Group / Couple

Explore free Group / Couple image prompts from YouMind's AI prompt library, grouped under subjects. Every prompt is curated from real creative workflows and ready to copy, adapt, and reuse.

Prompt to ImageImage to Prompt
GPT Image 2
Boyfriend Perspective Carousel Date
View full prompt & copy

Photorealistic true first-person boyfriend-perspective amusement-park date scene featuring an adult woman. Image logic: this image is literally viewed from the taller boyfriend’s eyes. She is making direct eye contact with him through the high lens, and the visible upward gaze is created by the real 30 cm height difference. Background identity: a night amusement-park carousel plaza with an illuminated merry-go-round covered in warm golden bulbs, painted horses, glossy platform reflections, decorative poles, a low metal fence, colorful ride lights, distant amusement-park bokeh, and a dark blue night sky. The carousel should feel layered, luminous, romantic, and dimensional rather than like a flat wall of lights. Depth lock: in the foreground, a softly blurred fence post, carousel-light flare, or glossy pavement reflection enters near the lens. In the middle ground, the subject stands close beside the low carousel fence. In the background, multiple layers of carousel horses, illuminated poles, rotating platform details, distant park lights, and the night sky recede behind her. True boyfriend-eye camera lock: place the lens exactly at her boyfriend’s natural eye level, approximately 30 cm above her eye line and 40–55 cm from her face. Use a clearly downward angle of approximately 18–24 degrees. Position the camera slightly in front of her near shoulder, not beside her profile. Point the optical axis directly toward the center between her eyes. Frame from the upper waist or lower chest to slightly above the head. Her eyes must remain clearly below the lens. Pose lock: her pelvis remains angled toward the carousel at approximately 35–45 degrees. Both feet remain naturally grounded. One hand rests simply on the top of the low fence. The other arm stays relaxed beside the body and may be partially cropped. Her upper torso rotates slightly toward her boyfriend without becoming a frontal portrait. Keep the near shoulder subtly closer to the lens and the shoulders relaxed. Head-direction lock: turn her head toward the lens far enough for both eyes to be fully readable. Retain a soft three-quarter face angle, with the nose direction approximately 15–25 degrees away from full frontal. Do not keep her face pointed toward the carousel. Direct boyfriend-eye-contact lock: both pupils and irises point directly into the center of the camera lens, as though she is looking into her boyfriend’s eyes. She is not looking at the carousel, a horse, beside the camera, or beyond the lens. The higher lens causes a clearly upward eye angle. Keep the chin level or slightly tucked. Expression lock: a sweet, affectionate, gently spoiled expression, as if she wants him to ride again or stay close for another moment. Softened eyelids, slightly lifted inner brows, relaxed cheeks, softly closed

Generate image
GPT Image 2
Three Kingdoms Pop-Up Book Scene
View full prompt & copy

Goal: Create a cinematic paper-craft pop-up book illustration for 三國演義, presenting Romance of the Three Kingdoms as an epic Chinese classical literature scene. Canvas: Wide 16:9 landscape composition, dark theatrical lighting, high-detail 3D layered paper diorama emerging from an open antique book on a wooden table. The book fills the bottom foreground with visible printed Chinese-style text, aged pages, a red-brown cover, and a central spine crease. Layout: The open book forms a pop-up battlefield and river panorama. Place the heroic character group on the left-center foreground, the burning naval battle on the right, mountains and fortress cities in the background, and large title typography in the upper-right sky. Subject details: Include exactly 4 main historical figures in layered paper-cut style: 1 stern armored warrior on the far left holding a spear beside a red banner marked 「張」, 1 elegant strategist in white robes at center front holding a sheathed or folded object and wearing ornate trim, 1 green-robed bearded general at center-right holding a tall curved guandao, and 1 elevated scholar-strategist behind them in pale robes holding a feather fan. Their costumes should be ornate Han-era fantasy armor and robes with gold embroidery, expressive faces, theatrical poses, and crisp cut-paper edges. Scene elements: Include exactly 6 prominent foreground props around the book scene: 1 standing war drum, 1 rack of upright spears, 1 rolled scroll, 1 open handwritten manuscript, 1 vertical stone marker labeled 「隆中對」, and 1 small fortress gate labeled 「荊」. In the right-side river battle, include exactly 5 large visible warships with black sails, red flags, and firelit silhouettes, plus smaller implied boats only as background texture. Add layered paper waves, smoke plumes, orange flames, fortress walls, banners, and troops in miniature scale. Background: Create a moonlit mountainous Chinese landscape with pagodas, cliffside fortresses, blue-black night sky, and a bright full moon on the upper left. The right background should glow with red-orange fire and smoke, contrasting against cool blue mountains on the left. Text content: In the upper right, write the large gold brush-calligraphy title 「三國演義」 with rough metallic texture. Below it, add the English subtitle “Romance of the Three Kingdoms”. Under the subtitle, add two smaller Chinese lines: 「作者:羅貫中」 and 「成書:約十四世紀」. Add a decorative plaque reading 「群雄逐鹿,智謀定天下」. Preserve the Chinese text exactly as visible. Visual style: Ultra-detailed cinematic paper art, dimensional pop-up book construction, layered cut-paper silhouettes, embossed gold calligraphy, dramatic rim light, volumetric smoke, miniature stage design, ornate historical fantasy realism, sharp focus, rich contrast, deep navy blues and fiery reds, museum-quality craftsmanship. Constraints: Keep the scene as a single coherent pop-up book spread, not a flat poster. Do not add modern objects, watermarks, logos, or extra main characters. Maintain readable typography and a premium cinematic book-cover feel.

Generate image
GPT Image 2
Manga Cat-Eared Girl Breaking Up Fight
View full prompt & copy

Create a clean black-and-white manga illustration on a plain white background showing exactly three anime girls in a tense confrontation, waist-up to mid-thigh framing, horizontal 4:3 composition. The center character is a short-haired cat-eared girl with pale bobbed hair, large animal ears, sharp confident eyes, and a simple oversized white T-shirt with jeans; she stands facing forward between the other two, arms stretched straight outward, one palm pressed to each girl's chest/shoulder as if physically stopping them from fighting, mouth slightly open as if scolding. On the left is a bespectacled girl with black hair in a messy low bun, wearing round glasses, bangs, an oversized sweater layered over a collared or ribbed neckline, and dark pants; she leans inward angrily with her mouth open, one hand raised near her chest. On the right is a short messy black-haired girl, wearing a loose oversized T-shirt tucked into high-waisted dark jeans; she leans inward aggressively, mouth open, one hand at her chest where she is being held back. Use expressive anime faces, dynamic body language, strong clean ink line art, delicate hatching and gray shading, glossy black hair highlights, minimal background, no text, no color except grayscale, crisp high-resolution manga sketch style.

Generate image
GPT Image 2
Blonde Girls at Summer Festival
View full prompt & copy

Create a photorealistic vertical smartphone snapshot at a lively Japanese summer festival at night, taken with a wide-angle phone flash from slightly above eye level. In the foreground, show exactly two young Japanese women with blonde hair crouching together on gray asphalt and looking directly into the camera. The woman on the left wears a dark navy yukata with pale floral patterns, beige geta sandals, a red obi visible behind her, and an ornate side hair ornament with white flowers, red accents, gold beads, and tassels; her hair is in a soft messy updo with bangs, she smiles warmly, holds a blue glass ramune bottle in one hand, and makes a peace sign with the other. The woman on the right wears a white yukata with large red flower and gray leaf patterns, a yellow obi with a black bow visible at the side/back, and black sandals; her hair is in two loose braids with wispy bangs, she has glossy gyaru-style makeup and big eyes, and she holds a white bowl of bright red shaved ice with a small white spoon. Make the background a busy matsuri street lined with illuminated food and game stalls, red-and-white striped booth curtains, hanging lanterns, warm string lights, festival-goers in yukata, a goldfish-scooping style stall on the left, candied-apple or snack display on the right, and a white cooler near the right edge. Use strong on-camera flash on the subjects, warm lantern bokeh in the distance, realistic skin texture, natural casual posing, shallow-to-moderate depth of field, high detail, candid social-media photo aesthetic. No text overlay, no watermark, no extra foreground people, no distorted hands, no duplicated bowls or bottles.

Generate image
GPT Image 2
Three AI Deities Fantasy Poster
View full prompt & copy

Create a cinematic dark-fantasy promotional poster for three personified AI models standing shoulder to shoulder in an ornate cosmic cathedral. Wide horizontal canvas, 16:9 aspect ratio, ultra-detailed photorealistic fantasy illustration with ethereal lighting, soft haze, gold and silver magical UI diagrams, arcane circles, and elegant serif typography. Main subjects: exactly 3 beautiful androgynous fantasy figures, waist-up, arranged left to right. Left figure: Claude Mythos, pale grayscale complexion, long silver-white hair, calm intense eyes, wearing layered white ceremonial robes with faint gold embroidery and luminous geometric sigils near the hands; expression serene and ancient. Center figure: GPT-Sol, radiant blonde woman with flowing wavy hair, warm golden skin tones, half-lidded confident gaze, wearing translucent ivory-gold robes with sunburst embroidery and delicate jewelry; a large glowing golden halo/astrolabe disk behind her head, making her the visual focal point. Right figure: Kimi K3, elegant dark-haired woman with cool pale skin, black wavy hair, wearing dark embroidered robes with silver patterns; she holds one hand up, palm open, levitating a luminous detailed full moon surrounded by blue-white holographic rings and star-map lines. Text content: add exactly 4 text blocks in elegant serif type. Left text block near the left figure reads “Claude Mythos\nDepth. Context.\nEternal Insight.”. Center text near the central figure reads “GPT-Sol\nIllumination. Creation.\nBoundless Potential.” Bottom-center headline reads “A New Generation.\nInfinite Intelligence.” Right text block near the moon reads “Kimi K3\nPrecision. Reasoning.\nBeyond the Known.” Keep the text readable, refined, and integrated into the magical interface graphics. Lighting and style: dramatic chiaroscuro, cool charcoal background, warm gold light radiating from the center, moonlit blue light from the right, grayscale silver aura on the left. Include concentric celestial rings, faint data glyphs, compass-like diagrams, sparks, and translucent magical overlays. High fashion fantasy robes, delicate fabric texture, detailed hair strands, cinematic depth of field, painterly realism, luxurious editorial poster composition. Avoid cartoon style, avoid extra characters, avoid distorted hands, avoid cluttered unreadable typography, no watermark.

Generate image
By @ar
GPT Image 2
Minimal Queue Illustration
View full prompt & copy

Create a minimalist flat vector illustration of four people standing in a line as if waiting in a queue, all shown in left-facing side profile on a warm off-white background. Use a simple editorial style with thick dark charcoal outlines, flat muted colors, and very little facial detail. The scene contains exactly 4 discrete human figures from left to right: 1) a young man in a black jacket and black pants wearing a rounded black backpack, standing upright with arms down; 2) a young woman with dark hair in a ponytail, wearing a muted blue long-sleeve top, slim black pants, black shoes, and a black crossbody shoulder bag; 3) a young man in a black outfit with a black backpack, holding a smartphone in one hand at chest height while looking slightly downward; 4) a young woman with shoulder-length dark hair wearing a muted blue top, long black skirt, black shoes, and carrying a white tote bag over one shoulder. Keep the figures evenly spaced, cropped slightly at the far right edge for the fourth person, with no text, no scenery, no shadows, and no extra objects beyond the 4 bags and 1 smartphone. Use a restrained palette of muted blue, black, charcoal gray, white, and cream, with clean hand-drawn linework and a calm modern urban mood.

Generate image
GPT Image 2
Baroque Composer Mystery Collage
View full prompt & copy

Create a dramatic cinematic historical collage in a wide 16:9 format about a lost classical music masterpiece. The scene is split diagonally by torn parchment and black-gold paint textures. On the left, show a terrified young mother in an 18th-century cream linen dress fleeing through a dark rain-slick European city street while clutching her small curly-haired son in her arms; behind them, a shadowy armed husband pursues them through blue fog near baroque church silhouettes and old street lanterns. On the right, show an elderly 18th-century composer, about 84 years old, with white powdered hair and a black velvet coat, seated at a candlelit wooden desk writing musical notation with a quill on manuscript paper. Behind him, include two sepia portrait busts or painted composer portraits, one with a rough red brushstroke across the eyes to suggest misattribution and historical mystery. Overlay the entire image with exactly three prominent manuscript-music elements: one sweeping golden staff of notes across the upper center, one torn sheet of musical score across the lower center, and one smaller red-and-gold notation fragment in the lower left. Add scattered gold ink splashes, black soot textures, torn paper edges, a red wax seal near the lower right, stacks of old papers, brass candlesticks with lit candles, and deep chiaroscuro lighting. Use a baroque thriller aesthetic, ultra-detailed painterly photorealism, moody blue shadows on the fleeing figures, warm amber candlelight on the composer, high contrast, textured parchment background, no modern objects, no readable text, no watermark.

Generate image
GPT Image 2
Warehouse Martial Arts Showdown
View full prompt & copy

Create a cinematic ultra-wide action keyframe in a 16:9 aspect ratio, set inside a dark abandoned industrial warehouse with damaged concrete walls, exposed steel beams, hanging cables, broken pipes, grimy pillars, a high shadowy ceiling, drifting haze, and a wet dirty floor that creates strong mirror-like reflections. Show exactly two fighters facing off across the frame: on the left, a blue and gold Chinese-inspired qipao combat dress with high side slit, white lace-up combat boots, hair in two buns, crouched in a guarded martial-arts stance with fists raised; on the right, a tight black tactical T-shirt, black cargo pants, black boots, and fingerless gloves, muscular build, standing wide in a boxer stance with clenched fists. Use dramatic low-angle framing, strong negative space between them, and intense backlighting from warm amber industrial lights deep in the corridor, with golden reflections on the wet floor. The mood should be gritty, tense, realistic, and high-budget, like a live-action fight scene keyframe. Emphasize cinematic contrast, volumetric smoke, rim light on both bodies, detailed textures, realistic skin, damp concrete, and deep shadows. No text, no logos, no extra characters, no weapons.

Generate image
GPT Image 2
Boyfriend POV Seaside Sunset Date
View full prompt & copy

Photorealistic boyfriend-perspective summer date scene featuring an adult woman. Image logic: the upward gaze must come from true boyfriend-perspective camera placement. The boyfriend is about 30 cm taller, and the camera must sit at his actual eye level so she is clearly looking up at him from below. The emotional core is a sweet affectionate upward gaze with a gently spoiled expression, created by real height difference and close romantic distance. Background identity: a vivid seaside boardwalk at sunset in midsummer, with a wide peach-pink-lavender sky, white railings, weathered wooden decking, reflective sea water, a distant Ferris wheel, small amusement lights beginning to glow, layered coastal buildings, and a soft evening breeze. The background should feel romantic and layered rather than like a flat sunset backdrop. Depth lock: in the foreground, a softly blurred railing corner, boardwalk post, or sea-light reflection enters close to the lens. In the middle ground, the subject stands near the inside edge of the railing, very close to the camera. In the background, receding boardwalk lines, the Ferris wheel, layered buildings, sea horizon, and sunset sky create strong depth. True boyfriend-POV camera lock: the camera is not a third-person observer and not a fashion-editorial camera. The lens is placed exactly where the taller boyfriend’s eyes would be, about 30 cm above her eye line, at very close conversational distance, approximately 45 to 60 cm from her face. Use a clearly readable downward viewing angle of about 18 to 24 degrees. The camera is positioned slightly in front of and just outside her near shoulder, as though her taller boyfriend has stepped close beside her and is looking down at her from his own real eye level. Frame from upper waist or lower chest to above the head. Her eyes and face must sit clearly below the lens, so the upward gaze is structurally unavoidable. Do not use a flat eye-level angle, do not use an observer camera, and do not use a neutral portrait camera. Pose lock: the subject has paused beside the railing while still oriented along the boardwalk. Her weight rests naturally on one leg, with the other foot slightly behind and mostly outside the crop. The torso remains mostly aligned with the walkway rather than turning fully into a portrait pose. One hand rests lightly on the railing behind or beside her hip as a simple support point. The other arm remains relaxed along the body and may be partially cropped or partially hidden. Shoulders stay lowered and natural. Upward-gaze lock: because the lens is truly above her, she looks clearly upward toward the camera from below. Her face remains in a soft three-quarter angle, not frontal. The head turns only a little toward him, while the eyes lift distinctly upward to the higher lens. Ke

Generate image
GPT Image 2
Crystal Panel Fashion Gallery
View full prompt & copy

4:5 Five ultra-realistic European fashion models displayed inside floating transparent crystal glass panels layered at different depths, each wearing luxurious contemporary haute couture outfits inspired by Paris and Milan Fashion Week, bold designer silhouettes, premium fabrics, statement accessories, elegant heels, effortlessly stylish actress-level fashion, vibrant emerald, sapphire, ruby, ivory and champagne tones softly blending through crystal reflections, luminous luxury studio lighting, glossy white gallery environment with subtle gradient illumination, cinematic editorial photography, Vogue campaign aesthetic, soft volumetric light, realistic reflections, premium depth, hyper detailed skin textures, ultra realistic, masterpiece, 2K, vertical 9:16

Generate image
GPT Image 2
Anhua Dark Tea Mountain Poster
View full prompt & copy

Goal: Create a cinematic horizontal promotional poster for a mountain tea-growing region, blending documentary photography and premium agricultural branding for 安化黑茶. Canvas: Wide 16:9 landscape poster, approximately 1200×675 px. Use a split panoramic layout with a strong horizontal divider: the upper half is an active tea harvest scene, the lower half is a misty tea mountain brand-information panel. Visual style: Hyper-realistic editorial photography, moody overcast light, cool green and blue-gray color grading, low mountain fog, deep contrast, premium government/enterprise agricultural publicity aesthetic. Use terraced tea fields across rolling hills, soft mist drifting between mountains, distant winding paths, and wet dark-green tea leaves. Typography should be elegant, high-end, and minimal, with large white Chinese calligraphy-style serif characters and small refined Latin letters. Upper scene: Show exactly 8 tea workers harvesting on terraced tea bushes. List them clearly in the composition: 1 large foreground woman at far left wearing a purple top, dark patterned headscarf, and a large woven bamboo basket on her back; 2 small worker near upper left-center with blue head covering and basket; 3 small worker in red clothing farther back; 4 small worker in purple farther back; 5 central foreground woman in blue plaid shirt and patterned headscarf picking tea with a bamboo basket at her side; 6 small worker right of center with headscarf and basket; 7 woman in maroon top picking tea on the right slope; 8 far-right worker near two large round bamboo trays filled with fresh tea leaves. Keep all workers natural and documentary-like, not posed. Main title area: Across the center, overlay the huge white Chinese headline 安化黑茶. Beneath it, centered in spaced small caps, add the English subtitle ANHUA DARK TEA. The title should partially cover the tea fields and slightly overlap the horizontal split, with subtle shadow for readability. Lower scene: A panoramic misty valley and tea terraces continue in the background. In the lower middle-right foreground, show exactly 4 older female tea farmers sitting or crouching together among tea bushes, wearing dark blue and purple rural clothing and patterned headscarves, sorting or examining fresh tea leaves; place a large woven basket behind them on the right. The mood should be warm, authentic, and communal. Side labels and icons: On the far left vertical margin, add a small hollow circle, vertical Chinese text 中国黑茶之乡, and a tiny leaf icon below it. On the far right vertical margin, add a small hollow circle, vertical Chinese text 安化山地茶园, and a tiny mountain-line icon below it. Central vertical microtext: Under the English subtitle near the middle, add four slim vertical Chinese text columns reading: “陈香木香 · 时间沉淀”, “安化核心产区”, “后发酵 · 黑茶”, and “山地茶园”. Keep these small, black or dark gray, and refined. Bottom information band: Along the bottom, add three compact blocks of white Chinese product information separated by thin vertical divider lines. Left block: “产区|湖南安化”, “采摘季|春末至初夏”, “海拔|山地丘陵”. Middle block: “茶类|黑茶”, “工艺|杀青 · 揉捻 · 渥堆 · 干燥”, “风味|陈香 木香 甘润”. Right block: “冲泡|95-100℃”, “建议|耐泡可煮”, “关键词|时间与醇化”. Use small Song/Ming-style Chinese type, generous letter spacing, and balanced alignment. Constraints: Use exactly 12 visible people total: 8 in the upper harvest panorama and 4 in the lower group scene. Use exactly 3 bottom information blocks, exactly 2 vertical side labels, and exactly 4 central vertical microtext columns. Do not add logos, QR codes, price tags, packaging mockups, or extra text. Keep the poster realistic, misty, premium, and rooted in Chinese tea mountain culture.

Generate image
GPT Image 2
Dying Composer Final Masterpiece
View full prompt & copy

Create a dark cinematic historical photomontage about an 84-year-old dying composer writing his final masterpiece from a sickbed. Use a wide 16:9 canvas with painterly realism, chiaroscuro lighting, distressed textures, and a tragic romantic-classical music mood. Center the scene on an elderly white-haired man in a dark robe, seated or propped in bed, hunched over illuminated parchment sheet music, writing notes with a pen; his wrinkled face is sorrowful and focused, lit by a warm spotlight from above/front. Surround him with exactly 2 secondary figures: on the left, a shadowy insane husband-like man in a black suit with wild curly hair, clutching his head in anguish, partially obscured by red-black smoke and torn musical manuscript; on the right, a grieving middle-aged mother in profile, hands clasped near her mouth, looking down toward a cracked abyss-like stone path fading into mist. Add exactly 4 prominent visual motifs: scattered manuscript pages in the foreground, flowing golden musical staves and notes sweeping across the composition, blood-red ink/smoke splashes on the left and upper background, and a deep jagged crack splitting the ground on the right. The background should suggest an old bedroom with rumpled white sheets and worn walls, blending into abstract darkness. Color palette: near-black shadows, sepia parchment, warm candlelit gold, dirty gray stone, and dramatic crimson red. No readable modern text, no captions, no logos, no clean digital UI; keep it gritty, emotional, operatic, and high-detail like a dramatic album-cover or magazine feature illustration.

Generate image
GPT Image 2
Romantic Just Married Wedding Poster
View full prompt & copy

Create a romantic horizontal wedding announcement poster featuring a young East Asian bride and groom in a polished studio portrait. Canvas: wide 16:9 landscape layout, soft blush-pink background with subtle glow and faint sparkles, bright airy retouched wedding-photo aesthetic. Main subjects: exactly 2 people centered near the top half, shown from waist up and leaning close together while looking at the camera. The bride stands on the left wearing a white lace wedding dress with sheer embroidered neckline, a translucent veil, elegant updo with pearl-and-flower hair ornaments, soft natural makeup, and one hand lightly lifting the veil; she holds a small bouquet of pale pink and white flowers near the center. The groom stands on the right wearing a black tuxedo, white shirt, black bow tie, white pocket square, small decorative boutonniere or silver deer-shaped brooch on the lapel, tousled dark hair, and round glasses. Typography and layout: place a huge bold coral-orange word LOVE across the entire bottom half, cropped slightly by the canvas edges, with the couple layered in front of and behind parts of the letters for depth. Overlay a large white handwritten brush-script phrase Just Married diagonally across the center over the couple and the large letters, including a long underline stroke and painterly texture. Bottom information row: include exactly 5 small centered text blocks separated by thin vertical lines: 1) "SAVE / THE / DATE", 2) 14 / FEB / 2027, 3) "CEREMONY" with a tiny plus/star ornament below, 4) MOONLIT / GARDEN, 5) "6:30 / PM". Add exactly 2 small white laurel ornaments near the lower left and lower right, plus a tiny sparkle beside the left laurel. Visual style: premium modern wedding invitation, soft high-key lighting, smooth skin retouching, pastel palette, coral-orange typography, clean editorial composition, delicate romantic atmosphere. Constraints: no extra people, no additional text beyond the specified words, keep all lettering legible, avoid watermark or logo.

Generate image
GPT Image 2
Cinematic First-Person Girlfriend Portrait
View full prompt & copy

Highly realistic cinematic portrait photography, 2160x3840 vertical composition, real camera texture, 50mm or 85mm portrait lens effect, shallow depth of field, clean and transparent summer natural light tones. A young and beautiful East Asian adult woman with soft heart-shaped face, exquisite classical features, bright almond/fox eyes, small bridge of the nose, naturally full lip shape, sweet, sunny, energetic, and cute. She is walking on a garden stone path / shaded path / European street / courtyard path, holding someone's hand behind her, capturing a first-person couple's perspective. She has long hair with natural slight curls, long straight hair, loose waves, airy bangs, with strands flying in the wind under strong natural backlight. She is wearing a white lace slip dress / beige slip dress / light blue short-sleeved top with a white skirt. Skin texture must be extremely realistic with fine pores and natural texture. The overall image has high realism, cinematic feel, and a heart-pounding summer vibe.

Generate image
GPT Image 2
Rainy Subway Betrayal Scene
View full prompt & copy

Create a cinematic photorealistic anime-to-live-action scene in a Korean subway exit stairwell at night during heavy rain. The image shows exactly three characters: a young man and young woman kissing halfway down the stairs in the foreground, and a solitary young man standing at the top landing under a black umbrella in the background. The foreground man has short dark tousled hair with shaved sides, a loose wrinkled beige button-up shirt with sleeves rolled, oversized dark navy pants, and white sneakers; one hand is in his pocket as he leans down into the kiss. The foreground woman has long black hair, a fitted black top or jacket, a red plaid pleated skirt, sheer black tights, and glossy black high heels; she presses one hand to his chest while leaning upward. The background observer has pale silver hair, a dark oversized hoodie, dark shorts, and sneakers, holding the umbrella above him while facing the couple with a quiet, lonely expression. Set the scene on a wide gray stone staircase with metal handrails on both sides, beige tiled subway walls, warm wall lights along the steps, and wet reflective stair treads. At the top opening, show a rainy neon-lit city street with blue and pink blurred signs and visible rainfall. Add Korean subway signage: a black sign on the left reading “Exit” and a large “2”, with smaller Korean destination text, plus blue station information boards on the right wall. Use a dramatic symmetrical composition looking upward along the stairs, with the kissing couple slightly left of center and the observer centered at the top. Lighting should mix warm tunnel lamps with cool rainy city glow, creating a moody romantic noir atmosphere about betrayal, invisibility, and heartbreak. Ultra-detailed, cinematic depth of field, realistic textures, wet reflections, 16:9 horizontal frame. Customize as needed with loose wrinkled beige button-up shirt, oversized dark navy pants, white sneakers, black top, red plaid pleated skirt, sheer black tights, glossy black high heels, pale silver-haired young man in a dark oversized hoodie and shorts holding a black umbrella, 2, and lonely romantic betrayal in the rain.

Generate image
GPT Image 2
Spain vs France World Cup Comic
View full prompt & copy

Goal: Create a colorful six-panel comic strip predicting a World Cup 2026 semi-final football match between Spain and France, in an energetic kid-friendly sports-cartoon style. Canvas: Square 1:1 image divided into exactly 6 rectangular panels arranged in a 2-column by 3-row grid, with thick black comic borders and slightly textured print-comic shading. Visual style: Bright saturated colors, bold ink outlines, dynamic motion lines, exaggerated joyful expressions, packed stadium backgrounds, waving red-yellow Spanish flags and blue-white-red French flags, green football pitch, dramatic perspective, speech bubbles, scoreboard banners, and lively crowd confetti. Characters are stylized young male footballers with large expressive eyes and athletic cartoon proportions. Panel layout and required content: 1. Top-left panel: Establishing match panel inside a huge stadium. A large scoreboard reads “WORLD CUP 2026 SEMI-FINAL” with Spanish and French flags and the matchup text “SPAIN VS FRANCE.” Show two main players facing off: a Spain player in a red jersey with number 9 and a France player in a blue jersey with number 10. Add two smaller players and a ball near midfield behind them. 2. Top-right panel: Goal action for Spain. The Spain number 9 player kicks the ball toward the net while a goalkeeper in a green kit dives and misses. Add a speech bubble reading “GOAL!” above the striker. 3. Middle-left panel: France equalizer celebration. Scoreboard reads “1 - 1.” A large speech bubble says “GOOOAL!” Show exactly 5 visible players celebrating: one Spain number 9 at the left edge looking disappointed or surprised, and four France players in blue celebrating, including the central number 10 with both arms raised and one France number 9 at right. 4. Middle-right panel: Intense duel. A banner at the top reads “TENSE ACTION!” Show the Spain number 9 and France number 10 running shoulder-to-shoulder, glaring competitively and chasing a football between them. 5. Bottom-left panel: Last-minute chance. A banner reads “LAST MINUTE CHANCE!” Show the Spain number 9 taking a powerful shot at goal while the green goalkeeper with number 4 leaps across the goalmouth. The ball flies dramatically toward the net with white speed streaks. 6. Bottom-right panel: Final result celebration in front of a stadium with the Eiffel Tower visible in the background. A scoreboard banner reads “FULL TIME” with both national flags and the final score line “SPAIN 1 - 2 FRANCE.” Add a speech bubble reading “WE’RE IN THE FINAL!” Show exactly 6 celebrating players grouped together: one Spain player in red number 9 in the center looking excited, surrounded by five France players in blue with raised fists and smiling faces. Text content to include exactly as visible: “WORLD CUP 2026 SEMI-FINAL”, “SPAIN VS FRANCE”, “GOAL!”, “GOOOAL!”, “1 - 1”, “TENSE ACTION!”, “LAST MINUTE CHANCE!”, “FULL TIME”, “SPAIN 1 - 2 FRANCE”, and “WE’RE IN THE FINAL!” Constraints: Use exactly 6 panels, keep all football jerseys clearly color-coded red for Spain and blue for France, make the final score SPAIN 1 - 2 FRANCE, avoid photorealism, avoid extra panels, avoid watermarks, and keep all text large, legible, and comic-book styled.

Generate image
Loading more prompts

FAQ

Where do YouMind prompts come from?
YouMind curates high-signal AI prompt examples from creator communities and public creative workflows. The library focuses on prompts that are useful to inspect, reuse, and adapt.
How are image prompt categories organized?
Image prompts are grouped into use cases, styles, and subjects. Use cases describe the job to be done, styles describe the visual treatment, and subjects describe what the image is mainly about.
How are prompts assigned to categories?
YouMind uses AI to analyze each image prompt, its title, metadata, and generated result when available, then assigns the closest categories. Editors can refine categories as the taxonomy evolves.
What is YouMind?
YouMind is an AI workspace for turning research, ideas, and creative references into usable outputs. The prompt library is one public part of that workflow, built to help creators learn from strong examples faster.