Prompts
Featured
Models
Submit
Blog

AhaPrompt

AI Prompts for Images, Video & Audio — Every Model, One Library

Explore

All Prompts
Featured Prompts
Image Prompts
Video Prompts
Audio Prompts
AI Models
Submit a Prompt
Blog

Languages

English
中文
日本語
한국어

Copyright © 2026 AhaPrompt All rights reserved.

Privacy Policy Terms of Service

HomeAI Prompt LibraryAI Video PromptsUndercover Agent Cold Brew Standoff

Undercover Agent Cold Brew Standoff

Seedance 2.5ByteDancevideo

Image1 = woman holding gun from behind; Image2 = woman in foreground receiving drink. Strictly keep both women's faces, hairstyles, clothing, and identities consistent — do not swap them. Generate a 20-second, 16:9, live-action cinematic, one continuous take, no BGM crime-suspense deadpan comedy short film. Modern cold gray indoor beverage area, silver soda machine, cold white overhead lights. Camera fixed at a low angle slightly in front of and beside the soda machine, roughly waist-to-chest height, 35–50mm, medium close shot, shallow depth of field, essentially static. 0–4s Image2 character B cautiously approaches the soda machine, movements restrained and natural, only one brief wary glance around, neutral expression, no smiling. 4–7s She places a transparent plastic cup under the dispenser nozzle, only uses peripheral vision to check behind her once, then focuses on the cup. 7–12s Orange-yellow drink flows into the cup and gradually fills it, the machine fails to stop in time. The drink must realistically overflow past the cup rim → run down the cup wall → flow over her fingers → drip and splatter onto the metal tray. B only slightly furrows her brow, purses her lips, tightens her fingers — a sub-one-second "oh no" reaction, not exaggerated. 12–14s | Key reversal The camera does not search for danger. A black handgun slowly enters the existing frame from B's right rear, muzzle approaching the side-back of her head; character A should not appear fully yet at this moment. B reacts: her gaze first stops → extremely slight confirmation glance to the right rear → expression instantly goes quiet, body freezes. No wide eyes, no open mouth, no screaming, no jerking her head around. 14–17s B stays facing the soda machine, very slowly stops handling the cup and gradually raises both hands. Camera position unchanged, begins one natural cinematic rack focus: foreground B gradually falls out of focus, A at the right rear gradually sharpens. 17–20s Image1 character A becomes the sharp subject: black straight long hair, gold long earrings, black one-piece swimsuit, one hand steadily holding the gun, expression completely calm and neutral — no sneer, no menacing face. She looks at B and speaks in an ordinary conversational low voice, calm and earnest: "You know too much." B keeps her hands raised, does not turn around, does not respond — only an extremely subtle pause in her gaze. The shot ends immediately after the final word of the dialogue. Performance principles: B: restrained alertness → intense focus → brief hesitation → instant freeze. The greater the danger, the less she performs. A: always calm, steady, neutral — the threat comes from the act of holding the gun, not her expression. **Sound:** Only real production sound: footsteps, plastic cup, soda machine, liquid flowing and overflowing, splatter on metal tray, fabric rustling, and the final Chinese dialogue. No music, no horror sound effects, no cocking sound.

Details

Type: AI Video Prompts
Aspect Ratio: 16:9
Duration: 0:20
Updated: Sep 4, 2026

Category

Short Film Cinematic Realistic

How to use this prompt

1Copy the full prompt with the copy button above.
2Open Seedance 2.5 by ByteDance, or your preferred AI video generator.
3Paste the prompt and keep the camera and motion terms — they steer the cinematography.
4Match the example's settings (16:9 · 0:20 · Short Film · Cinematic · Realistic), then iterate — small wording changes shift the output a lot.

Frequently asked questions

Which AI model generated this video?

This clip was generated with Seedance 2.5 by ByteDance. The prompt on this page is the exact text used to create it.

What settings does this prompt use?

The example was generated with Seedance 2.5 using: 16:9 · 0:20 · Short Film · Cinematic · Realistic. Reusing these settings gives the closest match.

How do I get similar results?

Copy the prompt as-is first, then change the subject while keeping the camera, motion, and lighting terms. Video models are sensitive to wording, so expect a few runs.

Can I modify this prompt?

Yes. Prompts work best as starting points — swap scenes, adjust pacing terms, or change the aspect ratio to fit your project.

More Seedance 2.5 prompts

Multi-shot sequence with hard cuts between shots. Keep the same characters and visual style throughout. No music or score — only natural diegetic sound. SHOT 1 A dirty, exhausted 18-year-old girl with dark auburn-brown hair in a messy low ponytail, warm brown eyes, faded olive-green military jacket, backpack and gloves, aims a bolt-action rifle inside an abandoned ornate mansion. Sweat, dirt, a cheek scrape and tears cover her face. Her hands tremble. She closes her eyes as a tear rolls down, then hears something and lowers the rifle, visibly heartbroken. SHOT 2 Over her shoulder, an infected golden-coated Golden Retriever sits on the debris-covered parquet floor. Matted fur, cloudy white eyes, wounds and dark veins. He trembles while softly whimpering and growling. SHOT 3 She slowly crouches, places the rifle on the floor, wipes her tears and gives the dog a small broken smile. She quietly speaks to him, pulls a worn yellow-green tennis ball from her jacket and gently rolls it toward him. SHOT 4 Extreme low-angle close-up of the tennis ball rolling through dust across the cracked parquet floor. It stops directly in front of the dog's paws. Hold on the still ball. HARD CUT / TRANSFORMATION SHOT 5 Same low camera angle and ball position, but now on a clean sunny residential basketball court. A healthy golden-coated Golden Retriever suddenly grabs the ball. His eyes are clear and warm brown, fur clean, playful and energetic. He shakes and plays with the ball. SHOT 6 Wide shot of the basketball court. The woman throws the ball and the happy dog sprints after it, catches it, runs back and drops it at her feet, ready to play. SHOT 7 Close-up of the clean, unharmed woman laughing while affectionately ruffling the dog's neck and chest. The dog happily pants beside her. SHOT 8 Wide peaceful shot. The woman and dog sit together in a pristine dark-green vintage convertible beside the court. She shares food from a tin can with him. He gently takes it and licks her fingers. CONSISTENCY Same woman throughout: dark auburn-brown hair, loose low ponytail, warm brown eyes, olive-green military jacket, khaki cargo pants and brown boots. Same Golden Retriever: infected and injured in the mansion, healthy and playful after the transformation. Mansion: abandoned ornate interior, tall arched windows, torn dark-red curtains, peeling damask wallpaper, shattered gilt mirror, broken furniture, debris, ceiling hole and strong sunlight beams. Court: clean residential basketball court, white lines, iron fence, flowering shrubs, stone townhouses, warm late-afternoon sunlight and soft shadows. Dark-green vintage convertible with chrome trim. Visual style: ultra-realistic, photorealistic, natural human and animal movement, handheld camera, shallow depth of field, ARRI Alexa 35 look, warm cinematic grade, subtle grain. Audio: ONLY natural breathing, house ambience, dog sounds, footsteps, ball sounds, birds and wind. ABSOLUTELY NO MUSIC OR SCORE.

Create a cinematic 15-second travel vlog featuring a young woman exploring London, shot in a natural handheld smartphone-vlog style. 0–3 sec: She walks out onto a busy London street, smiling at the camera, with iconic red double-decker buses, black cabs, and classic British architecture in the background. 3–6 sec: Quick walking shots through central London as she explores the streets, passing colorful shops and crowds, occasionally looking into the camera and laughing naturally. 6–9 sec: Cut to her standing near Big Ben and the London Eye, capturing a selfie-style moment while the city moves around her. 9–12 sec: She grabs a coffee and walks along the River Thames, with warm sunlight, reflections on the water, and London landmarks in the distance. 12–15 sec: End with a cinematic wide shot of her walking across Westminster Bridge, turning toward the camera with a smile as the London skyline glows during golden hour. Style: Realistic travel vlog, authentic handheld camera movement, smooth transitions, natural facial expressions, realistic skin texture, cinematic lighting, shallow depth of field, subtle motion blur, vibrant but natural colors, immersive London atmosphere, high-detail 4K look, energetic Gen-Z travel content.

Ultra-realistic cinematic 30 second live-action action sequence set in England during the late Victorian to early Edwardian era, circa 1880–1914, filmed like a high-budget period action thriller with darkly humorous British wit. Vertical 9:16, photorealistic, authentic historical production design, dramatic natural lighting, atmospheric fog, subtle analog film grain, realistic motion blur, cinematic depth of field, physically accurate horse and fabric movement. A beautiful young woman is the main character, wearing an elegant historically accurate Edwardian white wedding gown, layered lace, fitted bodice, modest high neckline, long flowing skirt, delicate bridal accessories, and an elaborate period-appropriate Edwardian updo hairstyle. She is riding inside a luxurious horse-drawn carriage racing violently along a muddy English countryside road. The environment features authentic period architecture, stone walls, gas lamps, mist, dirt roads, wooden fences, and distant Victorian-era buildings. Behind her, a sinister male criminal aggressively pursues the carriage on a powerful dark horse. He wears an impeccably tailored late-Victorian / Edwardian dark three-piece suit, waistcoat, formal shirt, tie, long wool coat, leather riding boots, and period hat. A white handkerchief covers part of his lower face, giving him a mysterious outlaw appearance. He carries a historically appropriate early 20th-century revolver. 0–1.5 SEC: Extreme wide cinematic establishing shot of the horse-drawn carriage racing through a foggy English road. The camera rapidly tracks backward at very low height in front of the carriage. Horse hooves violently strike the muddy ground, wheels bounce over stones, dirt and mist explode into the air. The criminal rapidly closes the distance behind them. 1.5–2.5 SEC: Fast whip-pan toward the pursuing rider. Low-angle tracking shot of the criminal and his horse galloping at full speed. His coat and handkerchief whip violently in the wind. He raises his revolver. Dramatic close-up of his eyes. 2.5–3.5 SEC: Rapid interior shot inside the moving carriage. The bride looks backward through the rear window and sees the criminal approaching. Her expression changes from fear to determination. Fast handheld push-in toward her eyes as the carriage violently shakes. 3.5–5.0 SEC: The carriage suddenly swerves. The bride grabs the roof structure and climbs upward through the opening in the carriage roof. Her long wedding dress and veil flow dramatically in the wind. The camera rapidly circles around her in a dynamic 180-degree movement. At the peak of her movement, create a brief dramatic TIME-FREEZE: her dress, veil, dust, horse mane and debris become momentarily suspended in mid-air. Then time instantly snaps back to full speed. 5.0–6.5 SEC: She emerges onto the roof of the moving carriage, crouching low while gripping the roof for balance. She draws a period-appropriate revolver and turns toward the pursuing criminal. Dynamic side-tracking camera moving between the carriage and horse, intense camera shake, realistic motion blur, flying dust and dramatic backlight. 6.5–8.5 SEC: A fast, intense moving gunfight. Rapid alternating close-ups between the bride and criminal. Both fire their revolvers while riding at full speed. Muzzle flashes briefly illuminate their faces. Bullets strike nearby wooden surfaces, producing splinters and debris. The bride ducks behind the carriage roof structure, then rises and fires again. Use rapid whip-pans, snap zooms, Dutch angles, extreme close-ups of eyes, hands and revolvers, low-angle tracking shots, and brief micro time-freezes immediately before gunshots, followed by explosive acceleration back into real time. Keep the choreography physically believable and spatially coherent. 8.5–9.0 SEC: The bride fires one final precise shot. MICRO TIME-FREEZE: the criminal's shocked expression, flying coat, horse mane, dust and debris freeze dramatically for a fraction of a second. Motion suddenly resumes. The criminal loses balance and falls dramatically sideways from the galloping horse, landing on the muddy roadside and rolling across the ground. His horse continues galloping forward without him. 9.0–10.0 SEC: Cut immediately to a medium close-up of the bride standing confidently on top of the moving carriage. Her elaborate Edwardian hairstyle remains composed, while her white wedding dress and veil flutter violently in the wind. She looks down toward the fallen criminal with a deeply annoyed, unimpressed, slightly judgmental British expression, raises one eyebrow and gives a subtle eye-roll. The intense action suddenly gives way to dry British sarcasm. In a natural upper-class British English accent, with deadpan delivery and restrained irritation, she says clearly: “Honestly… I only wanted to get married.” After a tiny pause, she adds with a subtle annoyed expression: “Must there always be an interruption?” She gives a tiny dismissive scoff, turns forward, and the carriage races away into the mist. The humor comes entirely from the contrast between the dramatic Victorian gunfight and her casually irritated reaction, as though the entire chase was simply an annoying interruption to her wedding day. CINEMATOGRAPHY: high-budget period action thriller, dynamic moving camera, low-angle tracking, rapid whip-pans, handheld chase shots, 180-degree camera orbit, Dutch angles, snap zooms, extreme close-ups, brief slow motion, dramatic micro time-freezes, explosive transitions back to real time, seamless match cuts between horse hooves, carriage wheels, revolver, eyes and flying wedding fabric. VISUAL STYLE: ultra-realistic photorealistic live-action, authentic England 1880–1914, historically accurate Victorian/Edwardian costumes and architecture, dramatic overcast sky, cold atmospheric fog, volumetric light, realistic mud and dust, physically accurate horses, detailed fabric dynamics, natural skin texture, subtle Kodak-st

STYLE: Hollywood disaster-action film, photorealistic live-action, ARRI Alexa 35, anamorphic cinematic lens, realistic Malaysian metropolitan city, practical stunt realism, believable destruction and debris physics, aggressive handheld tracking, natural lighting, cinematic contrast, motion blur, dust, shattered glass, sparks, immersive disaster sound. MAIN CHARACTER: Use Image 1. Maintain exact facial identity, hairstyle, clothing and continuity throughout. CORE RULE: ONE CONTINUOUS SURVIVAL SHOT. No teleportation or unexplained cuts. Every movement logically connects. The man constantly runs, stumbles, recovers, jumps, slides, climbs and changes direction. The environment is the antagonist. 00:00–00:03- EARTHQUAKE Low-angle tracking behind his feet as he runs through a Malaysian city street. Ground violently shakes, he nearly falls, buildings shake and glass explodes. Concrete crashes behind him. He looks back briefly and accelerates. 00:03–00:06- COLLAPSE Front tracking shot racing backward. Building façade collapses behind him. He sharply changes direction, jumps over a metal barrier as concrete blocks destroy his original path. Dust fills the street. 00:06–00:09- CAR IMPACT He reaches an intersection. Vehicles slide uncontrollably toward him. He dives at the last second. Camera dives with him. A car passes overhead. He rolls, immediately gets up and keeps running. 00:09–00:12-ROAD CRACK A huge fissure tears across the road. He runs onto a damaged car, uses it as a springboard and leaps across the collapsing pavement. Lands hard and continues running. 00:12–00:15- FALLING GLASS Side tracking shot. High-rise windows explode above him. Glass rains down. He shields his face, ducks beneath a falling metal sign and keeps moving. 00:15–00:18-COLLAPSE A building front collapses ahead. He spots a narrow gap beneath the debris, drops low and slides underneath. Concrete crashes above him. He emerges dusty and immediately runs. 00:18–00:21-VEHICLE CHAOS A bus crashes into cars. A spinning vehicle comes toward him. He jumps onto its hood, springs off the roof and lands on the opposite sidewalk as sparks erupt behind him. 00:21–00:24- ELEVATED ROAD FAILURE An elevated roadway breaks apart ahead. He sprints to the edge and performs a full-body gap jump over the collapsing section. Brief dramatic slow motion, then real-time. Hard landing, roll, recover, run. 00:24–00:27- DEBRIS CHASE Heavy dust reduces visibility. Close shoulder-level pursuit. Falling streetlights and concrete force sudden direction changes. He stumbles against a wall, pushes himself forward and keeps running. A distant vehicle explosion sends a dust shockwave toward him. 00:27–00:30- FINAL COLLAPSE Camera moves ahead, facing him. Massive buildings collapse behind him as he runs toward camera. He jumps over a concrete barrier. A gigantic slab crashes behind him, creating a huge dust cloud. He emerges through the dust still running. CUT TO BLACK. One final footstep. SOUND: Deep earthquake rumble, structural cracking, glass explosions, crowd panic, tires, metal impacts, concrete crashes, heavy breathing, sparks, distant explosion and final low-frequency collapse. PERFORMANCE: He behaves like a real person fighting to survive not an action hero posing. Fear, instinct and adrenaline control every reaction. Realistic balance, impacts and recovery. CAMERA: Low tracking, front pursuit, side tracking, shoulder-mounted chase, whip-pans, ground-level slides and brief airborne follow shots. Camera always follows his momentum. No random drone shots, floating cameras or impossible rotations. FINAL FEEL: Relentless 30-second survival adrenaline — RUN → COLLAPSE → EVADE → JUMP → IMPACT → RECOVER → RUN → BIGGER COLLAPSE → RUN. Duration: 30 seconds | Aspect Ratio: 16:9

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.

Create a highly realistic cinematic travel video of a young woman enjoying a peaceful sunset moment on an elegant waterfront terrace overlooking the Bosphorus in Istanbul, Turkey. She is wearing a sophisticated flowing cream-colored dress with delicate fabric details. Her long dark hair moves naturally in the gentle evening breeze. The video begins with a wide cinematic establishing shot of the Bosphorus, showing elegant waterfront buildings, traditional Turkish architecture, boats slowly moving across the water, and the Istanbul skyline glowing under the setting sun. The camera then slowly moves toward the woman from behind as she walks along the terrace beside a stylish glass railing. She gently places one hand on the railing and looks toward the Bosphorus. After a moment, she turns toward the camera with a subtle natural smile. The camera smoothly moves from a wide shot into a medium close-up, capturing her face, flowing hair, and the warm sunset reflections on the water. End with the camera slowly pulling back to reveal the woman standing against the breathtaking Istanbul skyline. Use realistic environmental movement: gentle waves on the Bosphorus, distant boats moving naturally, subtle wind, moving hair and dress fabric, birds flying in the distance, and soft atmospheric haze. Camera: smooth cinematic tracking, slow dolly movement, gentle orbit around the subject, natural parallax, 35mm lens, shallow depth of field, realistic motion blur, premium travel-film cinematography. Lighting: warm golden-hour sunlight, soft sunset glow, natural rim lighting on her hair and shoulders, realistic shadows, subtle lens flare, cinematic exposure. Visual Style: ultra-photorealistic, luxury travel commercial, premium tourism advertisement, realistic skin texture, detailed hair strands, natural facial expression, realistic fabric physics, cinematic composition, highly detailed Istanbul environment, 4K quality. Negative Prompt: cartoon, anime, CGI look, plastic skin, artificial face, distorted anatomy, extra fingers, extra limbs, deformed hands, unnatural walking, stiff movements, flickering, jittery camera, warped buildings, unrealistic water, duplicate people, oversaturated colors, excessive blur, low resolution, text, subtitles, watermark, logo.

A ultra-realistic casual smartphone vlog captures a young Korean woman in her early 20s experiencing a beautiful morning hot air balloon adventure. The footage feels completely personal and spontaneous, filmed mostly by her in arm-length selfie mode with occasional rear-camera views of the surroundings. Keep realistic handheld shake, imperfect framing, autofocus delays, exposure changes, walking movement, wind noise, and natural outdoor ambience—never cinematic, polished, or commercial. The same woman remains perfectly consistent throughout: petite oval face, brown eyes, natural coral lips, fair realistic skin, and long black hair. She begins by walking through an open field filled with colorful balloons being prepared, smiling into her phone and saying, "I came to ride a hot air balloon today!" She turns the camera around to show the balloons inflating and burners firing while saying, "The weather is really nice today!" She walks toward her balloon, climbs into the basket with assistance, and records as it slowly rises into the sky. Excitedly switching between the view below and her face, she says, "Look! It's going higher and higher!" She then films the beautiful landscape and nearby balloons floating in the morning sky, quietly saying, "The view from up here is really pretty." After enjoying a peaceful moment in the basket, the balloon gently lands in an open field. She laughs naturally during the landing, then records a final selfie after stepping out and says, "I had so much fun today! See you next time. Bye!" She waves and covers the lens with her hand to end the vlog. Keep natural blinking, breathing, spontaneous reactions, realistic balloon movement, passenger activity, wind and burner sounds throughout.

Use the uploaded reference image as the exact character reference. Start video directly from the scene as per prompt. Preserve her facial identity, hairstyle, eye color, skin tone, makeup, body proportions, and overall appearance throughout. Keep the same street, buildings, storefronts, sidewalks, trees, and camera path in every transformation. Create a 15-second ultra-realistic cinematic lifestyle video of a stylish young woman walking casually down the same city street, carrying a takeaway coffee and canvas tote bag. 0–5s — SUMMER She walks through a bright sunny street wearing a fitted top, denim shorts, sneakers, and sunglasses. Green trees, warm sunlight, open cafés, and people in summer clothing surround her. She takes a sip of coffee, smiles, then flicks her fingers. 5–10s — AUTUMN → WINTER With the exact finger-flick motion, the same street seamlessly transforms into autumn. Her outfit changes into a cozy sweater, jacket, skirt, and boots while the trees turn golden and leaves fall around her. She takes two steps, flicks her fingers again, and the exact same environment transforms into winter. Snow begins falling, trees become bare, storefronts glow warmly, pedestrians wear winter coats, and her outfit changes into a stylish wool coat, scarf, tights, and boots. Steam rises naturally from her coffee. 10–15s — SPRING She flicks her fingers one final time. The snow instantly melts into the same street in spring. Trees bloom with fresh green leaves and flowers, petals float through the air, pedestrians switch to light spring clothing, and her outfit transforms into a lightweight jacket, flowing skirt, and sneakers. She takes a final sip, looks directly into the camera, and smiles. Style: Ultra-photorealistic cinematic lifestyle film, seamless seasonal transformations, continuous walking motion, realistic weather physics, elegant fashion changes, smooth gimbal tracking, subtle handheld texture, realistic crowd behavior, detailed fabric and hair movement, cinematic color grading, 4K HDR, 24fps, 16:9. Important: The street geography and camera movement never change. Only the season, weather, vegetation, clothing, lighting, and pedestrians transform. No abrupt cuts during transformations. Negative Prompt: No identity drift, no changing buildings, no street layout changes, no duplicate people, no distorted hands, no extra fingers, no flickering, no unrealistic physics, no text, no subtitles, no logos, no watermark.

Browse all Seedance 2.5 prompts Explore AI Video Prompts