Crowd / Group

Explore free Crowd / Group video 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.

1377 promptsDaily highlights
Seedance 2.5
View full prompt & copy

Use the uploaded reference image as the exact character reference. Preserve her facial identity, hairstyle, eye color, skin tone, makeup, body proportions, Style: Early-2000s MiniDV home-video aesthetic, photorealistic live-action, shaky handheld camera, slight autofocus hunting, natural exposure shifts, motion blur, imperfect framing, warm afternoon light, authentic everyday atmosphere. A young woman from Korea wearing a fitted crop pink pastel tshirt spends a casual afternoon with her boyfriend in a quiet neighborhood. She films herself walking down the street, smiling at the camera while her boyfriend walks beside her. They stop at a small street-food stall, share a snack, laugh together, and continue walking. She playfully steals his sunglasses and puts them on, making him laugh. They sit together on a low wall, talk and tease each other, then walk through a small park while she records little moments on the handheld camera. As the sun begins to set, they stop under a streetlight. She turns the camera toward him, they exchange a warm smile, move closer, and share a brief natural kiss on the lips. The camera stays handheld and slightly imperfect as they laugh afterward and walk away together. Audio: Natural street ambience, footsteps, distant traffic, birds, casual conversation and laughter. No music. Negative prompt: No subtitles, text, logos, watermarks, identity changes, outfit changes, duplicate people, distorted hands, unnatural movements, or AI artifacts.

Generate video
Seedance 2.5
View full prompt & copy

Shot 1 (0–1.2s): Character matching reference image, seated on a stopped train, feverish and sweating as red checkpoint lights sweep outside. Shot 2 (1.2–2.4s): Soldiers and officials board, inspecting passengers with flashlights while everyone watches nervously. Shot 3 (2.4–3.6s): Close-up of her trembling hand; veins darken beneath her skin as her breathing becomes shallow. Shot 4 (3.6–4.8s): Official checks documents and stops beside her, unaware of the danger. Shot 5 (4.8–6s): Her eyes cloud white and her head tilts unnaturally toward him. Shot 6 (6–7.2s): She suddenly bites his arm; extreme close-up, shocked reaction, cinematic slow motion. Shot 7 (7.2–8.4s): Passengers scream and retreat as the injured official stumbles into the aisle. Shot 8 (8.4–9.6s): His bite wound rapidly develops branching dark veins as the infection spreads. Shot 9 (9.6–10.8s): Soldiers outside notice the chaos through the windows and raise the alarm. Shot 10 (10.8–12s): The official convulses violently under flickering lights. Shot 11 (12–13s): His eyes snap open bloodshot and empty—the transformation complete. Shot 12 (13–14s): He attacks a nearby passenger, triggering mass panic inside the confined car. Shot 13 (14–15s): Passengers rush for the doors, but soldiers outside slam and lock them shut. Shot 14 (15–16.2s): Soldier seals the exterior lock as passengers pound desperately on the glass. Shot 15 (16.2–17.4s): Wide view: passengers realize they are trapped inside the sealed train car. Shot 16 (17.4–18.6s): A newly bitten passenger transforms within seconds and attacks others. Shot 17 (18.6–19.8s): Survivors retreat toward the back, trapped between sealed doors. Shot 18 (19.8–21s): A passenger grabs a fire extinguisher and braces against the approaching infected. Shot 19 (21–22.2s): He blasts them with white extinguisher spray, filling the car with fog. Shot 20 (22.2–23.4s): Soldiers watch silently from outside with weapons raised, unsure whether to intervene. Shot 21 (23.4–24.6s): Fully infected character presses against the sealed door glass while survivors corner themselves. Shot 22 (24.6–25.8s): Survivors barricade inside a restroom as pounding and screams echo outside. Shot 23 (25.8–27s): Wide shot of infected and survivors battling inside the sealed car beneath harsh checkpoint lights. Shot 24 (27–28.2s): Soldier radios for backup as the train rocks from the chaos within. Shot 25 (28.2–30s): Exterior wide shot: motionless train at the checkpoint, sealed doors, fogged windows and silhouettes struggling inside trapped-horror ending.

Generate video
Seedance 2.5
View full prompt & copy

Realistic cinematic lifestyle video featuring a young Korean couple in their early 20s spending a fun day together. The video should feel like a beautiful scene from a realistic romance movie, but still look completely natural and believable, with authentic human behavior, realistic environments and real-world physics. No artificial beauty filters, no exaggerated acting, no unrealistic poses, no AI-looking faces. Maintain perfect character consistency throughout the entire video. CHARACTERS Girl: A young Korean woman in her early 20s with a petite oval face, brown eyes, natural coral lips, realistic fair skin and long black hair. Boyfriend: A young Korean man in his early 20s with realistic features, natural hairstyle and casual stylish clothing. Both characters must remain completely consistent throughout the entire video with no face morphing, identity drift or duplicates. STORY — A DAY OUT WITH HER BOYFRIEND 0:00–0:04 — He Comes to Pick Her Up The girl walks out of her home looking excited. Outside, her boyfriend is waiting for her beside a large stylish motorcycle. The motorcycle looks realistic and naturally parked. She sees him and smiles warmly. He smiles back and hands her a helmet. She puts it on naturally before getting onto the motorcycle behind him. 0:04–0:08 — Motorcycle Ride They ride through beautiful city streets together on the motorcycle. The girl sits safely behind him wearing her helmet, enjoying the ride. Natural wind moves her hair slightly. Show realistic traffic, road movement and city surroundings. The moment should feel romantic and exciting like a scene from a movie, but completely believable. 0:08–0:12 — Arriving at the Mall They park the motorcycle outside a modern shopping mall and walk inside together. They naturally talk and laugh while walking side by side. The boyfriend occasionally looks at her while she excitedly looks around the shops. 0:12–0:17 — Shopping Together They visit different stores and enjoy shopping together. The girl looks at clothes and accessories while her boyfriend waits nearby and gives playful reactions. She holds up something she likes, and he smiles approvingly. They laugh naturally together. 0:17–0:22 — Eating Together They sit together at a casual restaurant or food court inside the mall. Their food arrives, and they enjoy eating while talking and laughing. Include natural small moments: sharing food, smiling at each other and spontaneous laughter. Make their relationship feel genuine and comfortable. 0:22–0:26 — Leaving the Mall They walk out of the mall together carrying small shopping bags. The atmosphere is relaxed and happy. They reach the motorcycle, put on their helmets and get ready to leave. 0:26–0:29 — Riding Her Back Home They ride through the city as the day begins turning into evening. The streets and lights look natural and realistic. The girl enjoys the peacefu

Generate video
Seedance 2.5
View full prompt & copy

@Image 1 defines <Kid>'s face and hair, a 12-year-old girl in a mustard-yellow oversized hoodie, jeans and sneakers. @Image 2 defines <Dad>'s face, curly dark hair, green bathrobe over grey sweatshirt, red-and-black flannel pajama pants, white socks and slide sandals. FORMAT: 15 seconds / 9 cuts / action comedy, Hollywood fight with a deadpan punchline / no dialogue, no music. ENVIRONMENT: a sunny American city sidewalk in late afternoon, brick storefronts, parked cars, an ice cream cart with a striped umbrella further down the block, warm golden side light, long shadows. STYLE: ultra-realistic live-action feature film, anamorphic 40mm lens, shallow depth of field, crisp motion, natural skin and fabric texture, fine film grain, punchy contrast. Fast professional editing with whip pans and speed ramps. Aspect ratio 16:9. AUDIO: no dialogue, no music. Street ambience, distant traffic, sneakers and sandals on concrete, fabric rustle, heavy hits, breathing. Only two tagged sounds. TIMELINE: 0:00–0:04: Tracking shot from the front, low, gliding backward. <Dad> and <Kid> walk side by side down the sidewalk, she happily licking a tall vanilla soft-serve cone, he sipping a coffee, both relaxed, no words. 0:04–0:05: Three tattooed gangsters in black hoodies and gold chains step out of a doorway and cut across their path; the lead one shoulder-bumps <Kid>, the cone drops. Quick cut to an extreme close-up, low angle: the ice cream hits the pavement <wet splat>. <Kid>'s smile falls. 0:05–0:07: Slow push-in on <Dad>'s face. His eyes go from the melting cone up to the gangsters. His jaw sets, he hands <Kid> the coffee without looking at her and gently guides her one step behind him. Speed ramp: his bathrobe belt swings as he steps forward. 0:07–0:13: Rapid cuts, six shots. Whip pan: the lead gangster swings, <Dad> slips it and drives a straight right into his jaw <heavy crack>, the gangster's sunglasses fly. Cut: second gangster grabs the robe, <Dad> spins out of it like a matador, the empty robe lands on his face, elbow to the ribs, he folds. Cut: <Dad> catches the third one's wrist and slams him against a parked car, the alarm chirps. Cut: wide, all three stagger back into a heap against the storefront. Cut: <Dad> picks his robe up off the ground, shakes it once, pulls it back on. <Kid> stands safely by the wall the whole time, watching, coffee in hand, never in the fight. 0:13–0:15: Hard cut. Wide static shot at the ice cream cart. The three bruised gangsters stand in a neat line at the counter, one holding an ice pack to his jaw, <Dad> beside them in his robe. The gangster at the front turns and, with a sheepish nod, holds out a fresh, oversized vanilla cone with sprinkles to <Kid>.

Generate video
Seedance 2.5
View full prompt & copy

Create a 15-second ultra-realistic cinematic video of exactly two adult Korean best friends on a spontaneous midnight road trip through South Korea. Start with a rainy neon-lit city street, then show them getting into a stylish modern car, laughing, playing music, and driving through glowing streets before transitioning to a coastal highway at night. Capture playful moments inside the car, including singing and joking, then have them stop at an ocean viewpoint, take selfies, laugh, high-five, and finally stand together overlooking the ocean as the car headlights glow behind them. Use fast-paced cinematic cuts, authentic handheld footage, dashboard and exterior tracking shots, realistic nighttime lighting, wet reflections, natural skin, hair, clothing, expressions, motion blur, and subtle film grain. Maintain perfect character and visual continuity throughout—identical faces, hairstyles, outfits, body proportions, accessories, car, and identity, with no distortions, duplicated people, warped hands, flickering, or CGI appearance.

Generate video
Seedance 2.5
View full prompt & copy

30-SECOND CINEMATIC K-DRAMA SHORT — INTERACTIVE STORYTELLING Create a cinematic 30-second Korean drama-style short film. Focus entirely on the final video and storytelling — do not show any AI generation interface, prompts, workflow, or creation process. Story: A young Korean woman is sitting alone in a quiet upscale café at night, looking at her phone. She suddenly receives a mysterious message: “If you could change one moment from tonight… would you?” She looks up, confused. Across the café, a handsome young Korean man is standing near the window, watching her. Their eyes meet. He slowly walks toward her. He sits across from her and says softly: “You already made your choice.” She looks shocked and asks: “Who are you?” Suddenly, the café lights flicker. The environment briefly changes — the same café, but completely empty and darker. The man smiles and says: “Now you decide what happens next.” End with a dramatic close-up of the woman looking directly toward the camera, as if the audience must make the next decision. Visual Style: - Premium K-drama aesthetic - Cinematic Korean romance/mystery - Photorealistic Korean actors - Natural facial expressions and subtle emotions - Beautiful soft cinematic lighting - Shallow depth of field - Elegant upscale café location - Realistic skin texture - Smooth camera movement - Close-ups and medium shots - Atmospheric night lighting - Subtle suspense and emotional tension - High-end Netflix-style cinematography - Natural Korean drama color grading - Realistic body movement and eye contact 30-Second Structure: 0–5s: Woman alone in café, receives mysterious message. Strong visual hook. 5–10s: She looks around and notices the mysterious man. 10–16s: He approaches and sits across from her. 16–22s: Emotional dialogue: “Who are you?” — “You already made your choice.” 22–27s: Lights flicker and the café transforms into an empty, mysterious version. 27–30s: Man says, “Now you decide what happens next.” Cut to woman's intense close-up. Important: Make the video feel like the opening scene of an interactive K-drama series. Keep the pacing fast but cinematic, with strong visual storytelling and emotional tension. The audience should feel that their choice will determine what happens in the next episode.

Generate video
Seedance 2.5
View full prompt & copy

15s, 16:9 cinematic sci-fi action. [Image1] locks Alin: platinum-blonde hair, white corset top, blue jeans, brown boots. [Image2] locks zombie king Ston: long black hair, skeletal grey-brown skin, torn black clothes, pendant. 0–8.6s: rain-soaked cold grey-blue virtual rooftop. Fast, heavy close combat: Ston attacks; Alin blocks, elbows, knees, slips on wet ground, recovers, and fights back. Physical impacts, momentum, splashing puddles, no gore. Finally Ston’s fist rushes to Alin’s nose in extreme close-up; her eyes widen, breath stops, hands rise defensively. 8.6–9.5s: seamless match transition—Ston’s fist fills frame and becomes a black VR headset with a thin blue LED; rooftop collapses into a warm bedroom. 9.5–15s: Alin violently removes the headset, gasping, scans the messy amber-lit bedroom, presses her chest, then slowly settles back as the camera gently pulls away. Camera: rapid handheld action cuts, low-angle 24mm rooftop; 85mm fist close-up; stable 50mm warm bedroom pullback. Color: desaturated cyan-grey shadows and wet contrast in VR; 3200K amber practical light, warm skin, soft brown shadows in reality. Sound: wind, rain, impacts, low electronic pulse; then muffled transition, breathing, headset plastic, quiet room tone. No blood, injuries, extra characters, face drift, body distortion, broken hands, costume changes, UI, subtitles, watermark.

Generate video
Seedance 2.5
View full prompt & copy

Main Subjects: Young Spanish man, 22, messy dark hair, orange T-shirt, loose cargo pants, worn skate shoes. His female friend, 21, long brown hair tied back, light blue hoodie, faded jeans, trying to learn skateboarding. Location: Quiet residential plaza in Zaragoza, Spain, around 2004. Open concrete pavement, low steps, apartment buildings, parked scooters, benches, small trees and ordinary families passing by. No tourist landmarks. Visual Style: Ultra-realistic early-2000s MiniDV home video. Candid, playful and slightly chaotic, like footage recorded by a close friend. Camera Style: Consumer MiniDV camcorder, shaky handheld movement, imperfect framing, sudden pans, accidental zooms, autofocus hunting, exposure pumping, faded colors, soft contrast, motion blur, digital compression, slight sensor noise, no stabilization. Timeline — 15 Seconds: 00:00–00:03 — The man places the skateboard on the ground and demonstrates how to stand on it. 00:03–00:06 — His friend carefully steps onto the board while holding his arm for balance. 00:06–00:09 — She rolls forward for a second, loses balance and jumps off. Everyone laughs. 00:09–00:12 — She tries again, this time successfully rolling across the plaza. 00:12–00:15 — She celebrates with both arms raised while her friend cheers. The camera shakes from laughing. Audio: Skateboard wheels rolling, footsteps, Spanish conversation, laughter, distant scooters, children playing, birds and neighborhood traffic. No music, no narration. Goal: Make it feel like a forgotten Spanish MiniDV recording from 2004–a simple afternoon with friends captured accidentally and remembered forever.

Generate video
Seedance 2.5
View full prompt & copy

Photorealistic cinematic 15-second historical-fantasy action film of two adult male warriors engaged in a sword duel on the soaked deck of a large wooden sailing ship during a violent nighttime ocean storm. Massive waves violently rock the ship as rain falls diagonally through powerful winds. One warrior wears weathered dark leather armor and a soaked cloak, wielding a steel longsword. The second wears dark metal armor with a wet brown cloak and carries a shorter sword. Keep both warriors, weapons, clothing, and proportions completely consistent throughout. The duel begins with both fighters struggling to maintain balance as the ship tilts. They charge and exchange powerful sword strikes, with realistic blade impacts, recoil, footwork, slips, and recoveries. A hanging rope swings violently as the ship pitches, while barrels and loose debris slide naturally across the wet deck. A huge wave crashes over the side, sweeping water across the deck and forcing both warriors sideways. One drops to a knee while the other uses his sword against the deck for temporary support. They recover and charge at each other for one final clash beneath a flash of lightning. End with their blades locking as the ship rises on a massive wave, followed by a dramatic backward camera pull revealing the storm, ship, and enormous wave behind them. Cut to black on a thunderclap. Ultra-photorealistic live-action, cinematic 4K, grounded movie realism, realistic human biomechanics, physically accurate gravity, momentum, friction, sword collision, ship movement, water dynamics, rope physics, wind, rain, and balance. Dynamic handheld cinematography, realistic motion blur, natural depth of field, practical-looking effects, authentic storm lighting, immersive sound design. No CGI appearance, no superhero physics, no impossible sword movements, no floating objects, no teleportation, no distorted anatomy, no duplicated characters, no static posing, no unrealistic water or waves, no excessive slow motion, no modern clothing, no text, subtitles, logos, watermark, blood, or gore.

Generate video
Seedance 2.5
View full prompt & copy

Couple Exploring a Colorful Mural AlleywayUse the uploaded reference image as the exact character reference. Preserve her facial identity, hairstyle, eye color, skin tone, makeup, and body proportions Style Early-2000s MiniDV home-video aesthetic, photorealistic live-action, with handheld shaky camera, slight autofocus hunting, natural exposure shifts, motion blur, imperfect framing, and warm afternoon light creating an authentic everyday atmosphere.Scene Description: A young Korean woman in a fitted pastel T-shirt and casual jeans walks with her boyfriend through a vibrant alleyway covered in colorful street art murals. She films herself walking backward toward the camera with a bright smile, while her boyfriend walks beside her, enjoying the lively surroundings.They stop in front of a large, eye-catching mural. She playfully steals his baseball cap, puts it on, and strikes a pose, making him laugh. He then grabs her hand, and they take several selfies together against the colorful wall, capturing their candid they continue walking, the camera captures close-up shots of the detailed artwork and their playful interactions — gentle teasing, shared smiles, and casual touches. The handheld camera’s slight shakiness and imperfect framing add to the nostalgic home-video feel.They pause near a small bench. Sitting down, they talk quietly, exchanging smiles and playful glances. The warm afternoon sunlight filters through nearby trees, casting soft light and natural shadows.The scene ends with them walking away hand-in-hand, the camera capturing their backs as they disappear into the alleyway’s colorful embrace Audio: Natural street ambience with distant traffic sounds, occasional footsteps echoing in the alley, casual conversation, and laughter. No music or added sound effects.Negative prompt: No subtitles, text, logos, watermarks, identity or outfit changes, duplicate people, distorted hands, unnatural movements, or AI artifacts.

Generate video
Seedance 2.0
View full prompt & copy

Cinematic realistic scene inside a modern school restroom, three teenage girls wearing matching gray school blazers, white shirts, plaid skirts, and white sneakers. One girl sits on the countertop near the sinks while another stands in front of her with an intense hand gesture, and a third girl reacts dramatically in the background. Water splashes against the large mirror, creating a chaotic and tense atmosphere. Cool fluorescent bathroom lighting, realistic reflections, detailed facial expressions, natural body movement, cinematic composition, shallow depth of field, handheld camera feel, high-detail photorealism, dramatic color grading, 4K, vertical.

Generate video
Seedance 2.5
View full prompt & copy

Photorealistic cinematic Korean romance film set on a university campus during peak cherry-blossom season. Two longtime friends walk together beneath blooming cherry trees in the warm late-afternoon light. They talk casually before the woman gradually becomes nervous and slows down. She finally stops, takes a breath, and softly confesses that she has liked him for a long time. The man is genuinely surprised, pausing to process her words rather than reacting dramatically. She admits she was afraid he might stop being her friend. After a quiet emotional pause, he smiles warmly and reassures her. He gently takes her hand, and they continue walking together beneath the cherry trees as petals drift naturally around them. Natural Korean actors, subtle facial expressions, realistic walking and body language, soft spring breeze, authentic university atmosphere, cinematic depth of field, realistic skin and clothing, natural lighting, gentle handheld camera movement, emotional Korean-drama aesthetic, soft piano soundtrack, realistic environmental sound.

Generate video
Seedance 2.5
View full prompt & copy

Main Subjects: Young German man, 24, short messy dark-blond hair, light stubble, gray T-shirt, faded blue jeans, worn sneakers. His female friend, 23, shoulder-length brown hair, simple green sweater, black trousers, carrying a small cardboard box. Location: A modest apartment building in Berlin, Germany, around 2004. Narrow stairwell with beige walls, old wooden handrails, mailboxes near the entrance, bicycles parked downstairs. Inside the small empty apartment: wooden floor, plain white walls, second-hand furniture, stacked cardboard boxes, old kitchen cabinets, large windows overlooking ordinary residential buildings. Visual Style: Ultra-realistic early-2000s family home video. Authentic documentary feeling, imperfect and spontaneous. No cinematic polish, no modern aesthetics. Camera Style: Consumer MiniDV camcorder, heavy handheld movement, uneven framing, accidental zooms, autofocus hunting, exposure pumping, faded colors, soft contrast, slight motion blur, digital compression, sensor noise, occasional overexposure, no stabilization. Timeline — 15 Seconds: 00:00–00:03 — Camera follows them struggling up the stairs with cardboard boxes. One box nearly slips, causing everyone to laugh. 00:03–00:06 — They enter the empty apartment. The camera quickly pans around the room while the friend drops a box on the floor. 00:06–00:09 — They assemble a cheap second-hand chair. One part doesn't fit, and they stare at it confused before laughing. 00:09–00:12 — The man finally gets the chair together and proudly sits down. It makes a loud squeak. 00:12–00:15 — Both laugh while the camera shakes wildly. The man looks directly into the lens and says something casually in German. Audio: Cardboard scraping, footsteps on stairs, keys jingling, furniture sounds, German conversation, laughter, distant traffic, hallway echoes, birds outside. No music, no narration. Goal: Make it feel like a forgotten MiniDV recording from a German friend's first apartment move in 2004–awkward, funny, ordinary, intimate, and genuinely nostalgic.

Generate video
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 video prompt categories organized?
Video prompts are grouped into use cases, styles, and subjects. Use cases cover the production goal, styles cover motion or rendering language, and subjects describe the main scene or entity.
How are prompts assigned to categories?
YouMind uses AI to analyze each video 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.