GPT Image 2 prompts

Create a cinematic travel poster for {argument name="city name" default="Lisbon"} using a realistic street photograph style: two vintage yellow-and-red electric trams side by side on sunlit rails, close-up perspective, the left tram cropped large in the foreground and the right tram angled slightly away, with passengers visible through wooden-framed windows, overhead tram wires, parked cars, leafy trees, and bright European city architecture in the background. Add warm late-afternoon sunlight, deep shadows, rich contrast, glossy reflections on glass, and an authentic urban documentary feel. The image contains exactly 2 main trams: 1 foreground tram on the left with a large Coca-Cola-style red side panel, and 1 tram on the right marked with the number 56 near the top front corner. Overlay centered white typography across the lower-middle: a large expressive handwritten brush-script title reading {argument name="headline text" default="Lisbon"}, with a smaller all-caps serif tagline beneath reading {argument name="tagline text" default="WHERE EVERY CORNER TELLS A STORY"}. Include thin decorative horizontal divider lines on both sides of the tagline and a small diamond ornament centered below it. Compose as a polished tourism campaign image, 3:2 landscape aspect ratio, no border, no watermark, keep the text crisp and legible while preserving the realistic photographic background.

Create an emotional smartphone-style travel photograph of {argument name="city name" default="Lisbon"} in warm late-afternoon sunlight, showing exactly 2 vintage yellow-and-red street trams stopped side by side on curved tram tracks in a busy European street. The left tram is cropped close in the foreground with wooden window frames, a red side panel carrying a visible Coca-Cola advertisement, a small route sign reading “08,” and passengers partially visible through reflective windows. The right tram is slightly farther back, angled toward the viewer, with the number “56” near the roof, open doors and windows, passengers inside, and a beverage advertisement on the red lower panel. Include urban background details such as parked cars, leafy trees, bright building facades, hard shadows on asphalt, metal rails, and a candid street-photography feel. Apply high-contrast cinematic color grading, deep blacks, golden highlights, realistic lens reflections, and a nostalgic travel-poster mood. Overlay large centered white handwritten brush-script text reading {argument name="main title" default="Lisbon"} across the lower middle of the trams, with a smaller elegant all-caps serif subtitle beneath it reading {argument name="subtitle" default="WHERE EVERY CORNER TELLS A STORY"}. Add thin decorative horizontal lines around the subtitle and a tiny diamond ornament below. Keep the composition horizontal 3:2, photorealistic, slightly imperfect like a good phone snapshot, with no extra text or watermark.

Create a realistic editorial fashion triptych showing exactly 3 full-body female models standing front-facing in traditional Korean royal hanbok, separated by two clean vertical white dividers. Canvas is a square 1:1 composition, photographed at eye level with symmetrical spacing, each model centered in her own vertical panel. The background is the same softly blurred palace courtyard for all three panels: dark red wooden doors, muted architectural details, gray stone floor, shallow depth of field, overcast natural light, refined museum-catalog mood. All faces should be intentionally anonymized with a smooth soft blur while preserving the hair, headpieces, clothing, hands, and posture in sharp detail.

Subject count and details: exactly 3 models. Left model: pale pink jeogori and long outer robe with wide sleeves, lavender and purple waist sash, pale blue underskirt, delicate white floral embroidery on the lower robe, hands folded at the waist, black updo hair with ornate gold floral hair ornaments on both sides and top. Center model: deep navy blue embroidered outer robe with wide sleeves, white sleeve linings, red underskirt, richly patterned red-and-blue waistband, gold floral embroidery on sleeves and lower front panel, hands folded, black updo hair with a gold ornament centered on top. Right model: pale mint-green outer robe with wide sleeves, red front skirt panel, pale blue sleeve linings and hanging ribbons, red patterned waistband, floral embroidery on the lower red panel and robe edges, hands folded, black updo hair with multiple gold ornaments across the crown and sides.

Visual style: photorealistic high-fashion historical costume photography, ultra-detailed fabric texture, satin and brocade sheen, intricate embroidery, balanced soft lighting, muted colors, realistic proportions, elegant upright posture. Keep the composition formal and symmetrical, with no text, no watermark, no extra people, no props, and no modern objects. Use {argument name="number of outfits" default="3"} coordinated hanbok looks, with the main palette emphasizing {argument name="left outfit color" default="soft pink and lavender"}, {argument name="center outfit color" default="deep navy and crimson"}, and {argument name="right outfit color" default="pale mint green and red"}. Set the location as {argument name="background location" default="a blurred Korean palace courtyard"}.

Goal: Create a luxurious Korean-style beauty magazine infographic titled as a personalized makeup analysis guide for {argument name="character name" default="you"}, using a translucent, elegant female model with dewy skin, long dark brown hair, bare shoulders, and soft beige knit styling. The design should feel like a high-end cosmetic consultation sheet in white, ivory, pale gray, blush pink, and warm beige.

Canvas: Vertical poster, approximately 4:5 ratio, clean white-to-light-gray background, thin pale gray borders, delicate serif typography, airy spacing, soft natural lighting, polished editorial photography look.

Main layout: Place one large bust-up portrait of the female model on the upper left, occupying about 40% of the canvas width and 45% of the height. She faces forward in a graceful pose with one hand near her chin, glossy brown hair, off-shoulder cream top, luminous skin, and a calm feminine mood. At the top left, add small English text “MAKEUP VARIATION” and a large Japanese headline “あなただけの メイク分析ガイド”.

Point box: Under the large portrait, add a small bordered note box with the script heading “Point” and Japanese body copy describing clear skin, balanced features, pearl placement, and a refined elegant atmosphere.

Makeup variation grid: On the upper right, create exactly 4 smaller portrait tiles in a 2×2 grid, each showing the same woman with subtle makeup differences. Add pale blush label bars under each tile with these 4 Japanese labels: “ナチュラル”, “透明感メイク”, “大人っぽメイク”, “甘めメイク”.

Middle analysis area: Create three adjacent boxed columns across the middle.
1. “FACIAL FEATURE” column: exactly 4 horizontal feature rows with close-up photos and Japanese descriptions: one eye close-up, one nose close-up, one lips close-up, one ear/skin-side-face close-up.
2. “MAKEUP POINT” column: exactly 3 horizontal rows with close-up photos and advice text: eye makeup close-up, cheek/under-eye close-up, lip close-up.
3. “RECOMMEND COLOR” column: show exactly 16 circular color swatches grouped into 4 labeled rows with 4 swatches each. The labels are “EYE”, “CHEEK”, “LIP”, and “BASE”. Use muted rosy browns for eyes, soft pink-coral for cheeks, vivid rose-red/coral for lips, and ivory-peach-beige for base.

Lower analysis area: Create three boxed sections.
Left section “FACE TYPE”: large Japanese face type text “ソフトエレガント”, a short Japanese description about a balanced face with elegance and softness, and exactly 4 small hashtag chips: “# 大人顔”, “# 曲線寄りの直線”, “# 上品”, “# 華やか”.
Center section “BALANCE ANALYSIS”: a pink translucent radar chart with exactly 6 axes labeled in Japanese: “直線”, “大人”, “曲線”, “子供”, “カジュアル”, “クール”, with small numeric values around the chart.
Right section: exactly 8 Japanese style rating rows using star icons, labeled “フレッシュ”, “ソフト”, “エレガント”, “フェミニン”, “キュート”, “アクティブキュート”, “クール”, “クールカジュアル”. Use mostly black filled stars and pale gray empty stars.

Bottom strip: Add an “OVERALL TIP” section with exactly 5 compact tip cards in a horizontal row: eye close-up card, makeup brush on cheek card, lips close-up card, small face portrait card, and eyeshadow palette card. Each card includes a tiny image and short Japanese makeup advice text.

Footer: Add a centered Japanese closing sentence along the bottom: “あなたの魅力を引き出すメイクで、もっと自分を好きになれるはず。 ✨”

Visual style: Minimal luxury beauty editorial, Korean transparent-skin aesthetic, soft shadows, thin dividers, blush beige accent bars, elegant serif headings, delicate script for “Point”, realistic cosmetic photography, harmonious spacing, no clutter.

Customizable details: The model should have {argument name="hair color" default="dark brown"} hair, {argument name="skin finish" default="clear dewy translucent skin"}, the overall accent palette should be {argument name="accent color" default="pale blush beige"}, and the face type should read {argument name="face type label" default="ソフトエレガント"}.

Constraints: Keep all Japanese labels legible, use exactly the element counts specified, maintain the same editorial grid structure, avoid logos or watermarks, and do not add extra sections.

Create a cinematic high-end photomanipulation scene in a flooded, derelict New York City subway station. Vertical 2:3 frame, mid-shot, low eye-level camera half submerged at waterline. In the foreground, show {argument name="hero description" default="a soaked male action hero with short wet black hair, dark tactical clothing, and tense body language"} wading chest-deep through murky green-black water, gripping a black assault rifle with both hands; the rifle has a long suppressor, a vertical magazine, tactical rails, and a bright white flashlight beam aimed toward the viewer. Place exactly three opaque face-obscuring rectangles: one large dark brown square covering the hero’s face, one large blurred brown square covering the creature’s face, and one smaller blurred brown square over the creature’s raised hand area. Behind the hero, slightly right of center and out of focus, show {argument name="pursuer creature" default="a bloated pale zombie-like humanoid woman with mottled diseased skin, exposed chest, stringy wet yellow-green hair, and one arm reaching forward"} emerging waist-deep from the floodwater, creating splashes and droplets. The setting should include exactly two subway trains, one partially visible along the left background edge and one silver train along the right side; exactly three major rust-stained support columns visible in depth; overhead fluorescent strip lights receding down the ceiling; one dark station sign reading “Eastbound” in the distant center-left; one smaller dark sign reading “Delancey Street” on a right column; and one glowing red exit sign in the background. Use {argument name="color grade" default="cold teal-green shadows with sickly fluorescent highlights and small red accents"}, heavy humidity, water droplets suspended in the air, reflections and ripples on the water surface, gritty rust, grime, peeling paint, cinematic suspense lighting, shallow depth of field, photorealistic horror-action style, ultra-detailed, dramatic contrast, no extra text, no watermark except a small subtle four-point sparkle icon at the bottom right.

Goal: Create a realistic vertical 3:4 transformation collage showing a young woman being turned into a dark-haired fantasy elf warrior in a salon or backstage makeup studio.

Canvas: A single vertical image divided into exactly 12 equal rectangular panels arranged in a 3-column by 4-row grid, with thin white borders between panels. Each panel has a small white serif number in the upper-left corner, labeled exactly 1 through 12.

Subject: The same young adult woman appears in every panel, centered in a close-up portrait from chest or shoulders upward. She has {argument name="hair color" default="long black hair"}, pale skin, and a neutral forward-facing pose. Her face is intentionally obscured in every panel by a soft-edged rectangular beige blur or privacy mask covering the facial features while leaving hair, ears, neck, and outfit visible.

Setting and style: Photorealistic cinematic lighting, shallow depth of field, dark warm salon or dressing-room background with mirrors, shelves, makeup tools, blurred lights, and a professional makeover atmosphere. Use natural camera perspective and consistent lighting across all panels.

Panel sequence: Show exactly 12 distinct stages of the transformation:
1. Before look: the woman with loose long black hair, wearing a cream knit sweater, no elf ears or armor yet.
2. Hair preparation: hair clipped back with small metal salon clips, wearing a black salon cape; a makeup artist hand works near the cheek.
3. First prosthetic: a long pointed elf ear is being attached on one side, with a makeup brush or tool near the ear.
4. Both pointed elf ears visible, hair tucked back, black salon cape, clean early fantasy look.
5. Makeup detailing: both pointed ears visible, a brush applying makeup near the cheek or ear.
6. Finished prosthetic ears: both long pointed elf ears visible, dark hair loose, still in black salon cape.
7. Close elf portrait stage: pointed ears prominent, hair smoother and darker, black salon cape, no armor yet.
8. Hairstyling stage: hair partly braided with small silver ornaments or clips woven through the sides, pointed ears visible, wearing a lighter underlayer.
9. More advanced braided hairstyle: intricate dark braids with silver beads and accessories, pointed ears visible, fantasy styling becoming stronger.
10. Armor stage: the woman now wears ornate silver fantasy shoulder armor and chest armor with engraved details, braided hair and pointed ears visible.
11. Final makeup touch-up: same ornate silver armor and elf ears, a makeup artist hand applies finishing detail with a brush near the face.
12. Final completed character: fully transformed into an elven warrior wearing polished silver armor with gold accents, braided black hair with ornaments, long pointed ears, and a dramatic fantasy presence.

Constraints: Keep the same person, same camera angle, and same studio environment across all 12 panels. Include no extra text besides the numbers 1 through 12. Make the collage look like behind-the-scenes documentation of a professional fantasy character makeup and costume transformation. Avoid cartoon style; make it highly realistic, detailed, and cinematic.

Goal: Create a realistic 12-panel transformation progress collage showing a young woman being styled into a fantasy elf warrior, photographed in a dim professional makeup studio. The face must be intentionally obscured in every panel by a soft rectangular blur/mosaic privacy block centered over the face.

Canvas: Vertical 3:4 collage, approximately 768x1024, arranged as a clean 3-column by 4-row grid with thin white dividers between panels. Add small white serif numbers in the upper-left corner of each panel, labeled exactly 1 through 12.

Subject: A young adult {argument name="character gender" default="woman"} with {argument name="hair color" default="long black hair"}, pale skin, and a slim neck/shoulders. She begins in a simple cream knit top, then wears a black salon cape during the makeup and prosthetic stages, and ends in ornate silver fantasy armor. Keep the person in a centered bust portrait composition in every panel, facing mostly forward with slight head turns.

Setting and style: Hyper-realistic cinematic photography, shallow depth of field, warm studio lights and bokeh bulbs, blurred shelves of makeup tools and bottles in the background, muted dark brown and charcoal tones, natural skin texture, high detail, documentary behind-the-scenes feeling.

Panel-by-panel layout: Use exactly 12 discrete panels. Panel 1: plain before shot, long loose black hair, cream sweater, no elf features. Panel 2: hair clipped back with small silver clips, black salon cape, a makeup artist hand touches the jaw/cheek with a brush or applicator. Panel 3: first pointed elf ear prosthetic attached on one side, makeup brush applying detail near the cheek, black cape. Panel 4: both long pointed elf ears visible, hair tucked behind ears, black cape, no armor yet. Panel 5: makeup brush applies contour or color near the cheek, pointed ears visible, black cape. Panel 6: refined elf-ear look, centered portrait, ears sharp and symmetrical, black cape. Panel 7: closer finished prosthetic stage with both pointed ears clearly visible and loose dark hair around shoulders. Panel 8: hair partially braided with multiple small braids and decorative strands, one pointed ear visible, cream clothing returning at shoulders. Panel 9: more elaborate braided fantasy hairstyle with wet or glossy curls and small silver hair ornaments, pointed ears visible. Panel 10: ornate silver shoulder armor and high fantasy chest collar added, braided hair, pointed ears, studio background. Panel 11: makeup artist hand returns with a brush near the cheek while the subject wears silver armor and pointed ears, showing final touch-up. Panel 12: final completed {argument name="fantasy character type" default="elf warrior princess"} portrait in ornate silver armor with sculpted pauldrons, braided dark hair, long pointed ears, and dramatic heroic styling.

Text content: Only include the panel numbers 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, and 12. Do not add captions, logos, watermarks, or extra typography.

Constraints: Keep the same person, same studio, same camera distance, and same lighting across all panels. Maintain a realistic makeup transformation sequence rather than an illustration. Ensure every visible face is covered by a rectangular soft blur block, while ears, hair, hands, armor, and clothing remain sharp.

Create a dark cinematic fantasy close-up in a 16:9 widescreen frame: a rugged warrior or shaman stands on the left side of the composition, partially turned in profile, wearing a massive weathered dragon-skull headdress that extends to the right with bony teeth, spikes, horns, cracked scales, and reddish thorn-like protrusions. The character has long dark hair with one visible thick reddish-brown braid, a visible ear, and a rough fur cloak over the shoulder. Place a large opaque dark olive-black rectangular block over the center of the image, covering most of the character’s face and torso area like an intentional censor mask. The background is out of focus, foggy, and teal-green, suggesting a bleak outdoor medieval or tribal battlefield setting with vague silhouettes of posts or structures. Use shallow depth of field, moody low-key lighting, muted green-brown color grading, gritty texture, realistic creature-bone detail, and an ominous atmospheric tone inspired by {argument name="director mood" default="grim mythic fantasy cinema"}. The headdress should have exactly one prominent dragon skull head visible on the right, one visible braid, one fur shoulder mass, and one central censor rectangle. No text, no watermark, no bright colors.

Create a hyperreal cinematic nighttime photograph of {argument name="city setting" default="a modern downtown avenue between two massive glass skyscrapers"} during heavy rain, viewed from street level with a centered one-point perspective down the road. The scene shows exactly two towering dark office buildings forming a canyon on the left and right, with illuminated office windows and wet reflective facades. Between them rises one enormous vertical wall of ocean water, like a suspended aquarium or tidal wave stretching upward into the sky, its foamy rim curling at the top under a bright full moon partially veiled by clouds. Inside the blue-black water are three clearly visible whales: one large central whale swimming diagonally toward the viewer, one smaller whale below it, and one smaller whale higher in the distance; include many tiny fish silhouettes around them. The rain-soaked street below is glossy with mirror reflections of red traffic lights, car taillights, building lights, and moonlit blue water. Add a realistic urban traffic scene with several cars moving away from the viewer, including one prominent dark sedan in the lower center with glowing red taillights, and scattered pedestrians on both sidewalks and crosswalk areas holding umbrellas. Use {argument name="mood" default="awe-inspiring, surreal, dramatic, and ominous"}, deep navy and steel-blue color grading, high contrast, volumetric mist, street steam, rain streaks, sharp architectural detail, realistic reflections, and a 35mm cinematic lens look. No text, no watermark, no illustration style; make it feel like an impossible but photoreal event captured in a high-budget disaster-fantasy film.

Create a hyper-realistic vertical smartphone photo of {argument name="character description" default="a young Asian woman"} sitting courtside/in the lower audience section at a packed Los Angeles Lakers NBA game, framed waist-up in a close candid closeup. She is centered in the foreground, seated on a black arena chair, wearing {argument name="team hoodie" default="a black cropped Los Angeles Lakers hoodie with purple-and-gold sleeve stripes and a large number 23 on the front"}, black leather-look pants, and gold accessories including exactly 2 visible jewelry pieces: a thin gold necklace with a round pendant and a dangling gold earring. Her hair is dark, slightly messy, pulled back into a sleek ponytail with loose strands around the ears. Show her posture as calm and focused, hands resting low near her lap, watching the game action off-camera. Include exactly 3 prominent foreground spectators: the main woman in the center, a young man on the left in a purple Lakers hoodie looking left, and a young man on the right in a black Lakers zip hoodie holding a phone; obscure exactly 2 faces with flat rectangular skin-tone privacy blocks, one over the main woman's face and one over the right spectator's face. The background is a densely crowded basketball arena with hundreds of fans, upper seating tiers, bright stadium lights, LED ribbon boards, and readable arena signage such as {argument name="arena signage" default="LOS ANGELES LAKERS"} and a Toyota logo near the scoreboard. Use realistic indoor arena lighting, natural phone-camera perspective, high detail fabric texture, shallow-to-moderate depth of field, slight wide-angle distortion, authentic candid sports-event atmosphere, no glamour studio lighting, no watermark.

Create a premium conceptual beverage advertisement for {argument name="brand name" default="Coca-Cola"} on a vertical 4:5 canvas, with a deep red studio background and a cold red soda can centered in the frame. The can is covered in realistic condensation droplets, lit like a high-end FMCG product shot, with crisp metallic highlights on the rim, pull tab, and bottom edge. Place the white scripted {argument name="can logo text" default="Coca-Cola"} logo across the can, with small white text reading “ORIGINAL TASTE” below it. Add a surreal zipper opening across the middle of the composition: a shiny silver zipper runs horizontally from the left edge, crosses the front of the can, then curves upward and outward to the right, with the zipper pull positioned near the center-front of the can. The zipper divides two worlds: on the left, an orange sunset landscape with a glowing sun near the horizon, warm water or flat terrain, and a faint distant city skyline; on the right, an icy blue winter mountain scene with snow-covered pine trees, frosty mountains, mist, and cold condensation. The right zipper flap should look like a curved blue panel peeled open from the red surface, with droplets and zipper teeth along the edge. Use cinematic advertising lighting, ultra-realistic product photography, glossy condensation, shallow studio depth, and a clean Apple-level minimalist composition. Include exactly three visible text groups: top centered slogan “open happiness” with “happiness” in bold, main can logo and “ORIGINAL TASTE,” and bottom centered copy “real magic is inside” with “inside” in bold plus a tiny brand script beneath. No extra text, no people, no clutter, no watermark.

Create a premium conceptual FMCG beverage advertisement for {argument name="product name" default="Malta Guinness"}, shot as a luxury studio product photo on a monochrome golden-orange background. Center a single cold aluminum can upright, filling most of a vertical 4:5 frame, covered with realistic condensation droplets and glossy highlights. The can design is golden on the upper half and deep dark red on the lower half, with a small black harp crest above the large wordmark “Malta” and “GUINNESS” beneath it. Across the middle of the can, make the printed label look physically torn open like curled paper, with rough fibrous ripped edges and two curled flaps extending leftward; inside the horizontal tear, reveal a dramatic glowing scene of exactly 1 silhouetted athlete sprinting through dust against a radiant sunrise, symbolizing inner strength. Add subtle sunburst rays on the can surface behind the logo. Include exactly 3 small benefit words on the lower label: “VITALITY · GOODNESS · ENERGY”, plus small text “NON ALCOHOLIC MALT DRINK”. Place minimal campaign copy above the can reading “nourishment that strengthens”, with “strengthens” bold, dark, and heavier than the rest. Place bottom copy below the can reading “real strength starts within”, with “within” bold. Use award-winning Cannes Lions style advertising art direction: clean negative space, sharp product focus, warm cinematic lighting, premium retouching, realistic paper tear texture, no people outside the tear scene, no extra cans, no clutter, no watermark.

Create a premium conceptual beverage advertisement for {argument name="brand name" default="Sprite"}, shot like an award-winning Cannes Lions FMCG campaign with Apple-level minimal art direction. Use a vertical 3:4 canvas. Center a single cold green soda can standing upright on the boundary between two opposing environments: the left half is scorched heat with dry cracked desert ground, orange-yellow dust, and warm golden particles; the right half is icy refreshment with wet glossy green floor, scattered ice chunks, mist, water spray, and a cool white-blue vapor burst behind the can. The can is covered in dense condensation droplets and tiny highlights, with a silver rim and base, a white italic brand logo, and a yellow-green lemon-lime leaf icon near the top. Add a soft reflection of the can on the wet foreground. Background is a deep emerald green gradient, darker at the edges, clean and uncluttered. Place exactly one headline block in the upper-left corner reading {argument name="headline text" default="PAUSE
THE
HEAT."}; make it three stacked lines, bold uppercase sans-serif, with “PAUSE” and “THE” in white and “HEAT.” in yellow-green. Lighting should be dramatic studio product photography: crisp front-left highlights, cool rim light on the right, warm glow from the left, high contrast, realistic droplets, cinematic dust and mist particles, sharp can detail, shallow atmospheric depth, no people, no extra products, no watermark.

Create a polished conceptual FMCG beverage advertisement on a vertical 4:5 canvas. Use a deep cobalt-blue studio background and matching glossy tabletop with subtle reflections, minimal Apple-level art direction, crisp commercial photography, high contrast, clean negative space. On the left-center, show one exhausted young Black man in a plain white long-sleeve shirt, seated at the table with his head down and face hidden in his folded arms, body leaning forward as if drained. On the right foreground, place one upright 1-liter carton of {argument name="beverage brand" default="Chivita Active"} orange-citrus juice with a white carton body, orange fruit splashes, citrus and grapefruit imagery near the bottom, a white screw cap on top, and vertical blue “active” branding. Add a glowing neon orange battery icon over the man’s back and forearm area, with exactly five visible battery segments inside the outline, appearing partially charged and luminous. From the battery, draw one bright orange glowing cable arc that curves upward and plugs visually into the carton cap, implying the drink is recharging him. Add headline text in the upper left reading “{argument name="headline text" default="recharge naturally."}” with “recharge” in thin white lowercase, “naturally” in bold white lowercase, and the final period in orange. Add a small bottom-center tagline/logo reading “{argument name="bottom tagline" default="active starts here."}” with “active” in bold white/blue brand styling and “starts here.” in thin white. Lighting should be premium studio lighting with soft shadows, realistic product detail, sharp focus on the carton and glowing graphic, no extra objects, no people besides the single resting man, no clutter, no watermark.

Goal: Create a bold editorial fashion poster / magazine cover for a motivational design project, featuring a full-body studio portrait of {argument name="character name" default="Akinbinu Akintayo"} standing confidently in front of oversized typography.

Canvas: Vertical 4:5 poster, bright cyan-blue seamless studio background with a darker blue floor plane and soft vignette/shadowing near the bottom. High-contrast modern layout, cropped poster typography extending off the edges.

Main subject: One tall Black male model, full body, centered slightly right, standing upright with both hands in trouser pockets. He wears a dark olive-green button-up shirt tucked into matching tailored trousers with a black belt and polished black dress shoes. Short curly black hair. Face is intentionally obscured by a vertical soft-blurred rectangular block over the center of the face, while ears, hairline, neck, and outfit remain visible. Studio lighting from upper left, realistic shadows on the floor.

Typography style: Use huge uppercase condensed sans-serif lettering in fluorescent yellow-lime, bold and clean, layered behind and around the figure. Some words are partially hidden by the model or cropped by poster edges. Keep the typography flat, sharp, and poster-like.

Text content: Include exactly 9 visible text blocks: 1) top left small text: "A DESIGN BY AKINBINU AKINTAYO"; 2) top right huge title: "CARPE DIEM"; 3) left middle huge cropped text: "BEC-"; 4) center-right huge cropped text partly behind model: "MING"; 5) left lower-middle small text: "PROJECT BECOMING"; 6) right lower-middle small text: "AKINBINU AKINTAYO"; 7) lower left small text: "EP 27"; 8) center lower huge text: "OMING"; 9) bottom right huge title: "CARPE DIEM". Add two extra small motto lines at the very bottom left as part of the final block area: "MEMENTO MORI" and "MEMENTO VIVERE". Add a small lower-right phrase: "THE TIME IS COMING". The overall poster concept implies the phrase "BECOMING" split across the composition.

Layout: Place the model in the foreground so the typography is partially occluded by his body. The top-right "CARPE DIEM" should dominate the upper half, while another cropped "CARPE DIEM" anchors the bottom-right corner. The left-side "BEC-" should be very large and cropped off the left edge. The word fragments "MING" and "OMING" should appear in the middle and lower center, creating a layered typographic rhythm.

Color palette: Cyan-blue background, neon yellow-lime text, dark olive outfit, black shoes. Minimal colors, clean commercial poster finish.

Constraints: No logos, no watermark, no extra people, no props, no additional text beyond the specified typography. Preserve the bold fashion-editorial look and the intentionally obscured face.

Create a premium luxury patisserie product photograph of a limited-edition chocolate box inspired by an original anime-style girl character named {argument name="character name" default="Nozomu"}. The box is open on an elegant dark satin tabletop with crystal glassware, soft flowers, scattered sparkles, and a pale satin ribbon, photographed like a real high-end department-store confectionery gift set. The inside lid features a large illustrated package design: a dreamy moonlit night sky with teal-to-navy gradient, crescent moon, hanging gold stars, city skyline silhouettes, ornate gold corner filigree, pale pink and blue flowers, and an anime girl with long dark bluish-black hair with pink highlights, floral hair accessories, and an off-shoulder white ruffled dress; leave the face unobstructed in the generated image unless a privacy-safe blank face placeholder is desired. Add elegant gold Japanese-style branding text on the lid: {argument name="main name text" default="のぞむ"}, small romanized text {argument name="romanized name text" default="NOZOMU"}, script subtitle {argument name="collection title" default="Moonlit Dream"}, and small uppercase text "CHOCOLATE COLLECTION". In the lower tray, show exactly 10 luxury chocolates in a 2-by-5 grid with gold dividers and black paper cups: 1 glossy sky-blue dome with gold leaf, 2 cream rose-shaped chocolate, 3 faceted pale blue crystal chocolate, 4 dark round chocolate with gold crescent moon and starry night surface, 5 white daisy flower chocolate with gold center, 6 pale blue-white speckled dome, 7 pink flower chocolate with gold center, 8 glossy purple-blue heart chocolate with tiny star speckles, 9 faceted pale blush crystal chocolate with gold flecks, and 10 sky-blue marbled dome with gold constellation lines. Include a matching small display card in front of the box with the same branding text and moon motif. Use soft cinematic lighting, shallow depth of field, realistic reflections, delicate gold foil details, pastel celestial palette, ultra-detailed premium packaging, and a romantic fantasy luxury chocolate aesthetic. Avoid extra chocolates, avoid modern logos, avoid cluttered typography, and keep the box and all 10 chocolates sharply visible.

Goal: Create a 2x2 square collage of four highly realistic fine-art newborn photography portraits featuring the same newborn baby, with the baby’s face intentionally covered by a soft-edged square privacy blur in each panel while preserving a warm, dreamy, premium studio look.

Canvas: Square 1:1 image, divided into exactly 4 equal panels with no visible border lines, each panel a different themed newborn setup. Photorealistic DSLR newborn portrait style, shallow depth of field, soft diffused lighting, warm highlights, creamy bokeh, extremely detailed fabrics and props.

Subject: The same {argument name="baby age" default="newborn baby"} appears in all four panels, tiny and peacefully posed, with delicate hands and feet visible. Use {argument name="skin tone" default="warm light-to-medium newborn skin tone"}. The face in every panel must be obscured by a centered square blur/privacy block matching nearby skin colors, so no facial details are visible.

Layout and exact panel count: Use exactly 4 panels.
1. Top-left panel: A dreamy night-sky moon setup. The baby sleeps curled on a large ivory crescent moon prop, wrapped in a soft powder-blue knit swaddle with a matching blue sleeping cap. The background is deep navy with small golden stars, fluffy white clouds, and glowing fairy lights. Include the baby’s folded arms and blue pom-pom wrap details.
2. Top-right panel: A woodland nest setup. The baby is wrapped in muted sage-green fabric and nestled inside a chunky woven basket or nest, wearing a beige knit bonnet. Surround the baby with dark green foliage, small wildflowers, warm golden firefly-like lights, tree bark textures, and an enchanted forest atmosphere. Visible tiny hands and bare feet peek out from the wrap.
3. Bottom-left panel: A soft ivory-and-blush princess setup. The baby lies on a plush white feathered blanket, dressed in pale pink lace and embroidered tulle with pearls and delicate beadwork, wearing a matching ornate bonnet. Surround with pastel pink flowers, white feathers, cream clouds, soft drapery, and a fairytale nursery background with very bright airy lighting.
4. Bottom-right panel: A floral garden basket setup. The baby rests on a pink knitted cushion in a wicker basket, wearing a sheer blush lace outfit and a pink floral crown. Surround with roses, pale pink blossoms, greenery, and a softly blurred white garden bench or crib in the background. The baby’s arms rest in front, with a serene posed newborn photography composition.

Visual style: Luxury newborn photography, whimsical fairytale themes, ultra-realistic fabric texture, soft pastel palette, cinematic warm glow, high detail, gentle vignetting, creamy background blur, professional studio retouching.

Constraints: Generate exactly four distinct themed newborn portraits in one 2x2 collage. Keep all faces covered by square privacy blur blocks. No text, no watermark, no logos, no extra panels, no adult hands, no distorted limbs. Overall mood should be tender, magical, and elegant. Use {argument name="overall color mood" default="soft pastel blue, sage green, ivory, and blush pink"} and {argument name="lighting style" default="warm diffused fairy-tale studio lighting"}.

Use the uploaded portrait as the identity reference for the subject’s face, hairstyle, facial structure, and overall impression. Create a high-quality lifestyle editorial portrait of the same person sitting outdoors beside a wooden easel displaying a colorful street-style caricature portrait of them. The real person and the caricature must clearly resemble the same individual. Scene: - the person is seated on a simple wooden folding chair - beside them is a wooden easel holding a large caricature drawing - the setting is a sentimental urban art market - include illustration booths, handmade craft stalls, sketch displays, posters, cozy creative shopfronts, and a few softly blurred pedestrians - lively but not crowded - bright soft daylight, warm natural tones, shallow depth of field - realistic photography for the person and environment - vertical composition showing both the person and the caricature clearly Subject: - preserve the uploaded person’s recognizable identity - natural pose - calm, relaxed, slightly amused expression - stylish casual outfit that suits the subject - clean editorial lifestyle photography - do not force the same pose or expression for every subject Caricature direction: - the drawing on the easel must be a true observational street caricature, not a generic cute cartoon - the caricature artist should exaggerate the subject’s actual most recognizable facial traits - analyze the uploaded face and exaggerate only 2–4 distinctive features, such as eye shape, eyebrows, nose, lips, cheeks, jawline, chin, ears, hairstyle, or facial proportions - each caricature should feel custom-made for that specific person - avoid using the same default cute face for every person - avoid generic big eyes plus tongue-out expression - the caricature should be funny because it captures the person’s unique features, not because it uses a random silly pose Caricature style: - oversized head with smaller simplified body - playful but recognizable facial proportions - bold hand-drawn marker lines - quick sketchy pen strokes - colored pencil texture - lively street-artist energy - humorous but flattering - witty, expressive, and personality-driven - charming handmade imperfections - colorful accent doodles may be added, but keep the focus on the face Expression in the caricature: - choose a natural funny expression that fits the person’s facial character - possible expressions: raised eyebrow, shy smile, surprised eyes, confident smirk, awkward polite smile, exaggerated calm face, pouty lips, confused cute face, or gentle blank stare - the expression should vary depending on the subject - do not always use a tongue-out face - do not always use the same wide-eyed cute expression Caricature canvas: - large vertical drawing board or canvas on a wooden easel - the caricature should be clearly visible and occupy a major part of the image - it should immediately read as a funny street caricature - it should be more exaggerated than a portrait sketch - it should not look like a realistic fashion illustration - it should not look like a polished beauty drawing Important: - the caricature must be custom to the uploaded person - preserve recognizable identity through the exaggerated features - prioritize personality, likeness, and humor over generic cuteness - make the caricature feel like a real street artist observed the person and drew a witty exaggerated version Negative prompt: - no generic cute chibi face - no repeated default caricature face - no tongue-out pose - no identical silly expression for every subject - no random anime expression - no realistic portrait sketch - no polished fashion illustration - no beauty sketch - no weak exaggeration - no scary grotesque distortion - no ugly horror exaggeration - no distorted anatomy of the real person - no extra fingers - no badly drawn hands - no messy crowded background - no text - no watermark - no Eiffel Tower - no famous landmarks.

Create a cinematic visual titled: “THE PEOPLE WE BECOME.” The image should depict multiple stages of one human life existing simultaneously inside a single interconnected environment shaped by memory, growth and emotional transition. Avoid the feeling of: - a motivational poster, - a staircase timeline, - or separate portraits pasted together. Instead, the world itself should evolve naturally between life phases as if memories are physically blending into one another. The composition follows a winding stone pathway moving through different emotional spaces connected seamlessly across the image. At the bottom of the frame: A newborn sleeps inside a softly lit woven cradle near a dim bedside lamp. The atmosphere feels warm, silent and untouched. Nearby: - folded baby blankets, - soft shadows, - wooden toys, - faint moonlight through curtains, - dust particles drifting in warm air. The pathway slowly transitions into early childhood. A young child runs barefoot through a living room filled with scattered crayons, comic books, paper airplanes and half-built toy structures. Late-afternoon sunlight pours through large windows and reflects softly across wooden floors. The environment gradually changes again without hard separation. The next version appears around age 13: sitting alone on a rooftop during light rainfall wearing headphones and holding a notebook. Distant city lights blur softly behind him while unfinished sketches scatter beside him. The atmosphere becomes quieter and emotionally uncertain. Further along the path: A university-age version studies late at night at a cluttered desk illuminated only by a warm desk lamp and laptop screen. Around him: - highlighted textbooks, - coffee cups, - handwritten notes, - exhaustion, - ambition, - and isolation. Rain reflects softly across the apartment window behind him. At the highest point of the composition: An older version stands quietly overlooking a sunrise city skyline from a hillside path above the city. He looks calm rather than triumphant. His clothing is simple and grounded: rolled sleeves, slightly tired posture, hands in pockets, wind moving softly through his shirt. He should visibly feel like the same person shaped by every previous version. The transitions between life stages should contain subtle symbolic continuity: - flowers growing through cracks in concrete, - notebook pages blending into city architecture, - rainwater reflections becoming skyline lights, - old drawings faintly appearing on apartment walls, - childhood objects partially hidden inside later environments. Typography should remain minimal and restrained. Small serif text placed naturally near each stage: “Wonder.” “Becoming.” “Doubt.” “Discipline.” “Perspective.” No motivational quotes. No oversized typography. Lighting should evolve emotionally throughout the image: - warm soft childhood tones, - cooler rainy teenage atmosphere, - isolated tungsten lighting during study years, - balanced sunrise light in adulthood. The realism should feel grounded: - believable facial continuity across ages, - natural environmental texture, - subtle lens softness, - realistic lighting behavior, - physically believable spaces, - quiet cinematic atmosphere. The image should feel intimate and reflective rather than grand or overly dramatic. Mood: memory, identity, growth, loneliness, ambition, emotional evolution and the quiet passage of time.

Use the uploaded reference image as the exact facial identity reference for the character. Maintain the same face structure, eyes, nose, lips, hairstyle, beauty details, skin tone, and overall appearance consistency throughout the artwork.
Create an ultra-cinematic anime poster inspired by {argument name="anime style" default="dark fantasy military anime"} aesthetics similar to {argument name="reference title" default="Attack on Titan"}, blending photorealistic rendering with premium anime stylization. The girl should appear battle-worn yet beautiful, with subtle dirt marks, tiny scratches, realistic skin texture, glossy emotional eyes, and naturally wind-blown hair strands.
Frame the composition vertically in a luxury movie-poster layout. Chest-up side profile pose, looking upward toward the light with a determined, emotional, slightly hopeful expression. Preserve the same facial identity from the reference image with extremely high likeness accuracy.
Outfit should feature a detailed tactical military-style anime uniform with layered belts, leather harnesses, metallic combat gear, dark fitted jacket, realistic fabric folds, weathered textures, and a flowing scarf moving in the wind. Add cinematic ash particles, smoke, fog, embers, and shallow depth of field for atmosphere.
Background should depict a ruined war-torn city with giant walls, destruction, drifting smoke, distant soldiers using aerial mobility gear, and a massive titan silhouette fading into clouds behind her. The environment should feel epic, emotional, and large-scale.
Lighting should be dramatic {argument name="lighting time" default="golden sunset"} mixed with moody shadows and soft rim light illuminating the face and hair. Use realistic reflections, cinematic contrast, subtle film grain, and high-end Unreal Engine render quality.
Include premium Japanese poster design elements:
large bold vertical Japanese typography on the left side,
military insignia/emblem above the text,
small emotional quote underneath,
clean editorial spacing,
subtle paint-brush divider textures,
collectible IMAX anime poster aesthetic.
Color palette should combine smoky charcoal tones, warm amber highlights, muted reds, and cinematic contrast. Hyper-detailed, emotional, masterpiece quality, ultra realistic anime-meets-live-action style, 8K cinematic finish.

Ultra-detailed cyberpunk anime character design sheet of a {argument name="character age" default="teenage"} genius {argument name="archetype" default="hacker girl"} named “{argument name="name" default="NEO // RIN"}”, full body turnaround (front, side, back) plus close-up portrait and accessory callouts. Short silver-white bob haircut with neon cyan and magenta gradient streaks, glowing translucent cyber visor over one eye, pale skin, sharp violet eyes, calm confident expression. Oversized techwear jacket with black tactical cargo pants, belts, straps, dangling utility tags, cropped top, futuristic sneakers, holographic accessories, barcode decals, warning symbols, “BYTE//NULL” typography, hacker aesthetic.
Color palette: matte black, dark gray, white, neon cyan, neon pink.
Style inspired by high-end Japanese concept art, futuristic streetwear, cyberpunk fashion, Akira + Ghost in the Shell + modern anime key visual aesthetics.
Include clean character reference sheet layout with labeled details, logo designs, UI graphics, gadget closeups, and color palette on white background.
Highly polished cel shading, crisp lineart, soft glow effects, intricate clothing folds, layered accessories, dynamic fashion silhouette, professional game concept art quality, 4k, ultra detailed.

How would my {argument name="pet type" default="Cat"} look like if she was a {argument name="human role" default="person"}? Show it as accurately as possible according to her personality and her looks lol

A fresh summer skincare advertisement poster featuring a glowing {argument name="model description" default="young woman in a pastel yellow swimsuit"} who laughs playfully beside a giant {argument name="product" default="white sunscreen tube"} 3x her height with a bright orange cap, with the "{argument name="brand name" default="SOLGUARD"}" label on the tube and SPF 50+ clearly visible. The background is a bright tropical beach with soft white sand and a beautiful ocean blur, along with clean bold sans-serif typography "SOLGUARD" in warm orange filling the background. At the bottom, there is the tagline "Glow protected.", and a small text in the top-right corner reads "Designed with GPT Image 2" in grey, all captured in a photorealistic, summer skincare commercial style with bright airy lighting.

Create an ultra-realistic cinematic house exterior with stunning architectural design and premium visual aesthetics. The house can be {argument name="architectural style" default="modern, luxury, rustic, cottage, gothic, fantasy, royal, or minimalist"} in style. Include highly detailed architecture, large windows, elegant textures, beautiful landscaping, realistic pathways, glowing interior lighting, and immersive outdoor surroundings.

The environment should feel like a high-budget movie scene mixed with professional architectural photography and luxury real-estate advertising. Add dramatic cinematic lighting, volumetric sunlight, atmospheric fog, realistic reflections, shadows, {argument name="weather or time" default="rain or sunset mood"}, garden lights, trees, flowers, water elements, and detailed environmental effects for a visually powerful composition.

Use wide-angle cinematic camera perspective, depth of field, HDR lighting, ray tracing, photorealistic rendering, Unreal Engine quality, cinematic color grading, hyper-detailed textures, luxury aesthetic, masterpiece composition, ultra-realistic environment design, highly immersive atmosphere, 8K ultra detail.