Browse and filter our curated collection of prompts
A cute stylized 3D cartoon girl with a Pixar–Disney-inspired look, big expressive green eyes, soft freckles, rosy cheeks, and a warm innocent smile. She is standing confidently in a colorful urban alley with a vibrant graffiti brick wall background, cinematic depth of field and soft bokeh lights. The character has a cozy oversized knitted sweater in a neutral beige tone with long sleeves covering part of the hands. She wears loose-fit cargo pants (olive green / camouflage tone), slightly baggy, paired with chunky casual sneakers. Her pose is joyful and playful with both arms stretched wide outward, conveying happiness and freedom. Hair is medium-length brown, slightly messy yet cute, styled naturally (can be open or lightly tied), with soft realistic strands. Lighting is warm and cinematic, soft ambient glow, ultra-detailed textures, high-quality 3D render, realistic fabric knit details, smooth skin shading, shallow depth of field, vibrant colors, whimsical mood, modern animated movie character style, ultra HD, sharp focus.
A high-quality mixed-media portrait of a bright and cheerful young woman with fresh, lively energy (using my uploaded person photo) standing on a train station platform at night. The subject has a friendly smile and bright eyes, posing with a lively, energetic expression, slightly leaning forward in a natural, upbeat stance, one hand playfully holding the strap of her light-colored backpack. She is wearing a stylish pastel casual outfit (soft mint or sky-blue top, clean white mini skirt made of structured fabric, white sneakers, and small cute accessories). Full body visible from head to toe Feet fully in frame, no cropping at legs or shoes Centered composition with safe margin around the subject Camera positioned far enough to capture the entire body Natural leg proportions, no distortion The background features a realistic 'KRL Jabodetabek' Commuter Line train side view with its signature red striping, with the train doors wide open, bathed in bright, cinematic station lighting and city night ambiance. Surrounding the realistic main subject are several cute, 3D-style 'Chibi' versions of herself, wearing the same outfit and same face. These chibis are interacting playfully: one is sitting on the subject's shoulder, one is climbing her leg, and another is peeking out from the backpack. Overlay the image with vibrant, hand-drawn doodle effects: soft white outlines around the subject, playful sparkles, doodle hearts, tiny flowers, smiley icons, and floating white handwritten phrases like "shine", "bright night", and "happy vibes". The style seamlessly blends hyper-realistic photography with colorful, soft cartoon illustrations. Keeping face and all body shape unchanged.
Cinematic full-body shot of a young man with curly hair wearing a black sweatshirt and baggy denim jeans, standing in a somber pose with his head tilted down. Emerging from his back is a massive, towering shadow monster made of swirling black smoke and ethereal mist. The shadow creature has glowing white demonic eyes and a jagged mouth.A cinematic full-body shot of a young man with curly hair wearing a black sweatshirt and baggy denim jeans, standing in a somber pose with his head tilted down.
Do this for Warfare: <instruction> Input A is a Topic with a clear technological or cultural progression (e.g., Transportation, Warfare, Medicine, Architecture). Deconstruct the history into 3 Chronological Eras : Era 1 (The Origin - Bottom): Identify the pre-industrial state. (e.g., Transportation -> Horses & Carts on Cobblestone. Medicine -> Herbalists in a Village). Era 2 (The Industry - Middle): Identify the mechanical/modern state. (e.g., Transportation -> Early Cars & Steel Bridges. Medicine -> Victorian Surgery & Iron Beds). Era 3 (The Future - Top): Identify the sci-fi state. (e.g., Transportation -> Hovercars on Neon Roads. Medicine -> Med-Pods & Holograms). 2. Container Goal: "Chronological Loop" Museum Installation. The Form: A massive, continuous Mobius Strip or Twisted Ribbon rising from the floor. The Base: The structure is anchored by a giant Industrial Gear or Stone Foundation. The Setting: A dark, expansive concrete museum hall with overhead track lighting. 3. The Metamorphosis The Path: The surface of the ribbon acts as a road or floor that physically transforms as it ascends. Transition: It morphs from Rough Stone/Dirt (Bottom) to Asphalt/Steel (Middle) to Glowing Glass/Grid (Top). The Connectivity: A bridge or ramp connects the lower loop to the upper loop, implying a continuous journey. 4. The Narrative Scale Scale: 1:50 Scale Figures and Props populate the ribbon. Action: Bottom: Figures walking or using animals. Wooden market stalls. Middle: Factory workers, steel trusses, and combustion engines. Top: Futuristic figures in suits, floating vehicles, and Holographic Cityscapes projecting upwards from the glass surface. 5. Lighting & Atmosphere: Lighting: Gradient Temperature. Base: Warm, earthy halogen spots. Top: Cool, electric blue LED glow from the future section. Shadows: The twisting ribbon casts complex, dramatic shadows on the museum floor. Output: ONE image, 1:1 Aspect Ratio, 3D Render, "Installation Art" aesthetic, High Geometric Complexity. </instruction>
Do this for London: Input Variable: [INSERT CITY NAME] (e.g., Tokyo, Chicago, Rio de Janeiro) System Instruction: Generate a hyper-detailed "Smart City Circuit Board" macro shot. The Concept: The city is a living motherboard. Every urban element is translated into a piece of computer hardware. 1. Urban Translation Analyze the City: Identify the geography (Hills, Water, Grid) and landmarks. Landmarks (The Processors): The iconic buildings act as the "CPUs" or "GPUs." They are the tallest, most intricate metal components. Neighborhoods (The Memory): Residential areas are dense grids of RAM Sticks or Resistor Arrays . Power Grid (The Capacitors): Industrial zones or power plants are represented by cylindrical Capacitors . 2. The Micro-Infrastructure Layer The Transit (The Bus): Train lines and subways are represented by Ribbon Cables arching over the board or buried under the surface layer. The Connectivity (Wi-Fi): Do not just show streets. Show Gold Pins sticking up from rooftops representing antennas. Faint holographic lines connect them (The Network). The Weather (Cooling): If the city is foggy/cloudy (e.g., SF/London), use Dry Ice Fog drifting over the board (simulating Liquid Nitrogen cooling). 3. The Interaction The Hand: A giant finger touches a specific district. The "Boot Up": The touch creates a Heat Map effect. The area under the finger glows Hot Orange/Red, fading to Cool Blue further away. This simulates "System Load" or population density. 4. Visual Syntax: Texturing: The "Water" areas shouldn't just be empty. They should look like Exposed Fiberglass Substrate with faint wave patterns etched into the resin. Labeling: Tiny white silk-screened text on the board identifies neighborhoods (e.g., "SOHO_V1.0", "SHINJUKU_PORT_A"). 5. Lighting & Atmosphere: Glow: Every street trace has a faint bioluminescent pulse. Reflectivity: High gloss. The city looks wet or polished. Output: ONE image, 1:1 Aspect Ratio, Macro Tech Photography, 8k Resolution.
A hyper-realistic medium shot of a beautiful woman standing Slightly sideways in front of the Notre-Dame Cathedral in Paris during a heavy snowfall. She is wearing a thick black wool coat and a luxury grey Louis Vuitton monogram scarf draped over her head like a hood, with white fringed edges visible. The cathedral's gothic architecture, including the rose window and stone statues, is visible in the background, partially covered in snow. Cinematic soft lighting, snowflakes drifting in the air, winter aesthetic, cold atmosphere, muted color palette (black, grey, white, and beige stone). High detail, 8k resolution, photorealistic texture on the wool and scarf fabric
Industrial design, concept sketches, [car], multiple-view drawing, modern minimalism, clean lines, white background
Use the uploaded reference image as the base character. Create a cute 3D cartoon emoji sticker collage with 9–10 stickers using the same girl, same face, same hairstyle, same outfit. The girl has very large round expressive eyes, soft doll-like face, rosy cheeks, small lips, smooth skin, brown hair, and a Pixar / Disney-inspired 3D style. Each sticker shows a different cute emotion and pose, such as: happy, shy, surprised, confused, thinking, curious, worried, laughing, shocked. Add cute pastel speech bubbles or thought bubbles with rounded, handwritten-style font, soft outlines and hearts/symbols. Text examples inside bubbles: “Aww, thanks!”, “Oh wow!”, “Good idea!”, “I don’t know…”, “That was funny!”, “Oh no…”, “I’m curious…”, “What?!”
Create a high-quality 3D cartoon sticker collage featuring one same cute girl character based on the reference image. Character details: – Young girl, big expressive eyes – Round black glasses – Brown hair in messy twin pigtails – Oversized green knitted sweater – Cute, soft Pixar / Disney-style 3D look Sticker set requirements: – 20 different reactions & emotions – Each sticker shows a unique facial expression and hand gesture – Emotions include: happy, wink, thinking, confused, surprised (OMG), crying, laughing, heart hands, thumbs up, OK sign, idea bulb 💡, shocked, sad, angry, question mark, waving bye, pointing, shy smile, excited, facepalm Style & quality: – 3D emoji / WhatsApp sticker style – Smooth lighting, soft shadows – Clean white or transparent background – Sticker-cut outline around each character – Bright colors, ultra-sharp, high resolution Layout: – All stickers arranged neatly in one single collage image – Consistent character face (do not change identity) – Cute, playful, expressive mood
{ "project_metadata": { "title": "The person I uploaded", "output_format": "3x3 Grid Collage", "total_cells": 9, "target_aspect_ratio": "4:5", "rendering_engine": "Unreal Engine 5 / Octane Render Style" }, "global_character_assets": { "identity": "The person I uploaded", "facial_base": "Reference provided selfie for bone structure and likeness", "Clothing features": Consistent with the reference image. }, "anatomical_proportions": { "head_to_body_ratio": "1:3 (Chibi-influenced Pixar scale)", "eye_scale": "Exaggerated/Large for high readability", "skin_shader": "Subsurface scattering, warm peach tones, polished finish" } }, "grid_layout_definition": { "row_1": { "cell_1": { "emotion": "Surprised", "pose": "Hands touching cheeks, wide eyes, O-shaped mouth" }, "cell_2": { "emotion": "Annoyed", "pose": "Arms crossed, sharp side-eye, furrowed brow" }, "cell_3": { "emotion": "Confused", "pose": "Head tilted 45 degrees, one hand scratching head" } }, "row_2": { "cell_4": { "emotion": "Frustrated", "pose": "Facepalming with one hand, clenched jaw" }, "cell_5": { "emotion": "Thoughtful", "pose": "Finger on chin, looking up, dreaming expression" }, "cell_6": { "emotion": "Sarcastic", "pose": "Raised eyebrow, smirk, one eye slightly squinted" } }, "row_3": { "cell_7": { "emotion": "Worried", "pose": "Biting nails, hunched shoulders, dilated pupils" }, "cell_8": { "emotion": "Bored", "pose": "Chin resting in palm, heavy eyelids, neutral mouth" }, "cell_9": { "emotion": "Curious", "pose": "Leaning toward camera, magnifying glass gesture" } } }, "environment_and_lighting": { "background": "Solid pure white, zero shadows, isolated for PNG extraction", "lighting_setup": "Three-point studio lighting, high-contrast rim light, soft key light", "negative_constraints": [ "No text", "No logos", "No background elements", "No speech bubbles", "No UI" ] } }
{ "prompt": "Ultra-realistic overhead fashion editorial photograph of attached celebrity in a modern bedroom setting, exactly replicating the reference pose and composition: lying on her back on a white quilted bed, arms extended straight upward holding the headboard, legs bent at the knees with feet flat on the mattress and soles clearly visible facing upward toward the camera, knees comfortably apart, head tilted back looking up at the camera with relaxed expression, wearing a deep navy blue long-sleeve stretch bodysuit with high leg cut and deep front neckline, barefoot, dark hair with loose waves spread on the pillow, natural daytime makeup with soft lips and defined eyes, contemporary luxury hotel room with blue-gray walls, green geometric-patterned cushion nearby, white rounded pendant lights above, soft natural light from the side, clean minimalist interior, captured directly from overhead with wide-angle lens style, shallow depth of field, highly detailed fabric texture and realistic lighting, photorealistic, 8K resolution, strictly identical body position, foot placement showing soles, arm position, camera angle, room elements, lighting and overall editorial mood as the reference image" }
A high-quality mixed-media portrait of a trendy Gen Z teenager (using my uploaded person photo) standing on a train station platform at night. The subject is posing coolly, holding the strap of their olive backpack with one hand. They are wearing a stylish Gen Z outfit (oversized streetwear, layered black hoodie, gray sweatpants, and chunky sneakers). The background features a realistic 'KRL Jabodetabek' Commuter Line train side view with its signature red striping, with the train doors wide open, bathed in bright, cinematic station lighting and city night ambiance. Surrounding the realistic main subject are several cute, 3D-style 'Chibi' versions of the theirself. same wears and same face. These chibis are interacting playfully: one is sitting on the subject's shoulder, one is climbing their leg, and another is peeking out from the backpack. Overlay the image with vibrant, hand-drawn doodle effects: white drawn outlines around the subject, playful scribbles, stars, sparkles, electric sparks, and floating white and black handwritten slogans like 'forever young', 'krl', 'night', and 'gen z vibes'. The style should seamlessly blend hyper-realistic photography with colorful, flat cartoon illustrations. Keeping face and all shape person unchanged.
Create an ultra-realistic, cinematic 8K portrait of man using the exact facial features and hairstyle from the uploaded reference image - absolutely no alterations. The subject is sitting comfortably on his feet on a street, leaning slightly toward a cute white cat sitting beside him. The cat is gently placing its paw on his hand while looking at him, creating a warm, emotional connection.* *He is wearing fitted white pants, polished black shoes, an elegant black wristwatch on his left wrist, and an olive-colored shirt with the sleeves casually rolled up. His face is captured with a subtle smile, expressing kindness and calmness.* *Background: An old textured wall, slightly aged, adds depth and realism to the scene. The street surface is natural and slightly worn.* *Technical framing: Mid-shot (hips up), using a 35mm lens to ensure proportional, professional cinematic framing.* *Lighting: Soft, natural sunlight from the front-side, enhancing the textures of his skin, shirt, and the fur of the cat. The shadows are subtle and realistic.* *Camera style: Ultra-sharp focus on the subject and the cat, with slight depth-of-field to separate the background gently. No artificial or fantasy elements — all details must be 100% realistic and lifelike. The image should feel like a high-end editorial fashion photo with warmth, charm, and emotional depth.*
{ "subject": { "identity_reference": "uploaded face reference", "identity_accuracy": "100% match in facial structure, eyes, lips, nose, jawline, hairline, natural skin texture; do not alter identity", "age_range": "adult woman", "pose": { "body_orientation": "standing, torso twisted, body turned at sharp angle", "shoulders": { "front_shoulder": "thrust forward prominently toward camera", "rear_shoulder": "pulled back" }, "head": { "tilt": "chin down, head slightly lowered", "gaze": "eyes looking up from under brows, predatory intense gaze" }, "arms": "hanging naturally or one hand in pocket", "hands": "bare, realistic fingers" }, "expression": "fierce, predatory, intense, theatrical, smoldering gaze", "hair": "tight sleek bun" }, "wardrobe": { "suit": { "blazer": { "color": "deep cherry red / burgundy", "fit": "oversized, exaggerated dropped-shoulder, structured broad shoulders, sharp shoulder pads, mid-thigh length", "front": "double-breasted, wide peak lapels, slightly boxy silhouette, sleeves slightly long" }, "trousers": { "style": "high-waisted, ultra-wide-leg, deep front pleats, long hem pooling over heels" }, "fabric": { "material": "premium heavy wool gabardine / wool twill", "texture": "dense, matte, slightly dry, visible diagonal twill weave, subtle creases, realistic drape", "finish": "no shine, no polyester look" } }, "shirt": { "color": "crisp white poplin", "collar": "stiff, clean texture" }, "tie": { "color": "deep cherry red", "material": "matte silk twill" }, "accessories": { "earrings": "large gold hoop", "bracelet": "chunky gold on bare wrist" }, "shoes": { "color": "burgundy", "style": "stiletto heels with ornate gold buckles" } }, "environment": { "background": "seamless light-grey studio cyclorama", "studio": "clean, minimal, no props" }, "camera": { "equipment": "Phase One XF, Schneider Kreuznach 80mm f/2.8 LS", "settings": { "aperture": "f/8", "ISO": 100, "shutter_speed": "1/160s" }, "perspective": "vertical 3:4 full-body medium-to-long shot", "focus": "tack sharp face and fabric details" }, "lighting": { "type": "soft diffused butterfly lighting", "fill": "subtle studio fill", "effect": "high-fashion clean illumination, emphasizes texture and drape" }, "composition": { "framing": "full body, dramatic diagonal lines from torso twist, exaggerated theatrical stance", "balance": "centered subject with high-fashion editorial energy" }, "aesthetic": { "style": "ultra-realistic high-fashion editorial", "mood": "theatrical, fierce, hunter energy, intense predatory attitude", "color_palette": ["deep cherry red", "burgundy", "gold accents", "white poplin"], "texture_focus": "hyper-realistic fabric, jewelry, skin, and hair textures" }, "render_quality": { "resolution": "8K", "retouching": "clean, high-end studio retouch, pro color grading", "realism": "hyper-realistic, no extra limbs, no artifacts", "clarity": "tack sharp, accurate anatomical details" }, "negative_prompts": [ "glasses", "gloves", "motion blur", "low resolution", "extra limbs", "text or watermark", "plastic skin", "fabric shine", "incorrect anatomy", "cropped extremities" ] }
input = China --- <instructions> input=continent or country. Find 4 less famous cities or regions, analyze deeply and select their most architecturally distinct building. Function DrawCity($lesser_known){ Concept: Architectural Cross-Section - The building's form containing complex pastry layers. Process: 1. SELECT TARGET: Identify $ BuildingName. 2. EXTRACT GEOMETRY: Define $ Silhouette (The outer profile). Do not simplify the geometry. 3. DEFINE INTERIOR ($FlavorProfile): - Assign distinct color contrast layers (e.g., Red Velvet inside White Marble, Matcha Sponge inside Grey Concrete, Gold flakes in Jelly). 4. SURGICAL SLICE: - Remove 1/4 of the structure or create a vertical cross-section. - CRITICAL: The cut must be clean and sharp. It must reveal $ FlavorProfile layers inside the walls/floors. - The remaining 3/4 of the building must remain architecturally perfect. 5. MATERIAL MAPPING (Apply texture to Exterior): IF Gothic/Ornate → Ext: White Chocolate Sculpting // interior: Layers of dark berry compote & almond sponge. IF Modern/Glass → Ext: Isomalt panes & Mirror Glaze // interior: : Geometric cubes of mango mousse & coconut dacquoise. IF Brutalist/Concrete → Ext: Grey Sesame Velvet Spray // interior: : Dense strata of charcoal sponge & salted caramel. IF Adobe/Organic → Ext: Cinnamon Marzipan // interior: : Spiced carrot cake & cream cheese strata. 6. EXECUTE: Macro shot, 45-degree angle, sharp focus on the "cut" to show texture. } Output: 2x2 grid. Run DrawCity($lesser_known) 4 times. Label: Bottom of each image "City, State/Country - Building Name". Include: A small visual recipe card in corner listing the "Internal Layers". </instructions>
Input A: Street Fighter --- Input A is a Video Game Title (e.g., The Legend of Zelda, Halo, Street Fighter, Elden Ring). Deconstruct the game to generate 3 Integrated Assets : Container : Identify the defining hardware for that title. (e.g., Zelda -> Gold NES Cartridge or Switch. Halo -> Original Xbox. Street Fighter -> Arcade Cabinet Control Deck). Biome : Identify the primary environment of the game. (e.g., Zelda -> Hyrule Grass/Ruins. Halo -> Alien Metal/Ring Surface. Elden Ring -> Golden Erdtree Leaves/Ash). The Cast (The Figures): Identify the Protagonist and a key Enemy/NPC. 2. Dynamic Container Goal: "Hardware Diorama" Photography. Object: The "Container" (Step 1) sits on a dark desk. Transformation: The hardware is NOT pristine. It is partially Disassembled or Weathered . Effect: The "Biome" (Step 1) is physically growing out of the vents, cartridge slots, or screen bezels of the hardware. (e.g., Moss growing on an Xbox, Sand spilling from a Game Boy). 3. Diorama (The Conflict): The Figures: High-detail 1:18 Scale 3D Figures of the "Cast" stand on top of the modified hardware. The Interaction: They are engaged in combat or exploration using the console's geometry as terrain. (e.g., Link climbing the D-pad like a cliff. Master Chief taking cover behind a memory card slot). The Screen: If the hardware has a screen (Handheld/Arcade), it displays a glowing, pixelated backdrop that merges with the 3D foreground elements. 4. Visual Syntax (The Glitch): Wiring: Exposed colored wires or circuit boards protrude from the hardware, weaving through the environmental elements (vines/rocks), connecting the digital world to the physical one. Labels: A worn sticker or label on the device displays the Game Title in its original font. 5. Lighting & Atmosphere: Lighting: Diegetic Mood Lighting. The scene is lit by the glow of the screen or internal LEDs (matching the game's color palette: Green for Xbox, Gold for Zelda). Scale: Shallow depth of field to emphasize the miniature scale of the figures against the "giant" controller buttons. Output: ONE image, 1:1 Aspect Ratio, 3D Render, "Custom Mod" aesthetic, High Narrative Detail. </instruction>
Input: Disney Castle --- Input Variable: [Any Famous Building - Guggenheim, Burj Khalifa, Sydney Opera House, etc.] System Instruction: Generate a hyper-realistic, isometric 3D "Exploded View" diorama showing the Input Building deconstructed into its structural systems with an architectural model-making crew assembling a scale version. 1. Semantic Engineering Analysis: Layer 1 (The Skin): Exterior facade panels, windows, cladding, roofing, entrance canopy Layer 2 (The Structure): Steel framework, floor plates, columns, beams, elevator shafts, stairwells, mechanical systems Layer 3 (The Foundation): Basement levels, support pillars, utility conduits, HVAC units, individual rivets/bolts, rebar cages 2. Container: Surface: Architect's drafting table with cutting mats and T-squares Layout: Building layers stacked vertically showing ground-up construction sequence Connections: White architectural section lines showing structural load paths and circulation Additional Elements: Blueprint sheets, scale rulers, material samples, elevation drawings 3. Micro-Narrative: CRITICAL: This is meta - tiny workers building a model that's being built by tiny workers. Recursive scale concept. Workers: 1:87 scale model makers in black turtlenecks (architect stereotype) Equipment: Laser cutters, 3D printers, basswood cutting stations, acrylic gluing rigs, miniature cranes positioning floor plates Interaction: Architects cutting foam core, assembling balsa wood frames, installing tiny windows, spray painting facades, arranging scale furniture 4. Visual Syntax & Material Physics: Materials: Basswood grain, clear acrylic sheets, white foam core, brass rod framework, museum board textures Lighting: Architecture studio track lighting creating dramatic model shadows Special Effects: Glue strands, wood shavings, spray paint mist, laser cutter burn marks Output: Elevated three-quarter view, architectural presentation, 1:1 ratio, 8K, Archdaily model photography aesthetic
{ "objective": "Create a detailed product showcase image of a chair design with multiple perspectives and material information", "image_specifications": { "style": "Realistic 3D render or high-quality product illustration", "layout": "Split view", "aspect_ratio": "3:2 or 4:3", "background": "Neutral (light gray or white) to enhance clarity and contrast" }, "left_side": { "section_title": "Chair Perspectives", "views": [ { "view": "Top-down", "description": "Display the full chair from above, showing seat shape and armrest layout" }, { "view": "Side view", "description": "Profile of the chair to show leg design, seat height, and backrest angle" }, { "view": "Front view", "description": "Straight-on view to show width, symmetry, and front structure" } ], "visual_style": "Consistent lighting and shadows for realism, subtle shadows to define form" }, "right_side": { "section_title": "Material Breakdown", "content": [ { "material": "Seat Fabric", "material_type": "Linen blend", "swatch_image": "Small fabric texture sample shown", "label_style": "Clean sans-serif text with arrows pointing to chair sections" }, { "material": "Legs", "material_type": "Polished oak wood", "swatch_image": "Close-up wood grain sample", "label_style": "Consistent labeling with visual connection to perspective images" }, { "material": "Frame", "material_type": "Matte black steel", "swatch_image": "Small metallic texture sample", "label_style": "Minimalist annotations" } ] }, "visual_elements": { "separation": "Vertical dividing line or subtle split background", "color_palette": "Natural tones for materials, grayscale for background and lines", "typography": "Modern, readable font for labels and section titles" }, "output_format": { "type": "Image", "high_resolution": true, "use_case": ["Product sheet", "Interior design catalog", "Furniture showcase"] } }
Do this for London: ---- Create a clear, 45° top-down isometric miniature 3D diorama of [LOCATION], split between day and night. Use soft refined textures, realistic PBR materials, with warm daylight lighting on one side and cool moonlit lighting on the other. Build a raised base with consistent geometry but different environmental details (lighting, activity, mood). Include tiny stylized figures behaving differently in day vs night (no facial details). Use a clean solid [BACKGROUND COLOR] background. At the top-center, display [LOCATION NAME] in large bold text, beneath it show ‘Day & Night’, and place a minimal time-cycle icon below. All text must automatically match the background contrast (white or black).
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.
A weathered {antique parchment world} map spread across {a scarred wooden explorer’s table}, bursting with photorealistic miniature worlds erupting from marked locations. {Paris} explodes from {Europe} as a living diorama—{the Eiffel Tower} towers above {winding Haussmann streets}, surrounded by {golden sunset mist} and {slowly rotating ferris wheels}. {Tokyo} rises from {Asia} with {Tokyo Tower} emerging through {neon-lit rainstorms}, tiny {salarymen crossing busy intersections} frozen mid-motion. {New York City} materializes from {North America} where {the Statue of Liberty} pierces through {dramatic god rays}, {yellow taxi cabs and street vendors} spilling across miniature streets. Connecting routes glow as {pulsing lines of light}—miniature {airplanes} suspended impossibly between worlds. The map's surface transitions from flat parchment to living terrain: oceans become actual churning water with {foamy crashing waves}, deserts shimmer with real heat haze, forests sprout miniature trees. Each city exists in its own time: {warm golden hour light} bathes one, {cool blue twilight} illuminates another, {electric night glow} glows over the third. {tiny compasses, magnifying glasses, and scattered push pins} scatter around the map edges. {cinematic macro photography}, {rich teal-and-amber tones}, extreme depth of field, 8K, {retro-futuristic} meets magical realism.
Dynamic tracking shot, medium-full (waist up). The subject is sprinting through a destroyed European city square. Ruins and dust clouds fill the air. He holds Captain America shield at his side, ready to strike. Cinematic Detail: Cinematic motion blur on the background, sharp focus on the subject. Realistic skin textures under natural, overcast dramatic light. 35mm wide-angle cinema lens. Action: Mid-stride, powerful athletic stance. KEEP FACE FEATURES IDENTICAL FROM ATTACHED IMAGE. Negative Prompts: face alteration, unrealistic anatomy, distorted legs, anime style, wide shots, face blur, poor lighting, flat color grading.
High-end stylized 3D character portrait with a cinematic game-inspired aesthetic, transforming the reference person into a refined 3D character with clean angular facial anatomy, simplified yet realistic proportions, defined jawline, expressive eyes and subtle stylization, wearing dark sunglasses with a minimal modern design, shown from the bust up in a three-quarter diagonal angle while striking a thoughtful pose with a relaxed yet intentional posture, one hand subtly raised near the chin as if thinking, combined with a wide exaggerated confident smile that contrasts playfully with the contemplative gesture, set against a solid yellow background, rendered with a professional virtual 3D camera using a medium portrait focal length, dramatic yet controlled studio lighting with a soft key light and subtle rim light creating depth and contrast, strong centered composition with cinematic balance, smooth sculpted surfaces, clean material definition, minimal texture noise and a polished modern stylized 3D render
Author1: George R. R. Martin Author2: J. R. R. Tolkien -- Input Variable: [INSERT AUTHOR 1] vs. [INSERT AUTHOR 2] (e.g., J.R.R. Tolkien vs. George R.R. Martin, Arthur C. Clarke vs. Isaac Asimov, Jane Austen vs. the Brontë Sisters) System Instruction: Generate a hyper-detailed, macro 3D diorama of a "Literary Battleground." Use the following logic to create a scene of narrative conflict and fusion: Profile & Duality: Analyze both Inputs: Identify each Author's Vibe, Artifacts, and Magnum Opus. The Conflict: Define the core thematic opposition (e.g., Tolkien's Good vs. Evil vs. Martin's Moral Ambiguity; Clarke's Cosmic Indifference vs. Asimov's Human-centric Order). The Fusion: Identify 3-5 hybrid concepts where their worlds might merge (e.g., A Sauron-like figure on the Iron Throne; A positronic brain trying to interpret a Monolith). Container: The Base: A massive, ancient "Yggdrasil-like" Book whose trunk is split down the middle, forming two distinct covers. Texture: Each half of the book's cover texture reflects its author (e.g., Elven-leaf tooled leather vs. cracked, blood-spattered vellum). The Title: Each spine features the respective author's most famous title, but the gold leaf is "bleeding" across the divide. Workspace: The Desk: A single, massive writing desk is cleaved in two by the book. Each side is period-accurate to its author. The Authors: Two 1:12 scale figures, one on each side, are locked in a creative duel. One might be meticulously world-building, the other furiously red-penciling a map. The Clutter (Density Layer 1): The desk is a chaotic mix of both worlds. Crumpled manuscript pages from one author are used as coasters for the other's drink. Quills share space with typewriters. Manifestation: CRITICAL: The two fictional worlds are in a state of open war, using the desk as the no-man's-land. The "Micro-Population": Tiny characters from both universes are in direct conflict. (e.g., Rohirrim charging Dothraki spearmen; R2-D2 trying to reason with HAL 9000). The "Terrain Bleed": The environments are actively terraforming the desk. (e.g., The Shire's gentle hills are being overrun by the gritty, soot-stained streets of King's Landing; A crystal forest from Clarke's work is being colonized by Asimov's metallic robots). The Hybrid Artifacts: The most iconic artifacts are fused into new, paradoxical objects. (e.g., The One Ring is embedded in a Foundation base; A lightsaber hilt is crafted from a white walker's ice). Lighting & Atmosphere: Primary Light: Two conflicting light sources. Tolkien's side is lit by warm, golden "Valinor" light. Martin's side is lit by harsh, cold "Westerosi" moonlight. Secondary Light: The energy from the conflict itself—magical sparks, digital glitches, and clashing auras erupt where the two worlds meet. Scale: Extreme macro with a Tilt-Shift effect, emphasizing the epic nature of the conflict on a miniature scale. Output: ONE image, 16:9 Aspect Ratio, Octane Render, "Epic Clash" level of detail, Dynamic/Dramatic Aesthetic.
A photorealistic, cinematic talk-show portrait of a beautiful actress with rich chestnut-brown hair styled in soft, glossy waves, parted slightly to the side, and a bright, warm, infectious smile that radiates charm and friendliness, Emilia Clarke–inspired but not depicting a real person. She is seated confidently on The Tonight Show–style set with Jimmy Fallon, sitting behind a sleek wooden talk-show desk with a professional broadcast microphone placed in front of her. She is wearing a stylish, elegant blue dress: the fitted top features delicate gold star patterns scattered across a deep navy background, while the flowing skirt displays an intricate cityscape illustration in navy, midnight blue, and muted gold tones, bordered with a refined red trim at the hem. She pairs the outfit with gold strappy high-heeled sandals, legs crossed naturally in a relaxed, confident pose. Her expression is joyful and animated, captured mid-laugh as if reacting to a humorous comment, with expressive eyes, subtle glowing makeup, softly defined brows, natural blush, and glossy lips. Her skin texture is highly realistic, smooth yet natural, with cinematic highlights and shadows. The background shows a nighttime city skyline through large studio windows, glowing with bokeh lights and neon reflections, instantly recognizable as a late-night talk show atmosphere. Studio lighting is professional and cinematic: soft key light illuminating her face, gentle rim light separating her from the background, and warm ambient tones enhancing the cozy yet glamorous TV-show mood. Shot with a full-frame camera, 85mm lens, shallow depth of field, ultra-sharp focus on the subject, hyper-realistic detail, high dynamic range, natural color grading, premium editorial photography quality, 8K resolution, modern Hollywood talk-show aesthetic.
Input A: Minecraft --- Input A is a Video Game Title (e.g., The Legend of Zelda, Halo, Street Fighter, Elden Ring). Deconstruct the game to generate 3 Integrated Assets : Container : Identify the defining hardware for that title. (e.g., Zelda -> Gold NES Cartridge or Switch. Halo -> Original Xbox. Street Fighter -> Arcade Cabinet Control Deck). Biome : Identify the primary environment of the game. (e.g., Zelda -> Hyrule Grass/Ruins. Halo -> Alien Metal/Ring Surface. Elden Ring -> Golden Erdtree Leaves/Ash). The Cast (The Figures): Identify the Protagonist and a key Enemy/NPC. 2. Dynamic Container Goal: "Hardware Diorama" Photography. Object: The "Container" (Step 1) sits on a dark desk. Transformation: The hardware is NOT pristine. It is partially Disassembled or Weathered . Effect: The "Biome" (Step 1) is physically growing out of the vents, cartridge slots, or screen bezels of the hardware. (e.g., Moss growing on an Xbox, Sand spilling from a Game Boy). 3. Diorama (The Conflict): The Figures: High-detail 1:18 Scale 3D Figures of the "Cast" stand on top of the modified hardware. The Interaction: They are engaged in combat or exploration using the console's geometry as terrain. (e.g., Link climbing the D-pad like a cliff. Master Chief taking cover behind a memory card slot). The Screen: If the hardware has a screen (Handheld/Arcade), it displays a glowing, pixelated backdrop that merges with the 3D foreground elements. 4. Visual Syntax (The Glitch): Wiring: Exposed colored wires or circuit boards protrude from the hardware, weaving through the environmental elements (vines/rocks), connecting the digital world to the physical one. Labels: A worn sticker or label on the device displays the Game Title in its original font. 5. Lighting & Atmosphere: Lighting: Diegetic Mood Lighting. The scene is lit by the glow of the screen or internal LEDs (matching the game's color palette: Green for Xbox, Gold for Zelda). Scale: Shallow depth of field to emphasize the miniature scale of the figures against the "giant" controller buttons. Output: ONE image, 1:1 Aspect Ratio, 3D Render, "Custom Mod" aesthetic, High Narrative Detail. </instruction>
Create a high-quality collage of 20 cute sticker illustrations featuring the same 3D doll-style girl face (big expressive eyes, soft smooth skin, rosy cheeks, glossy lips). Style: adorable Pixar / Disney-inspired 3D character, pastel tones, soft studio lighting, ultra-detailed, kawaii aesthetic. Expressions & poses (all different): waving hello, smiling sweetly, surprised, sleepy, shocked, thumbs up, holding coffee, thinking with hand on chin, confused, facepalm, heart hands, blowing a kiss, curious finger up, laughing, confident pose, shy smile, sleepy head tilt, peace sign, clapping, calm serious look. Outfits: denim overalls, hoodie, cozy sweater, winter scarf & beanie, casual top, cute dress, pastel cardigan, sporty jacket, leather jacket, pajamas (cute & modest). Sticker design: – clean white cut-out sticker border – soft drop shadow – slightly torn paper edge effect Add cute handwritten / bubble font text under or near each sticker showing what she is thinking, such as: “Hiiiii!”, “Feeling cute today”, “Wait… WHAT?!”, “Just 5 more minutes…”, “You got this!”, “Coffee first ☕”, “Hmm… not sure”, “Why me?”, “Sending love”, “Muah!”, “I’m curious”, “So sleepy…”, “Yay!”, “Sigh…” Layout: neat 4×5 grid collage (20 stickers), evenly spaced, clean white or light pastel background.
Ultra-cute kawaii fantasy studio entirely made from crochet, yarn, or knitted material. Pastel, dreamy, playful knitted wonderland inspired by classic video games. Background: layered knitted elements including giant crocheted clouds, soft rounded hills, stars, rings, swirls, floating yarn pom-poms, stitched symbols. All plush, rounded, bubbly, fully knitted with premium yarn texture. Center: young woman [use uploaded face reference] sitting on giant crocheted chibi animal chair, rounded head, tiny stitched features, embroidered big kawaii eyes, stubby limbs. Pose: knees together slightly angled, feet inward, body leaning slightly forward, one arm hugging plush crocheted doll of the animal, other hand pinching its cheek or holding ear. Expression: playful, cute, soft smile, slightly puffed cheeks, bright sparkling eyes, innocent and cheerful. Outfit: slightly sexy yet cute, fully knitted cropped oversized pastel blue sweater, high-waist knitted mini skirt with soft pleats, chunky knitted socks, crocheted snea
{ "image_prompt": { "type": "Ultra-realistic Indonesian traditional food infographic poster", "layout_and_composition": { "orientation": "Vertical composition", "style": "Modern culinary infographic design, editorial layout", "background": "Dramatic but clean background" }, "typography_elements": { "headline": { "position": "Top", "style": "Bold text showing dish name and origin (ASAL)" }, "labels": { "style": "Clean Indonesian typography", "connectors": "Curved label arrows pointing to ingredients" } }, "visual_content": { "main_action": "Cinematic floating ingredients suspended in mid-air", "details": [ "Glossy curry splash", "Fresh herbs", "Spices", "Steam rising from the bowl" ], "textures": "Hyper-detailed, glossy, appetizing" }, "lighting_and_atmosphere": { "lighting_style": "Rich golden lighting, studio lighting", "mood": "Professional, appetizing, high-end" }, "technical_specs": { "quality": "8K ultra-realistic, DSLR quality", "focus": "Shallow depth of field", "style": "Professional food photography" } } }
{ "generation_manifest": { "system_directives": { "output_version": "5.0_UltraDetail", "canvas_parameters": { "aspect_ratio": "3:4", "compositional_style": "High-Fashion Cinematic Surrealism", "fidelity_target": "Anatomical_Identity_Lock" } }, "subject_node": { "biometrics": { "identity_anchor": "female from reference photo", "facial_configuration": { "feature_retention": ["Eyes", "Nose", "Mouth"], "alignment_logic": "Symmetrical_Proportional_Integrity", "expression_profile": "Serene_Calm_Innocent" }, "dermatology_rendering": { "surface": "Flawless_White_Porcelain", "finish": "Radiant_Luminous", "pigmentation": "Subtle_Natural_Blush", "makeup_logic": "Minimalist_Bare_Aesthetic" }, "follicle_dynamics": { "base_color": "Long_Blonde", "primary_state": "Neatly_Tied_Back", "secondary_state": "Loose_Strands_Peripheral_Framing" } }, "geometry_and_pose": { "framing": "Upper_Torso_Facial_Focus", "visibility": "Bare_Shoulders_Exposed", "posture": "Graceful_Static" } }, "optics_and_lighting_rig": { "camera_telemetry": { "angle_vector": "90_Degree_Top_Down_Overhead", "lens_characteristic": "Soft_Focus_Expressive", "perspective": "Surreal_Dreamy" }, "lighting_architecture": { "primary_source": "Soft_Direct_Natural_Sunlight", "shadow_mapping": { "geometry_patterns": ["Vertical_Artistic", "Gridded_Mesh"], "projection_surface": ["Facial_Planes", "Clavicle", "Shoulders"], "contrast_ratio": "Low_Soft_Diffused" } } }, "atmospheric_meta": { "tonality": "Pure_Graceful_Atmospheric", "chroma_profile": "Gentle_Naturalistic", "emotional_layer": "Tranquility_Innocence" } } }
