AI image prompts for Midjourney, Flux, DALL-E, and Stable Diffusion

Create A vibrant, digital caricature-style illustration of a smiling woman [ use the uploaded photo as reference] with light red dress. The art style features bold black outlines, expressive facial features, and a clean white background with playful red accent marks around her head to convey high energy and joy. Vertical portrait, 4K. High resolution.

Use 100% face above uploaded photo photorealistic portrait, bearded man in his late 28s or early 30s sitting casually on the cold ground in front of a sleek silver Porsche 911 GT3 with large black rear wing and widebody kit, he is leaning back slightly against the car, wearing black Fear of God Essentials hoodie, black loose pants, white Nike socks, white sneakers,dark sunglasses,with black hair,black beard, relaxed confident vibe, urban industrial background with dark gray metal building facade, overcast daylight, cold weather atmosphere, high detail, sharp focus, cinematic lighting, shot on iPhone 16 Pro or professional camera, natural colors, 8k

{ "image_parameters": { "style": "Canon IXUS aesthetic", "type": "Point-and-shoot photography", "quality": "Hyper-realistic", "tone": "Sharp, direct", "lighting_and_atmosphere": "Realistic, flash-style/direct lighting" }, "subject": { "constraints": { "facial_identity": "Match reference image exactly 100%", "face_edits": "None allowed" }, "hair": { "style": "Long, natural, lightly messy layered look", "movement": "Blowing gently in the wind", "details": "Strands slightly covering part of face" }, "makeup": { "cheeks_and_nose": "Soft pink blush with blurred effect", "lips": "Subtle pink-orange tinted outline" }, "expression": [ "Cute", "Naive", "Cheerful", "Slightly sexy/undone charm" ], "pose": { "body_position": "Half-sitting, half-standing", "action": "Flicking hair" }, "clothing": { "top": "Black strapless top", "bottom": "Low-waisted jeans with a floating waistline", "neck": "Thin black fabric choker/wrap" }, "accessories": [ "Small pendant necklace", "Gold watch" ] }, "environment": { "setting": "Modern pub", "foreground_props": [ "Round table", "Bottle of liquor", "Glass of liquor" ] } }

Hyper-realistic photography of massive volumetric clouds forming the shape of a majestic elephant, highly detailed and anatomically accurate cloud structure, soft yet dense cumulus clouds with realistic depth and texture, dramatic afternoon golden-hour lighting, sunlight rays (god rays) piercing through the clouds, subtle shadows and highlights enhancing form. Foreground: a vast natural meadow with realistic grass, depth of field, and atmospheric perspective. Multiple small elephants grazing naturally across the field. Mid-air: flock of small birds flying dynamically around the cloud formation, adding scale and motion. Environment: cinematic sky with soft gradient tones, slight haze, natural color grading, ultra-realistic lighting, global illumination, volumetric fog, physically accurate shadows. Style: DSLR photography, 85mm lens, f/2.8 aperture, shallow depth of field, HDR, 8K resolution, sharp focus, intricate details, photorealism, no CGI look. Mood: calm, majestic, surreal yet believable, nature documentary realism. --ar 3:4 --quality 2 --style raw

<role>Expert enamel pin badge designer</role> <context>Reference photo: [reference photo]</context> <instructions> Create a travel souvenir enamel pin badge as a composed scene. Make the defining landscape, terrain, or landmark the main body and occupy most of the badge. If a person appears prominently, include them as a small simplified figure at true relative scale within the landscape, preserving the original spatial relationship and scale. Render the person with flat enamel color blocks matching their real clothing and hair colors. Use a smooth plain light skin-tone enamel face. Use thin polished gold outlines around the silhouette and internal dividers, glossy enamel fills, gentle even lighting, a soft sheen on the gold lines, and a very subtle drop shadow. Follow the scene's own outer contour. Place the badge centered on a flat dark navy coarse linen texture, filling about 60% of the frame. </instructions> <constraints> Keep the figure fully colored, the face light, the person subordinate, the landscape fully visible, the badge front-facing, the presentation clean, glare minimal, the style stylized enamel, and the image clean and unmarked. </constraints> Generate the final enamel pin badge image.

<role> You are an experimental editorial poster designer and typographic art director specializing in high-contrast ink-print portrait design. </role> <context> Create a poster for [HUMAN]: a side-profile portrait defined by [FEATURE]. The design language is raw, brutalist editorial print — bold black silhouette blocks, sharp negative space, rough ink edges, fragmented stencil shapes, tiny editorial microtext, vertical typographic accents, and expressive hand-drawn calligraphic marks. The paper is minimal off-white, the layout is asymmetrical, and the vertical composition is cropped. The graphic design logo "[LOGO]" sits near the footer. Target aspect ratio: 4:5. </context> <task> Generate the complete poster image, including one large readable text block that states "[TEXT]" in 2 to 4 stacked lines. </task> <constraints> - Place the "[TEXT]" text block only inside the neck and body area of the portrait, never overlapping the face or the outer background. - Render the text as oversized scribbled lettering that feels fused into the black silhouette, and keep every letter legible. - Use a black and off-white palette only. - Keep the layout asymmetrical with a cropped vertical frame. - Preserve the raw ink print texture and the 4:5 aspect ratio. </constraints> <format> Deliver a single finished poster image, 4:5 aspect ratio, no mockups, frames, or captions. </format> <tone> Raw, minimal, experimental, and print-authentic. </tone> Generate the poster now.

<role>Expert graphic poster illustrator</role> <context>Create a raw sketchy portrait poster with a 4:5 aspect ratio.</context> <instructions>Create a raw sketchy graphic portrait poster of [HUMAN] wearing [CLOTHING], half-body and large in frame, with [ANIMAL] closely beside them in the lower foreground. Use broken black ink contours, loose sketch lines, scratchy hatching, irregular stroke weight, fast gestural marks, simplified anatomy, flat cel-like shadow blocks, and reduced detail. Keep the face oversized and central, crop around mid-torso, and render [SCENERY] as 2 to 3 bold silhouette shapes behind the subject. Use a restrained [COLORS] palette with one dominant warm field, one cool counter-field, dark inked shadows, and pale highlight accents. Add a narrow warm off-white poster border and very light print texture. Finish with strong graphic poster energy, intentionally imperfect strokes, and a raw sketchy look. Create the poster.</instructions>

<role> You are a mixed-media visual designer. </role> <context> Create a vertical mixed-media memory card from [uploaded photo]. </context> <instructions> Use an exact 50/50 vertical split. Keep the top half as the unchanged original photo. Make the bottom half textured off-white handmade paper with a muted irregular color patch matching the photo tones. Redraw the main subjects as a simple dark wax-crayon sketch with loose imperfect lines and minimal details. Add a short handwritten English phrase and subtle Risograph grain. Use a quiet nostalgic Morandi-style aesthetic with generous negative space and an original composition. </instructions> Create the final image.

<role>Expert editorial artist and visual designer specializing in collectible art prints</role> <instructions> Create a visually unforgettable editorial art poster of a dreamlike futuristic world where familiar everyday life meets surreal architecture. Key composition: - Grand sculptural buildings with clean geometric shapes - Winding roads leading to [iconic focal point] - Oversized plants and tiny people for whimsical scale - Unexpected floating elements - Dramatic perspective with cinematic atmosphere - Single iconic focal point as anchor Style blend: - Vintage travel-poster design merged with modern luxury editorial aesthetics - Sophisticated muted color palette: [color palette] - Soft natural light with subtle film grain - Tactile paper texture - Minimal composition, no clutter - Nostalgic yet futuristic, whimsical but premium - Highly detailed, instantly recognizable silhouette Technical requirements: - Vertical 4:5 aspect ratio - No photorealism - Pinterest-worthy, Instagram-viral aesthetic - Collectible art print quality</instructions> <context>Destination: Premium art print collection, editorial spreads, gallery exhibitions. Audience: Design collectors, architecture enthusiasts, luxury lifestyle market. Mood: Elevated whimsy, quiet wonder, timeless sophistication.</context> Generate the poster now.

<role>Concept artist</role> <instructions>Create an original psychological dark‑surrealist scene set in a colossal underground archive. Use endless shelves of sealed black books that rise like skyscrapers and dissolve into fog. In the central aisle, a solitary figure in bone‑white clothing kneels before an open book on the floor. No text appears on the pages. From the blank pages emerges a life‑size figure made of dense black smoke, standing face‑to‑face with the kneeling person. The smoke figure has no eyes or mouth; its chest holds a small locked crimson door. Thin threads connect that door to the kneeling person’s hands, symbolizing a secret self being acknowledged. Compose the scene with vertical 9:16 framing, towering shelves forming a narrow symmetrical canyon, a high‑angle shaft of cold silver light, and the two figures placed small in the lower center to emphasize oppressive scale. Use black paper, aged stone, floating ash, volumetric fog, subtle polished‑floor reflections, and premium photorealistic dark concept art. Apply refined editorial composition to evoke quiet dread and introspection rather than horror spectacle. Color palette: obsidian black, graphite, bone white, cold silver, and a single muted crimson accent on the tiny door. Constraints: The artwork must be entirely original, with blank book pages containing absolutely no writing. No recognizable person, text, symbols, logos, signatures, borders, or watermarks. Avoid visible letters or runes, portrait close‑ups, split faces, black substance on skin, glowing eyes, gore, skulls, conventional ghosts, fantasy wizard styling, or imitation of any named artist. Generate the artwork as described.</instructions> <context>Vertical social‑media artwork for the “Your Dark Side” theme, stylized‑concept asset.</context>

<role>You are an expert image generation assistant that creates realistic travel field-note posters from uploaded photographs.</role> <task>For each photo uploaded, produce ONE individual Rubber Stamp Travel Field Notes Poster in 4:3 landscape format. Never create collages or combine multiple photos.</task> <context>The poster consists of two zones sharing a natural visual transition with no obvious dividing line:</context> <left_zone>LEFT — ORIGINAL PHOTOGRAPH (≈58% of frame): - Preserve the original subject, perspective, terrain, architecture, plants, people, spatial relationships, natural light, shadows, textures, and atmosphere. - Apply only subtle editorial treatment: gentle tonal balancing, restrained color grading, slightly softened highlights, and extremely fine natural film grain. - It must still look like a real photograph taken on location. - Natural cropping is allowed to fit 4:3, but do not stretch, distort, move, replace, or redraw the main subject. - Avoid excessive sharpness, HDR effects, artificial clarity, cinematic color grading, or overly perfect details.</left_zone> <right_zone>RIGHT — AGED PAPER FIELD NOTES (≈42% of frame): - Use warm off-white, slightly aged paper with believable physical texture: subtle paper fibers, fine grain, faint handling marks, matte surface. - Keep large areas completely unprinted. - It should feel like a real sheet from an architect's travel notebook, not a designed poster background. - Avoid overly strong stains, decorative textures, vintage filters, or artificial grunge.</right_zone> <stamp>SMALL RUBBER STAMP: - Study the photograph and identify only the few visual features that make the location immediately recognizable. - Reduce them into a compact, imperfect multi-color rubber stamp impression. Do not reproduce the photograph element by element. - Simplify aggressively, retaining only: distinctive architecture/silhouette, important roof/tower/dome/arch shapes, mountain or terrain contours, shoreline or road direction, a few recognizable trees/vegetation forms, simplified settlement layers, and one or two important foreground shapes. - Remove crowds, cars, dense windows, repetitive buildings, tiny vegetation, decorative objects, and insignificant background details. - Place the stamp in the lower-middle portion of the right paper area, occupying approximately 30–38% of the right section's height. Keep generous blank paper around it. - Extract 2–4 muted spot colors naturally from the photograph (e.g., carbon black, deep green, brick/muted red, ochre, slate blue, taupe). Do not force colors if the photograph suggests a different restrained palette. - Each color should appear as a separate physical ink layer. - Make the print feel genuinely handmade: slightly uneven pressure, tiny gaps in ink, dry areas, paper showing through, rough carved edges, irregular line thickness, small contour breaks, granular ink texture, faint ghosting, slight natural color-layer misregistration, subtle edge variation. - Avoid perfectly aligned digital layers, smooth vector edges, clean gradients, or artificially exaggerated distress.</stamp> <typography>FIELD-NOTE TYPOGRAPHY: - Generate a small amount of text based only on the actual location and imagery: • Location — English name • No. — Number • Three short English keywords • Gregorian calendar year - Place the text below or beside the stamp within available whitespace. - Use a small, understated typewriter or archival field-note style with very slight mechanical irregularity. - Keep it quiet and secondary to the photograph. - Spell everything correctly. Do not add slogans, brands, tourist phrases, decorative quotes, or unnecessary text.</typography> <constraints> - Overall feel: a real travel photograph mounted beside a small handmade field stamp on an architect's personal notebook page. - The photograph must remain the strongest visual element. - The stamp should feel like a small fragment of memory extracted from the photograph, not a second illustration. - Use restrained contrast, natural imperfections, believable paper texture, and slightly imperfect printing. - The final result should feel quiet, tactile, documentary, collectible, and genuinely handmade. - DO NOT use: obvious dividing lines, circular seals, postage-stamp borders, perforations, wax seals, sticker layouts, souvenir-card designs, generic travel templates, smooth vector logos, polished digital illustrations, cartoon styling, 3D rendering, plastic textures, glossy gradients, excessive saturation, HDR effects, excessive text, decorative clutter, overly clean geometry, perfectly aligned ink layers, dense miniature architecture, or any alteration/redrawing of the original photograph.</constraints> <format>Output a single 4:3 landscape image per uploaded photo.</format> <tone>Documentary, quiet, tactile, collectible, genuinely handmade.</tone> Generate the image now.

<role> You are a cinematographer and editorial photography art director crafting prompts for photorealistic AI image generation. </role> <task> Produce one complete, copy-ready image-generation prompt for the scene titled "Whispers of Spring." </task> <context> Scene: A peaceful pathway beneath blooming cherry blossom trees on a warm spring afternoon. Pink blossoms fill the canopy overhead while delicate petals drift gracefully through the air. Soft sunlight filters through the branches, creating a dreamy, enchanting atmosphere. Subject: A young woman walks away from the camera, then gently turns her head over her shoulder with a soft, mysterious smile. She wears a flowing natural linen dress that moves gracefully with the breeze, highlighting her delicate facial features and effortless elegance. Details: Wind carries countless pink cherry blossom petals across the frame while warm sunlight creates glowing highlights. Every strand of hair moves naturally in the breeze. Include ultra realistic skin texture, lifelike fabric folds, soft floral surroundings, and subtle atmospheric haze for cinematic realism. Atmosphere: Elegant, peaceful, romantic, dreamy, timeless, cinematic, graceful, enchanting. Lighting: Warm spring sunlight filtering through cherry blossom branches, soft natural illumination, glowing highlights, volumetric light rays, gentle ambient shadows, subtle atmospheric haze. Composition: Cinematic editorial portrait, 85mm lens, three-quarter over-the-shoulder pose, shallow depth of field, creamy bokeh, balanced framing with flowering trees, soft leading lines, immersive visual storytelling. Style: Photorealistic, masterpiece, editorial fashion photography, analog film aesthetic, dreamy pastel color palette, ultra realistic skin texture, highly detailed, shallow depth of field, creamy bokeh, atmospheric haze, HDR, cinematic realism, 8K. </context> <constraints> - Output a single block of flowing descriptive prose, 120-180 words. - Weave subject, action, setting, lighting, composition, and style into one cohesive paragraph. - Use precise sensory and photographic language; keep every specified detail. - Exclude titles, headings, section labels, negative prompts, camera metadata, and commentary. </constraints> <format> Return only the prompt paragraph as plain text. </format> <tone> Luminous, poetic, cinematic, and confident. </tone> Write the finished prompt now.

<role> You are a precision portrait image generator specializing in identity-locked hairstyle lookbooks. Your craft is absolute facial fidelity and disciplined adherence to locked attributes across every panel. </role> <context> Reference photo: [reference photo of the person]. Output: one single image containing a 3-column x 4-row grid of 12 panels, numbered 1 to 12, in a 4:5 vertical (portrait) aspect ratio. </context> <instructions> SINGLE VARIABLE RULE: The only element that changes between panels is the hair on the head — its shape, style and length. Everything else stays exactly as in the reference photo. IDENTITY LOCK (CRITICAL): Reproduce the same real person in all 12 panels. The face must be identical to the reference in every frame. Preserve exactly: facial bone structure, jawline, cheekbones, nose shape, lips, eye shape and spacing, eyebrows, skin tone, and skin texture including pores and natural imperfections. Keep overall facial proportions, the same age, and the reference's exact expression. Present the face naturally, never beautified, slimmed or otherwise altered. LOCKED IN EVERY PANEL: - Eyes: fully visible and unobstructed in all 12 panels. No sunglasses of any kind. - Hair color: exactly as it appears in the reference photo across all 12 panels. Change shape, length and style only. - Makeup and skin: reproduce the reference makeup identically in every panel — same lip color, same eye makeup, same brow grooming. If the reference shows no makeup, keep all 12 panels makeup-free. Do not add, remove or alter makeup between panels. - Clothing: the same clothing visible in the reference photo, replicated exactly. - Accessories: keep all visible accessories from the reference (earrings, necklaces, rings, bracelets, piercings, watch, prescription glasses, etc.). Never omit, resize, recolor or restyle an accessory. Prescription glasses stay in every panel. - Background: plain, uniform, solid light grey studio backdrop in every panel — zero objects, zero textures, zero gradients, no room, no furniture, no environment. THE 12 HAIRSTYLES (panel order): 1. Pixie cut — very short, textured, slightly tousled top with tapered sides and nape. 2. Classic bob — chin-length, straight, blunt ends, clean middle part. 3. Long layered waves — past the shoulders, soft voluminous waves with face-framing layers. 4. Sleek low bun — pulled back smoothly into a tight low bun at the nape, no flyaways. 5. Curtain bangs, medium length — soft parted fringe framing the face, falling just past the shoulders. 6. High ponytail — sleek, smooth crown, length falling behind. 7. French bob — short, ending at the jawline, with a soft blunt micro-fringe across the forehead. 8. Long straight hair, middle part — very long, sleek, pin-straight, well past the shoulders. 9. Shaggy wolf cut — medium length, heavy layers, choppy fringe, textured and voluminous, slightly wild. 10. Elegant updo — swept up into a polished chignon with soft face-framing tendrils. 11. Short curly crop — short voluminous curls all over, natural texture, tapered at the sides. 12. Side-swept Hollywood waves — long, glamorous deep side part, sculpted vintage waves cascading over one shoulder. PHOTOGRAPHIC SPECS: Canon EOS R5, 85mm f/1.4 lens, studio portrait lighting with a soft key light and subtle fill, shallow depth of field with sharp focus on the face, natural skin rendering with visible pores, realistic individual hair strands with no plastic or CGI look. Keep lighting, color grading and exposure consistent across all 12 panels. Photorealistic, high detail, hyperrealistic, 8K. Straightforward photographic rendering — no illustration, no painterly effect, no over-smoothing. Number each panel 1 to 12 clearly in its top-left corner. </instructions> <final_action> Generate the complete 12-panel grid now: one image, 3 columns x 4 rows, 4:5 portrait ratio, with only the hair varying across panels. </final_action>

<role>Expert hand-drawn illustration artist</role> <context>Reference image: [reference image]</context> <instructions>Transform the subject from [reference image] into a cute, quirky hand-drawn doodle illustration. Preserve recognizable facial features, hairstyle, face shape, clothing, accessories, and identity. Use a minimalist children's storybook / fashion sketch aesthetic with loose, imperfect black ink lines, visible scribbly pencil strokes, subtle cross-hatching, and a handmade feel. Design an oversized head, small simplified body, dot-like eyes, tiny minimal mouth, soft rounded features, rosy pink blush, messy expressive hair, playful proportions, and a relaxed whimsical pose. Render in black-and-white pencil/ink doodle style with rough sketch lines, dense scribbled details, light hand-colored accents, subtle watercolor/crayon-like coloring, minimal shading, clean white/off-white background, and generous negative space. Keep the result hand-sketched, adorable, expressive, and effortlessly stylish. Create the final illustration.</instructions>

<role> Luxury travel-art visual director </role> <instructions> Create one premium tourism campaign image for [COUNTRY] as a seamless cinematic panorama inside a transparent crystal/glass architectural frame on a glossy reflective surface. Include iconic landmarks, historic architecture, distinctive landscapes, local transportation, cultural elements, national flag, flowers, and recognizable scenery. Use warm golden-hour light, soft haze, pastel cream, champagne, muted blue, and sage tones, delicate clouds, subtle birds, realistic glass refraction, rainbow prism edge highlights, and a softened mirror reflection below. Add elegant editorial typography at the top: “[COUNTRY]”, “THE SOUL OF [COUNTRY]”, and “A JOURNEY THROUGH TIME • 2026”. </instructions> <context> Sophisticated luxury travel magazine aesthetic, photorealistic yet painterly, fine-art composition, serene atmosphere, premium advertising photography, symmetrical balanced framing, soft film grain, 8K, vertical 4:5, clean composition, minimal text, no modern UI elements. </context> Create the image.

<role>Expert AI Image Generation Prompt Engineer & Luxury Beverage Art Director</role> <instructions> Create a single optimized prompt for generating a Cannes-level premium summer campaign poster for fictional lemon drink brand "LIMORA" using a strict 2-column × 3-row grid (6 equal panels, thin white dividers). <context> - Brand: LIMORA (fictional premium lemon beverage) - Format: Unified high-end advertising storyboard, 6 frozen iconic moments from a luxury summer commercial - Visual concept: Ultra-realistic miniature young woman (same across all panels) in surreal oversized citrus world on bright sandy beach - Hero: Lemon product system (whole fruit, slices, juice, ice, sparkling drink, sorbet) — hyper-real, tactile, sunlit - Style: Hyper-real premium surreal advertising photography, luxury FMCG campaign, cinematic micro-world illusion </context> <constraints> COMPOSITION: - Strict 2×3 grid, equal panels, thin white dividers, consistent horizon line, consistent beach-ocean background, unified lighting - Miniature woman + oversized lemon object centered each panel; sea softly blurred BG, sand sharp FG - Strong commercial clarity, readable at distance VISUAL FLOW (Panel 1→6): - Escalating action: touch → recline → squeeze → travel → embrace → taste - Repeating directional rhythms: hair, arms, legs, juice droplets, spoon, lemon slice, straw, entering hand position - Subtle diagonal energy per panel; citrus world feels alive, breezy, sparkling PANEL NARRATIVE SEQUENCE: 1. Woman hugs giant whole lemon on sand; giant adult hand descends from above positioning lemon; lively, slightly off-balance pose 2. Woman reclines inside halved lemon (luxury chaise), dark sunglasses, tiny parasol drink pick; floating lemon slice lowered from above like citrus sun 3. Giant hand squeezes vertically cut lemon from above; translucent juice streams/droplets arc downward; woman reacts dynamically beneath, arms raised, body tilted 4. Woman rides refined wooden cart piled with lemons, pulled by whimsical premium lemon-shaped creature/harness; artisanal, stylish, physically grounded 5. HERO CLIMAX: Tall branded LIMORA glass dominates — ice, lemon slices, pale sparkling liquid, condensation, green straw, cocktail umbrella; woman hugs glass joyfully; strongest product-selling moment 6. Woman sits inside halved lemon; large polished spoon descends from above carrying glossy lemon sorbet/crushed ice; playful anticipation CHARACTER (consistent across all 6): - Ultra-realistic miniature young woman, fitted green floral mini dress, white sandals, long dark wavy hair - Coherent anatomy: correct proportions, realistic shoulders, collarbones, arms, waist, hips, thighs, knees, calves, ankles, feet, perfect hands (5 fingers) - Expressions per panel: surprised delight → relaxed confidence → playful alarm → exhilaration → joyful refreshment → amused anticipation - Photorealistic skin: pores, tonal shifts, knee/elbow texture, elasticity; no plastic AI finish LIGHTING: - Bright premium seaside daylight, soft upper-left sun, gentle atmospheric diffusion - Luminous fresh summer lighting across all panels; short soft-edged shadows, crisp dimensional highlights - Sparkling highlights on juice droplets, pulp, ice, spoon edges, sunglasses, glass rim, condensation - Luxurious, refreshing, physically consistent panel-to-panel MATERIALS: - Lemons: ultra-detailed peel pores, dimpling, rind thickness, glistening wet pulp, cut translucency, realistic juice behavior - Glass: high-clarity premium, accurate refraction, heavy base, condensation beads, crisp "LIMORA" logo, ice transparency, sparkling carbonated feel - Sorbet/juice: glossy, semi-translucent, cold, wet, appetizing, physically accurate - Dress: lightweight summer cotton, tiny green floral print, natural wrinkles, fabric tension, wind-responsive edges - Hair/skin: realistic strands, fine flyaways, natural shine, believable texture - Giant hand: realistic adult fingers, soft skin compression, natural nails, coherent scale perspective - Cart/props: refined warm wood grain, polished wheels, believable joints/harness - Beach: fine sunlit sand with micro footprints/pressure marks, soft shoreline blur, clean turquoise sea with pale foam COLOR SYSTEM: - Dominant: lemon yellow; support: fresh citrus green, turquoise sea, pale sky blue, warm beach beige, crisp white highlights, restrained natural skin tones - Bright, appetizing, summery, clean, internationally commercial; no random accent colors TYPOGRAPHY & BRANDING: - Minimal, original, premium, modern, secondary to visual storytelling - Refined English branding ONLY on hero glass ("LIMORA") + optional tiny campaign line below grid: "LIMORA — Bright in Motion" - No copied text, no Chinese text, no existing brand names NEGATIVE CONSTRAINTS (must avoid): - Copied text, Chinese text, existing brand names, cartoon style, toy-like figure, grotesque oversized head, deformed anatomy, extra/missing/fused fingers, twisted wrists, broken limbs, distorted feet, AI plastic skin, over-smoothed skin, fake citrus texture, unrealistic juice physics, muddy lemon pulp, cloudy glass, weak product focus, inconsistent lighting/horizon, messy grid, cluttered props, meme aesthetic, cheap humor, childish illustration, low-resolution detail, oversaturated colors, dead black patches, distorted giant hand perspective </constraints> <format> Output a single, complete, production-ready image generation prompt string incorporating all above specifications in logical order: [Composition] → [Visual Flow] → [Panel Sequence] → [Character] → [Lighting] → [Materials] → [Color] → [Typography] → [Art Direction] → [Negative Prompt]. Use clear section headers. Preserve all [variables] as placeholders where applicable. </format> <tone>Professional, precise, art-direction authoritative, commercially polished</tone> Final action: Output ONLY the optimized prompt string. </instructions>

<role>Professional travel-fashion photographer and image editor</role> <context>Reference person: [reference_image]. Output: 9:16 vertical full-body outdoor fashion photograph.</context> <instructions>Create a dreamy ultra-photorealistic outdoor fashion photograph of the person from [reference_image] standing naturally on a grassy mountain ridge. Preserve the exact facial identity, face shape, facial proportions, eyes, eyebrows, nose, lips, skin tone, hairstyle, hairline, and recognizable features. Compose a full-body vertical portrait with the subject slightly below center, body slightly turned toward the camera, face naturally toward the viewer, one hand holding several thin white strings attached to one enormous fluffy white cloud floating above like a whimsical balloon bouquet, and the other hand resting naturally. Set the scene in a high-altitude mountain landscape with distant blue-green mountains, delicate wild grass, and a vast open sky. Dress the person in a completely modest, elegant, fully covered light-blue maxi dress with loose long sleeves, high neckline, opaque fabric, ankle-length flowing skirt, simple white closed-toe sneakers, and a small woven crossbody bag. Add tasteful round dark sunglasses. Keep the original hairstyle and hair color, with a few natural strands moving gently in the mountain breeze. Use bright natural midday sunlight, soft atmospheric illumination, realistic skin texture, natural fabric details, physically accurate lighting, subtle natural shadows, crisp gentle exposure, realistic depth of field, cinematic atmospheric perspective, high dynamic range, and a clean airy dreamy color palette of sky blue, soft white, pale powder blue, natural green grass, and distant blue mountains. Maintain realistic anatomy, natural hands, believable string connection, and a peaceful summer atmosphere.</instructions> Create the photograph.

<role>You are an image transformation specialist that converts people in photographs into adorable hand-drawn doodle characters while leaving the background untouched.</role> <instructions> Transform ONLY the people in [uploaded_photo] into cute hand-drawn doodle characters. Keep the original photographic background completely unchanged. PRESERVE THE BACKGROUND: Keep the original sky, landscape, buildings, water, furniture, ground, plants, railings, objects, lighting, colors, perspective, camera angle, framing, and textures as close to the original photo as possible. Do NOT redraw, simplify, illustrate, or apply doodle/crayon/pencil effects to the background or environmental objects. TRANSFORM ONLY PEOPLE: Replace each person with a charming, naive doodle version while preserving: - exact number of people - original position and relative scale - front/back/side/three-quarter orientation - head and body direction - pose and gesture - arm and leg positions - interactions with people or objects - hairstyle, clothing colors, and major accessories ORIENTATION RULES: - If someone faces away, keep them back-facing. - If sideways, keep them sideways. - If facing forward, keep them forward. - Never rotate a person toward the viewer or invent a face that is not visible. CUTE DOODLE STYLE: Freely reinterpret realistic anatomy into an adorable, imperfect character: - oversized round head - tiny compact body - short simplified arms and legs - tiny hands and feet - cute awkward proportions - loose scribbled hair - tiny dot eyes and simple facial features when visible - rosy scribbled cheeks when appropriate Keep the original pose recognizable, but simplify and slightly exaggerate it for cuteness. DRAWING STYLE: Loose naive hand-drawn doodle, like a quick children's sketch. Use thin shaky black outlines, imperfect shapes, overlapping sketch lines, scribbled colored-pencil or crayon fills, uneven coloring, white gaps, and slightly messy edges. The character should look intentionally roughly drawn but extremely cute. OBJECTS: Objects, furniture, scenery, and items around the people should remain photographic whenever possible. A doodle character may naturally touch or hold a real photographic object. INTEGRATION: Keep correct scale, ground contact, depth, and occlusion so the doodle characters naturally occupy the same locations as the original people. PRIORITY ORDER: 1. Original photographic background 2. Person position and scale 3. Exact body orientation 4. Pose and gesture 5. Cute exaggerated doodle character design AVOID: Full-image illustration, background doodling, realistic anatomy, anime, manga, 3D cartoon, polished digital art, vector lines, changed poses, changed orientation, added people, or invented faces. </instructions> <context> Input: [uploaded_photo] Output: A single image where only the people are transformed into cute hand-drawn doodle characters, with the original photographic background preserved exactly. </context> <format>Return ONLY the transformed image. Do not add text, captions, borders, or overlays.</format> <tone>Precise, visually descriptive, and strict about preserving the background and person orientation.</tone> Final action: Generate the image using [uploaded_photo] and apply the transformation exactly as specified.