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
Anime Classroom Sleeping Student Scene
View full prompt & copy

Create a wide 16:9 anime-style classroom illustration with warm afternoon sunlight streaming through tall windows on the left, wooden desks, school bags, a green chalkboard with faint math equations, wall posters, a teacher's podium, and a door on the right. Show exactly 5 main characters in the classroom: 1) a strict young female teacher with long dark brown hair in a navy school-uniform-like jacket standing behind the podium, angrily pointing and throwing a piece of chalk; 2) a cheerful short blonde girl at the left desk wearing a black military-style beret and orange-black jacket, laughing with eyes closed; 3) a tiny purple-haired chibi girl in a lavender beret and outfit standing on a small stool beside a desk, gently poking or trying to wake someone; 4) a blonde schoolgirl asleep face-down at the front-right desk, messy hair, hair clips, navy blazer, plaid skirt, black boots, looking exhausted; 5) a dark-haired ponytail schoolgirl at the right desk in a navy uniform, startled with a sweat drop while watching the sleeping girl. Add a large comic thought bubble above the sleeping blonde girl showing exactly 7 miniature characters on a stage scene: the same blonde girl standing proudly in the center under warm spotlight, one smiling adult male teacher or host beside her, one elderly bald man clapping, and four smaller students around them applauding or watching. Use expressive manga faces, clean line art, soft cel shading, detailed classroom props, dynamic motion lines around the flying chalk, and a humorous school-comedy mood. Character customization: the sleeping girl is a blonde schoolgirl with hair clips, the teacher is a strict long-haired brunette teacher, the small helper is a tiny purple-haired chibi girl in lavender, the left student is a cheerful blonde girl in a black beret and orange jacket, and the setting is a Japanese-style classroom at sunset. Avoid photorealism, avoid extra characters outside the listed 12 visible figures, and do not add readable text beyond faint chalkboard equations.

Generate image
GPT Image 2
Realistic Family Lifestyle Portrait
View full prompt & copy

Use the uploaded photo as the composition and pose reference. Create an ultra-realistic family lifestyle portrait of a father with his four children, preserving the natural arrangement from the reference: the father standing on the left holding the youngest child in one arm, while the three older children stand closely beside him, hugging and leaning toward him naturally. Keep the warm, playful family connection and realistic differences in height and age. Change the clothing completely to a coordinated, decent smart-casual family style. Dress the father in a clean cream long-sleeve polo shirt, tailored dark-brown trousers, and elegant white leather sneakers, with a simple wristwatch. Dress all four children in coordinated cream and earthy-brown outfits appropriate for their ages—neat polo shirts or modest tops paired with tailored trousers, skirts, or comfortable chinos and clean neutral sneakers. Keep the outfits stylish, modest, contemporary, and family-friendly, without large logos, chains, or excessive accessories. Replace the vehicle/background with a beautiful upscale outdoor garden setting featuring a modern luxury home in the distance, manicured green lawn, decorative plants, subtle stone pathways, and softly blurred trees. Use warm late-afternoon natural light filtering through the greenery for an elegant and welcoming atmosphere. Keep everyone naturally interacting rather than appearing overly posed. The youngest child should remain comfortably held by the father, while the other children gather affectionately around him with cheerful, natural expressions. Use professional lifestyle photography, realistic skin texture, accurate anatomy, natural body proportions, detailed clothing fabrics, soft cinematic lighting, subtle depth of field, realistic shadows, balanced exposure, and crisp facial details. Full-body vertical composition, premium family photoshoot aesthetic, photorealistic, high resolution. Important: If individual facial reference photos are provided, preserve each person's facial identity, natural skin tone, hairstyle, age, and distinctive features without beautifying or Deleterious their identity.

Generate image
GPT Image 2
Medieval Village Girl at the Well
View full prompt & copy

Create a highly detailed anime-style semi-realistic illustration set in an old European medieval village courtyard beside a stone water well. The main subject is one young woman, a gentle village girl, shown from the waist up in the foreground, turned slightly sideways but looking directly at the viewer with a soft smile. She has warm chestnut brown hair in a long loose braid over one shoulder, wispy bangs, fair skin with a subtle blush, bright gray-blue eyes, and delicate round wire-frame glasses. Dress her in a traditional peasant outfit: cream puff-sleeve blouse, dark forest-green fitted bodice with front lacing, green gathered skirt, and simple waist sash. Behind her, show exactly four background villagers near the well: 1) a young woman in a brown corset dress standing at left, 2) a small child partly hidden near the bucket chain, 3) a boy standing behind the well, and 4) two young women on the right drawing water together counted as one paired group interaction but visibly two figures, softly blurred by depth of field. Include a circular stone well in the left foreground with a wooden roof beam, hanging iron chain, and metal bucket; rustic cream plaster houses with dark roofs in the background; and a distant church tower with a pointed steeple rising into a bright hazy sky. Use medieval countryside atmosphere with no modern objects except the character's subtle fantasy-style glasses. Lighting should be warm late-afternoon sunlight from behind and above, creating rim light on her hair, soft bloom, gentle shadows, cinematic depth of field, painterly realism, intricate clothing folds, natural skin texture, and a peaceful nostalgic mood. Vertical portrait composition, 3:4 aspect ratio, no text, no watermark.

Generate image
By @眩
GPT Image 2
Chibi Royal Horse Twin Princes
View full prompt & copy

Create a soft, high-detail chibi anime illustration of two royal horse-anthro twin children standing side by side in a bright palace throne room. The image shows exactly two characters: the left twin has fluffy short silvery white hair, pale skin, droopy lavender eyes, a calm slightly sleepy expression, a white horse ear and fluffy white tail, and wears a miniature white-and-gold prince uniform with blue accents, medals, epaulettes, a fur-trimmed cape, jeweled sash details, gloves, and dark boots; the right twin has long dark navy black hair tied low with loose curls, pale skin, large green eyes, a gentle smiling expression, a white horse ear and long dark tail, and wears a matching white-and-gold royal uniform with red accents, medals, epaulettes, fur-trimmed cape, black boots, and delicate pearl chains. Each twin wears one oversized ornate crown, for exactly two crowns total: gold frames with red velvet centers, pearl garlands, small jewel finials, and bright sparkle highlights. Place them in front of a large plush red throne with gold carved arms and trim, tall palace windows pouring in white light, blue royal banners with subtle horse emblems on both sides, a red carpet, and a glossy gray-and-white checkerboard floor. Use a dreamy gacha-game character style, oversized heads and tiny bodies, delicate eyelashes, soft blush, pastel lighting, shimmering magical particles, lens-flare sparkles, and polished fantasy royalty details. Composition should be a medium-wide frontal view, symmetrical and cute, with the throne centered behind them and both characters fully visible from crown to boots. No text, no watermark, no extra characters.

Generate image
GPT Image 2
3D Paper Quilling Wedding Scene
View full prompt & copy

A high-detail 3D paper quilling art piece featuring a romantic bride and groom sitting in an open-top vintage pastel pink car, crafted entirely from rolled and coiled paper strips on a clean white background. The groom has black hair and is wearing a dark purple paper-quilled suit jacket, white shirt, and a purple bow tie. The bride has styled brown hair with a flowing white veil and wears an intricate white quilled wedding gown; they lean toward each other in a sweet, romantic pose. The vintage car is decorated with large, layered quilled pink roses along its body, with deep purple coiled paper tires. Framing the top of the scene is a large heart-shaped arch made of purple, lavender, and pink quilled flowers with green paper leaves and small purple butterflies hovering nearby. The bottom area features cascading lavender paper blossoms, pink starburst flowers, and elegant white paper filigree scrollwork. Soft studio lighting from above creates subtle, realistic drop shadows under each raised paper layer, emphasizing the tactile, three-dimensional craft quality --ar 1:1

Generate image
GPT Image 2
Japanese Chibi Storybook Illustration
View full prompt & copy

Create a cute hand-drawn Japanese chibi illustration of two characters interacting in a sweet, playful moment. Use a soft traditional colored-pencil and crayon drawing style, with visible sketchy pencil strokes, slightly rough imperfect outlines, gentle pastel coloring, and a handmade children’s storybook feel. Characters should have oversized heads, tiny bodies, simple oval black eyes, tiny smiling mouths, rosy cheeks, and expressive innocent faces. Give them natural, adorable poses and interactions, with clothing and hairstyles matching the requested scene. Keep the composition clean and minimal on a plain white background, with plenty of negative space. Add small hand-drawn decorative elements such as hearts, sparkles, or motion lines around the characters where appropriate. Soft pastel palette, subtle paper texture, delicate linework, slightly imperfect coloring, cozy wholesome romantic atmosphere, full-body composition, centered characters, high-quality illustration.

Generate image
GPT Image 2
Identity-Preserving Romantic Couple Portrait
View full prompt & copy

Use the uploaded image as the only facial reference and preserve 100% facial identity, hairstyle, beard, skin tone, and natural skin texture. A medium shot of a young man and woman standing together leaning against a tall dark blue outdoor lamppost. The man on the left has short dark hair, slight facial hair, and is wearing a dark grey long-sleeve henley shirt with dark jeans and black wrist bracelets. The woman on the right has long wavy brown hair, smiling at the camera, and is wearing a bright pink long-sleeved floral printed dress or kurta. Natural outdoor lighting, soft blurred background, realistic portrait photo style.

Generate image
GPT Image 2
Photo-to-Sketch Editorial Journal
View full prompt & copy

Create a nostalgic editorial photo-to-sketch artbook page based on the reference image. Preserve the same subjects, pose, facial expressions, clothing, composition, and emotional atmosphere from the original photograph. Divide the page vertically into two connected sections: the upper section is a cinematic, ultra-realistic photograph with soft natural lighting, subtle film grain, shallow depth of field, authentic colors, and an intimate candid feeling; the lower section transforms the exact same scene and characters into a loose black-and-white hand-drawn ink illustration on warm off-white textured paper, with expressive imperfect lines, rough cross-hatching, minimal shading, and a handmade sketchbook aesthetic. Add tasteful editorial typography around the illustration, including a small numbered title, short poetic handwritten-style caption, and tiny documentary-style notes, creating the feeling of a premium contemporary photography journal or Japanese-inspired visual diary. Keep generous cream-colored negative space, subtle paper texture, slightly imperfect ink printing, understated vintage layout, sophisticated minimalist graphic design, emotionally warm and cinematic, cohesive transition between photograph and drawing, high detail, natural proportions, authentic human anatomy, no watermark, no logos.

Generate image
GPT Image 2
Convenience Store Fight Scene
View full prompt & copy

Create a cinematic, realistic action still set inside a brightly lit convenience store at night. The scene shows an athletic young woman with tan skin and long dark hair in a high ponytail wearing a red cropped tank top and black pants, frozen mid-fight as she vaults sideways over the checkout counter with one hand planted on the glass display case and one leg extended in a powerful flying kick. Count exactly four visible people: 1) the woman hero at center-left, focused and intense; 2) a masked robber on the far left in a black ski mask and dark gray hoodie, recoiling with both hands raised; 3) a second masked robber in the foreground center-right, seen from behind in a black ski mask and dark hoodie, facing the woman; 4) a scruffy male bystander on the right wearing an olive green T-shirt and beige cargo pants, standing near snack shelves and holding a bottled drink while watching anxiously. The store interior should include a glass checkout counter filled with colorful small packaged goods, a cash register on the left, sliding glass entrance doors and dark windows behind the counter, fluorescent ceiling reflections, brick-red tile flooring, and multiple racks of bright chip bags and snacks on the right and back wall. Use a wide 16:9 movie frame, eye-level perspective, dynamic frozen motion, realistic anatomy, gritty modern crime-thriller mood, natural fluorescent store lighting mixed with night reflections, shallow cinematic depth of field, detailed textures, and a high-budget film still look. Avoid text overlays, logos, captions, watermarks, extra characters, gore, or cartoon styling.

Generate image
GPT Image 2
Fashion Editorial Mixed-Media Sketch
View full prompt & copy

Transform the people in the reference photo into a stylish hand-drawn fashion illustration while keeping their facial features, poses, expressions, hairstyles, clothing, body proportions, and overall composition recognizable. Use a mixed-media aesthetic combining a realistic photographic background with detailed pencil-and-colored-pencil sketching on the people. Add visible hand-drawn cross-hatching, rough pencil strokes, subtle ink outlines, textured shading, and slightly imperfect sketch details. Keep the clothing highly detailed with realistic fabric folds and denim texture. Surround each illustrated person with a thick irregular white sticker/paper-cutout border, as if they were individually cut out by hand. Add small pieces of semi-transparent white masking tape around the edges of some figures, creating a scrapbook/editorial collage effect. The background should remain realistic, softly lit, natural, and slightly blurred, creating a strong contrast between the photographic environment and illustrated subjects. Aesthetic: Korean/Japanese fashion editorial, contemporary street-style illustration, scrapbook collage, fashion sketchbook, photorealistic background + hand-drawn characters, clean but imperfect pencil artwork, cozy muted tones, subtle film grain, soft natural lighting, premium editorial photography. High detail, realistic faces, natural anatomy, expressive eyes, detailed hair strands, realistic clothing textures, clean composition, full-body framing, professional fashion editorial quality. Avoid overly cartoonish proportions, CGI appearance, excessive saturation, distorted hands, extra fingers, warped faces, or overly smooth digital painting. For the exact “3 friends walking” look Add this at the end: Three stylish young adults walking together casually, interacting naturally and looking at each other, full-body shot, candid friendship moment, urban university/campus setting, relaxed oversized streetwear, wide-leg jeans and trousers, sneakers, tote bags and backpacks, photographed at eye level.

Generate image
GPT Image 2
Subtle Cinematic Scene Punch-In
View full prompt & copy

Using the provided reference image, make a very subtle production-style edit: keep the same living-room scene, characters, composition, camera angle, lighting, and mid-century film still look, but punch in slightly toward the right-side man and clean up the image. Preserve the woman as a blurred foreground shoulder/head on the left, the man seated in the teal chair, the fireplace, cabinet, lamp, and decor placement. Improve facial clarity, fabric texture, edge definition, and color consistency while maintaining a natural cinematic look. Do not change the actors, expressions, clothing, room layout, or add any new objects. Output in a 16:9 frame with the same warm indoor color grade.

Generate image
GPT Image 2
Darwin and Brahms in 1859
View full prompt & copy

Create a wide cinematic surreal illustration comparing Charles Darwin and Johannes Brahms in the year 1859. Use a luminous pastel, pearlescent 3D digital-painting style with translucent glass ribbons, soft ivory light, mint, aqua, peach, rose, and lavender gradients, highly detailed faces, and a dreamy museum-poster composition. The canvas is a 16:9 horizontal scene. Place exactly 2 main historical figures: on the left, an elderly Darwin with a bald head, thick white beard, thoughtful expression, and cream Victorian coat, surrounded by calm readers; on the right, a young Brahms with wavy blond-brown hair, formal 19th-century suit, bow tie, and serious profile, seated at a glossy grand piano. Between them, create a dramatic S-shaped pathway made from piano keys that begins in the foreground center and curves upward into a branching evolutionary tree with translucent leaf-like forms, visually merging music and biology. Include exactly 9 quiet reader figures on the left side, rendered like semi-transparent pastel sculptures, each holding or reading a book or paper; arrange them in layered rows around Darwin to imply that his ideas are being studied. Include exactly 12 audience figures on the right side, rendered in warm pink, orange, and violet glassy tones, reacting negatively to the music with raised hands, open mouths, pointing, and booing gestures; add subtle curved sound-wave marks near the upper-right crowd. Add floating iridescent spheres and flowing ribbon shapes around the scene, with a large translucent swirl framing Brahms and another sweeping ribbon behind Darwin. The mood should contrast contemplation and reception: left side calm, scholarly, cool-toned; right side theatrical, heated, chaotic. No written text, no captions, no logos, no watermark.

Generate image
GPT Image 2
Candid iPhone Selfie with Celebrity
View full prompt & copy

Take an extremely ordinary and unremarkable iPhone selfie, with no clear subject or sense of composition-just a quick accidental snapshot. The photo has slight motion blur and uneven lighting from streetlights or indoor lamps, causing mild overexposure in some areas. The angle is cute and giving the picture a deliberately mediocre feel, as if it was taken absentmindedly while pulling the phone from a pocket. The main character is [uploaded person], and Dwayne Johnson stands next to him/her, both caught in a casual, imperfect moment. The background shows a lively new york street light at night, with neon lights, traffic, and blurry figures passing by. The overall look is intentionally plain and random, capturing the authentic vibe of a poorly composed, spontaneous iPhone selfie.

Generate image
GPT Image 2
Romantic Sunset Sketch Portrait
View full prompt & copy

Create a romantic cinematic outdoor portrait at sunset. A young man with thick dark tousled hair and a short beard sits on an old weathered stone bench in a garden or historic terrace, looking up thoughtfully toward the right. He wears a cream, camel-brown, and navy color-blocked knit sweater with the visible handwritten text I can't live without you, plus exactly 2 small graphics on the chest: one red heart and one red rose stem. He holds a pencil in one hand and an open sketchbook in the other, showing a realistic pencil portrait of a beautiful young woman with long wavy hair and earrings. In the sky above and behind him, create a large dreamy semi-transparent face of the same woman, softly blended into glowing orange clouds as if she is a memory or vision; she has long dark wavy hair, delicate makeup, dangling floral earrings, and a sparkling necklace, with a gentle smile. The background includes exactly 1 vintage black streetlamp glowing warmly on the upper left, rose bushes with red flowers, old stone architecture on the right, and a low sun near the horizon. Use golden-hour lighting, warm amber and orange tones, romantic atmosphere, shallow depth of field, realistic photography style with subtle fantasy compositing, high detail, soft haze, natural skin texture, 3:4 vertical composition. No extra people, no watermark, no distorted hands, keep the sketchbook portrait clearly visible.

Generate image
GPT Image 2
Luxury Nail Clipper Commercial Ad
View full prompt & copy

Generate a 3:4 vertical commercial advertisement for high-end stainless steel nail clippers. The overall style uses warm dark brown, coffee, and champagne gold tones, soft indoor natural light, shallow depth of field, high-end lifestyle photography, and exquisite product photography fusion, creating a warm, private, and intimate atmosphere. In the upper right of the screen is an adult East Asian female with smooth black long hair, wearing a black sleeveless top. She leans in close to the male on the left of the screen, the frame showing only the lower half of her smiling face, shoulders, arms, and hands, with her eyes and the top of her head naturally cropped by the upper edge of the canvas. She shows naturally white teeth and a relaxed, intimate expression. In the left foreground, there is a faint glimpse of an adult male, his body facing away from or to the side of the camera, showing only his shoulder, upper arm, and part of the forearm wearing a brown fine-textured knit short-sleeved shirt, his head completely out of frame. The brown fabric has clear fine horizontal textures and natural wrinkles. The female's hand gently rests on and caresses the male's upper arm, her five fingers naturally extended, fingers slender, nails neatly trimmed, rounded, and without colored polish. The female's hand is the visual focus of the middle ground, while the male's body is slightly blurred. It must clearly show 'the female's hand is touching the male's arm,' and must not be mistakenly drawn as touching a sofa armrest. In the lower right foreground of the lower half of the screen is a large silver stainless steel nail clipper, placed diagonally on a light gray-brown fabric cushion, pointing from lower left to upper right. The nail clipper is in an open state, the base almost horizontal toward the right, and the press handle raised at about 45 degrees toward the upper right. The product combines mirror and brushed stainless steel, with sharp blades, precise pivots, clear edge highlights, and realistic metal reflections. The front end of the nail clipper's press handle has dense horizontal anti-slip patterns, and the middle is laser-engraved with gray Chinese characters: 'Zhang Xiaoquan'. The tail of the base has a fine metal file surface and a circular hanging hole. The product must be structurally accurate, clear, and sharp, being the most important product visual focus in the picture, and must not be deformed into scissors, pliers, or other tools. In the upper left corner, a white brush-script brand name is placed: 'Zhang Xiaoquan'. To the right of the brand name, a small white English sans-serif font is used, strictly divided into two lines: 'Zhang Xiao Quan' and 'Since 1628'. In the upper-middle left of the screen, an extra-large white Chinese Songti or high-contrast serif font is used, strictly divided into two lines: 'Trim your nails well,' and 'Touch wherever you want.' Below the title, a thin gold horizontal line is placed, and then small light off-white text is written: 'Sharp and durable · Exquisite trimming · Caring for every intimacy'. Four sets of low-key gold thin-line icons and two lines of functional text are arranged horizontally at the bottom of the screen: Group 1: 'Sharp blade' / 'Easy trimming' Group 2: 'Quality steel' / 'Lasting as new' Group 3: 'Comfortable feel' / 'Stable anti-slip' Group 4: 'Exquisite and portable' / 'Portable care' A gold thin-line circular badge is placed in the lower right corner, using larger gold Chinese characters inside, strictly in two lines: 'Century' / 'Craftsmanship'. Below the badge, it says: 'Started in 1628' / 'Focusing on knives and scissors, inheriting craftsmanship'. Use about a 50mm commercial portrait lens effect. The focus is on the silver nail clippers and the female's neatly trimmed fingers, while the character's face, the male's body, and the indoor background are slightly softened. Warm main light shines from the upper right, forming soft highlights on the skin, brown knit fabric, and metal edges of the nail clippers. The background maintains a dark brown gradient, without adding identifiable furniture or clutter.

Generate image
GPT Image 2
Cinematic 3D Animated Selfie Scene
View full prompt & copy

Use the uploaded reference photo of the girl ONLY as the identity and facial reference. Create a highly detailed, cinematic 3D animated selfie scene featuring the same young woman in the foreground, surrounded by four cute animated family characters. MAIN GIRL: Preserve the girl's recognizable facial identity from the reference photo, including her face shape, eyes, nose, lips, freckles, skin tone, and natural facial proportions. She has long flowing auburn/red hair extending down over her shoulders and chest. She is wearing a simple black long-sleeve top. POSE: The girl is holding the camera at arm's length, taking a close selfie. Her face is centered in the foreground with a natural gentle smile. Her arm extends toward the camera naturally, creating a realistic selfie perspective. FOUR ANIMATED CHARACTERS: Place four expressive 3D animated characters closely behind her: - A young boy on the left wearing a red shirt, with large expressive eyes and thick black eyebrows. - A young girl on the right wearing a bright yellow outfit, with large round eyes and curly orange hair styled into distinctive spiral curls. - An adult woman behind the girl on the left, with short curly brown hair and a pink top, looking surprised. - An adult man behind the girl on the right, with short curly dark hair, thick eyebrows, a blue shirt, and a surprised expression. All four characters should have a polished high-end 3D animated movie appearance, expressive faces, smooth stylized skin, detailed hair, and believable proportions. ENVIRONMENT: Set the scene inside a cozy traditional Japanese-style room with green tatami flooring, wooden framing, pale green walls, a low wooden table, a glass-front cabinet, pink sliding curtains on the left, framed artwork on the walls, a small fish painting, and a pink wall clock. CAMERA: Realistic handheld smartphone selfie perspective, close wide-angle framing. The main girl's face and upper body dominate the foreground while all four animated characters remain clearly visible behind her. LIGHTING: Warm, soft indoor lighting with realistic shadows and subtle highlights. Natural cinematic exposure with detailed textures. STYLE: Premium cinematic 3D animated film aesthetic, highly polished character rendering, realistic materials, detailed hair, expressive eyes, soft skin shading, believable lighting, clean composition, high-end animated movie quality. COMPOSITION: Match the overall composition and character arrangement of the reference scene: girl in the center foreground, red-shirt boy on the left, yellow-shirt girl on the right, adult woman behind left, adult man behind right. IMPORTANT: Keep the girl's identity consistent with the uploaded reference photo. Do not change her facial features. Do not change her hair color. Do not add the small reference-photo frame. Do not create a collage. Do not add

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.