Character Prompt Examples Collection

Transform the subject into a stylized 3D character with soft clay-like materials, rounded sculptural forms, exaggerated facial features, pastel + vibrant color palette, smooth subsurface scattering skin, large cartoon eyes, simplified anatomy. Render against a bold blue studio background with soft frontal lighting and subtle shadows. Playful, surreal, polished character-design aesthetic similar to modern stylized 3D illustration. Keep the original photo’s composition and framing.

在「东京塔」的位置，根据当地当前时间氛围和实时天气制作图片。请让指定的角色在该地点游览，使其融入场景。 生成画面： 生成一张画面为竖版3:4比例，单张图固定九宫格布局，三行三列，每个格子为独立镜头。 相机与视角： – 使用超广角或鱼眼感的镜头（大约等效全画幅 12–18mm 的观感） – 相机角度必须与原图有显著变化，可以使用的夸张机位包括： • 从正下方向上看的仰视视角 • 从正上方向下看的俯视视角 • 贴近地面的超低机位 • 从上往下的高机位 • 倾斜的「荷兰角度」构图 – 始终营造强烈的透视缩短效果：离镜头最近的身体部位显得巨大，其余身体在透视中向远处延伸 – 最终效果必须像一张大胆的时尚或街拍照片，完全写实，而不是插画或二次元风格 靠近镜头的身体部位（1–2 个，有时 3 个）： – 每一张编辑图中，选择一到两个主要身体部位极度靠近镜头（在更复杂的姿势中，有时可以是三个） – 在不同图像之间要变化这些部位，不要总是同一个地方靠近镜头 – 可以靠近镜头的身体部位包括： • 一只或两只手 / 手指向镜头伸出 • 一只或两只脚 / 鞋子 / 靴子贴近镜头 • 膝盖或大腿 • 脸部非常靠近镜头 • 在前倾姿态中靠近镜头的肩膀或胸部 – 选中的身体部位应当极度接近镜头，几乎要碰到镜头，可清晰看到皮肤纹理、布料纹理和真实的广角畸变 姿势与整体身体（复杂且多变）： – 创造与极端视角相匹配的强烈、酷炫、充满动感的姿势 – 随机使用不同类型的姿态，包括： • 站立姿势中，一条腿或一只手朝镜头伸出 • 蹲下或贴地半蹲 • 坐在地面上或坐在物体上 • 平躺在地面上，腿或脚朝向镜头 • 身体大幅向前探向镜头 • 扭转躯干、交叉双腿或弓起背部，形成更具动感的身体线条 – 允许使用复杂姿势，例如： • 两只手都靠近镜头，摆出手势（比耶、三角形、用手指做画框、指向观者等） • 双脚都朝向镜头 • 一只手和一只脚同时作为前景的大型元素 • 脸部靠近镜头，同时手或脚也在透视关系中出现 – 即使在极端透视缩短下，也要保持合理可信的人体结构 机位与态度（随机化）： – 随机改变相机角度与方向（朝上、朝下、侧向、倾斜构图），同时保持画面构图视觉上平衡、有冲击力 – 气质保持酷、从容，自信，偏向时尚大片或街头风格，具体依照原始穿搭气质 – 面部表情可以变化（严肃、俏皮、自信、神秘等），但必须始终看起来是同一个人 光线与画面渲染： – 保持真实的阴影以及与地面 / 地板的接触关系 – 高分辨率与清晰细节，能看到皮肤纹理、布料纹理以及材质高光 变化与随机性： – 每一张小图都应当与其他小图有明显区别，在以下方面保持多样化： • 相机角度 • 姿势类型 • 哪些身体部位最靠近镜头 • 构图方向（正向、倾斜、俯视、仰视等） – 避免一再重复完全相同的「单脚贴近镜头」构图，要呈现丰富多样的动态姿势和机位变化 严格规则： – 不要把人物换成别人 – 不要改变服装类型；只能通过姿势、视角以及衣物的自然运动来改变表现方式 – 不要把场景移动到指定经纬度以外的地点；始终保持在指定经纬度地点的合理延展范围内 – 不要添加文字、标志、水印或图形设计元素 – 不要改成油画、插画或动漫风格；必须保持照片级写实效果

Role & Subject: A massive, encyclopedic 16:9 3D infographic poster titled "THE EVOLUTION OF [Product Name]". The visual style is a high-end fusion of museum-grade product photography and complex technical engineering blueprints. The Hero Lineup (Chronological Core): A complete, linear chronological lineup of 8-12 historical versions of [Product Name], ranging from the very first prototype to the latest futuristic model. They are arranged with precision on a measurement scale/ruler base running horizontally across the center. Rendering: Hyper-realistic 3D, 8k resolution. Emphasis on the evolution of textures: showing the aging of early [Material Vibe] vs. the pristine, high-tech finish of modern versions. Brand Atmosphere (The Canvas): Background: A deep, rich [Brand Color] textured background. It is heavily layered with low-opacity watermarks of vintage patent drawings, handwritten engineering notes, and newspaper clippings related to the brand's history. Header: A prominent, high-contrast brand logo displayed at the top center, with a bold typography title. The "Hyper-Dense" Information Layer (The PUNCH Style): The layout is overwhelmed with organized information (creating a "Data aesthetics" look): Dense Annotation Network: Hundreds of fine white hairlines connecting specific [Key Components] (e.g., curves, buttons, engines) to compact text blocks and data tables floating in the space. Contextual Zones: "Era Modules" floating above the products, representing different historical decades with iconographic markers. Magnifying Inserts: Circular "Zoom-in" lenses scattered in empty spaces, showing extreme macro close-ups of texture details and internal mechanisms. Tech Specs Strip: A structured data bar at the very bottom listing precise specifications (weight, dimensions, year, material code). Technical Specs: Octane render, Unreal Engine 5 aesthetic, editorial layout, information design masterpiece, volumetric lighting, sharp focus, professional color grading. --ar 16:9 --v 6.0 --stylize 300 「以泡泡玛特发展史为例」

需要上传2张照片：1、上传人物照片 2、上传想要在手机上显示的图像，再输入以下提示词 { "edit_type": "extreme_wide_angle_phone_edit", "source": { "_hint": "元画像の人物・服・雰囲気を編集するベース。新キャラ禁止。", "mode": "EDIT", "reference_images": { "first": "base_photo_person_and_environment", "second": "screen_content_for_phone" }, "preserve_from_first": { "_hint": "顔・髪型・服装は必ず同一人物として扱うための固定。", "same_person_or_group": true, "same_faces": true, "same_hairstyles": true, "same_outfits": true, "same_environment_style": true } }, "identity": { "_hint": "表情の統一化。人物のアイデンティティを崩さず保持。", "keep_identity_consistent": true, "all_people_clearly_recognizable_as_original": true, "expression": "bright_natural_smile" }, "camera_effect": { "_hint": "スマホを近づけたときの誇張パースを美しく安定化。", "perspective": "extreme_wide_angle", "style": "dynamic_photorealistic", "near_objects_appear_large": true, "far_objects_recede_dramatically": true, "allow_view_from_above_or_below": true }, "pose": { "_hint": "元画像と同じポーズ禁止。手の動きを強調して破綻防止。", "pose_can_change": true, "must_be_completely_different_from_reference": true, "do_not_replicate_or_approximate_original_pose": true, "style_tags": [ "stylish", "complex", "fluid", "powerful" ], "focus_on_expressive_hands": true, "avoid_arm_distortion": true, "allow_multiple_body_parts_near_lens": true }, "phone": { "_hint": "スマホ専用領域。持ち方・向き・手元の自然さを定義。", "allowed": true, "holding_styles": [ "one_handed", "two_handed", "low_angle", "high_angle", "tilted", "sideways", "near_chest", "near_hip", "casual_carry", "partially_toward_lens" ], "rules": { "_hint": "“レンズに向ける強制”を避け、自然な持ち方で画面が見える構図へ。", "each_person_may_hold_one_phone": true, "priority_is_natural_and_relaxed_body_structure": true, "do_not_force_phone_directly_toward_camera": true, "screen_should_be_naturally_visible_when_possible": true } }, "screen_replacement": { "_hint": "差し替えスクリーン。UIなし・歪みなし・自然な貼り込み。", "target": "visible_phone_screen", "use_second_reference_image_as_content": true, "overlay_cleanly_on_visible_screen_area": true, "fit_without_distortion": true, "respect_screen_shape": true, "no_additional_cropping": true, "ui_constraints": { "_hint": "SNSバーやアプリ枠の発生を完全禁止。", "no_ui": true, "no_icons": true, "no_status_bar": true, "no_app_frame": true, "show_only_content_from_second_reference": true } }, "environment": { "_hint": "元写真の空気感を保つが、季節や天気には依存しない汎用設計。", "preserve_environment_style_from_reference": true, "lighting_consistent_with_reference": true, "expand_space_for_wide_angle_view": true, "keep_texture_and_color_tone_consistent": true }, "composition": { "_hint": "スマホ近接によるダイナミック構図の安定化。", "dynamic_but_readable": true, "extreme_depth_emphasis": true, "allow_phone_close_to_lens": true, "keep_all_people_visually_balanced": true }, "constraints": { "_hint": "意図せぬ変化を禁止する保護設定。", "no_new_characters": true, "no_change_in_age_or_gender_presentation": true, "no_costume_change": true, "no_change_to_reference_location_type": true, "respect_original_photographic_style": true } }

Role & Subject: A massive, encyclopedic 16:9 3D infographic poster titled "THE EVOLUTION OF STARK INDUSTRIES IRON MAN SUITS". The visual style is a high-end fusion of museum-grade product photography and complex technical engineering blueprints. The Hero Lineup (Chronological Core): A complete, linear chronological lineup of 10 historical versions of Iron Man Armors, ranging from the crude, bulky Mark I prototype forged in a cave to the sleek, bleeding-edge Mark LXXXV nanotechnology model. They are arranged with precision on a glowing holographic measurement scale/ruler base running horizontally across the center. Rendering: Hyper-realistic 3D, 8k resolution. Emphasis on the evolution of textures: showing the aging of early crude welded scrap metal, heavy iron, and exposed wiring of the Mk I vs. the pristine, highly-polished hot-rod red and gold plating, and fluid nanotech finish of modern versions like the Mk 50 and Mk 85. Brand Atmosphere (The Canvas): Background: A deep, rich Hot Rod Red and metallic Gold textured background, resembling an armored plating surface. It is heavily layered with low-opacity watermarks of vintage Stark Industries patent drawings, handwritten engineering notes by Tony Stark (with coffee stains), and newspaper clippings related to the Avengers' history. Header: A prominent, high-contrast STARK INDUSTRIES logo displayed at the top center, with a bold typography title. The "Hyper-Dense" Information Layer (The PUNCH Style): The layout is overwhelmed with organized information (creating a "Data aesthetics" look): Dense Annotation Network: Hundreds of fine white and cyan hairlines connecting specific components (e.g., Arc Reactors, Repulsor Transmitters in palms, Articulated Helmet Faceplates, Micro-missile Compartments, Flight Stabilizers) to compact text blocks, energy output charts, and data tables floating in the volumetric space. Contextual Zones: "Era Modules" floating above the suits, representing different phases (e.g., "AFGHANISTAN ESCAPE," "THE AVENGERS INITIATIVE," "ULTRON OFFENSIVE," "INFINITY WAR NANO-TECH") with iconographic markers. Magnifying Inserts: Circular "Zoom-in" lenses scattered in empty spaces, showing extreme macro close-ups of texture details like the crude welding on Mark I, the mechanical joint articulation of Mark III, and the fluid nano-particle assembly of Mark LXXXV. Tech Specs Strip: A structured data bar at the very bottom listing precise specifications (Model Number, Weight in tons/kg, Power Source Type, Year of Creation, Primary Material Code). Technical Specs: Octane render, Unreal Engine 5 aesthetic, editorial layout, information design masterpiece, cinematic volumetric lighting, sharp focus, professional color grading, blockbuster movie poster vibe. --ar 16:9 --v 6.0 --stylize 350

{ "image_request": { "goal": "Create a mixed-media reality-bending mirror selfie / blending 2D anime characters into a 3D real-world photo / cozy autumn academia fashion meets otaku dream", "meta": { "image_type": "Mixed Media Composite / Anime in Real Life / Mirror Selfie / Fashion Snapshot", "quality": "Best Quality, Photorealistic Center Subject, Sharp Anime Lines, Mixed Dimensionality", "color_mode": "Full Color / Natural Indoor Tones / Warm Beige & Brown Palette", "style_mode": "raw_photoreal blended with cel-shaded anime", "aspect_ratio": "3:4", "resolution": "1080x1920" }, "creative_style": "A playful fusion of dimensions where 2D anime characters seamlessly occupy a real-world space. The photorealistic central figure wears a cozy 'Autumn Academia' outfit, contrasting with the flat, cel-shaded anime characters. The vibe is a casual, dream-like hangout caught in a mirror reflection.", "overall_theme": "Anime meets reality / Autumn Academia Fashion / Mirror selfie with fictional characters", "mood_vibe": "Cozy, stylish, playful, surreal, dimensional barrier breaking", "style_keywords": [ "mixed media", "mirror selfie", "anime in real life", "autumn academia", "cable knit texture", "cel-shaded", "photorealistic fashion", "hallway reflection" ], "subject": { "count": "3 (1 human female, 2 anime males)", "type": "human and anime characters", "identity": "Center: Young woman (Photorealistic). Left: Spiky black-haired anime male (Megumi style). Right: White-haired anime male (Gojo style).", "identity_preservation": { "description": "Center subject is a photorealistic human wearing the specific autumn outfit. Side subjects retain distinct 2D anime art style.", "notes": "Maintain clear stylistic distinction: Highly detailed texture on the cardigan/skirt vs. bold anime lines for the boys." }, "age_appearance": "Young adults", "skin": "Human: Natural texture, soft lighting. Anime: Flat cel-shaded tones.", "clothing": { "top": "Human: White cotton poplin shirt worn under a loose, oversized beige wool cable-knit cardigan. Left Anime: Black long-sleeve shirt. Right Anime: White t-shirt.", "bottom": "Human: Brown plaid/tartan flannel mini skirt and black knee-high socks. Left Anime: Grey pants. Right Anime: Black pants.", "accessories": "Human: Smartphone (taking the photo). Right Anime: Sunglasses.", "textures": "Emphasize the high-depth weave of the beige cardigan and the flannel texture of the skirt on the human subject." }, "facial_features": { "expression": "Human: Obscured by phone or neutral/soft smile. Left Anime: Cool, stoic, arms crossed. Right Anime: Confident, smirk, adjusting glasses." }, "hair": { "style": "Human: Natural styling suitable for an academic look. Left Anime: Spiky energetic black hair. Right Anime: White hair with bangs down." } }, "pose_action": { "overall_pose": "Casual group mirror selfie. Center subject stands straight taking the photo holding phone. Left subject leans casually against the mirror frame. Right subject stands tall.", "body_position": "Standing, full body visible in mirror reflection to show the skirt and knee-high socks.", "hands": "Center: Holding phone. Left: Arms crossed. Right: Touching sunglasses/face." }, "environment": { "setting": "Indoor hallway or lobby with high ceilings and reflective surfaces (matches original scene to keep the context).", "location": "Modern building interior with marble/tiled walls and glass elements.", "lighting": "Natural daylight filtering in, highlighting the texture of the wool cardigan.", "atmosphere": "Clean, bright, casual everyday hangout." }, "background": { "color": "Beige, tan, brown (marble stripes) - compliments the beige/brown outfit.", "effect": "Reflected in mirror, showing a tiled floor and a glass door leading to the outside." }, "lighting": { "type": "Natural diffuse", "source": "Windows/Doors behind the subjects (reflected)", "quality": "Soft, even. Creates soft shadows on the cable-knit texture.", "tone": "Warm neutral." }, "camera": { "sensor_format": "Smartphone Camera", "position_angle": "Eye-level mirror reflection", "framing": "Vertical portrait shot capturing full bodies.", "composition": { "framing": "Mirror frame visible with geometric grid lines overlaying the reflection.", "depth": "Deep depth of field." } }, "post_processing": { "final_touch": "Digital composite look. Ensure the lighting on the photorealistic cardigan matches the environment, while anime characters remain 2D." }, "negative": { "style": "3D render of anime characters, messy drawing, bad anatomy, low resolution", "content": "distorted faces, extra limbs, human subject looking like a drawing, anime characters looking too realistic" }, "additional_controls": { "special_notes": "Focus on the material contrast: Real wool and flannel vs. Anime flat colors.", "vibe": "Fan edit, OOTD (Outfit of the Day)." } } }

让指定角色看起来像是在经纬度 35.63323748316045, 139.88033890258112 处观光。设计一个类似摄影集的精美版面。充分利用 9:16 的比例，为这本日本杂志制作一个专题页面。这将是一个重要的阅读页面，会影响访问量，因此请尽可能多地包含信息。

Create a captivating poetic visual composition based on this prompt, seamlessly integrating the four lines of the quatrain into a unified masterpiece. Each panel perfectly illustrates one line of the poem, with the corresponding verse and the poem’s title and author elegantly embedded within its respective scene using Chinese characters. Together, these panels form a harmonious and cohesive panoramic artwork. Rendered with rich detail, cinematic lighting, 8K resolution, and highly refined textures. --ar 4:3 Poem Title: 登鹳雀楼

{ "subject": "reference upload image - maintain exact consistency with uploaded image. Person sitting on bed ledge holding fanned stack of cash, looking upward with exaggerated expression, slightly tongue out", "pose": "sitting on bed ledge, legs spread, holding fanned A stack of Japanese 10,000 yen bills in both hands at chest level, head tilted back looking upward", "character": { "face": "reference upload image", "hair": "reference upload image", "body_type": "reference upload image", "skin_tone": "reference upload image" }, "clothing": "reference upload image - maintain exact consistency with uploaded image", "accessories": { "jewelry": "reference upload image", "props": "large stack of cash bills fanned out in hands, scattered A stack of Japanese 10,000 yen bills on surface, yellow designer bag visible in background" }, "expression": "Mouth wide open with a melted, dazed, uncontrollable smile, Eyebrows drooping heavily downward, looking upward with exaggerated expression, mouth open, energetic and celebratory, "environment": { "location": "reference upload image", "setting": "reference upload image", "background": "reference upload image", "surface": "reference upload image" }, "lighting": { "type": "night photography with camera flash", "source": "clean white room lights, camera flash", "quality": "warm artificial lighting mixed with flash, creates contrast and highlights subject" }, "camera": { "angle": "low angle, shot from below looking up at subject", "perspective": "close-up, environmental portrait", "technique": "flash photography" }, "style": { "aesthetic": "luxury lifestyle photography", "mood": "energetic, celebratory, aspirational", "color_palette": "warm tones, contrast colors" }, "consistency_note": "Use uploaded reference image for all character features including face, hair, body type, skin tone, facial structure, clothing, and accessories. Maintain strict visual consistency with reference image.", "output": { "aspect_ratio": "9:16", "orientation": "vertical" } }

4K hyper-detailed fashion photograph featuring hyper-realistic rendering. **Crucial Character Consistency:** The character featured is precisely the same person shown in reference images , maintaining consistent facial features, hair style, and body structure across all shots. { "core_structure": { "description": "一张超写实的电影感肖像，描绘了一位身着华丽唐代服装（齐胸襦裙）的年轻女子，手持红色刺绣团扇，在飘雪的黑色背景中回眸。", "elements": [ { "object": "人物主体", "attributes": ["年轻东亚女性", "精致唐风妆容(花钿, 面靥)", "回眸姿态", "优雅"] }, { "object": "服饰 (唐风)", "attributes": ["唐代齐胸襦裙 (Tang Dynasty Qixiong Ruqun)", "袒领/低胸抹胸 (Low-cut bodice)", "半透明大袖衫 (Sheer wide sleeves)", "飘逸的披帛 (Flowing Pibo ribbon)", "红色与金色主调"] }, { "object": "发型", "attributes": ["唐代高髻 (High bun)", "牡丹花发饰", "金步摇", "华丽发梳"] }, { "object": "道具", "attributes": ["红色刺绣团扇 (保持不变)", "精致流苏"] }, { "object": "环境", "attributes": ["飘落的雪花 (Falling snow)", "黑色背景 (Dark background)", "微光氛围"] } ] }, "style_definition": { "primary_style": "photorealistic | cinematic | classical Chinese portrait", "rendering_quality": "8k resolution | ultra-detailed | masterpiece", "surface_textures": ["silk", "lace", "skin texture", "snow particles"], "lighting": "rim lighting | soft facial spotlight | moody dark atmosphere" }, "technical_specifications": { "camera_settings": { "depth_of_field": "shallow depth of field", "focal_length": "85mm", "aperture": "f/1.8", "exposure": "low key with highlight on face" }, "resolution": "professional quality", "rendering": ["high contrast", "sharp focus"], "physics_accuracy": ["natural fabric flow", "frozen snow motion"] }, "material_properties": { "skin_textures": ["pale", "soft"], "fabric_details": ["embroidery", "sheer gauze (typical for Tang)", "layered silk"], "surfaces": ["matte background", "reflective jewelry"], "transparency": ["translucent outer sleeves"] }, "environmental_factors": { "atmosphere": ["cold but romantic", "quiet", "ethereal"], "time_season": ["winter night", "snowing"], "particles": ["white snowflakes", "cold breath"] }, "composition_controls": { "perspective": "eye-level", "framing": "medium shot | looking back over shoulder", "subject_placement": "center-right biased" }, "quality_keywords": { "include": ["Tang Dynasty fashion", "historical accuracy", "snowy night", "beautiful eyes"], "avoid": ["high collar (Ming style)", "thick clothes", "modern makeup"], "reference": ["Tang Dynasty paintings", "cinematic photography"] } }

{ "meta_control": { "generation_mode": "multi_panel_consistent", "priority_stack": ["identity_lock", "perspective_physics", "material_fidelity", "environmental_coherence"], "quality_target": "editorial_print_ready" }, "intent": { "primary": "High-fashion streetwear editorial with extreme wide-angle perspective study", "secondary": "Technical demonstration of foreshortening and forced perspective", "publication_context": "Double-page spread, fashion magazine collage layout" }, "frame": { "aspect_ratio": "3:4", "layout": { "type": "2x2 grid collage", "gutter_width": "2px white or seamless", "panel_uniformity": "identical dimensions per panel" } }, "subject": { "type": "Human female fashion model", "identity_lock": { "enforcement_level": "strict", "anchor_features": ["face_geometry", "skin_tone", "body_proportions", "hair_style"] }, "biometrics": { "age_presentation": "22-26", "height_cm": 175, "build": "Slender athletic, model proportions", "ethnicity_presentation": "Northern European features" }, "facial_signature": { "structure": "Angular diamond face, high cheekbones, defined jawline", "eyes": "Sharp almond, steel grey, graphic black winged liner extending 8mm", "nose": "Refined, straight, small silver hoop piercing on left nostril", "lips": "Natural shape, matte nude-pink", "skin": "Fair, visible pores and natural texture, subtle peach fuzz, tiny freckle cluster left cheekbone", "expression_default": "Cool confidence, intense direct eye contact, composed" }, "hair": { "style": "Platinum blonde straight bob, blunt bangs ending at eyebrows", "texture": "Silky, light-catching, individual strand definition", "behavior": "Natural movement responding to pose changes" }, "wardrobe": { "jacket": { "item": "Oversized bomber jacket", "material": "Ripstop nylon, high gloss", "color": "Neon orange (vivid, saturated)", "state": "Unzipped, hanging open", "light_behavior": "Sharp specular highlights, visible weave texture" }, "top": { "item": "Crop top", "material": "Black synthetic mesh, diamond pattern", "fit": "Tight, stretched across torso", "transparency": "Semi-sheer, skin visible through weave" }, "pants": { "item": "Tactical cargo pants", "material": "Heavy cotton twill, matte", "color": "Charcoal grey", "details": "Multiple pockets, silver buckles, black nylon straps, baggy fit" }, "footwear": { "item": "Platform sneakers", "color": "White, chunky sole", "condition": "Clean but worn, realistic sole texture" } }, "accessories": { "neck": "Layered heavy silver Cuban link chains, 3 chains varying thickness", "hands": "Silver rings on index and middle fingers both hands" } }, "panels": [ { "id": 1, "position": "top-left", "concept": "Extreme low-angle sneaker perspective", "camera": { "height_cm": 10, "distance_cm": 35, "angle": "Looking up at 75 degrees" }, "composition": { "foreground_dominant": "Right sneaker sole filling 40% of frame, laces in sharp focus", "midground": "Legs receding upward", "background": "Torso and face small in upper frame, looking down at camera" }, "subject_pose": "Standing, weight back, right foot extended toward lens", "expression": "Looking down, slight smirk" }, { "id": 2, "position": "top-right", "concept": "Bird's-eye reaching hand", "camera": { "height_cm": 200, "distance_cm": 60, "angle": "Looking straight down" }, "composition": { "foreground_dominant": "Hand reaching up, fingers spread, appearing oversized", "midground": "Face looking up", "background": "Body compressed, pavement visible around edges" }, "subject_pose": "Deep squat, one arm reaching directly up to camera", "expression": "Intense upward eye contact, serious" }, { "id": 3, "position": "bottom-left", "concept": "Fisheye face extreme close-up", "camera": { "height_cm": 150, "distance_cm": 20, "angle": "Dutch tilt 20 degrees" }, "composition": { "foreground_dominant": "Face filling 70% of frame, nose and eyes enlarged by proximity", "background": "Environment warping and curving at edges, slight motion blur" }, "subject_pose": "Leaning face toward camera, shoulders back", "expression": "Piercing eye contact, one eyebrow slightly raised, confident" }, { "id": 4, "position": "bottom-right", "concept": "Seated knee-forward perspective", "camera": { "height_cm": 40, "distance_cm": 50, "angle": "Slight upward looking" }, "composition": { "foreground_dominant": "Knees and shins large in frame, cargo pant texture detailed", "midground": "Torso leaning forward", "background": "Face in upper third, hands resting on knees" }, "subject_pose": "Seated on pavement, knees up, leaning toward camera", "expression": "Relaxed confidence, soft direct gaze" } ], "environment": { "location_type": "Urban industrial alleyway", "surfaces": { "ground": "Weathered concrete pavement, cracks, texture, subtle debris", "walls": "Concrete and brick, metallic rolling security doors, faded graffiti tags" }, "atmosphere": "Gritty urban, authentic street context", "consistency_rule": "Identical environment visible across all four panels" }, "lighting": { "source": "Natural afternoon sunlight", "quality": "Hard directional light", "direction": "High side-light, approximately 45 degrees from left", "shadow_character": "Sharp-edged, deep shadows", "color_temperature_kelvin": 5500, "fill": "Minimal, ambient bounce from pavement only", "specular_behavior": "Strong highlights on nylon jacket, chain jewelry, sneaker rubber" }, "camera_global": { "lens": "Ultra-wide rectilinear, 12-14mm equivalent", "aperture": "f/8", "depth_of_field": "Deep, foreground to background sharp", "distortion": "Barrel distortion, edge stretching, exaggerated foreshortening", "sensor": "Full-frame, high resolution" }, "post_processing": { "color_grade": { "contrast": "High", "saturation_subject": "Vivid, especially neon orange jacket", "saturation_background": "Slightly desaturated, muted", "blacks": "Deep, crushed slightly", "highlights": "Preserved, not blown" }, "texture": "8K resolution equivalent, visible skin texture, fabric weave, material detail", "film_treatment": "Subtle RAW photo grain, not excessive" }, "negative_constraints": { "style_rejection": ["illustration", "anime", "cartoon", "painting", "drawing", "3d render", "CGI", "digital art", "AI art look", "smooth skin filter", "beauty filter"], "anatomical_rejection": ["extra fingers", "missing fingers", "fused fingers", "extra limbs", "anatomical errors", "broken joints", "impossible body positions"], "consistency_rejection": ["face change between panels", "different person", "clothing change", "hair color change", "inconsistent skin tone", "different lighting between panels"], "technical_rejection": ["blur", "low resolution", "jpeg artifacts", "noise", "watermark", "text", "logo", "signature"], "lens_rejection": ["telephoto compression", "portrait lens look", "85mm aesthetic", "no foreshortening", "flat perspective"] } }

A hyper-realistic isometric miniature diorama encased in a cubic enclosure. Structure: The cube features two solid back walls [describe the texture/material of the back walls, e.g., textured with brick, wood paneling, forest greenery, stone blocks] forming the [describe the setting type, e.g., urban backdrop, cozy room corner, dungeon cell], and two transparent glass front walls, creating a perfect cutaway view. The entire scene is strictly contained within this cube. Inside the cube is [SCENE DESCRIPTION: Describe the specific iconic movie scene environment. Mention key props, furniture, floor texture, and specific clutter that makes the scene recognizable]. Character: A photorealistic miniature person, representing [ACTOR NAME] as [CHARACTER NAME]. They are wearing [describe the iconic outfit/costume in detail]. The character is [ACTION: describe their pose/action, e.g., sitting, dancing, standing], with a [EXPRESSION] expression. [Optional: mention any specific hand-held props]. Materials & Textures: All elements feature hyper-realistic textures (e.g., [list 2-3 specific textures relevant to the scene, e.g., weathered wood, velvet fabric, rusted metal]). It looks like a masterfully crafted, museum-quality miniature model. Lighting: [ATMOSPHERE NAME]: [describe light sources and mood, e.g., warm golden sunlight, harsh fluorescent light, moody noir shadows], creating cinematic depth within the glass enclosure. Background: A clean, solid neutral grey background completely isolating the cube. No table texture, no blurred room surroundings, no external clutter. Camera: A detailed macro photograph from a slightly elevated isometric three-quarter view, centering on the front glass corner. High aperture to keep the entire miniature in focus.

Top-tier clay stop-motion animation style poster for [在此填入核心主题/人物] - MAXIMUM EXPRESSION & IMMERSION [1. VISUAL STYLE & ATMOSPHERE | 核心画风] - Style: 3D Clay Art, Q-version cute proportions, Stop-motion Animation aesthetic. - Texture: Soft matte clay, visible fingerprints, rounded edges, slight imperfections (handmade feel). - Camera: Macro photography, shallow depth of field (Bokeh), diorama effect. - Color Palette: [在此填入颜色关键词，如：Soft Pastel, Dark Gothic, Vibrant Neon]. [2. IMMERSIVE COMPOSITION | 沉浸式构图] - Concept: A seamless 3D micro-world. The character is embedded in the environment, not just standing in front of it. - Perspective: [在此填入视角，如：Low angle, Top-down, Fish-eye, Isometric]. - Foreground: [在此填入前景物体，用于增加纵深感]. - Mid-ground: Q-version [在此填入人物描述] doing [在此填入动作], surrounded by [在此填入环境元素]. - Background: [在此填入背景元素], blurred for depth. [3. LIGHTING & MOOD | 光影氛围] - Lighting Type: [在此填入光效，如：Warm golden hour, Cold moonlight, Dramatic spotlight, Volumetric lighting]. - Shadow: Soft, colored shadows (not pitch black). [4. INTEGRATED TEXT DESIGN | 文字物理化融合] - Main Title: "[在此填入中文标题]" and "[在此填入英文标题]". - Title Style: The text is PHYSICALLY formed by [在此填入标题材质，如：Clouds, Wood, Neon tubes, Stone]. - Body Copy: "[在此填入中文文案]" / "[在此填入英文文案]". - Copy Placement: Written directly on [在此填入文案载体，如：A floating paper, A wall, A road sign] within the scene. - Font Style: [在此填入字体风格，如：Handwritten, Graffiti, Elegant calligraphy], natural and textured. [5. TECH SPECS | 技术参数] - Resolution: 4K Definition, High Fidelity, Octane Render style. 💡 如何像设计师一样填写？（使用指南） 为了达到最佳效果，请在填写[ ]内容时参考以下“心法”： 1. 构图 (Perspective) - 打破常规 不要只用“平视”。尝试： Low angle (仰视)：表现伟大、压迫感（如贝多芬、诺兰）。 Top-down (俯视)：表现掌控、精致感（如韦斯·安德森、莫扎特）。 Inside-out (内部视角)：如从后备箱看出去、从山洞看出去。 2. 标题材质 (Title Material) - 脑洞大开 不要让 AI 随便生成字体，指定一种和主题相关的**“物体”**： 写音乐家？标题由**“五线谱”或“乐器零件”**组成。 写赛车手？标题由**“赛道沥青”或“轮胎痕迹”**组成。 写厨师？标题由**“面粉”或“蔬菜切片”**组成。 3. 文案载体 (Copy Placement) - 拒绝字幕 不要让文字悬浮在空中，给它找个**“落脚点”**： 写在飘落的树叶上。 写在斑驳的墙壁上。 写在扔在地上的纸团上。 写在显示器的屏幕里。

In a room infused with subtle magical ambience, {Reality} stands with their back to the camera, gazing intently into a slightly oversized oval magic mirror. The mirror appears realistic and physically accurate, with a natural reflective sheen and believable optical behavior, yet within its surface faint currents of mystical light and soft energy ripples flow gently, creating a subtle multicolored iridescence that blurs the line between realism and fantasy. In the reflection, the image of {Inner_Reflection} appears—symbolic, powerful, and metaphorically resonant. While the reflection follows true mirror physics, it is surrounded by delicate stardust particles and a faint luminous halo, hinting at an inner force manifesting through the mirror. Soft golden sunlight enters from a side window, blending naturally with the mirror’s gentle magical glow. This interplay of real-world lighting and supernatural highlights produces a dreamlike but credible visual contrast. {Reality} and the reflected {Inner_Reflection} occupy most of the composition, with the mirror proportioned only slightly larger than the character—large enough to feel mystical, yet still realistic and grounded. Rendered in cinematic lighting, surrealist style, ultra-detailed realism, 8K resolution, highly lifelike. --- {Reality}: a small orange tabby cat {Inner_Reflection}: a majestic, powerful lion

A highly detailed photorealistic aerial shot looking down on a colossal Korean young woman wearing a stylish jacket and layered outfits, positioned in a crowded Tokyo street; the giant is playfully driving a tiny car with her hands while interacting with nearby buildings and street signs, tiny people and cars clustered near her feet for scale; visible close-up hands and textured clothing details; morning daylight with soft directional sunlight casting long gentle shadows, cool urban reflections on wet pavement, slight atmospheric haze and depth of field, high-resolution, crisp details, cinematic composition with leading lines along the street, muted vibrant color palette, realistic skin textures and fabric wrinkles, subtle motion blur on the tiny cars, photorealistic lens characteristics

A clear, floating cute 3D cartoon diorama scene in a circular composition with rotational symmetry, echoing a yin-yang layout: Scene: - a single floating circular emblem viewed from isometric bird's-eye perspective (45° angle looking down). - one swirling half of the circle shows [Subject]'s most iconic defining scene or aspect (primary realm). - the opposite swirling half is the contrasting opposite realm, occupying the complementary yin-yang territory. - both realms share the same gravity direction and isometric orientation. - each half may be a continuous shared landmass OR two structurally separate diorama units that curve around each other, forming a recognizable yin-yang composition. Interpret narrative essence: - treat [Subject] as ONE overarching theme or entity with TWO conflicting aspects. - let each realm embody one aspect in a clear, visual way: the first half leans into aspect A, the opposite half leans into aspect B. - use characters only where they naturally serve the contrast: they may appear in one realm, both realms, or take different forms — repetition is optional, never a strict requirement. - place 2 distinct symbolic objects, each rooted naturally in its own world, echoing each other across the curve to suggest what was abandoned or gained between these two aspects. Yin-yang relationship: - design the two realms as interlocking, yin-yang-like shapes inside the circle: interlocking territories that echo yin-yang flow. - place the most focal element of each realm at its "yin-yang eye" position — the visual anchor point within each half's territory. - the two realms should feel spatially intimate and cohesive — bring them closer together to create a unified, compact circular emblem rather than loosely scattered islands. - the two halves are typically structurally separate with a subtle atmospheric gap, but may share ground where narrative calls for it — when adjoining, boundaries flow naturally through lighting, color temperature, and ground material shifts. - edge treatment: encourage organic overflow at key points — tall structures gently break the circular silhouette, ground edges fade atmospherically rather than clip sharply. Composition: - clean, dramatic circular multiverse — the circle reads as one unified, spatially compact emblem, with two interlocking narrative poles sitting close and relating to each other. - amplify contrast between the two realms: maximize visual tension to make the duality unmistakable. - vast open view: the scene extends naturally to its edges without boundary walls, fences, or enclosures — the horizon remains visible and unobstructed. Shadow: BARELY visible, extremely soft non-contact shadow with expansive fadeout — extends well beyond the diorama's footprint with a gentle gradient that blurs into the background. Viewed from bird's-eye perspective, nearly circular in shape. Render: - C4D. high poly with soft shading, rounded edges and bevels. - realistic PBR materials with tactile authenticity — avoid glossy plastic or resin appearance. - intricate textures, delicate detail, vivid harmonized colors. SSS texture:true. - CRITICAL: ground planes must remain flat and level with natural material textures appropriate to each realm. Background: - a single unified, clean, subtle gradient sky as the shared environment of both realms, providing generous breathing space around the circular diorama. Typography (top-center, cinematic poster-style design): - a prominent title "[Subject]" in a slim elegant serif (remove the brackets). - beneath it, a poetic, insightful subtitle that distills the story’s deepest truth or tension into one profound line. - create clear visual hierarchy through scale and weight contrast; allow auto line wrap and slight overlap with the top of the circle if needed. Enhance: - professional cinematic lighting, shaped to emphasize the contrast between the two realms while keeping both legible. - if characters are present, use dynamic, emotionally expressive poses that clearly align with the aspect of their realm. - strong sense of visual depth within each realm. Scene / lighting / cultural aesthetics: - contextually appropriate to [Subject]. Negative: - [cropped elements at canvas edges, plastic/resin, hard cartoon outlines, underexposed, creepy, ceiling]. ar=1:1 [Subject] =

A glowing oval portal stands between {Real_World_Scene} and {Portal_Inner_Scene}. Outside the portal, the real-world environment is {Real_World_Scene}, depicted with realistic textures, grounded atmosphere, and gritty or natural tones. Inside the portal lies {Portal_Inner_Scene}, vibrant, imaginative, and contrasting sharply with the real world. {Portal_Inner_Character} is stepping through the portal, turning back with a dynamic glance while holding the viewer’s hand, as if guiding them into the other world. The portal emits mystical blue-purple light, drawn with clean outlines and soft shading consistent with the character’s style. Optional overall visual style: {Art_Style} (defaults to a bold contrast between anime and reality). Camera angle: third-person perspective, clearly showing the viewer’s hand being pulled into the new world. No blur; sharp visual distinction between the two worlds. Aspect ratio: 2:3. ---- Real_World_Scene: A winter street in Tokyo, low-saturation neon lights with a faint snowy haze Portal_Inner_Scene: A futuristic city street glowing with blue holograms, neon refracting through the air Portal_Inner_Character: A cyborg girl with mechanical limbs wearing a semi-armored exosuit

Rendered as a complete Poster design (suggested aspect ratio 3:4 or 9:16 for a full vertical poster). The overall visual style is a Soft-Focus Healing Style combining a Wes Anderson aesthetic, characterized by dreamy, cozy, warm and soft volumetric lighting. 4K Resolution, high aesthetic value. [SCENE & MATERIAL STYLE]The entire scene is rendered with a distinctive material mix of Soft Matte Clay (哑光软陶) and a little soft Felt (少许羊毛毡), creating fluffy and tactile textures throughout the composition. The color palette is dominated by soft Pastel colors (Morandi/Macaron tones). [TEXT INTEGRATION]The scene integrates a creatively formed main title using environmental elements (e.g., formed by clouds, branches, or clay objects). It also includes a small, delicate, thin-stroke handwritten Chinese slogan that blends softly into the environment, appearing as part of the scene's texture rather than an overlay. 生成示列（爱因斯坦）：

{ "Objective": "Create a hyper-realistic 8K surreal winter fantasy portrait featuring a young ethereal woman and a majestic deer sharing an intimate moment in a snowy forest.", "Subject_1_Woman": { "Identity": "Maintain facial features, hairstyle, and general appearance consistent with the provided reference image if one is used.", "Appearance": { "Skin_Tone": "Pale, ethereal", "Hair": "White-blonde hair with cold highlights", "Eyelashes": "Icy, frosted texture", "Accessories": [ "Luxury ski goggles" ], "Wardrobe": { "Coat": "Vintage wool plaid coat in cool winter tones" } }, "Pose_Expression": { "Position": "Standing very close to the deer, face-to-face", "Emotion": "Calm, intimate, surreal connection" } }, "Subject_2_Deer": { "Description": "Majestic lifelike winter deer", "Appearance": { "Fur": "Thick, realistic, dusted with snow", "Antlers": "Wrapped creatively in colorful plaid fabric" }, "Pose": "Standing still, facing the woman, sharing a silent moment" }, "Scene": { "Setting": "Snowy forest with tall pine trees", "Atmosphere": [ "Surreal", "Fantasy-inspired", "Quiet and intimate" ], "Environmental_Elements": { "Snowfall": "Soft drifting flakes surrounding both subjects", "Background": "Blurred pine trees with cinematic depth of field" } }, "Lighting": { "Style": "Cold cinematic lighting", "Characteristics": [ "Soft highlights on faces", "Cool blue-white ambient tones", "Subtle rim lighting enhancing the winter mood" ] }, "Visual_Style": { "Aesthetic": "Hyper-realistic winter fantasy drama", "Resolution": "8K ultra-detailed", "Mood": "Moody, emotional, atmospheric storytelling", "Texture_Details": [ "Snow-dusted fur and hair", "Detailed plaid fabric", "Frost textures", "Realistic skin and lighting interplay" ], "Film_Quality": "Looks like a still frame from a high-budget fantasy drama" }, "Output_Requirements": { "Format": "Image", "Orientation": "Portrait or cinematic frame", "Quality": "Ultra-high detail, surreal realism, editorial film look" } }

{ "title": "Shopping Version", "description": { "real_woman": { "appearance": "A real human woman wearing a stylish polka dot dress", "pose": "Holding shopping bags with a happy expression", "style": "Full photorealistic photography", "details": "Vibrant colors, sharp detail, realistic skin texture, natural lighting", "restriction": "Must remain photorealistic and not cartoon" }, "background_comic": { "style": "Intricately detailed multi-panel black-and-white comic strip", "character": "Same woman depicted as a cartoon", "story_panels": [ "Entering the store excitedly", "Fighting over sale items", "Trying ridiculous outfits", "Struggling with an overflowing cart", "Checking an empty wallet with a shocked expression" ], "connection": "Comic narrative continues directly from her realistic shopping pose" }, "overall_goal": "Create a seamless story where the photorealistic woman is the 'real moment' inside her own comic adventure" } }