自然 プロンプト例

Edit this photo without changing the face a beautiful woman with fair skin lit by bright morning sunlight from a strong golden directional light source creating clear shadows on her face and hair

Generate a sleek digital artwork of me (use my uploaded face), designed in the style of a modern vector poster portrait. Visual Style & Elements: A crisp vector aesthetic featuring strong line work and smooth, flat color shading. Apply striking, high-contrast tones: light peach skin with gentle reddish shadowing. Hair should be rendered with clean, stylized edges in deep brown/black shades, with faint highlights. Beard should appear sharp, defined, and naturally blended into the facial structure. Set the background to a solid red tone.

{ "project_name": "3D_Caricature_Collage_Olive_Green", "prompt_structure": { "subject": { "type": "Woman", "style": "3D Caricature", "appearance": "Highly polished, clean, meticulous detail", "clothing": "Deep olive green hoodie (rich, muted earth tone)" }, "composition": { "type": "Collage", "layout": "Six-panel grid (3 columns x 2 rows)", "framing": "Close-up portraits" }, "variations": { "panel_1": "Happy", "panel_2": "Surprised", "panel_3": "Serious", "panel_4": "Cute", "panel_5": "Sassy", "panel_6": "Confident", "facial_features": "Artistic exaggerations, widened eyes, arched eyebrows, broad smiles" }, "environment": { "background": "Bold, vibrant colors distinct for each panel", "lighting": "Soft ambient lighting, sculpting subtle textures, crisp definition" }, "text_elements": { "content": "Shreya Yadav", "type": "Signature", "style": "Elegant, legible" } }, "technical_params": { "aspect_ratio": "3:4", "quality": "High definition, 8k, cinematic lighting", "render_engine": "Octane render / Unreal Engine style" }, "full_prompt_text": "A six-panel collage (3 columns, 2 rows) featuring a highly polished 3D caricature of a woman wearing a deep olive green hoodie. The character maintains a consistent identity across all panels but displays six distinct emotions: happy, surprised, serious, cute, sassy, and confident. Facial features are artistically exaggerated with widened eyes and expressive mouths. Soft ambient lighting highlights skin texture and fabric folds. Backgrounds are bold and vibrant, contrasting with the muted olive hoodie. High-end digital art style, crisp definition. Signature text 'Shreya Yadav' included." }

{ "subject": { "description": "A rugged male survivor walking through an overgrown city street", "mirror_rules": "Reflection in broken shop window", "age": "40s", "expression": "wary, scanning the horizon, tired", "hair": { "color": "salt and pepper", "style": "overgrown, messy beard" }, "clothing": { "top": { "type": "flannel shirt and denim jacket", "color": "faded blue and red plaid", "details": "holes in elbows, sun-bleached, dirt stains" }, "bottom": { "type": "jeans", "color": "dark grey", "details": "muddy knees, frayed hems" } }, "face": { "preserve_original": true, "makeup": "dirt smudges, sun spots, realistic weathering" } }, "accessories": { "headwear": { "type": "none", "details": "N/A" }, "jewelry": { "earrings": "none", "necklace": "none", "wrist": "broken analog watch", "rings": "wedding band on chain around neck" }, "device": { "type": "flashlight", "details": "clipped to backpack strap" }, "prop": { "type": "hiking backpack", "details": "large, olive green, bedroll attached, worn fabric" } }, "photography": { "camera_style": "Cinematic realism, 35mm wide lens", "angle": "wide shot establishing environment", "shot_type": "full body walking away from camera slightly", "aspect_ratio": "16:9", "texture": "detailed foliage, crisp sunlight, natural colors" }, "background": { "setting": "ruined city street reclaimed by nature", "wall_color": "concrete covered in ivy", "elements": [ "rusted cars", "tall grass cracking through pavement", "collapsed building in distance", "deer visible in background" ], "atmosphere": "quiet, desolate, beautiful decay", "lighting": "overcast soft daylight, diffuse shadows, melancholy feel" } }

"A surreal, whimsical digital illustration of a young woman with pale pink skin and voluminous, floating black hair. Her head is horizontally split open at the nose level. Inside the hollow of her head, a tiny, miniature version of herself (wearing the same attire) is standing and physically lifting the top half of the head (containing the closed eyes and forehead) up with her hands. The space inside the split head reveals a dark blue starry night sky or cosmic void. Art style: Modern flat illustration with a lo-fi, grainy texture. Soft pastel colors including lavender, periwinkle, and peach. The shading is subtle and soft using gradients. There is a noise overlay/stipple effect giving it a retro print look. The background is a solid soft purple gradient with scattered white stardust. Emotional, dreamy, metaphorical."

Extreme close-up of a human hand holding a giant vertical pill. The pill has a clear glass top section and the lower 3/4 is matte bright-red, with bold, clean, perfectly aligned typography that reads: BASKETBALL LEGENDARY. Inside the pill, show a person whose face must match the attached photo 100% exactly — no changes to facial structure, proportions, expression baseline, or any detail. The face must display a natural, realistic, wide laughing expression. Inside the pill, the person is performing a dynamic basketball dribbling pose with high energy, labeled with the account name 'MICHAEL JORDAN'. Scene style: funny, chaotic, thrilling, slightly creepy, and intense. Background: an NBA basketball court, with full cinematic lighting, dramatic shadows, and rich color depth. Camera angle: aerial extreme close-up focused on the pill in the hand. Texture: ultra-HD realism with fine grain, crisp micro-details, glass reflections, and smooth matte material fidelity. Ratio 3:4. Ensure motion, energy, and dynamic movement inside the pill while keeping the pill perfectly vertical.

主题和形式：两位年轻女性朋友创作的高分辨率现代日本大头贴风格拼贴画。 布局：由 3x3 网格组成的单个图像（共 9 帧）。 主题：圣诞节 风格：生动、全彩、明亮、动感地再现现代日本大头贴灯光效果。 背景：简单的纯色或主题色背景（带有小爱心等精致装饰）。 摄影特点：每幅画面都有一条细细的白色或装饰性边框。景深浅（虚化）。 主题和姿势： 两位年轻的女性朋友，穿着符合主题的搭配服装。 生动、活泼、明快的表达。 这九张图清晰地描绘了以下列表中九种不同的流行大头贴姿势。 9 种不同的姿势（3x3 网格）： 第一行： “抓头发爱心”姿势：一人俏皮地抓着头发，另一人用双手比出一个小爱心。两人都面带笑容。 “双手心形”姿势：两位伴侣用双手在中心形成一个大大的心形。脸上洋溢着灿烂快乐的笑容。 “捏手臂”姿势：两人双臂交叉，其中一人或两人都轻轻捏着对方的脸颊或手臂。表情生动活泼，充满喜悦。特写镜头展现对方的脸部。 第二排：4.“双臂交叉大爱心”姿势：两人双臂交叉，用空着的那只手比出一个大大的爱心。笑容灿烂而充满活力。5.“承诺之心”姿势：一人做出“手指发誓”的手势，另一人用手比出一个小爱心。笑容俏皮而温暖。6.“手牵手爱心”姿势：两人手牵手，各自用空着的那只手比出半个爱心，组成一个完整的爱心。笑容温柔甜美。 第三排：7.“双臂交叉撅嘴”姿势：两人双臂交叉，略带夸张的撅嘴或“得意”（或严肃）的表情，似乎在强忍着笑意。8.“双手合十，脸颊贴心”姿势：两人手牵着手，双手分别放在脸颊上，在脸颊周围画出一个心形。笑容可爱迷人。9.“双臂交叉，手心相印”姿势：两人双臂交叉，每人用一只手分别画出一个小的心形。笑容自信而时尚。特写镜头展现了他们的脸部。 其他装饰： 多个发光的霓虹心形图案叠加。 每一帧画面上，都以霓虹灯风格，沿着脸部的外轮廓写着与主题相关的字母。 在每个面板上添加多个符合主题的不同霓虹线条艺术涂鸦（例如星星、箭头、饱和线条、花朵、动物耳朵等）。 主要限制：所有9张照片必须保持主体、服装、背景风格和光线的严格一致性。浅景深，这是大头贴的典型特征。 请勿：添加任何文字、徽标、标签、水印、符号、数字或其他任何类型的文本元素（上述指定的文本元素和霓虹线条艺术涂鸦除外）。

{ "objective": "Generate an image based on a detailed character portrait description.", "image_generation_prompt": { "subject": { "gender": "female", "portrait_type": "close-up", "angle": "side angle", "aesthetic": "edgy, modern, mysterious, confident, slightly provocative" }, "appearance": { "hair": { "color": "light gray", "length": "short", "texture": "wavy", "style": "modern, slightly messy, partially covering forehead" }, "face": { "skin_tone": "fair", "features": "sharp", "eyebrows": "straight, neat, dark", "lips": "naturally pink with a slight sheen" }, "expression": "calm but intense" }, "clothing_and_accessories": { "headwear": "black bandana with white swirl patterns", "outfit": { "jacket": "black zip-up jacket, left open", "inner_shirt": "black T-shirt with green and red graphic art on the chest" }, "jewelry": { "neck": "thin silver chain", "ear": "small silver earring" } }, "lighting_and_background": { "lighting": "front light highlighting facial features and outfit", "background": "bright blue sky" }, "style": { "vibe": "striking and stylish", "focus": "expression and trendy fashion details", "mood": "modern and edgy" }, "aspect_ratio": "3:4" }, "response_format": "Use this JSON object as the structure for an image generation model prompt." }

我想要一张超真实的照片，但内容又有点超现实。感觉就像一个孩子放学后，偷偷从教室门缝里看到一个神奇的景象：哆啦A梦竟然真的在空无一人的教室里，像个小老师一样，认真地准备着化学课。 整个画面要非常写实，但又充满了童话般的温馨和惊奇。 画面内容 主体： 哆啦A梦本人，活生生地站在教室的讲台前面，而不是画在黑板上。他看起来是立体的，有光滑的质感，就像动画里走出来的一样，但又完美地融入了这个真实的环境里。 人物细节：哆啦A梦站在讲台旁，身体微微侧着，表情认真又亲切，仿佛在思考怎么给大雄他们讲课。 他的一只手拿着一根小小的教鞭，指向他身后的黑板。 他的黄色铃铛在教室的光线下有微微的反光，肚子上的四维口袋看起来鼓鼓的。 背景细节（黑板）：他身后的黑板上，画着一幅用各色粉笔手写的化学元素周期表。这个周期表看起来就像是哆啦A梦刚刚亲手画上去的，色彩丰富，带有一点可爱的风格。 可以用不同颜色的粉笔（比如黄色、蓝色、粉色）来区分不同的元素区域，让整个画面色彩更丰富。 文字： 在黑板的顶上或者角落，用可爱的粉笔字体写上标题：“哆啦A梦的科学教室”。 环境与构图 场景： 一间普通的日本教室，桌椅摆放整齐，夕阳的余晖从窗户照进来，营造出一种安静、温暖的氛围。 构图： 画面比例是4:3。从学生的座位视角看过去，哆啦A梦和讲台在画面的中心位置。 前景： 画面最前面可以带到一两张学生的课桌椅，让视角更具代入感。讲台上可以放着一盒彩色粉笔和一个黑板擦。 风格和技术要求 风格： 照片写实主义。关键在于真实的环境和光影，与哆啦A梦这个动漫角色的奇妙结合。 光线： 温暖的午后自然光从窗户斜射进来，光线要自然地打在哆啦A梦身上，在他圆滚滚的身体上形成柔和的光影和高光，让他看起来有体积感，并且在他的脚边投下淡淡的影子，这能让他看起来更真实。 焦点： 焦点要清晰地对准哆啦A梦，黑板上的内容也很清楚，但前景的课桌可以稍微有点模糊。 千万不要出现！ 不要让哆啦A梦看起来像个塑料玩具或模型，他得是活的。 不要有其他任何人物，特别是大雄、静香他们。 不要把画风变成动画截图或纯CG，一定要是照片的感觉。 构图要稳，不要用奇怪的低角度或鱼眼镜头。 颜色别太鲜艳，要符合真实光线下的色彩。

{ "scene_description": "A soft, kawaii aesthetic mirror selfie of a cute young woman in a Disney store, embracing a fluffy pink Aristocats theme.", "image_reference": { "path": "[UPLOADED_IMAGE]", "weight": "high", "influence": "face_and_body_structure" }, "subject": { "type": "The woman from the uploaded image", "age": "match input image", "features": { "hair": "soft curls or twin tails with ribbons", "expression": "sweet smile, head tilted, eyes wide and innocent", "makeup": "heavy blush (igari style), pink glossy lips, soft lashes" }, "attire": "a fluffy white off-shoulder sweater dress (angora texture) with pink satin ribbons tied on the sleeves, white knee-high knitted socks", "accessories": "white cat ears headband with pink bows (Marie style), holding a pink strawberry milkshake prop, pearl bracelet", "position": "standing with knees slightly bent together (cute pose), holding phone with both hands." }, "action": { "primary": "taking a cute selfie", "secondary": "holding a drink", "effect": "radiating softness and charm" }, "environment": { "setting": "Pastel plushie section of Disney store", "foreground_elements": [ "pink phone case with charms", "fluffy texture of dress close to lens" ], "background_elements": [ "stacks of pink and white plushies", "pastel floral decor", "soft retail lighting" ] }, "lighting": { "style": "Soft diffused beauty light", "key_light": { "type": "Ring light effect", "color": "Soft pink/peach undertone", "illuminates": "rosy cheeks and fluffy textures." }, "background_light": { "color": "Pastel pink glow" }, "shadows": "very soft, almost non-existent shadows" }, "style": { "medium": "Smartphone photography", "aesthetic": "Coquette, Kawaii, Soft Girl, Pastel Goth light", "quality": "Dreamy, soft focus edges", "details": "visible fluff on sweater" }, "visual_description": { "core_subject": "An embodiment of cuteness and comfort.", "attire_physics": "The sweater looks incredibly soft and touchable; ribbons drape naturally.", "skin_rendering": "Soft-focus, airbrushed look (beauty filter simulation)." }, "lighting_and_atmosphere": { "type": "Dreamy Interior", "specifics": "Bloom effect on highlights.", "color_grade": "Pastel palette, low contrast, rosy tint" }, "attire_customization": { "current_clothing": "Fluffy white sweater dress, pink ribbons, knee socks", "customizable_clothing": "Can swap for a pink gingham sundress." }, "camera_and_lens": { "focal_length_feel": "35mm", "aperture_effect": "f/2.0", "camera_angle": "Slightly high angle (selfie standard)", "lens_type": "Smartphone front camera simulation", "bokeh_style": "Creamy pastel bokeh" } }

A full-body artistic portrait of the woman from the reference image, keeping the exact same face. She is elegantly seated on the floor wearing a modern black top, soft loose gray jeans, and chunky gray-and-white sneakers. Her long, waist-length wavy milky-brown hair flows naturally, with half of it beautifully braided. She is laughing while looking upwards, capturing a confident candid smile. The background is an artistic monochrome (black and white) composition featuring a soft, blurred close-up side profile of the same face, creating a stylish dual-layer aesthetic. High-quality soft lighting, realistic textures, cinematic realism, and an artistic portrait vibe.

Present a clear, side miniature 3D cartoon view of [YOUR CITY] tallest buildings. Use minimal textures with realistic materials and soft, lifelike lighting and shadows. Use a clean, minimalistic composition showing exactly the three tallest buildings in Sopot, arranged from LEFT to RIGHT in STRICT descending height order. The tallest must appear visibly tallest, the second must be clearly shorter than the first, and the third must be clearly shorter than the second. All buildings must follow accurate relative proportions: if a building is taller in real life, it MUST be taller in the image by the same approximate ratio. No building may be visually stretched or compressed. Each building should stand separately on a thin, simple ceramic base. Below each base, centered text should display: Height in meters — semibold sans-serif, medium size Year built — lighter-weight sans-serif, smaller size, directly beneath the height text Provide consistent padding, spacing, leading, and kerning. Write “YOUR CITY NAME” centered above the buildings, using a medium-sized sans-serif font. No building top should overlap or touch the text above.Use accurate architectural proportions based on real-world references.Maintain consistent camera angle and identical scale for each building model. No forced perspective. Use straight-on orthographic-style rendering. Do not exaggerate or stylize size differences beyond proportional accuracy. Use a square 1080×1080 composition.Use a clean, neutral background. Ensure no extra objects are present.

{ "image_request": { "goal": "Create a cinematic portrait based on the provided reference photo, preserving the subject’s face exactly as it appears in the reference (no alterations to facial structure, proportions, features, or expression).", "subject": { "identity_preservation": { "description": "The face must remain completely unchanged from the reference photo — 1000% identical in all visible facial details, proportions, contours, expression, and micro-features.", "notes": "No stylization, morphing, or reinterpretation of the facial structure. Only the scene, pose, and atmosphere change." }, "pose": { "body_position": "The woman is standing with her back to the camera.", "head_turn": "She turns her head over her shoulder, looking toward the viewer.", "gaze": "Soft, melancholic, and intense." }, "appearance": { "skin": "Smooth, pale skin with gentle cinematic texture.", "hair": { "style": "Long, straight hair.", "movement": "Slightly tousled by the wind." }, "clothing": { "top": "Black backless top with delicate thin straps draping down the back." }, "props": { "bouquet": "A bouquet of black roses held close to her face." } } }, "environment": { "setting": "A moody lakeside or riverside.", "weather": "Overcast grey skies.", "atmosphere": "Soft, misty, melancholic, and subtly gothic." }, "lighting": { "type": "soft diffuse lighting", "source": "natural overcast daylight", "tone": "desaturated, muted highlights", "mood": "gothic, melancholic, cinematic", "shadow_quality": "soft, low-contrast shadows" }, "color_grading": { "palette": "desaturated neutrals, soft greys, washed-out cool tones", "mood": "cinematic and atmospheric" }, "composition": { "framing": "Cinematic shoulder-turned portrait with focus on the face and roses.", "depth": "Shallow depth of field; background slightly blurred.", "emphasis": "Emotional intensity in the eyes; contrast between pale skin and black roses/top." }, "style": { "visual_style": "cinematic realism", "tone": "moody, atmospheric", "genre_influence": "dark romantic, gothic melancholy" } } }

Generate a photorealistic image of a cafe terrace in the Marais district of Paris on a Wednesday morning in March 2025. It is a crisp, cool spring morning with clear skies. Locals are drinking coffee. In sharp focus should be a young woman with a pixie cut wearing a scarf, stirring a cappuccino and looking thoughtfully to the side; the waiter and street traffic behind her are blurred. The photo should have the candid, natural morning light feel of an iPhone image.

{ "type": "image_generation", "subject": { "reference": "Use uploaded photo for 100% face and body consistency", "description": "Young woman with long brown hair", "attire": { "outerwear": "Cream/off-white denim jacket", "innerwear": "White t-shirt", "accessories": "Apple digital watch on wrist" } }, "pose": { "action": "Taking a mirror selfie", "framing": "Close-up portrait" }, "props": { "phone_model": "White Nothing Phone (2)", "phone_details": "Distinctive transparent back design visible" }, "environment": { "lighting": "Soft and warm", "background": "Blurred indoor context" }, "style": { "aesthetic": "Ultrarealistic, high-detail, 8k resolution", "medium": "Photography" }, "text_overlay": { "content": "Shreya Yadav", "placement": "Signature style" } }

facelock_identity": "true", "accuracy": "100%", scene"Colorful Y2K scrapbook poster aesthetic, vibrant stickers, multiple subjects wearing the same outfit and hairstyle with different poses and cutouts, colorful strokes and lines, frameless collage style. Includes: close-up shot with heart-shape fingers, full-body squatting pose supporting chin while holding a white polaroid camera, mid-shot touching cheek while blowing pink bubblegum, mid-shot smiling elegantly while holding a cat ,seated elegantly with one eye winking and peace sign, and mid-shot holding daisy flowers. Holographic textures, pastel gradients, glitter accents, playful doodles, magazine cut-out graphics, chaotic yet balanced layout, extremely artistic and visually engaging", main_subject": { "description": "A young Y2K-styled woman as the main focus in the center of the scrapbook collage.", "style_pose": "Playful and confident Y2K pose — slight side hip pop, one hand holding a lens-flare keychain, face toward the camera with a cute-cool expression, slight pout, candid early-2000s photo vibe." outfit": { "top": "Cropped oversized sweater in pastel color with embroidered patches", "bottom": "pastel skirt with a white belt", "socks": "White ankle socks with colorful pastel stripes", "shoes": "white sneakers", "accessories": [ "Colorful plastic bracelets", "Chunky colorful rings", "Sparkling belly chain", "hairstyle": "type": "Y2K half-up half-down", "details": "Pastel flowers clips,thin front tendrils, wavy dark brown hair with bubblegum-pink tint on the lower strands, iconic early-2000s look." additional_visuals": "Heart, star, and butterfly stickers", "Retro sparkles", "Polaroid frames", "Neon outlines", "Doodle borders", "Magazine cutout texts: 'SO CUTE!', '199X!', 'GIRL VIBES'", "Pastel lighting", "Glossy dreamy retro glow", "Ultra-aesthetic scrapbook layout" photography_rendering": { "color_grading": "Cinematic neon Y2K", "lighting": "Soft flash lighting","skin_texture": "Smooth glossy finish", "rendering": "High-detail hyperrealistic Y2K scrapbook tone", "quality": "8K", "composition": "Perfectly balanced and artistic" negative_prompt": "no realism that breaks Y2K aesthetic, no modern 2020s clothing, no messy composition, no blurry face, no distorted hands, no extra limbs, no face warping, no low resolution, no grain, no muted colors, no watermark, no AI artifacts"

Role（角色设定） 你是一位专精 日系青春电影 与 可爱少女日常写真 的顶级摄影导演。你擅长用电影分镜和细腻光影，捕捉女主从容又笨拙的小失误，营造出暖心、治愈、略带喜剧感的早晨通勤场景。 Task（任务目标） 根据以下描述，生成一张 4 格拼接构图（Four-panel composition，2x2 网格：上左、上右、下左、下右）。 必须保持同一位日系少女形象在四格中 面孔与特征 100% 一致：黑色或深棕色齐肩直发、空气刘海、淡妆、身材偏纤细。 她的穿着为 日系少女通勤风：浅色针织开衫、白衬衫、格纹半身裙、帆布鞋，背一只简洁的单肩包或双肩包。 Visual Guidelines（视觉规范） 画面质感：cinematic, Japanese movie still, 8K, soft light, shallow depth of field, subtle film grain, natural skin texture。 色调：清晨暖色调，偏柔和的奶油色与浅蓝色，高光不过曝，整体偏 温柔、干净、可爱。 背景：日本城市住宅区与地铁站环境，干净街道、路牌、自动贩卖机、站牌等细节。 构图：2x2 网格布局（Upper-left, Upper-right, Lower-left, Lower-right），每一格都是一帧电影截图。 Panel Breakdown（四格分镜拆解） 上左（Upper-left）——【迟到的预感 / The Late Morning】 视角（Camera Angle）：室内门口处的中近景，略微高机位，好像观众站在玄关看她匆忙出门。 动作（Action）：她一边踩着鞋，一边抓起门边的包和手机，嘴里咬着一小块吐司或饭团，身体微微前倾准备冲出去。 表情（Expression）：困倦中带点慌张，眼睛微睁，眉毛略上挑，带着“糟了要迟到”的可爱慌乱。 重点（Focus）：清晨从门外洒进来的暖阳勾勒出她的轮廓，玄关处杂乱但温馨的小物（鞋架、雨伞、地垫）虚焦，突出少女的慌忙瞬间。 上右（Upper-right）——【街角小跑 / Corner Dash】 视角（Camera Angle）：略低机位的侧面全身景，仿佛跟拍镜头，背景是安静街区与十字路口。 动作（Action）：她背着包小跑，裙摆和头发随风轻轻扬起，一只手按着包带防止晃动，另一只手看腕表或手机时间。 表情（Expression）：有点紧张又带点好笑的无奈，嘴角微微撅起，眼神专注前方。 重点（Focus）：路边的自动贩卖机、路牌、低饱和的街景在运动模糊中掠过，地面晨光与她的影子形成斜斜的引导线，强化“赶时间”的节奏感。 左下（Lower-left）——【楼梯冲刺 / Stair Sprint】 视角（Camera Angle）：从地铁站楼梯下方向上拍摄的低机位，仰视她奔上楼梯或往站台方向跑。 动作（Action）：她扶着扶手快速上楼梯，步伐轻快，裙摆随着动作轻轻摆动，包斜跨在身侧。 表情（Expression）：稍微喘气但坚持、认真的神情，眉头轻皱却不失可爱。 重点（Focus）：楼梯上的光影分明，顶端可见写有站名的牌子与一点点天空。背景路人略虚化，突出少女努力赶车的剪影，整体仍保持干净、清爽的画面感。 右下（Lower-right）——【刚好赶上 / Just in Time】 视角（Camera Angle）：地铁车厢内的中近景，略高机位，好像站在她对面看着她。窗外有轻微运动模糊的隧道景色。 动作（Action）：她站在车门附近，双手抓着包带或扶手，微微弯腰喘气，肩膀仍有一点起伏。 表情（Expression）：松了口气的可爱微笑，脸颊略微泛红，眼睛里有轻松和自我调侃的感觉，像是在心里说“总算没迟到”。 重点（Focus）：柔和的车厢灯光照在她的脸上，皮肤质感细腻自然。背景是朴素的车厢座位与几位乘客的模糊轮廓，营造温柔又日常的通勤氛围。 Technical Constraints（技术限制） Consistency：四格中少女的脸部特征、发型、身材比例、服饰风格必须完全一致，确保是同一角色。 Style：hyper-realistic yet soft, cinematic, Japanese slice-of-life movie still, natural color grading, soft focus, bokeh。 Atmosphere：可爱、治愈、轻松、带一点小紧张但完全日常向，像青春爱情电影开头的通勤片头。

{ "subject": { "type": "young woman", "pose": "lying on her back, taking a selfie with her right arm extended upward", "expression": "soft smile, relaxed and natural", "gaze": "looking toward the camera", "skin_details": { "complexion": "smooth, warm, sunlit glow", "freckles": "visible on nose and cheeks" }, "hair": { "color": "medium brown", "length": "long", "style": "loose, spread out on the pillow around her head" }, "eyes": { "color": "light blue or green", "makeup": "subtle eyeliner" } }, "clothing": { "top": { "type": "ribbed tank top", "color": "white", "fit": "form-fitting", "neckline": "scoop neck" }, "bottoms": { "type": "jeans", "color": "light blue", "visibility": "partially visible" }, "accessories": { "earrings": "small studs", "necklace": "thin, minimal chain" } }, "environment": { "location": "bed or soft resting surface", "bedding": { "pillow": "white", "sheets": "white" }, "background": "neutral wall and edge of headboard or furniture barely visible" }, "lighting": { "type": "natural sunlight", "direction": "coming from upper left of frame", "effect": "creates warm highlights and soft shadows on face and torso" }, "composition": { "camera_angle": "top-down selfie angle", "framing": "close-up of face, upper torso, and part of jeans", "focus": "sharp on face and upper body", "colors": "warm skin tones, white bedding, brown hair, neutral background" }, "mood": "warm, relaxed, comfortable, natural" }

os_environment: - Choose one: "Windows 11 style desktop" or "macOS Sonoma style desktop" - If not specified, let the model choose the most natural OS UI - Use authentic UI elements based on the selected OS subject: - A character based on reference image A - Rendered with semi-3D, anime-style shading - Clear solid shadows and highlights defining volume - Appears as a desktop mascot overlay interacting with real OS UI composition: - A realistic computer desktop in 16:9 aspect ratio - Include authentic-looking application windows and icons - Character positioned naturally on or around these UI elements action: - Allow the model to freely choose mascot-like behaviors such as: - lying across the top edge of a window - sitting on a window frame - touching, inspecting, or reacting to icons - peeking from behind folders or apps - Actions should feel physically grounded and slightly playful location: - Displayed on a real OS-style desktop (Windows/macOS) - Show recognizable UI elements (e.g., Chrome window, folder icons, taskbar/dock) - Icons and windows appear authentic but used only as background elements style: - Semi-3D anime shading (soft cel-shaded look) - Defined shadows instead of rim lighting - Clean digital rendering that blends naturally with real desktop UI camera_lighting: - Neutral frontal or top lighting to create solid, directional shadows - Soft ambient light to keep color harmony with the desktop - Screenshot-like straight-on camera angle colors: - Desktop in cool OS-like tones - Character colors follow reference A accurately - Shadows emphasized for 3D volume text: - None unless needed edit_instructions: - Use reference A for character accuracy - Emphasize 3D-like volume with clear shadow planes - Ensure the character appears layered above real desktop UI elements - Keep real UI assets unmodified and only as contextual background references: A: "Character appearance reference" extras: - high resolution - realistic OS UI rendering - clean compositing and precise layer separation - allow creative mascot-like movement

Use facial feature of attached photo. A close-up shot of a young woman displayed on the screen of a compact Canon digital camera. The camera body surrounds the image with its buttons, dials, and textured surface visible, including the FUNC/SET wheel, DISP button, and the “IMAGE STABILIZER” label along the side. The photo on the screen shows the woman indoors at night, illuminated by a bright built-in flash that creates sharp highlights on her face and hair. She has long dark hair falling across part of her face in loose strands, with a soft, slightly open-lip expression. The flash accentuates her features against a dim, cluttered kitchen background with appliances, shelves, and metallic surfaces softly blurred. The mood is candid, raw, nostalgic, and reminiscent of early 2000s digital camera snapshots. Colors are slightly muted with cool undertones, strong flash contrast, and natural grain from the display. No text, no logos inside the photo preview itself. Scale ratio: 4:5 vertical Camera: compact digital camera simulation Lens: equivalent to 28–35mm Aperture: f/2.8 ISO: 400 Shutter speed: 1/60 with flash White balance: auto flash Lighting: harsh direct flash on subject, ambient low light in the background Color grading: nostalgic digital-camera tones, high contrast flash, subtle display grain, authentic screen glow.