Cozy Suburban Diorama

{ "image_generation_specification": { "meta": { "type": "photorealistic_lifestyle_fashion_collage" }, "subject": { "identity": { "Woman": "Use from the reference image", "likeness_era": "Modern lifestyle editorial" }, "physical_appearance": { "hair": { "color": "Dark brown", "style": "Long, loose, center-parted", "texture": "Straight to softly wavy, lightly wind-swept" }, "expression": { "mood": "Joyful, playful, carefree", "details": "Soft smile, joyful laughter, confident relaxed expressions" }, "pose": { "position": "Standing and moving naturally across multiple frames", "orientation": "Front-facing, rear three-quarter view, mid-movement, and close medium portrait poses" } }, "attire_and_accessories": { "clothing": { "item": "Maxi dress", "color": "Soft pink", "style_details": [ "Small red and green floral print", "Short puff sleeves", "Fitted bodice", "Flowing skirt silhouette" ], "fabric_texture": "Lightweight, airy, flowing fabric" }, "jewelry": { "item": "Earrings", "metal": "Minimal neutral metal", "style": "Simple, understated design" }, "additional_accessories": [ "Light brown ankle boots", "Sunglasses worn in one frame" ] } }, "environment": { "immediate_setting": { "location_type": "Outdoor garden and landscaped estate grounds", "era_vibe": "Romantic countryside resort atmosphere", "interior_details": { "elements": [ "Mediterranean-style architecture with arches and columns", "Flower beds", "Green lawn", "Trees surrounding the grounds" ] } }, "view_through_window": { "description": "Open outdoor scenery surrounding the subject", "elements": [ "Distant mountains", "Clear blue sky", "Lush greenery" ] } }, "photographic_execution": { "style": "High-end lifestyle fashion editorial photography", "quality": "High-resolution imagery with crisp subject detail", "lighting": { "source": "Natural sunlight", "quality": "Bright midday light with soft yet defined shadows, cheerful and vibrant" }, "composition": { "framing": "Vertical four-image grid collage combining full-body and medium shots", "depth_of_field": "Moderate depth of field with clear background and gentle separation from the subject" } } } }

Tilt-shift 3D model diorama in 4:5 aspect ratio, highlighting Tokyo Tower and the Shibuya Crossing at sunset. Tiny pedestrians and cyclists navigate the bustling streets, while cherry blossoms drift gently from nearby trees. Neon signs and LED billboards glow softly in the background.

{ "reference_images": { "product_image": "UPLOADED_IMAGE", "usage_rule": "Use the uploaded image as the exact visual reference for the product’s form, proportions, materials, and overall identity. Do not redesign or reinterpret the product." }, "layout": { "canvas": { "orientation": "vertical", "aspect_ratio": "3:4", "background": "warm neutral paper-like surface" }, "structure": { "top_section": "lifestyle_hero", "bottom_section": "technical_specification" } }, "top_section": { "type": "lifestyle_product_image", "composition": { "placement": "top_center", "scale": "dominant", "margin": "generous whitespace around product" }, "environment": { "setting": "minimal architectural interior", "lighting": { "type": "natural sunlight", "direction": "angled side light", "quality": "soft but high-contrast shadows" }, "floor": "subtle concrete or stone surface", "background": "textured plaster wall" }, "rendering": { "style": "editorial lifestyle photography", "detail": "high realism", "color_grading": "warm, muted, premium" } }, "bottom_section": { "type": "technical_specification_panel", "layout": { "grid": "modular", "alignment": "clean, architectural" }, "technical_drawings": { "placement": "bottom_left_and_center", "style": "architectural line drawings", "views": [ "front view", "side view", "three-quarter cutaway or profile view" ], "projection": "orthographic", "line_style": { "color": "muted red or sepia", "weight": "fine technical lines" }, "annotations": { "type": "measurement and construction callouts", "language": "neutral technical labels", "density": "minimal, editorial" } }, "materials_panel": { "placement": "bottom_right", "content": { "type": "material_swatches", "count": "3-4 depending on product", "format": "square or rectangular samples" }, "textures": { "source": "derived from the product materials", "examples": [ "fabric", "leather", "metal", "wood", "plastic" ] }, "labels": { "style": "small editorial captions", "tone": "technical but refined" } } }, "typography": { "style": "minimal editorial", "usage": "subtle captions, no large headlines", "color": "soft black or dark brown" }, "overall_style": { "mood": "design catalog / product design journal", "aesthetic": "architectural, premium, calm", "avoid": [ "clutter", "bold colors", "heavy branding", "overly decorative graphics" ] }, "constraints": { "do_not": [ "change product design", "invent new materials", "add logos unless present in reference", "use perspective distortion in drawings" ] } }

Create a highly detailed isometric 3D interior diorama of a (Scandinavian minimal) (urban apartment living room) Design the space with coherent architecture, furniture, lighting, materials, and decoration that naturally match the chosen concept. Use realistic textures, soft natural daylight, gentle shadows, and a calm minimal white background. Perspective: isometric cutaway diorama. Ultra high detail, premium interior visualization, soft global illumination.

Convert the uploaded photo into a cheerful and cute 3D Pixar-style animated portrait. Keep the person’s facial features, hairstyle, and unique expression so the character clearly resembles the real person. Use a smooth and clean cartoon style. Apply soft skin shading, expressive eyes, and a polished animated look while preserving the original identity. Place the character against a plain white studio background with clean, even lighting. Keep the outfit the same as in the reference

[LEGO], complete brand identity grid, 3x3 layout, nine tiles showing a full cohesive brand system, light gray seamless background, soft diffused studio lighting, subtle shadows, clean modern minimal style, consistent color palette of [bright red] [classic yellow] [pure white], high-end studio mockups, ultra-realistic, 8k, 1:1, tile 1 primary logo lockup on paper card, tile 2 secondary logo mark and monogram variations inspired by interlocking brick geometry, tile 3 color palette swatches and typography specimen poster with playful geometric letterforms, tile 4 packaging mockup for [modular building brick set], tile 5 hero product photo for [classic interlocking bricks assortment], tile 6 set of three products for [collectible mini construction kits] in different sizes, tile 7 stationery mockups business card letterhead envelope with stud-pattern embossing, tile 8 social media post mockups and phone screen UI preview featuring bold block layouts, tile 9 lifestyle scene featuring [modular building brick set] with colorful creative desk props matching the brand, no people, no readable real-world brand names, no watermark.

Photorealistic edit using the input person photo as strict identity reference: keep the same face, facial features, facial proportions, skin tone, hairstyle (color/bangs/length/volume), outfit (design/material/layers), and accessories unchanged (no face swap, no new person, no hair/outfit/accessory change). Only transfer the target pose/gesture: seated on a chair/sofa, pelvis anchored on the seat, torso slightly reclined backward ~15–25°; shoulders mostly facing camera with a slight right-shoulder lift. Legs: confident leg-cross (one leg crossed over the other at the knees), the top leg is the foreground leg closest to the lens; foreground thigh/knee strongly foreshortened and oversized, thigh angled upward toward camera ~30–45°, knee raised high; lower leg drops toward the bottom of frame; feet not visible. The supporting leg stays lower and farther from the lens, knee angled outward ~20–35°, partially occluded by the top thigh. Right arm: elbow bent ~90° and lifted; forearm near-vertical beside the face; right hand near right cheek/temple with palm facing inward (toward the face), back of hand facing camera; fingers in a relaxed curl with index finger slightly extended; light fingertip/knuckle contact on cheekbone/temple with subtle contact shadow (no floating). Left arm relaxed downward; left hand rests on the top thigh near mid-thigh, palm-down with fingers straight/slightly splayed, visible contact shadow and slight pressure indentation. Occlusion must match: foreground thigh occludes pelvis and most of the far leg; right hand partially occludes jawline/cheek edge ~10–20%. Camera/framing locked: low-angle from below knee height looking upward ~10–20° (NOT front-high, NOT overhead-vertical), wide-angle look 18–24mm, close distance; exaggerated perspective with legs/thighs much larger than head; 2/3 body framing, crop at mid-shin/below knees, no feet visible; size ratio guide: foreground thigh occupies ~45–55% frame width, head ~18–25% frame height. Expression add-on (keep identity): chin slightly raised, half-lidded eyes, subtle smirk, arrogant queen-like gaze down toward camera. Clean realistic skin texture, no glam retouch; solid seamless backdrop, flat and textureless,pure light powder blue (approx #B0E0E6).; no new props.Negative Prompt: identity drift, face swap, different person, altered facial proportions, altered facial features, altered skin tone, altered hairstyle, altered hair color, altered bangs, altered outfit, altered accessories, new jewelry, heavy makeup, beauty retouching, plastic skin, waxy skin, wrong pose, uncrossed legs, wrong leg-cross direction, knees not crossed, wrong hip flexion, wrong knee angles, wrong limb direction, wrong body plane, wrong torso recline, wrong torso rotation, wrong weight placement, impossible anatomy, dislocated shoulder, broken elbow, broken wrist, twisted wrist, incorrect hand gesture, wrong palm orientation, floating hands, missing contact shadow, wrong contact point, extra fingers, missing fingers, fused fingers, deformed hands, incorrect occlusion, wrong crop, feet visible, cut-off hands, bad perspective, inconsistent foreshortening, overhead-vertical camera, front-high camera, low-res, text, watermark, logo, background clutter, extra props, added objects

Create an ultra-wide infographic poster titled “Kyoto Iconic Travel Classics Atlas”, with a 21:9 horizontal layout in true 8K resolution. The visual language blends ceramic glaze and jade-like softness, expressing calm luxury, precision, and cultural depth. The overall mood is restrained, warm, and translucent—evoking the feeling of a museum-grade exhibition combined with refined cultural branding. All on-image text is in English. Background and overall material tone * Background features a light rice-white to misty off-white gradient, similar to a high-end ceramic exhibition space * Global lighting is gentle and diffused: soft HDRI illumination with subtle rim light, avoiding harsh contrast or strong shadows * Color palette centers on jade white, pale celadon, soft moss green, warm beige, with minimal accents of vermilion or muted gold (no more than 3–4 dominant hues across the entire image) Layout: eight equal-width “ceramic/jade plaques” (strictly eight columns) * The central composition uses a strict eight-column grid, each column designed as a ceramic-style information plaque * Plaque material resembles fine white porcelain glaze: rounded corners, smooth highlights, subtle reflective sheen, clean edges * Borders may include an extremely delicate gold trace or jade-edge effect, applied with restraint * Shadows are soft and shallow, as if the plaques are placed on a curated museum display surface Core visuals: realistic 3D landmarks (PBR) with a serene glazed aesthetic * Each column top features one real, iconic Kyoto landmark (automatically select eight authentic sites, no fictional entries) * Use realistic 3D environment rendering with physically based materials, while maintaining a calm, jade-like visual softness * Materials must follow real-world physical rules: wood, stone, tile, water, foliage, and paper surfaces rendered with accurate PBR properties * Unified color grading: soft highlights, moderate contrast, low saturation, and gentle warmth inspired by ceramic glaze and polished jade * Composition emphasizes depth and quiet grandeur through layered space and subtle scale references (small figures, lanterns, trees) * Water elements (rivers, ponds, moats) should display delicate reflections and smooth tonal transitions * Avoid cartoon styles, low-poly geometry, plastic textures, excessive sharpness, or dramatic cinematic lighting Detail view: glazed “micro dish” or “jade charm” window * Each column includes one small detail window in the lower-right corner, using a single consistent shape across all columns * Option A: a small circular dish resembling a porcelain saucer, showcasing fine details (wood grain, roof tiles, stone steps, garden gravel, water ripples) * Option B: a jade-charm-shaped window with rounded contours, highlighting close-up textures and materials * Surfaces should exhibit soft glaze or jade-like highlights with smooth, rounded edges * A thin, elegant leader line connects the detail window to the main 3D landmark, accompanied by a concise 2–6 word label Text per column (concise, refined, understated) * Landmark name (4–8 English words, refined serif typeface recommended) * Two short informational lines: * Highlight: maximum 8 words * Best for: maximum 6 words * Text color uses ink gray or bluish charcoal; accent colors appear only in small dots or separators Top title area (museum exhibit label style) * Main title: Kyoto Iconic Travel Classics Atlas * Subtitle: one refined positioning sentence, maximum 18 words, calm and poetic in tone * Top-right corner includes five small glazed color dots: pale celadon, jade white, moon white, warm beige, with a subtle vermilion accent Bottom information band (exhibition caption style) * A full-width bottom band divided into four sections by fine lines, resembling museum display captions * Kyoto at a glance: one sentence, maximum 22 words * Visiting tips: three bullet points, each no more than 12 words * Cultural trivia: three items, each no more than 18 words * Timeline: 3–6 key nodes (era or year plus keyword), connected with minimal linear icons using thin, consistent strokes Automatic landmark selection rules * Cover at least five categories: natural scenery, historical temples or shrines, traditional architecture, museums or cultural institutions, classic streets or seasonal night scenes, and intangible cultural experiences (tea ceremony, festivals, crafts) * If necessary, fill gaps with safe, general entries such as “Kyoto National Museum” or “Historic Gion District” * All landmark names must be real and verifiable; if uncertain, use conservative generic naming and never fabricate locations Output constraints * English text only * Strong alignment, minimalist spacing, generous white space * No logos, no branding marks, no watermarks * True 8K ultra-high resolution, suitable for cultural tourism displays and horizontal social media covers