Architecture / Interior

Explore free Architecture / Interior 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.

1426 promptsDaily highlights
Seedance 2.5
View full prompt & copy

Create a 15-second ultra-realistic cinematic travel film, 16:9 vertical, 4K HDR, photorealistic live-action, premium Chinese travel-commercial quality A young couple explores a breathtaking ancient Chinese mountain town built along steep hillsides. Traditional wooden buildings with dark tiled roofs, narrow stone stairways, red lanterns, mist-covered mountains and a deep valley surround them. Authentic Chinese architecture and natural environmental details. No fantasy appearance. 0–3s: Wide establishing shot from behind the couple as they walk slowly up an ancient stone staircase. Hundreds of traditional houses rise dramatically along the mountain behind them. Warm lanterns glow between the buildings while soft morning mist moves through the valley. 3–6s: Camera smoothly follows the couple from a closer angle. They walk naturally side by side, looking around with genuine curiosity. The woman briefly points toward a beautiful hillside temple while the man looks up at the architecture. Natural walking, subtle gestures and realistic clothing movement. 6–10s: They reach a small traditional wooden balcony overlooking the enormous mountain valley. Camera moves around them in a smooth cinematic arc, revealing layers of ancient rooftops disappearing into mist-covered mountains. A few birds fly naturally through the distant valley. 10–13s: The couple continues along a narrow lantern-lined street. Warm light reflects on the slightly wet stone pavement. They pass small traditional shops and wooden houses while distant mountains remain visible between the buildings. 13–15s: Camera rises smoothly above the couple, revealing the entire ancient mountain town cascading down the hillside, glowing lanterns scattered throughout the architecture and enormous misty mountains surrounding the town. End on a breathtaking cinematic aerial reveal. STYLE: Ultra-realistic travel documentary, authentic Chinese mountain-town architecture, realistic human movement, natural facial expressions, physically accurate cloth and hair movement, atmospheric mountain mist, realistic stone and wood textures, cinematic depth of field, natural lighting, subtle film grain, smooth gimbal movement, premium tourism commercial, 4K HDR. CAMERA: One continuous logical camera movement, smooth tracking, gentle orbit, gradual aerial rise, realistic perspective, natural motion blur, no teleportation, no sudden scene changes. NEGATIVE: cartoon, anime, CGI look, fake architecture, distorted buildings, warped stairs, duplicate people, unnatural walking, floating objects, excessive fog, oversaturated colors, flickering, camera jumps, blurry faces, text, subtitles, logos, watermark.

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

SCENE: Tatami edge at night, 16:9. Locked close-up on a small ceramic incense burner. A single stick stands. No face. No readable writing on the ceramic. ACTION: One thin thread of smoke rises, wavers once, and thins. The stick glows at the tip only. No second stick. No hand entering. FOCUS: Tack-sharp on the ember tip and the first ten centimeters of smoke. Background fusuma is one stop soft. PHYSICS: Smoke is light and continuous. It does not become a fog wall. It does not pool like liquid. No CGI ribbon. LIGHT: The ember is the only warm point. Cool room around it. No beauty key. STYLE: Photoreal cinematic, period Japan, ceramic glaze and ash texture, soft grain. No anime. No text. No watermark. No logos.

Generate video
Seedance 2.5
View full prompt & copy

Create a 30-second ultra-realistic continuous action sequence featuring a female warrior escaping across a collapsing high-altitude bridge while a colossal stone hand, still connected to a giant disappearing into the clouds, repeatedly crashes downward. The warrior has shoulder-length hair blowing backward in the wind and wears a dark, fitted tactical suit with worn metal elements, water stains, dust, and scratches. A dual mechanical grappling-hook system is mounted on her back. The hooks activate only after she loses support or begins falling and must physically latch onto solid surfaces before generating tension. The bridge is wet, cracked, heavily damaged, and suspended above a fog-filled abyss, with exposed rebar, hanging cables, and scattered debris. Use ultra-realistic materials, natural physics, cool gray-blue tones, overcast lighting, atmospheric depth, 35mm cinematic photography, subtle handheld movement, realistic motion blur, and natural depth of field. ACTION FLOW 0–5s: She slides rapidly across the wet bridge as the surface cracks beneath her. The giant's enormous hand descends through the clouds above, casting a growing shadow. 5–9s: The bridge collapses. She falls, then fires her grappling hook only after losing support, catching a hanging steel cable and swinging sideways. 9–14s: She releases the cable, lands briefly on a falling concrete fragment, and uses the impact and reaction force to redirect herself upward. 14–19s: The giant's hand violently slams into the bridge. She narrowly escapes beneath it as concrete, rebar, water mist, and debris explode outward. 19–24s: The shockwave throws her onto the rough stone hand. She slides, fires her hook into a crack, and uses the cable tension to redirect toward the palm. 24–27s: She accelerates across the palm and leaps toward its center. 27–30s: The hand crashes down again, blasting her back toward the remaining bridge. She lands into another slide as the bridge begins cracking in the exact same configuration as the opening shot, creating a seamless loop. No weightless movement, impossible grappling, teleportation, artificial glow, or clean CG appearance. Every movement must show believable weight, momentum, friction, acceleration, and impact.

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
Seedance 2.5
View full prompt & copy

Create a 15-second cinematic cozy lifestyle video of a young woman spending a peaceful afternoon at a charming café. Use the provided facial reference to maintain her exact identity, facial structure, skin tone, hair, and overall appearance throughout the entire video. Her face should remain naturally hidden or partially obscured in every shot by her hair, camera angle, or framing, while still using the reference for accurate character consistency. Character & outfit: She wears a soft white feminine top, light blue relaxed-fit jeans, a pink gingham shirt casually tied over one shoulder, a delicate heart necklace, and carries a cream canvas tote bag. Keep the outfit, accessories, hairstyle, and character completely consistent. 0–3 sec — Arriving at the café: Show her walking toward a small, charming café surrounded by greenery. Capture her from behind and from the side as she approaches the glass entrance, gently holding her tote bag. Warm afternoon sunlight creates a soft, peaceful atmosphere. 3–6 sec — Entering: She opens the café door and walks inside. Reveal a cozy interior with warm cream walls, wooden tables, vintage-style shelves filled with cups, soft wall lamps, a small bakery counter, and a cute checkerboard tile detail. Camera follows her naturally from behind, keeping her face hidden. 6–9 sec — Exploring the café: She slowly looks around the café, browsing the menu and pastry display. Show close-up details of her hand holding the tote strap, her pink gingham shirt, coffee cups on shelves, handwritten menu boards, and warm ambient lighting. 9–12 sec — Coffee moment: She sits at a small wooden table beside a window overlooking lush greenery. A freshly prepared latte is placed in front of her with beautiful heart-shaped latte art. She gently picks up the cup and enjoys the cozy moment, with her face still outside the frame or covered by her hair. 12–15 sec — Peaceful ending: Camera moves into a top-down shot of the latte on the table, her hands resting beside the cup and the cream tote bag nearby. She takes a slow sip, then the camera gently pulls back to reveal the warm café atmosphere. Visual style: cozy café aesthetic, warm natural sunlight, soft golden tones, realistic textures, subtle film grain, shallow depth of field, gentle handheld camera movement, candid lifestyle photography, peaceful weekend mood, natural human movements, cinematic realism. Important: Maintain one identical character throughout. Do not change her facial features, hairstyle, body proportions, clothing, necklace, or tote bag. Her face should never be clearly revealed, but the facial reference must still be used to preserve her identity. Vertical 9:16, 15 seconds, realistic cinematic video, smooth transitions, no text, no subtitles,

Generate video
Seedance 2.5
View full prompt & copy

Create a 30-second, 1080p ultra-realistic documentary-style personal home video showing an ordinary summer day in the life of a young Korean grey-hat security researcher living alone in Seoul. The footage should feel spontaneous, intimate, imperfect, slightly secretive, and genuinely observed rather than performed. Nothing should feel like a movie hacker scene. No glowing green code walls, no dramatic cyberpunk lighting, no masks, no hoodies pulled over the face, no exaggerated typing, no floating holograms, no fake “ACCESS GRANTED” interfaces, no police raids, no guns, no explosions. The subject should simply feel like an intelligent, obsessive young man whose daily life quietly revolves around computers, security research, curiosity, and ethically ambiguous boundaries. MAIN SUBJECT: The same young Korean man in his early 20s throughout the entire video. Naturally handsome but ordinary-looking, realistic skin texture, slightly tired eyes, calm expression, subtle dark circles from poor sleep, naturally messy medium-length black hair falling loosely over his forehead, very light stubble. He wears a loose faded charcoal T-shirt, relaxed dark olive trousers, worn white socks or sneakers depending on the scene, and a simple silver wristwatch. No stereotypical hacker clothing. Keep his face, identity, body proportions, hairstyle, clothing, watch, posture, and overall appearance completely consistent from beginning to end. His personality should feel quiet, observant, slightly introverted, dryly amused, highly focused, and emotionally understated. HOME / LOCATION: A small older studio apartment in a quiet residential neighborhood of Seoul. The apartment should feel lived-in rather than designed. Small desk pushed against a wall, two mismatched computer monitors, mechanical keyboard, wired mouse, old laptop, cheap desk lamp, notebooks with handwritten diagrams, USB drives, tangled charging cables, router, half-finished canned coffee, empty instant noodle cup, small desk fan, external hard drives, phone charger, laundry drying indoors, books stacked unevenly, curtains moving slightly from an open window. Outside the apartment: narrow Seoul residential alleys, concrete walls, utility poles, rooftop water tanks, parked scooters, bicycles, small staircases, neighborhood convenience stores, apartment entrances, delivery boxes, summer trees, overhead wires, distant traffic. No recognizable companies, no real website names, no real credentials, no identifiable private information, no real hacking targets. Any computer interfaces should look believable but fictional and non-instructional. CAMERA / VISUAL STYLE: Authentic casual personal-video footage captured with an older consumer digital camera. Handheld camera operated by a friend spending the day with him. Natural camera shake. Imperfect framing. Occasional autofocus hunting. Slight exposure changes when moving between the dark apartment and bright outdoor sunlight. Soft detail. Mild motion blur. Subtle digital noise. Slightly muted colors. Imperfect white balance. Natural compression artifacts. Occasionally the camera reacts too late, catches only part of an action, briefly focuses on the wrong object, or accidentally frames empty space. No stabilization. No gimbal. No drone shots. No cinematic push-ins. No dramatic shallow depth of field. No commercial color grading. No stylized cyberpunk lighting. No impossible screen reflections. No polished cinematography. The footage should feel like someone simply followed their friend around for one ordinary day. 00:00–00:05 — LATE MORNING / WAKING UP: He is asleep sideways on his bed in the small apartment while sunlight leaks through thin curtains. A laptop remains open on the desk from the previous night. Its screen shows an ordinary dark terminal window with harmless scrolling system logs and diagnostic text. A desk fan rotates slowly. His phone vibrates on the floor. He wakes up, reaches down sleepily, checks the phone, squints at the screen, then sits on the edge of the bed for several seconds. He runs one hand through his messy hair. The camera operator is already inside the apartment. He notices the camera, looks mildly annoyed for half a second, then gives a tired little smile. The autofocus briefly locks onto the laptop instead of his face before correcting. Natural morning room sound only. 00:05–00:10 — FIRST CHECK OF THE DAY: He sits at the desk barefoot with one knee raised slightly under the chair. One monitor displays a fictional vulnerability-reporting dashboard. The other shows terminal windows, log files, documentation, network diagrams, and harmless test-environment data. He slowly scrolls through a page while drinking canned coffee. He types naturally, pauses often, rereads something, leans closer to the screen, then quietly says something under his breath that cannot clearly be heard. Avoid exaggerated typing speed. Avoid showing real exploit commands, credentials, malware, or actionable hacking instructions. The camera stands slightly behind his shoulder, occasionally drifting out of focus because the bright monitor confuses the autofocus. He notices something interesting. His posture changes slightly. He stops drinking. His expression becomes focused. No dramatic reaction. 00:10–00:14 — SOMETHING DOESN'T LOOK RIGHT: He opens several fictional system logs and compares them across both monitors. He writes a few words into a paper notebook beside the keyboard. The notebook contains rough arrows, boxes, timestamps, fictional IP ranges, question marks, and incomplete handwritten notes. Nothing should be readable enough to function as real instructions. He tests something only inside a clearly isolated local lab or sandbox environment. A small progress indicator finishes. He leans back. A tiny smile appears. Not triumph. More like: “I found something strange.” He glances toward the camera. The friend holding the camera quietly laughs. He shakes his head and turns back toward the computer. 00:14–00:18 — LEAVING THE APARTMENT: He closes the laptop, leaves the desktop running, slips on his sneakers, grabs his phone, and walks downstairs. The camera follows him through an older apartment stairwell. Bright summer sunlight causes the camera exposure to blow out temporarily when they step outside. He walks through a narrow neighborhood alley. Hands in pockets. Quiet. He buys a cold bottled drink from a tiny convenience store or vending machine. No identifiable branding. He stands outside drinking it while checking something on his phone. For a moment, he looks completely ordinary. An elderly neighbor walks past. A bicycle passes in the distance. Cicadas are loud. He pockets the phone and continues walking. 00:18–00:22 — PUBLIC WIFI / SECOND THOUGHTS: He sits alone at an outdoor concrete table beneath a shaded residential structure or small neighborhood rest area. His laptop is open. He connects through his own portable hotspot or clearly controlled test connection. The screen shows fictional security research notes and a draft report. He appears to be deciding whether to send something. His finger hovers over the trackpad. He stops. Reads the screen again. Deletes one sentence. Rewrites it. The feeling should subtly suggest that his work sometimes exists in an ethical gray area without showing any illegal action. He finally closes the laptop without sending anything. He looks across the street for several seconds. A small breeze moves his hair. The camera remains quiet. 00:22–00:26 — BACK HOME / DISCLOSURE: Early evening. He is back at the desk. The room is darker now. Only the weak desk lamp, monitor glow, and orange sunlight from the window illuminate the apartment. He opens the fictional report again. The document contains a neutral vulnerability summary with sections resembling: “Summary,” “Observed behavior,” “Impact,” “Re

Generate video
Seedance 2.5
View full prompt & copy

Hero = a rugged battle-hardened man around 35, weathered face, dark stubble, a brow cut, a dirty white tank-top vest, worn dark trousers and boots, dirt and grime. Fierce, exhausted, unbroken. Appearance only. Gang1 = a squad of rugged cartel henchmen in dirty casual clothes, unshaven and mean, armed with machetes. Appearance only. Gang2 = cartel enforcers in dark tailored suits, disciplined and armed with blades. Appearance only. Boss = a cartel boss around 45, sharp cold face, slicked-back greying hair, a trimmed beard, an immaculate white suit with a dark shirt. Powerful and menacing. Appearance only. Building = a rundown abandoned cartel hideout at dusk — a grimy derelict concrete building, a battered entrance door, a dim gritty ground floor with peeling walls, bare bulbs, debris and a staircase at the back, and a moody upper floor with tall grimy windows and shafts of dim light. Desaturated gritty grey-brown palette. Environment only. SCENE: a gritty one-man-army action sequence. A rugged exhausted man in a dirty white vest kicks in the door of an abandoned cartel hideout and fights his way through a machete-armed gang on the ground floor, then climbs to the upper floor where suited enforcers and their white-suited boss wait. He takes down the enforcers and defeats the boss in a final duel, standing victorious. Intense, raw, cinematic martial-arts action. TECHNICAL: 16:9, cinematic gritty desaturated grey action grade, dynamic handheld fight camera, low moody light, dust and haze, fine film grain, photorealistic raw action quality. CUTS: CUT 1 (0-5s): The man walks up to the grimy building at dusk, shouts "Come out!", and kicks the door in — storming into the dim ground floor where machete-armed henchmen ready their weapons. CUT 2 (5-12s): The fight erupts — brutal fast hand-to-hand combat, he dodges machete swings, disarms and takes down the whole squad one by one across the gritty room, using pillars and furniture. Dynamic changing angles. CUT 3 (12-17s): The room cleared, he strides to the staircase and climbs to the upper floor — where a squad of suited enforcers and the white-suited boss behind them are waiting. A tense standoff. CUT 4 (17-24s): The enforcers attack; he fights them down in fast fierce combat until only the boss remains. The two face off across the light-shafted room, breathing hard. CUT 5 (24-30s): The final duel — hero and boss clash in an intense one-on-one, trading heavy blows, until the hero lands a decisive final blow and the boss drops to the floor, beaten. The hero stands over him, victorious, in a shaft of dim light. Epic final hero frame. END. RULES: References are appearance only, do not recreate. Keep the hero's face and white vest, and the boss's white suit, consistent acro

Generate video
Seedance 2.0
View full prompt & copy

(1998 Tim and Eric Infomercial Aesthetic) (Medium: SD BetaSP Broadcast Camera) [SCENE START] INT/EXT. SUBURBAN HOUSE AND STREET - DAY Camera: Handheld tracking, quick snap zooms, low-resolution NTSC color bleed, harsh video lighting Lighting: Flat bright studio fills mixed with harsh overhead sunlight, slight chromatic aberration SUBJECT: @steve: oversized vintage ugly plaid suit jacket, holding slim black folding smartphone, deadpan face. Crowd: Suburban neighbor walking dog outside. ACTION: [Time 00:00-00:02]: @seeksteve pulls black brick phone from pocket, unfolding screen twice, VO: 'They folded twice.' Third panel keeps expanding infinitely across kitchen counter with rapid hinge clicks. When screens unfold they always remain together and there’s are never gaps between them. [Time 00:02-00:08]: @seeksteve walks as screen accordion expands endlessly through dining table crushing it as we witness splintering wood snapping the table in half, smashes through sliding glass door with realistic glass-shattering physics as the door shatters the wall starts falling apart with drywall caving in and dust building causing absolute mayhem, deploying like black glass carpet onto driveway with rapid machine gun clicks, VO: 'We kept going. Galaxy Hundredfold. Phone. Tablet. Driveway.' [Time 00:08-00:12]: High angle shot shows @seeksteve standing at end of black glass runway stretching down street, glass phone runway stretches all the way to house in house in background, car swerves to avoid the glass phone runway but drives into house, house was already crumbling but it now falls down completely, VO: 'Know when to hold em, know when to fold em… Unlimited.' Smash cut to product title text Samsung Galaxy Hundredfold, placed over scene depicting firefighters arriving to the scene, black gradient slightly blurred so product text remains focus. ATMOSPHERE: The vibe is deadpan and surreal and destructive. Absurdly commercial tone with @seeksteve maintaining serious product presenter energy throughout extreme physical impossibility and destruction. [STYLE MODIFIERS] Reference: Tim and Eric Awesome Show, VHS Tape, Commercial B-Roll, Disaster Footage Audio implication: Deadpan male voiceover, rapid mechanical hinge clicking, wood table splintering, glass shattering, wall crumbling, muffled car honk, screeching car tires, impact of vehicle with house, dead silence at end

Generate video
Seedance 2.5
View full prompt & copy

A cinematic 15-second monochrome lifestyle video featuring a young Asian woman [use reference imaeg] in an oversized white shirt and oversized trousers, moving naturally through a modern house and garden. • Scene 1 (0–3s): She wakes up and sits on the edge of the bed, sunlight softly falling across her face as she looks toward the window. • Scene 2 (3–6s): In front of a mirror, she casually fixes her messy hair, smiling subtly at her reflection. • Scene 3 (6–9s): She walks barefoot through the kitchen, playfully spinning a mug in her hand before taking a sip. • Scene 4 (9–12s): Outside, she walks through the garden while gently touching the leaves and flowers along the path. • Scene 5 (12–15s): She sits beside the swimming pool with her feet in the water, looking peacefully toward the camera as the scene fades out. Cinematic black-and-white photography, soft natural lighting, subtle film grain, realistic skin texture, candid expressions, intimate framing, gentle handheld camera movement, smooth transitions, editorial fashion-film aesthetic, minimal and elegant atmosphere.

Generate video
Seedance 2.0
View full prompt & copy

Create a vlog-style home video of a quiet and cool high school library committee girl after school, filmed by her friend on the same committee. 480p. Composed of a montage of short shots (approx. 2 seconds each) with hard cuts. Each shot is a different moment, 1 shot = 1 small event. No transitions or fades. Since it is filmed by a fellow committee friend, she is slightly relaxed and shows her true expression at the end. [Main Subject] Same Japanese high school girl throughout. Cool beauty. Slanted eyes, long eyelashes, thin well-groomed eyebrows, realistic white skin texture, no makeup, sharp nose, thin lips, sharp jawline. Quiet eyes behind silver-rimmed glasses. Straight black shoulder-length hair. White short-sleeved shirt, navy pleated skirt, indoor shoes. Quiet and expressionless. Face, body, hairstyle, glasses, and uniform are completely consistent. [Location] Summer school library after hours. Rows of tall bookshelves, checkout counter, window seats with western sun, picture book corner. No ads or brands. [Camera] Handheld old household digital camera. Natural shaking, imperfect framing, focus hunting, exposure fluctuations from the sun, light motion blur, subtle noise, suppressed colors. No gimbals, drones, slow motion, or cinematic lighting. [Shot List] 1. Walking between shelves with books, notices camera, finger to lips. 2. Reaching for high shelf, fails, goes for stool. 3. Stamping books at counter, rhythmic hands. 4. Profile reading by window. 5. Opening a book in empty corner. [Physics] Realistic physics. [Audio] Ambient library sounds only. [Atmosphere] A record of a quiet girl's unseen habits. Warm and deeply human.

Generate video
Seedance 2.5
View full prompt & copy

[10-second manual pencil sketch drawing time-lapse] In professional digital drawing software, starting from a completely blank cream-white paper canvas, use a mouse cursor visible throughout the process to gradually reconstruct the provided reference image. Maintain the characters, poses, composition, long hair, and clothing of the reference image, as well as the scene relationships like the lake surface, arched bridge, distant mountains, willows, and pleasure boats. 0:00-0:02 Start with a blank canvas; the cursor quickly establishes character proportions and overall composition, outlining characters, lake surface, arched bridge, distant mountains, and main environmental contours. 0:02-0:04 Quickly refine the line art of characters and background, drawing faces, features, long hair, and clothing; simultaneously add bridges, mountains, willows, pleasure boats, and background figures. 0:04-0:06 Use a graphite pencil for quick cross-hatching to establish light and shadow on hair, face, clothing, and environment. Retain natural cross-hatching, repeated lines, broken lines, and manual correction marks. 0:06-0:08.5 Continuously refine facial features, hair strands, clothing folds, and environmental details to gradually form a complete manual pencil sketch. 0:08.5-0:09.5 Complete final details, erase a small amount of extra construction lines, and stably display the finished work. 0:09.5-0:10 The cursor moves to the bottom left corner of the screen to complete the final signature '● DeepBlue' with natural handwritten strokes. The signature can only appear at the end, and the cursor stays after completion. Style: High-speed manual pencil sketch time-lapse photography; cream-white paper, graphite lines, natural hatching, cross-hatching, paper texture, realistic hand-drawn marks. The canvas is the visual subject, with a simple and credible UI. Core Requirements: Blank canvas → Composition → Sketch → Detailed line art → Hatching light and shadow → Refinement → Completion → Final signature. All screen changes must be gradually produced by the visible cursor's actual drawing, and subsequent frames must be built on the previous stage. Prohibit characters or backgrounds from suddenly appearing, prohibit direct switching to the finished image, prohibit color painting, watercolor, 3D, anime style, and cinematic transitions.

Generate video
By @PSS
Seedance 2.5
View full prompt & copy

Create a 15-second ultra-photorealistic late-night workplace vlog inside a tiny local radio station. Use six fast handheld shots recorded on a consumer camcorder from the late 1990s. CHARACTER LOCK: One adult female radio host in her late 30s, short auburn hair, black rectangular glasses, burgundy cardigan, charcoal T-shirt, dark jeans and silver over-ear headphones around her neck. She carries one paper coffee cup. Preserve her identity, clothes, glasses, headphones and cup throughout. 0–2s — IMMEDIATE HOOK: The red ON AIR lamp suddenly illuminates while she is still rushing through the studio door with coffee in one hand and a stack of records slipping from the other. Her alarmed face and the glowing lamp fill the same frame. 2–4.5s: She catches the records against her chest, sets the coffee down and slides into the broadcast chair. The camcorder pans late and briefly crops her head. 4.5–7s: Close shot of her hands rapidly checking three record sleeves. One sleeve is empty. She looks under the console as the turntable continues spinning silently. 7–9.5s: She finds the missing record beneath a notebook, places it on the turntable and lowers the needle with one second to spare. Her movements are urgent but precise. 9.5–12s: She pulls on the headphones, opens the microphone channel and leans toward it. Her panic disappears into a calm professional smile; no audible scripted speech is required. 12–15s: The camera pulls back through the booth glass. She points at the saved record and silently celebrates with one small fist pump while the clock advances and the coffee cup trembles beside the speaker. VISUAL STYLE: 4:3 late-1990s consumer camcorder, fluorescent studio light, analog equipment LEDs, soft tape noise, low dynamic range, minor color bleed, imperfect white balance and clumsy zoom. No modern cinematic lighting or polished commercial composition. AUDIO: Door, record sleeves, chair wheels, turntable motor, needle contact, console switches, headphone movement, room tone and faint record crackle. No background score, narration or intelligible copyrighted music. CONSTRAINTS: One host only. Equipment, records, coffee, glasses and headphones remain consistent. No spilled coffee, broken equipment, duplicated props, readable station branding, subtitles, logos or watermark.

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.