GPT Image 2 prompts

Create a photorealistic vertical magazine-style fashion photo of {argument name="character name" default="a young East Asian woman"} running away from the camera on an empty wide asphalt road at golden hour, captured from an extremely low rear tracking angle with a dynamic wide-angle lens. She is mid-stride and turning her head back over her shoulder toward the camera with a bright spontaneous smile, short black bob hair blowing dramatically in the wind. She wears {argument name="top" default="a dusty pink sleeveless tie-back tank top"}, {argument name="shorts" default="dark charcoal fitted athletic shorts"}, and white sneakers. Emphasize long legs in perspective, natural skin texture, cinematic sunset rim light, warm orange sunlight from the low horizon on the left, blue sky with scattered soft clouds, subtle film grain, motion blur streaking along the road surface, shallow depth of field, realistic lens distortion, lively candid energy, and an editorial summer road-trip mood. Keep the composition vertical 9:16, subject centered slightly right, no text, no watermark, no extra people, no vehicles close to the subject.

Create a cinematic widescreen film still of {argument name="character" default="a young person with short black hair"} running away from the camera through a quiet forest. The subject is centered slightly left, seen from behind, mid-stride, with one bare arm bent and visible, wearing a flowing {argument name="outfit" default="sleeveless translucent white dress or robe"} that trails dramatically to the right like a soft veil caught by motion. The forest contains tall, straight tree trunks receding into depth, dense green undergrowth, and a faint dirt path on the left foreground. Use cool teal-green color grading, early morning mist, soft diffused natural light, shallow depth of field, gentle motion blur on the fabric and background, and an emotional dreamlike music-video atmosphere. Compose in a 2.39:1 cinematic aspect ratio, low-to-mid camera height following behind the runner, with realistic photography, soft focus edges, no text, no logos, no extra people.

Goal: Create a realistic vertical mobile-night-photography triptych of the same young woman during a late-night city walk, with the feeling of three consecutive casual snapshots captured on a phone.

Canvas: A tall vertical 9:16 image divided into exactly 3 equal horizontal photo panels stacked top to bottom, edge-to-edge with no captions, borders, logos, or watermark.

Subject: The same {argument name="character description" default="young East Asian woman in her early 20s with long loose dark brown hair, natural makeup, soft smile, slim build"} appears in all 3 panels. She wears {argument name="outfit" default="a fitted gray sleeveless tank top, loose light blue jeans, and a small black leather shoulder bag with thin straps"}. Keep her face consistent across all panels.

Setting: Late-night urban sidewalk beside a glossy white rectangular-tile wall on the right, with a quiet road, crosswalk markings, metal poles, railings, glass reflections, distant apartment windows, traffic lights, and streetlights on the left. Use mixed cool and warm street lighting, reflective white tiles, wet-looking highlights, and soft city bokeh in the background.

Panel count and poses: Use exactly 3 panels. Panel 1, top: medium shot from behind and slightly to the side as she walks along the sidewalk, turning her head back over her shoulder toward the camera with a gentle smile. Panel 2, middle: closer portrait, she faces the camera and reaches one open hand toward the lens to block it playfully; the hand is large and motion-blurred in the foreground while her smiling face remains visible behind it. Panel 3, bottom: seated crouching pose beside the tiled wall, knees bent, one elbow resting on her knee and cheek leaning on her hand, looking up at the camera with a relaxed affectionate smile; black shoulder bag visible near her side.

Camera and style: Hyper-realistic candid smartphone night mode photography, natural skin texture, shallow depth of field, 28mm wide-angle mobile lens feel, slight handheld perspective, high ISO but clean, realistic motion blur only on the reaching hand, cinematic urban lighting, soft highlights on hair and tiles, muted gray-blue night palette with warm amber reflections.

Constraints: Keep the scene text-free. Do not add extra people. Do not change clothing between panels. Maintain believable anatomy, consistent facial identity, and realistic phone-photo composition.

Create a vertical full-body fashion portrait in a minimalist sunlit studio: on the left, a photorealistic young East Asian woman with {argument name="hair color" default="long black hair"} poses gracefully against a plain warm gray wall, wearing a fitted ivory ribbed knit long-sleeve maxi dress with a scoop neckline and a high side slit, plus white pointed high heels. She forms a heart shape above her head with both hands, smiles softly while looking slightly to the side, stands on one leg, and bends the other leg back in a cute playful pose. On the right side of the same wall, draw a large black pencil manga-style sketch version of her, matching the pose and outfit but exaggerated with an anime face, one eye winking, open cheerful smile, long flowing hair, curvy silhouette, and sketched high heels. Surround the manga figure with exactly 5 hand-drawn hearts, 4 sparkle/star doodles, and 3 short exclamation marks above the head. Use a seamless blend of real photography and wall illustration, as if the drawing is sketched directly onto the wall beside the model. The scene has soft natural daylight, diagonal window-shadow stripes across the floor and lower right wall, a clean concrete floor, warm neutral tones, realistic skin texture, elegant editorial styling, and no visible text or watermark. Keep the composition balanced with the real model occupying the left half and the manga sketch occupying the right half, both full-body and similar scale. Optional customization: make the model's outfit {argument name="dress color" default="ivory"}, set the background to {argument name="studio wall color" default="warm light gray"}, and make the overall mood {argument name="mood" default="cute, elegant, playful"}.

Create a single 4:5 vertical editorial photo-real image of a young woman standing beside a black hand-drawn doodle alter ego on a plain indoor wall. The real person is {argument name="character description" default="a shy young East Asian woman with long dark brown hair and straight bangs"}, full body, positioned on the left third of the frame, leaning lightly against an off-white concrete wall, smiling bashfully with one hand covering her mouth and the other arm relaxed down. She wears {argument name="outfit" default="a cream fitted camisole, dark denim cutoff shorts, bracelets, and black platform flip-flops"}. Use soft natural sunlight from the upper left, with diagonal window-shadow shapes on the wall and concrete floor, realistic skin, realistic fabric, quiet minimal background, no text.

On the right two-thirds of the wall, draw exactly 1 energetic manga-style black ink doodle character as if sketched directly on the wall: a cartoon version of the same woman with long hair and bangs, huge laughing open mouth, closed happy eyes, freckles, sleeveless top, dark shorts, bracelets, and flip-flops. The doodle character is mid-jump with arms stretched wide, one leg bent backward, body tilted forward, and one sketched hand reaching toward the real woman’s shoulder as if her chaotic inner self is bursting out beside her. The doodle should be monochrome black line art with expressive hatching, messy sketch strokes, motion lines, and no color fill except black ink shading.

Surround the doodle with exactly 15 decorative doodle elements: 4 stars/sparkles, 3 hearts, 2 cloud puffs, 1 speech bubble containing a heart, 1 exclamation mark cluster above the head, and 4 short motion-burst line groups. Keep the contrast between the composed real woman and the wild doodle persona clear and humorous. Composition should feel like a trendy social-media portrait, clean wall backdrop, realistic photography blended seamlessly with wall-drawn illustration, high detail, natural perspective, no collage, no split panels, no watermark.

Create a bright, high-detail anime illustration of {argument name="character name" default="a young girl"} standing in a sunny countryside road, viewed from a low slightly wide-angle perspective, centered full body from thighs up. She has long flowing {argument name="hair color" default="pale ash-blonde"} hair blowing dramatically to the right, large amber-brown eyes, a calm slightly blank expression, and wears red round glasses. She is dressed in a loose light sky-blue short-sleeved shirt dress with a rounded collar, front buttons, gathered waist seam, and fluttering hem. Add exactly 4 main personal items/outfit elements: one oversized woven straw sun hat with ragged decorative edges held by her raised left hand, one pair of red round eyeglasses, one pale blue dress, and one dark red hardcover book tucked under her right arm. The background is a vivid summer rural landscape with a dirt path, green hills and distant blue mountains, a small village with exactly 6 visible houses, and a sunflower patch on the left foreground with exactly 5 clearly visible sunflower heads. Use a clear blue sky with towering white cumulus clouds and a strong sun flare in the upper right corner. Style should be polished Japanese anime key visual art with luminous backlighting, glossy highlights on hair and fabric, soft painterly clouds, saturated summer colors, delicate linework, and slight imperfect AI-art roughness in hair strands and outlines. Add a tiny unreadable white artist-signature scribble in the lower right corner, but no other text. Mood: {argument name="mood" default="dizzy summer daydream, gentle and wistful"}.

Create a cinematic, realistic anime-style night scene at a Japanese summer festival shrine approach. In the foreground left, show a young woman in side profile from the waist up, gazing upward with parted lips at a large golden firework blooming high in the dark smoky sky; she wears a deep navy yukata patterned with pale purple bellflower blossoms, with an obi bow visible at her back, and her dark hair is gathered in a loose low bun with delicate hair ornaments. In the foreground right, slightly farther back, show a young man turned partly away but glancing back over his shoulder, wearing a dark casual yukata or festival shirt, with a pale fox mask tilted on the side of his head. The wet stone-paved shrine path recedes between them toward a distant torii gate at center, lined with warm glowing festival lanterns and small stalls, with tiny blurred figures in the background. The atmosphere should feel quiet and bittersweet after leaving the crowded festival, with lantern reflections on damp stones, deep blue-black shadows, rim lighting from the fireworks, soft smoke, and highly detailed painterly realism. Use a vertical 4:5 composition, dramatic low-light contrast, shallow depth of field, no text, no watermark. Customize the woman as {argument name="woman appearance" default="young Japanese woman with dark hair in a loose low bun"}, the man as {argument name="man appearance" default="young Japanese man with tousled dark hair and a fox mask"}, the yukata pattern as {argument name="yukata flower pattern" default="pale purple bellflower blossoms"}, the setting as {argument name="festival setting" default="wet stone shrine approach with lanterns and a distant torii gate"}, and the sky feature as {argument name="firework color" default="large golden firework"}.

Create a soft pastel anime illustration of {argument name="character name" default="a shy squid-themed maid girl"} sitting on the edge of a high bed in a bright minimalist bedroom, viewed from a low angle so her oversized platform shoes dominate the foreground and her face looks down toward the viewer. She is a petite teenage anime girl with {argument name="hair color" default="short black bob hair with pink-dyed inner ends"}, pale skin, sleepy half-lidded eyes, and a slightly embarrassed expression. Her outfit is a black-and-white frilly maid-inspired dress with an off-shoulder cut, long detached black sleeves with white trim, a white ruffled apron edge, black garter straps, white knee socks, puffy white leg warmers, and chunky black Mary Jane platform heels with pink trim. Use {argument name="accent color" default="mint turquoise and soft pink"} throughout the design. Include exactly 7 visible squid/octopus motifs: one mint squid hat perched on her maid headband, one mint squid hair clip, one mint squid emblem on her chest, one mint squid plush held in her lap, one mint squid print on her sock, one pink octopus emblem on the shoe, and one mint squid graphic on the drink cup. Include exactly 4 visible bows: a mint bow at her collar, a mint bow on her sleeve, a pink bow at the top of her sock, and a pink bow on her leg warmer. Place her in a clean pastel room with pale blue walls, white ceiling, white furniture, a pale blue mattress, a round white side table with a pink band, and a transparent drink cup with ice and a pink straw on the table. Add soft background props: a white door with a pale blue keyhole-like poster, a low white cabinet or desk with stacked books and a pink-framed object. The style should be high-quality Japanese anime character art, delicate linework, airy lighting, low contrast, glossy highlights, subtle blush, clean cel shading, soft white negative space, and a cute futuristic kawaii aesthetic. Use a vertical {argument name="aspect ratio" default="2:3"} composition, no text, no watermark, no extra characters.

Create a square digital 3D illustration of a stylized deformed human girl bust portrait on a deep black background. The character is shown from the upper torso up, turned slightly three-quarters to the viewer’s left, with a large head, small chin, short neck, slim shoulders, and a mildly annoyed or unimpressed expression. She has heavy-lidded eyes looking sideways to the left, downturned brows, a tiny nose, and a small closed frown. Her hair is an abstract sculptural bob made of thick rounded ribbon-like masses: one large sweeping bang across the forehead, two puffy side locks, and rounded layered hair volumes behind the ears. Remove natural object-specific colors and render the entire character as smooth matte clay-like forms with luminous gradients instead of outlines: blend {argument name="main gradient colors" default="hot pink, violet, cyan, soft blue, peach, and mint green"} across the skin, hair, and clothing so all parts share the same iridescent color language. Dress her in a simple short-sleeve hooded top with a soft rounded hood opening and rolled sleeve cuffs, also made from the same smooth inflated abstract shapes. Use soft studio lighting, subtle ambient occlusion in the creases, velvety subsurface shading, high-quality 3D render detail, and a dreamy toy-sculpture aesthetic. Composition should place the face in the upper center, torso cropped near the lower edge, with generous black negative space and no scenery. Add a small elegant handwritten signature and date in the bottom-right corner reading {argument name="date text" default="July 25, 2026"} and {argument name="signature text" default="Oyagi"}.

Create a photorealistic low-angle summer street photo of a startled {argument name="cat color" default="black"} cat standing directly under a vintage Japanese hand-cranked shaved-ice machine, with a mound of bright white crushed ice piling on the cat’s head like a snowy hat while ice flakes spray and fall around its face. The cat has wide green-yellow eyes, an open tiny mouth with small fangs visible, wet whiskers, and a red collar with a small gold bell. The shaved-ice machine is tall, weathered, and painted teal-blue, with ornate metal legs framing the cat, a large circular crank wheel on the upper right, and a cylindrical ice-shaving drum above the cat. At the top of the machine is a decorative sign with the red kanji {argument name="top sign text" default="氷"} surrounded by blue wave motifs and small red flowers. On the left side in the background, include exactly 1 hanging fabric banner angled in the breeze, printed vertically with {argument name="banner text" default="かき氷"} in red and blue wave graphics near the bottom. Set the scene outdoors under a vivid blue sky with scattered fluffy white clouds, strong midday sunlight, crisp shadows, sparkling ice particles, realistic fur detail, shallow depth of field, and a humorous candid snapshot feeling. Use a square 1:1 composition, the cat centered in the lower half, the shaved-ice machine towering above it, no extra animals, no extra people, and no watermark.

Goal: Create a realistic 16:9 desktop screenshot of Microsoft PowerPoint in Japanese, showing a course slide deck being edited with a Copilot/Claude model selection panel open on the right.

Canvas: Wide landscape screenshot, 1200×675 style, crisp UI capture, light gray PowerPoint chrome, no browser frame. The main focus is a PowerPoint editing workspace with a dark title slide centered.

Layout: Show the full PowerPoint window with the ribbon across the top, slide thumbnail strip on the left, main slide canvas in the center, and an AI assistant side panel on the right. Use Japanese UI labels throughout the PowerPoint interface. The file name in the top title area should read {argument name="file name" default="Udemy_Power-Automate-Basic-Material.pptx"}, followed by a Japanese last-updated note and time. The top ribbon should include Japanese tabs such as File, Home, Insert, Draw, Design, Transitions, Animations, Slide Show, Record, Review, View, and Help, plus add-in buttons for Copilot, PowerPoint, Designer, Claude, Teams presentation, and Share.

Left thumbnail strip: Show exactly 8 visible slide thumbnails, numbered 1 through 8. Slide 1 is selected with an orange border and is the same dark cover slide as the main canvas. Slide 2 is a teal agenda/overview slide. Slide 3 is a white process/workflow slide with green diagram elements and two illustrated people. Slide 4 is a white slide with three horizontal list rows. Slide 5 is a white slide with a blue interface screenshot and arrows. Slide 6 is a white slide with a software screenshot and callout box. Slide 7 is a white slide with a row of colorful cards and icon illustrations. Slide 8 is a white slide with a flowchart-like screenshot and a turquoise callout.

Main slide: Create a dark cinematic cover slide with a black-to-navy overlay over an architectural night scene: glowing modern stacked glass buildings on the right, misty atmosphere, pathways and tiny walking people below, trees in the lower right, and a deep dark empty area on the left for text. In the upper left of the slide place a small orange clownfish mascot wearing a tiny black top hat. The main title text should be large, bold, white Japanese: {argument name="main title text" default="クイックに学ぶ\nPower Automate クラウドフロー"}. Under it, add a cyan subtitle: {argument name="subtitle text" default="触ったことがなくてもOK — Microsoft 365 で始める業務自動化の第一歩"}. Beneath that, add a smaller white description line: {argument name="description line" default="全5回のハンズオン＋AI活用コラムで、クラウドフローを体験する実践コース"}. At the bottom left of the slide, add the author line in white: {argument name="author line" default="ギークフジワラ｜@geekfujiwara"}. Keep the slide text aligned left with generous spacing.

Right AI panel: Show a white assistant panel titled in Japanese as a presentation-related assistant. At the top right of this panel, show an open model dropdown. The dropdown must contain exactly 5 visible choices: Auto with a checkmark and a short Japanese description, Claude, Claude Opus 4.8, Claude Opus 5, and GPT. Emphasize the Claude Opus 5 row with a red rectangular outline. Under Claude Opus 5, show the provider label Anthropic in small gray text. Include additional Japanese panel buttons below such as opening the presentation, explaining the slide, and cleaning up the slide layout.

Visual style: Make it look like an authentic Microsoft PowerPoint desktop screenshot, with accurate spacing, rulers, ribbon icons, scrollbars, status bar, zoom control, and tiny UI text. Use soft antialiasing, subtle shadows, and realistic Windows app proportions. The image should read as a social-media screenshot demonstrating PowerPoint Agent Mode and multi-model selection.

Constraints: Do not add any extra slide thumbnails beyond the 8 visible thumbnails. Do not obscure the main slide title. Preserve the red highlight around Claude Opus 5. Avoid watermarks, browser tabs, or unrelated windows.

Create a photorealistic luxury skincare product still life on a 4:3 horizontal canvas. Show exactly 3 unlabeled cosmetic containers standing on a clear acrylic block: 1 tall matte milky-white lotion bottle with a rounded-shoulder shape and translucent white flip cap on the left, 1 transparent pale-blue cylindrical bottle filled with clear liquid and a satin silver cap in the center, and 1 pale lavender-pink pump bottle with a white pump dispenser on the right. Arrange them tightly grouped, centered slightly to the right, with the center blue bottle a little shorter than the white bottle and the pump bottle slightly taller than the blue bottle. The acrylic pedestal should be rectangular, glossy, transparent, and covered with visible water droplets along the front face and top surface. Use a cool misty spa atmosphere: frosted glass background with vertical condensation streaks, many tiny water droplets, soft blue-gray and white gradient lighting, and low lavender-tinted fog drifting around the base. Lighting should be high-key, diffused, backlit through the wet glass, with soft reflections and gentle bloom. No readable labels, no branding, no people, no text, no extra products. Emphasize clean hydration, freshness, dewy condensation, and premium cosmetic advertising photography.

Create a vertical anime fantasy character illustration of a blindfolded priestess-warrior standing in a sunlit cathedral interior. The subject is an elegant adult woman with very long flowing {argument name="hair color" default="pale platinum blonde"} hair, loose waves, small side braids, and a black ribbon tied near the back of her head. She wears a wide black cloth blindfold covering her eyes, with a calm, slightly parted-lips expression and a graceful upright pose. Her outfit is a fitted white ceremonial gown with blue-violet trim, off-shoulder neckline, long white sleeves, high side slits, decorative straps at the hips, and small gold star-like ornaments; include a red jewel pendant at her neck and matching small red gem accents on the bodice. She holds one tall dark staff or spear in her right hand, with a black shaft and ornate gold spearhead, plus a dark gold-edged guard detail near the lower visible section. The setting is a grand stone church or cathedral with tall columns, warm sunlight streaming from the right, dark shadowed stone architecture behind her, and a soft blue stained-glass window blurred in the upper left. Use a polished high-detail anime style, dramatic warm rim lighting, soft floating dust or light particles, strong line art, smooth cel shading, luminous highlights on hair and fabric, shallow depth of field, and a low-angle waist-up to thigh-up composition emphasizing heroic elegance. Keep the image tasteful fantasy fashion, no text, no watermark, no extra characters.

Goal: Create a cute single-panel chibi anime comic scene in a cozy apartment room, featuring three small characters reacting to a wall-mounted air conditioner.

Canvas: Wide horizontal 16:9 illustration, clean digital anime style with soft shading, warm indoor lighting, crisp line art, gentle pastel colors, and a humorous slice-of-life tone.

Layout: Place a large white wall-mounted air conditioner in the upper left-center of the room, blowing visible pale blue streams of cold air downward. One chibi girl is clinging happily to the front of the air conditioner as if hugging it. Two other chibi girls stand on the right side of the room, looking up at her. Put exactly 2 large white speech bubbles with black outlines above the two standing girls.

Characters: Include exactly 3 chibi anime girls. 1) Left/upper character: a small cheerful blonde girl hugging the air conditioner, eyes closed, big smile, tiny pink hearts floating around her; she wears a black tactical idol-style outfit with orange accents, black gloves, thigh straps, utility pouches, black boots, and a black beret decorated with star ornaments and small horn-like accessories. 2) Center-right character: a blonde chibi girl with long wavy hair, worried or confused expression, one gloved hand near her mouth; she wears a black and red military/tactical outfit with a red tie, black beret with a red star, belts, dark stockings, and small boots. 3) Far-right character: a lavender-haired chibi girl with a neat bob haircut, round white glasses, calm speaking expression, and one raised index finger; she wears a white sailor-style uniform, white peaked cap with a gold wing emblem, blue bow, white thigh-high socks, side pouch, and blue hair ribbon.

Speech bubbles: Use exactly 2 bubbles. The center-right girl’s bubble says {argument name="left speech bubble text" default="大きなセミが居るわね？"}. The far-right girl’s bubble says {argument name="right speech bubble text" default="セミリタイアした元アイドルですね。"}. Keep the speech text bold, black, centered, and readable.

Room details: Show a beige wall corner with wooden trim and wooden floor. On the far left, include a window with blue curtains and a bright outdoor sky/greenery view. Beneath it, include a low wooden cabinet with exactly 3 visible details: a small framed picture, a potted plant, and a row of books. In the foreground, include exactly 3 table items: a glass of iced drink with a blue straw, a black remote control, and a blue tissue box with white tissues. On the right, include a potted plant near a door. Add a small wall outlet under the air conditioner. The air conditioner display should show {argument name="air conditioner temperature" default="25°C"} with a tiny green indicator light.

Visual style: Chibi proportions with oversized heads, expressive faces, glossy eyes, soft highlights, playful pink hearts, cozy domestic background, polished Japanese mobile-game illustration quality.

Constraints: Use exactly 3 characters, exactly 2 speech bubbles, and exactly 3 foreground table items. Do not add extra characters, extra panels, captions, watermark, or logo.

Create a studio portrait on a vertical 4:5 canvas with a plain dark gray seamless background and soft, realistic photography lighting. Show one real young adult Asian man standing slightly left of center, full body visible, wearing {argument name="outfit" default="an oversized black hoodie, a white undershirt peeking out, loose light-wash denim shorts, white crew socks, and white-and-red sneakers"}. He has {argument name="hair and glasses" default="short textured black hair with straight fringe and black rectangular glasses"}, a mildly confused, skeptical expression, and he looks to his right toward the empty space. His posture is relaxed with arms down, feet planted, and shoulders slightly turned. Above his head, add exactly 2 black hand-drawn question marks, one larger and one smaller, as doodle accents. To the right of him, create his mischievous doodle shadow as if drawn in rough black charcoal or marker directly on the background: a cartoon version of the same man, larger and more energetic, grinning widely with oversized glasses, wearing a hoodie, shorts, socks, and sneakers. The doodle shadow is in a playful dancing pose with one knee raised, one foot on the ground, both arms up making peace signs; include exactly 2 visible peace-sign hands. Add expressive sketch marks around the doodle: exactly 3 small exclamation strokes above the doodle head, exactly 1 tiny question mark near the left raised hand, exactly 5 curved motion marks around the arms, leg, and body, and a scribbled dark ground shadow under the doodle foot. Style the doodle with loose, messy, crosshatched black lines, semi-transparent enough to read as a drawn shadow but bold enough to stand out. Keep the real person photorealistic and the doodle shadow 2D hand-sketched, with no other objects, no watermark, and no extra text.

Create a vertical fashion editorial portrait at an ancient Greek temple ruin in bright natural daylight. A young East Asian woman with {argument name="hair color" default="dark brown shoulder-length hair"} stands in a relaxed three-quarter pose slightly right of center, head tilted down and eyes softly lowered, with a calm introspective expression. Wind blows loose strands of hair across her face. She wears an airy {argument name="shirt style" default="white sheer linen button-up shirt"} with rolled sleeves, open collar, and the front tied in a knot at the waist, paired with high-waisted cream trousers and a matching cream belt with a rectangular buckle. Add delicate gold jewelry: small dangling earrings and a fine necklace with a small pendant. Background: sunlit classical stone columns and marble ruins resembling the Parthenon, softly blurred with shallow depth of field, warm beige stone tones, pale blue sky, scattered ancient blocks underfoot, and a few tiny distant tourists barely visible. Camera and composition: medium portrait from thighs to head, 2:3 vertical crop, subject occupying the right half while temple columns fill the left background, natural perspective, editorial travel-fashion photography. Lighting and style: warm Mediterranean sunlight, soft shadows, subtle film grain, creamy highlights, muted ivory and sand palette, realistic skin texture, elegant minimal styling. Add a small white bottom-center brand mark reading {argument name="brand text" default="WILDCORE | Kuro"} in a clean spaced sans-serif plus handwritten script style. Avoid extra text, logos, heavy makeup, exaggerated posing, or modern city elements.

Create a literary magazine cover style poster about {argument name="city greeting" default="Nanjing, good morning"}. Use a wide horizontal 16:9 canvas with a muted pale olive-green background and lots of quiet negative space. Place the main typographic weight in the upper-right: huge black Chinese calligraphic serif characters reading {argument name="main headline" default="南京,早安"}, thick, elegant, slightly oppressive like inked magazine masthead typography. Directly beneath the headline, add a thin horizontal rule on both sides of a small Chinese subtitle reading “城市清晨问候特辑”, and to the right add italic English text “Good Morning, Nanjing”. On the right-middle, set the date {argument name="date" default="2026.07.25"} in refined black serif numerals, with smaller Chinese text below: “星期六　农历六月十三”, then a tiny centered dash. Below that, create a compact almanac-style information block with a small red sun icon and the label “今日宜忌”, dotted divider lines, and exactly 2 circular badges: one labeled “宜” followed by “散心、看树、尝鲜”, and one labeled “忌” followed by “仓促、发呆过头、错过晨光”. At the bottom-right, add spaced small caps English “CITY MORNING GREETINGS”, a diagonal slash, and a small Chinese quote: “把日子过成诗 / 把清晨过成喜欢的样子”. In the lower-left, depict the theme object as naive crayon drawing rather than realism: exactly 2 illustrated food objects, a decorative handheld fan and a plate of sliced salted duck with orange egg-like centers. The fan should be ornate, rounded, outlined in dark green, filled with childlike swirls, flowers, cloud motifs, yellow, blue, white, and green crayon scribbles, with a brown handle and teal tassel. The plate should be a simple blue-outlined oval containing several thick slices of duck rendered with rough white, brown, orange, and red crayon strokes. Add small playful doodles around them: one red star, one green circle, one yellow squiggle, one tiny green vine flourish, three short white accent strokes, and a few small blue dash marks near the plate. Overall style: calm editorial cover, literary magazine layout, refined black typography contrasted with innocent wax-crayon illustration, minimal color palette, soft paper texture, no photorealism, no extra objects, no watermark.

A high-end studio portrait of {argument name="character description" default="[CHARACTER DESCRIPTION]"}, interacting with a large circular cutout centered within a thick matte {argument name="wall color" default="[OUTER WALL COLOR]"} wall. The wall shows realistic 3D depth (around 8 cm) with soft rounded inner edges and smooth shadow falloff. Inside the circular opening, a clean {argument name="background color" default="[INNER BACKGROUND COLOR]"} backdrop contrasts with the wall, clearly separating the inner and outer spaces. The model {argument name="interaction style" default="[INTERACTION STYLE]"}. Lighting: balanced studio setup — soft diffused key from front-left and mild fill from right, creating gentle highlights and subtle shadow along the rim to define depth and separation between wall and background. Camera: straight-on, centered composition, 3:4 vertical portrait framing. Ultra-detailed 8K studio photography with sharp focus and natural tonal depth. Mood: [modern | editorial | cinematic | minimal | playful | bold]. No text, watermark, or extra props beyond the wall, circular cutout, and model.

A beautiful, hand-drawn 2D animated portrait in the {argument name="style" default="classic Disney style"}, capturing a {argument name="subject" default="young woman"} with a strong, confident expression looking up toward the viewer from a high-angle perspective. She wears magnificent {argument name="outfit" default="traditional tribal attire"}, featuring a massive headdress of colorful, layered feathers, intricate beadwork necklaces and belts, and delicate feather accessories on her arm. Her face is adorned with beautiful tribal paint patterns, and her hair is styled in a clean, Egyptian-inspired bob. She stands amidst a lush, vibrant jungle background with soft, dappled sunlight filtering through the canopy, creating a soft, magical depth of field. The style features clean linework, smooth cel shading, and a nostalgic, cinematic feel. Aspect ratio 9:16.

A nostalgic 1980s–1990s {argument name="style" default="Japanese anime cinematic illustration"}, highly detailed hand-painted background, warm golden-hour and neon lighting, soft film grain, subtle watercolor texture, expressive anime characters with natural proportions and detailed eyes, realistic architecture and interiors, slice-of-life atmosphere, emotional storytelling, cozy urban Japan, dramatic perspective, beautiful reflections, volumetric sunlight, soft shadows, rich color grading, intricate environmental details, quiet contemplative mood, Makoto Shinkai-inspired lighting, vintage Studio Ghibli atmosphere, city pop aesthetic, retro Japanese nostalgia, analog photography feel, perfectly composed cinematic framing, ultra-detailed digital painting, masterpiece quality. 1. {argument name="scene one" default="Train Scene: A Japanese high school boy in a black gakuran uniform sitting alone inside an old commuter train at sunset"} 2. {argument name="scene two" default="Retro Diner: A stylish young woman sitting in a retro American-style diner at night, drinking a vanilla milkshake"} 3. Cozy Bedroom: A girl reading a book on the floor of her cozy bedroom, morning sunlight streaming through lace curtains, sleeping cat on the windowsill, cassette player, vintage posters, books, plants, soft pastel colors, warm peaceful atmosphere, nostalgic 90s Japanese bedroom. 4. Japanese Street: A schoolgirl walking through a quiet suburban Japanese neighborhood during golden hour, sailor school uniform, utility poles, narrow residential street, glowing clouds, warm evening light, peaceful everyday life, highly detailed environment, cinematic perspective.

A premium cinematic editorial photo collage featuring the same {argument name="subject" default="beautiful young woman"} appearing consistently across {argument name="number of photos" default="seven"} photographs arranged in a clean Pinterest-inspired lifestyle grid. The mood is {argument name="mood" default="warm, romantic, carefree, and inspired by nature"}. The entire collage is captured during golden hour beneath a lush blooming bougainvillea tree filled with vibrant pink flowers. Every image maintains perfect facial consistency, hairstyle, clothing, lighting, and color grading.

Using the provided reference image, create an ultra-realistic vintage black-and-white photo booth collage featuring the same {argument name="subject" default="young woman"} with identical facial features, long voluminous wavy dark hair, soft natural makeup, and glowing skin. The composition consists of four evenly spaced photo booth frames arranged in a clean 2×2 grid with thin white borders, photographed inside a classic photo booth with a simple curtain backdrop. She wears an oversized {argument name="attire" default="white NFL-style football jersey with bold black number 11"}, black striped sleeves, and an athletic vintage aesthetic. She also wears a black baseball cap with a white star logo, layered silver necklaces, rings, and minimal jewelry. Each frame captures a different candid pose: 1. Leaning slightly toward the camera with lips puckered in a playful kiss expression. 2. Looking sideways with a relaxed, thoughtful expression. 3. Holding strands of her hair with both hands while looking directly into the camera. 4. Smiling brightly, winking one eye, and sticking out her tongue in a playful pose. The images feature authentic film grain, soft monochrome contrast, subtle vignette, slight photo booth imperfections, gentle skin texture, realistic fabric folds, soft diffused lighting, and a nostalgic early-2000s aesthetic. Style Keywords: black and white photo booth, vintage film, NFL jersey, oversized sportswear, baseball cap, Pinterest aesthetic, Y2K, candid portraits, Kodak Tri-X, monochrome editorial, nostalgic, photorealistic, ultra detailed. Negative Prompt: low quality, blurry, anime, cartoon, CGI, plastic skin, distorted anatomy, extra fingers, duplicate face, duplicate limbs, watermark, logo, text, poor lighting, oversharpened, low resolution, artifacts, inconsistent face, different hairstyle, cropped body, bad composition.

A RAW, ultra-realistic smartphone photo of a beautiful young {argument name="ethnicity" default="Asian"} woman standing naturally in a modern home kitchen. She has fair porcelain skin, large dark brown eyes, a small straight nose, naturally soft pink lips, and an oval face with delicate features. Her {argument name="hair style" default="dark brown hair is loosely tied back in a low ponytail"} with soft wispy curtain bangs framing her face. She wears a fitted heather-gray spaghetti-strap crop camisole and a light pink digital sports watch on her left wrist. She casually holds a white ceramic bowl filled with dark soup in one hand and a stainless-steel soup ladle with a mint-green handle in the other. She looks directly into the camera with a gentle, relaxed smile and a calm expression. The kitchen features white tiled walls, a clean countertop, a stainless-steel range hood, and everyday cooking utensils, creating a realistic lived-in environment. Captured as if a friend quickly snapped the photo using a modern smartphone. Slight handheld framing, subtle perspective distortion from a 26mm equivalent mobile lens, natural indoor ambient lighting, soft shadows, realistic skin texture, tiny sensor noise, HDR processing, automatic white balance, authentic exposure, shallow computational depth of field, casual composition, unposed lifestyle photography, imperfect framing, extremely photorealistic, RAW mobile camera quality, no beauty filters, no AI look, no studio lighting, high detail, 8k.

Ultra-realistic studio portrait of a person transformed to resemble the reference face, centered composition, head-and-shoulders framing, neutral facial expression, looking directly at the camera, wearing a {argument name="clothing" default="plain black crewneck sweatshirt"} and {argument name="accessories" default="transparent acetate eyeglasses"}, clean modern haircut matching the reference, detailed skin texture, subtle facial hair if applicable, cinematic magenta and cyan rim lighting, smooth purple gradient background, soft beauty lighting, high contrast, sharp focus, 85mm lens, shallow depth of field, photorealistic, ultra-detailed, editorial photography, symmetrical composition, 8K. Place a small inset reference image in the bottom-right corner with a thin white rounded border.

Negative prompt:
low quality, blurry, cartoon, painting, overprocessed skin, extra facial features, asymmetrical eyes, distorted glasses, bad anatomy, noise, watermark, text, logo, oversaturated colors, cropped head, duplicate features.