visibility through transparent/cutaway sections Measurements, dimensions, and precise scale markers Material callouts and quantities Color-coded arrows for function/flow: RED (power/battery), BLUE (data/connectivity), ORANGE (thermal/processor), GREEN (sensors/haptics) Simple schematics or cross-sectional diagrams where relevant Place “OBJECT” title in a hand-drawn technical box (top-left corner). Style: Black linework (technical pen/architectural), sketched but precise. Object remains clearly visible. Educational museum-exhibit vibe. Clean composition, balanced negative space. Perspective: Isometric 3D angle—tilted to show depth, dimension, and internal architecture dramatically. Like a professional product teardown or engineering manual. Colors: ~10-15% accent density. Black dominant. White background. Output: 1080×1080, ultra-crisp, social-feed optimized.

[BRAND NAME] | [COLOR] Act as a 3D Type Designer and CGI Artist working at the intersection of streetwear culture, Y2K aesthetics, and high-end digital sculpture. Your references: Nigo, Futura, Guccimaze, Soulwax art direction. --- PHASE 1: TYPOGRAPHIC CONCEPT Render the word or logotype [BRAND NAME] as a fully 3D sculptural object — not a flat text with extrusion, but a living, inflated, organic type sculpture. Style: Wildstyle graffiti DNA fused with inflatable balloon morphology. Letters are not separate — they flow into each other as one continuous organic mass. Each letterform has: bulbous pneumatic body as if inflated under high pressure from within, stretching the surface taut. Aggressive spike extensions — sharp tapered protrusions erupting between and around letters, directional, asymmetric, energetic, some long and blade-like, others short and thorn-like. Wildstyle overlaps — letters partially occlude each other creating depth layers, classic graffiti ambiguity where readability fights with visual complexity. Organic connective tissue — negative spaces between letters filled with stretched membrane forms, like rubber pulled between two inflated surfaces. --- PHASE 2: MATERIAL & SURFACE Single unified material across the entire sculpture — no color variation between letters. Material type: high-gloss latex / inflated rubber / soft silicone — the surface behaves like a balloon skin stretched to near-bursting point. Subsurface scattering: active — light penetrates slightly into the material, creating a translucent inner glow at thin edges and spike tips. Thinner areas read lighter, denser volumes read darker. Specular highlights: large, soft, slightly elongated — the kind you get on inflated latex, not hard plastic. Multiple secondary highlights in concave zones. Apply [COLOR] as the sole material color of the entire sculpture — this is non-negotiable. [COLOR] defines the pure midtone of the material. Highlights push toward the most luminous near-white version of [COLOR]. Shadow zones and deep crevices push toward the darkest most saturated version of [COLOR]. The entire chromatic range of the sculpture lives within the [COLOR] family — no hue deviation, no neutral grays. --- PHASE 3: COMPOSITION & STAGING Background: pure white (#FFFFFF) — clinical studio isolation. Zero texture, zero gradient. Shadow: none, or absolute minimum contact shadow directly beneath the sculpture — the object appears to float slightly. Orientation: horizontal spread — the sculpture is wider than tall, expanding laterally. Spike elements breach the invisible bounding box on all sides — top spikes reach upward, side extensions push outward. Camera angle: straight-on frontal, slightly elevated 5 to 10° above center — reveals the full typographic mass while showing the 3D depth of overlapping elements. Depth of field: none — sharp from foreground spikes to background letter bodies, every detail in focus. Scale feel: monumental — as if the sculpture is 2 meters wide in physical space, photographed in a white infinity studio. --- PHASE 4: TECH SPECS Render engine: Octane Render or Redshift — physically accurate subsurface scattering mandatory. Global illumination: large soft HDRI dome light, neutral white temperature 5500K. No directional shadows. No rim lights. No background elements. Ray tracing: on — for accurate specular and inter-reflection between letter surfaces. Anti-aliasing: maximum — edges must be razor-clean against white background. Output feel: this is a CGI product render, not AI art. Precision over expressionism. Aspect ratio: 1:1 square — centered composition with breathing room on all four sides.

The generated image uses the uploaded image as a reference for the character, wearing a high-necked, tight-fitting black long-sleeved dress. A cluster of withered wood and orange-pink flowers lies beside an old newsstand, the grainy texture of vintage film interwoven, the blurred background with noticeable trailing shadows, and the double-image effect creating a fantastical atmosphere. A bewitchingly beautiful girl, carrying flowers, is shown in profile, her fair skin delicate and translucent. Her exquisite face is blurred with motion, the outline of her figure slightly swaying with the panning camera, the soft focus making the image even more hazy and languid. A warm-toned, low-saturation filter enhances the effect, her long, backlit hair glowing with a soft glow, the messy strands sweeping wildly across her jawline, the details concealing a captivating yet dangerous allure. Cute movements add dynamism, the motion blur blending with the film grain, creating a trendy, Instagram-worthy image while the blurred image outlines a dynamic scene full of story, cleverly balancing bewitching and sweetness.

A handcrafted felt miniature illustration of [Celebrity] reimagined as a soft wool doll character. The figure has simplified facial features, button-like eyes, subtle smile, and carefully crafted felt textures. He is wearing an outfit inspired by his iconic casual tech style—dark jacket, simple t-shirt, and trousers—recreated in knitted wool and fabric. The scene has a whimsical, storybook feel with grassy felt terrain, pastel hills, and a bright sky with soft clouds. Macro photography look, shallow depth of field, soft natural lighting, stop-motion animation aesthetic, ultra-detailed fibers and fabric textures, cozy yet futuristic mood, cinematic composition, high quality.

[BRAND NAME]. Act as a World-Class Editorial Designer. PHASE 1: DYNAMIC SUBJECT LOGIC. - Subject Selection: Autonomously analyze [BRAND NAME]. - Layering (The Sandwich Effect): Interweave the subject with background shapes. Some parts of the car/person must be hidden behind geometric blocks, while other parts (wheels, limbs, props) must overlap them to create 3D depth. PHASE 2: GRID & GEOMETRY. - Layout: A clean 2x2 grid composition. - Overlays: Superimpose large, bold geometric arcs and circles over the grid. - Visual Balance: Place one iconic product prop (e.g., a floating key fob for cars or a ball for sports) in a separate quadrant to balance the subject. PHASE 3: SOPHISTICATED MUTED PALETTE. - Color Direction: DO NOT use aggressive neon or oversaturated colors. - Palette: Identify the core colors of [BRAND NAME] and shift them to a "Sophisticated Muted" spectrum. - Tones: Use desaturated, earthy, or "dusty" versions of the brand colors (e.g., instead of hot pink, use dusty rose; instead of bright mint, use sage green; instead of royal blue, use slate blue). - Finish: Matte, flat color blocks with zero gradients. PHASE 4: PHOTOGRAPHY & LIGHTING. - Subject Style: High-end commercial studio photography. - Lighting: Soft, diffused studio lighting with gentle highlights. No harsh shadows. - Integration: The subject must feel physically embedded into the graphic grid. PHASE 5: MINIMALIST BRANDING. - Logo: Place a clean, single-color [BRAND NAME] logo in the center of one background block. No taglines, just the iconic symbol.

{ "image_prompt": { "type": "Hyper-realistic food infographic", "subject": { "cuisine": "Indonesian", "base_element": "Traditional bowl with steaming hot dish at the bottom", "levitating_ingredients": [ "Juicy meat", "Crispy tofu", "Glossy sauce splashes", "Fresh herbs", "Chilies", "Lime", "Garlic", "Fried shallots" ] }, "composition": { "layout": "Clean vertical composition", "arrangement": "Realistic gravity-defying/floating elements", "background": "Rustic wooden surface", "visual_hierarchy": "Bowl anchored at bottom, ingredients rising vertically" }, "graphic_design_elements": { "labels": "Clear Indonesian text", "lines": "Thin white pointing lines", "style": "Editorial infographic layout, professional food magazine style" }, "lighting_and_mood": { "lighting": "Cinematic studio lighting", "color_palette": "Warm tones", "effects": "Dramatic steam, motion-frozen ingredients" }, "technical_specs": { "camera_settings": "Shallow depth of field, sharp focus, DSLR look", "details": "Ultra-detailed textures", "resolution": "8K ultra-realistic" } } }

Untitled work

A minimalist, black-and-white flat vector illustration portrait of [NAME], rendered in the expressive "Notion avatar" art style. LINE WORK & VIBE: Style: Use THICK, UNIFORM black outlines (monoline weight). The lines should feel organic, smooth, and confident, not rigidly geometric or robotic like generic icons. Vibe: The character should have a distinct personality and a relaxed, cool, or friendly expression. Focus on stylized features, unique hairstyles, and defining accessories to convey character. SELECTIVE BLACK FILLS (CRITICAL): Unlike pure outline icons, utilize Solid Black Fills selectively and strategically. Where to Fill: Use solid black for prominent hair masses, beards, eyebrows, sunglasses, or dark clothing elements. Where to Keep White: The skin, main face area, and lighter elements must remain pure flat white inside the thick outlines. COMPOSITION & TECHNICAL: No shading, no gray tones, no gradients. Only pure Black and pure White. Clean bust or headshot composition centered on a white background. High contrast, clean 2D vector graphics.

{ "meta": { "image_quality": "High", "image_type": "Photo" }, "global_context": { "scene_description": "Close-up portrait of a young person's face covered with colorful paper stickers and glossy adhesive residue. Central focus on eyes, nose, lips; subject blowing a pink bubblegum bubble. Stickers vary in size, text, icons and layered overlap; hair strands frame face at edges. Skin shows freckles, pores, and sheen from adhesive or moisture.", "time_of_day": "Neutral/studio lighting", "weather_atmosphere": "Indoors/controlled", "lighting": { "source": "Artificial", "direction": "Frontal with slight top", "quality": "Soft", "color_temp": "Neutral" } }, "color_palette": { "dominant_hex_estimates": ["#E7B1B6", "#F6C0D0", "#C9A38C"], "accent_colors": ["Pink","Magenta"], "contrast_level": "Medium" }, "composition": { "camera_angle": "Eye-level", "framing": "Extreme close-up (face fills frame)", "depth_of_field": "Shallow (background indistinct)", "focal_point": "Eyes and central bubble" }, "objects": [ { "id": "obj_001", "label": "Face", "category": "Person (head)", "location": "Center", "prominence": "Foreground", "visual_attributes": { "color": "Light beige skin with pink undertones and freckles", "texture": "Smooth with visible pores, glossy adhesive patches", "material": "Skin", "state": "Sticker-covered, slightly wet/glossy", "dimensions_relative": "Large relative to frame" }, "micro_details": [ "Freckles concentrated on nose and cheeks", "Shiny adhesive residue streaks on forehead and cheeks", "Fine vellus hairs visible", "Pores visible on nose and cheeks" ], "pose_or_orientation": "Frontal", "text_content": null }, { "id": "obj_002", "label": "Eyes (pair)", "category": "Facial feature", "location": "Upper-center", "prominence": "Foreground", "visual_attributes": { "color": "Gray-green irises with dark limbal ring", "texture": "Wet/glossy cornea, visible eyelashes", "material": "Biological", "state": "Open, neutral expression", "dimensions_relative": "Medium" }, "micro_details": [ "Tiny specular highlights on each cornea", "Sparse lower lashes, fuller upper lashes", "Slight shadow under lower lids" ], "pose_or_orientation": "Facing camera", "text_content": null }, { "id": "obj_003", "label": "Pink bubble", "category": "Object (gum)", "location": "Lower-center", "prominence": "Foreground", "visual_attributes": { "color": "Pastel pink", "texture": "Smooth, slightly translucent", "material": "Gum", "state": "Inflated/intact", "dimensions_relative": "Large relative to mouth" }, "micro_details": [ "Two bright specular reflections on sphere", "Seamless edge against lips" ], "pose_or_orientation": "Centered over mouth", "text_content": null }, { "id": "obj_004", "label": "Stickers (assorted)", "category": "Adhesive stickers", "location": "Entire face and neck, concentrated forehead and cheeks", "prominence": "Foreground", "visual_attributes": { "color": "Multicolor: magenta, yellow, blue, white", "texture": "Paper/plastic with glossy varnish, torn edges", "material": "Paper/plastic adhesive", "state": "Layered, partially torn, some wrinkled", "dimensions_relative": "Varied small-to-medium" }, "micro_details": [ "Large 'POP ME' magenta sticker on forehead", "Partial torn sticker fragments near nasolabial fold", "Small rectangular stickers with tiny printed text", "Edges lifting, adhesive shine around perimeters" ], "pose_or_orientation": "Affixed flat or slightly peeled", "text_content": "Multiple small logos and words (e.g., 'POP ME')" }, { "id": "obj_005", "label": "Hair strands", "category": "Hair", "location": "Left and right edges framing face", "prominence": "Background/foreground overlap", "visual_attributes": { "color": "Light brown", "texture": "Fine, slightly wet", "material": "Hair", "state": "Loose strands", "dimensions_relative": "Thin relative to face" }, "micro_details": [ "Individual strands crossing forehead edges", "Slight adhesive sheen on some strands" ], "pose_or_orientation": "Hanging down" } ], "text_ocr": { "present": true, "content": [ { "text": "POP ME", "location": "Forehead", "font_style": "Bold/Decorative", "legibility": "Clear" } ] }, "semantic_relationships": [ "Stickers are affixed to Face", "Bubble covers mouth, partially obscuring lips", "Adhesive residue creates glossy highlights on skin", "Hair strands frame and partly overlay stickers" ] }

一名23歲日本女性，只穿著寬鬆的薄款粗針織毛衣，毛衣滑落單側肩膀。靠著清晨的窗邊，陽光從背後灑落，逆光穿透針織縫隙形成柔和的光暈，優美的身形輪廓展露無遺。她用一手整理散亂的長髮，神情放鬆。色調自然柔和，畫面唯美且不暴露敏感部位。 --ar 3:4