🎬 2000+ curated Seedance 2.0 video generation prompts — cinematic, anime, UGC, ads, meme styles. Includes Seedance API guides, character consistency tips, and advanced video workflows.
A curated collection of high-quality video generation prompts for ByteDance's Seedance 2.0
⚠️ Copyright Notice: All prompts are collected from the community for educational purposes. If you believe any content infringes on your rights, please open an issue and we will remove it promptly.
Seedance 2.0 is a video generation model developed by ByteDance. It is the industry's first model supporting simultaneous quad-modal input — image, video, audio, and text.
Key Features:
🎥 Text-to-Video — Generate videos from text descriptions
🖼️ Image-to-Video — Animate static images into dynamic videos
📹 Video-to-Video — Transform and extend existing videos
🎵 Audio-Driven — Generate videos driven by audio input
📐 Up to 1080p resolution, 4–15 seconds duration
🔊 Auto dubbing & scoring — Automatic voiceover and background music
📊 Statistics
Metric
Count
📝 Total Prompts
5030
⭐ Featured Prompts
6
🔄 Last Updated
2026-07-20
🔥 Featured Prompts
⭐ Hand-picked prompts with outstanding results
No. 1: Seedance 2.0: 15-Second Cinematic Japanese Romance Short Film
📖 Description
A highly detailed, 15-second multi-scene prompt for Seedance 2.0, designed to generate a cinematic, ultra-realistic Japanese high school pure love short film. The prompt specifies scene setting (empty classroom, warm golden sunlight, dust motes), camera movements, character consistency (no deformation/drift), subtle micro-expressions, synchronized breathing/lip movements, dialogue, and sound effects (cicadas, pen scratching, low-frequency heartbeat, soft piano). The narrative focuses on the intense, awkward, and intimate emotional tension between a girl writing and a boy secretly watching her, culminating in a shy confrontation.
📝 Prompt
15-second cinematic Japanese drama pure love ambiguous short film, ultra-realistic quality, warm golden sunlight in an empty classroom in the afternoon, spilling through the blinds onto the side-by-side desks, fine dust motes slowly floating in the light beams, old wooden desks, extremely natural subtle movements, breathing, and eye tension, characters maintain consistent faces, clothing, and hairstyles throughout without deformation, drift, or artifacts, real slight chest rise and fall synchronized with breathing, shallow depth of field, creamy blurred background, warm film grain, 8K sharp, Japanese youth restrained heart-fluttering suffocating atmosphere.
0-4 seconds: Extremely slow push-in shot from a medium shot of the desktop to a close-up of the two people's side profiles sitting side-by-side. A pure girl in a summer school uniform is focused on writing notes with her head down, long black hair and stray hairs by her ears are gently lifted by a slight breeze, long eyelashes cast subtle shadows, skin is naturally pink and tender, a slight, unintentional upturn of the corner of her mouth in concentration, light and even breathing.
4-9 seconds: Switch to a close-up of the boy. His school uniform collar is slightly loose, he props his elbow on the desk and secretly turns his head to gaze at her, his eyes filled with gentle, restrained affection and tenderness, pupils slightly dilated, his Adam's apple gently rolls. Suddenly noticing her pen pause, he quickly and flusteredly turns his head to pretend to look at his own notes, his earlobes quickly turn slightly red, his fingertips tremble slightly as he grips the pen, occasionally glancing at her from under his bangs, his breathing is slightly disordered, and his lips are tightly pressed in an effort to remain calm.
9-15 seconds: Extreme close-up of both faces in the same frame, slow-motion eyes suddenly meet: the girl slowly turns her head, first showing a dazed surprise, then quickly and shyly lowers her head for 0.3 seconds, gently biting her lower lip, her cheeks and earlobes instantly bloom with cherry blossom pink, her moist eyelashes timidly look up to meet his gaze again, while softly and shyly whispering, "...What are you looking at?"; the boy freezes completely, his pupils dilate, and he is stunned for 0.4 seconds, then flusteredly and quietly stutters in response, "N-nothing...". The girl whispers even quieter, biting her lip and peeking at him again, continuing to whisper, "...Liar.". The boy pauses, then gently sighs and whispers, "...Just looking at you.", the corner of his mouth slowly curls up into a shy, gentle, crooked smile, fine lines appear at the corners of his eyes, and his breathing noticeably deepens. An invisible current seems to pull the ambiguous tension between their faces, sharing each other's breathing temperature, the background completely melts into layers of creamy, dreamy light spots, warm halos, and fine air particles.
Lip synchronization is natural and precise, emotional micro-tremors and breathing are synchronized, dialogue is low-energy whispering with a shy tone, natural short pauses between 200-400 milliseconds, the mouth only moves slightly when speaking, without exaggeration or robotic feel, perfect natural lip-sync and emotional authenticity.
Overall Sound Effects: Distant summer cicada chirping faintly, the soft scratching sound of the pen touching the paper, the almost inaudible low-frequency pulse of their heartbeats, finally fading into a very light, airy piano. The dialogue is completely naturally integrated into the scene as whispers, the girl's voice is soft and shy, the boy transitions from flustered stuttering to gentle.
Character identity is maintained throughout, real subtle head tilts, eye movements, and breathing synchronization, no text, watermarks, or subtitles, pure Japanese style youth secret crush heart-fluttering suspense.
No. 2: Hollywood Haute Couture Fantasy Video Prompt
📖 Description
A detailed, multi-scene video generation prompt for Seedance 2.0, designed to create a Hollywood Haute Couture Fantasy film. The prompt specifies style, resolution (8K), rendering engine (Unreal Engine 5), duration (15 seconds), and three distinct camera/action sequences involving a model in liquid blue-and-white porcelain that shatters into ink-wash swallows, culminating in a 3D fluid ink vortex.
📝 Prompt
[Style] Hollywood Haute Couture Fantasy blockbuster, 8K ultra-clear, Photorealistic, High-fashion Editorial Style, Unreal Engine 5 fluid rendering, visual illusion. [Duration] 15 seconds. [Scene] An endless, real-life Salar de Uyuni (Sky Mirror) salt flat. The sky is filled with oppressive dark clouds, and the ground perfectly reflects everything like a mirror, with the overall picture presenting a minimalist, cool tone. [00:00-00:05] Shot 1: Haute Couture Entrance and Porcelain Skin. Camera position: Extremely low-angle upward shot, ultra-telephoto lens zoom-in. Action: An Asian female model with a highly recognizable, high-fashion face walks coolly on the water surface. Effect: She is wearing not fabric, but a long dress made of flowing, real Liquid Blue-and-White Porcelain. As she walks, the skirt makes a crisp collision sound like real ceramic, with a flowing luster on the surface. The traditional blue-and-white patterns move across the white porcelain-textured skirt as if alive. [00:05-00:10] Shot 2: Physical Shattering and Ink-wash Descent. Camera position: Extreme close-up of the face, focus rapidly pulls back. Action: The model suddenly stops, stares coldly at the camera, and snaps her fingers crisply. Effect: The moment the fingers snap, her blue-and-white porcelain dress does not fall, but instantly explodes into thousands of extremely photorealistic Ink-wash Swallows. These swallows carry real water droplets and ink marks, dragging black fluid afterimages in the air, spinning frantically around her. [00:10-00:15] Shot 3: Dimensional Dissolution and Abyss Reflection. Camera position: High-altitude overhead shot, camera rapidly rotates and descends. Action: The swarm of ink-wash swallows plunges into the mirrored lake water beneath the model's feet. Effect: The surface tension of the originally solid salt lake instantly disappears. The entire extremely realistic world begins to violently bleed and dissolve like concentrated ink dropped into clear water. The real dark clouds and the model's figure transform entirely into an extremely grand 3D Fluid Ink Vortex, completely swallowing the camera into a black and white interwoven abyss.
No. 3: Modern Rural Aesthetics Healing Short Film Video Prompt
📖 Description
A detailed, three-shot prompt for Seedance 2.0 to generate a healing, cinematic short film in the Modern Rural Aesthetics style. It specifies the style (Cinematic Commercial, 4K/8K, Extreme Macro, natural light, ASMR), the setting (a modern open kitchen with a garden view), the character (a focused creator in linen), and specific actions for three scenes: picking a tomato, precise cutting, and a quiet moment of eating.
📝 Prompt
[Style]
Modern Rural Aesthetics, Cinematic Commercial quality, shot with Sony A7S3/cinema camera, 4K/8K ultra-clear, Extreme Macro, natural transparent lighting, healing ASMR, no historical costume drama feel.
[Scene]
A well-maintained modern farmhouse open kitchen, background is a lush vegetable garden, bright sunshine.
[Character]
Modern Rural Creator, black long hair casually tied up with a wooden hairpin, wearing a dark blue comfortable linen outfit, clear makeup, focused and peaceful eyes.
[Shot Details]
[00:00-00:05] Shot 1: Morning Harvest (The Freshness)
Visuals: High-definition close-up. Morning sunlight hits the plants with side backlighting.
Action: The Creator's bare hands (long, clean fingers) pick a bright red tomato with glistening dew drops from the vine.
Details: Extremely sharp focus, clearly showing the fuzz on the tomato surface and the trajectory of sliding water droplets. Background is blurred high-quality green.
[00:05-00:10] Shot 2: Extreme Craftsmanship (The Craft)
Visuals: Indoor stove area, full of life but spotless.
Action: The Creator is cutting vegetables, movements are skilled and precise (non-performance nature).
Details: Macro lens captures the moment the knife blade slices through the ingredients, juice splattering. Then switches to the orange flame flickering in the earthen stove, light and shadow are warm and real.
[00:10-00:15] Shot 3: Tranquil Time (The Moment)
Visuals: Full shot/Medium shot.
Action: A delicate home-cooked dish is placed on the wooden long table in the yard. The Creator sits down quietly, gently tidies a stray hair, and picks up a bite of food.
Atmosphere: Steam slowly rises against the backlight, the scene is so quiet you can almost hear the wind, showcasing the ultimate sense of relaxation modern people yearn for.
No. 4: Live-Action Anime Adaptation: Water vs. Thunder Breathing Duel
📖 Description
A highly detailed, 15-second prompt for generating a live-action adaptation of an anime-style duel, featuring 'Water Breathing' (blue water dragon) versus 'Thunder Breathing' (golden lightning). The prompt specifies the style (Hollywood live-action, dark samurai, 4K, fast cuts), scene setting (misty forest under moonlight), and three distinct, action-packed shots detailing character actions, special effects, and the final collision of powers.
📝 Prompt
Live-Action Anime Adaptation · Breathing Technique Decisive Battle (15 seconds · Super Burning Special Effects Version)
【Core Focus】: Water Breathing (Blue Water Dragon) VS Thunder Breathing (Golden Lightning), live-action extreme speed duel.
【Style】: Hollywood live-action anime adaptation film quality, dark samurai style, 4K ultra-clear, extreme fast cuts, explosive particle light effects, no gore.
【Duration】: 15 seconds
【Scene】: Misty forest under the moonlight, muddy ground, falling leaves.
[00:00-00:05] Shot 1: Water Melody Prelude · Starting Stance (Sense of charging)
Visuals: A young samurai wearing a green and black checkered haori (jacket), lowering his center of gravity under the moonlight, gripping his sword with both hands.
Action: He takes a deep breath, and the surrounding air instantly solidifies. As he draws his sword, a giant blue water dragon, condensed from high-pressure water flow, appears out of thin air, rotating rapidly around his body and blade, emitting the roar of flowing water.
Special Effects Details: The water flow has a realistic sense of splashing, illuminating the dark forest.
[00:05-00:10] Shot 2: Thunder Flash · Charge (Sense of extreme speed)
Visuals: The opponent, a blonde swordsman wearing a yellow triangular patterned haori, is crouched extremely low, adopting the posture of Iaijutsu (sword drawing technique).
Action: The ground suddenly explodes, and he instantly transforms into a dazzling golden lightning afterimage, refracting and charging through the forest in a "Z" shape at a speed undetectable by the naked eye.
Special Effects Details: Golden electric arcs and scorched fallen leaves remain in the places he passes.
[00:10-00:15] Shot 3: Water and Thunder Collision · Final Sound (Ultimate move clash)
Visuals: Extreme speed collision. The young samurai swings the giant blue water dragon down to meet the attack, and the blonde swordsman, transformed into lightning, crashes into him head-on.
Action: The two swords violently collide in the center of the frame.
Special Effects Spectacle: The blue water dragon and the golden lightning instantly explode, forming a massive water-thunder energy storm that spreads outwards. The surrounding large trees are snapped in half by the energy wave, and mud and light obscure the camera. The scene ends in an extremely dazzling blue, yellow, and white light.
A detailed, 15-second prompt for Seedance 2.0 to generate a 16:9 horizontal street rap music video (MV) featuring an 80-year-old woman. The prompt specifies the style (neon purple/blue cool tones, explosive atmosphere), character appearance (silver hair, leather jacket, hip-hop accessories), scene breakdown (0-3s intro, 3-7s rapping, 7-11s dancing, 11-15s climax/conclusion), specific Rap lyrics, camera techniques (low angle, 360-degree rotation, quick cuts), and sound design (Trap electronic music, heavy 808 drums).
📝 Prompt
16:9 horizontal screen, street rap MV style, neon purple and blue cool tones, explosive cool and fierce atmosphere. 0-3 seconds: Medium shot push-in, city street night scene with flashing neon lights, an 80-year-old silver-haired woman stands in front of a graffiti wall, short silver-white hair styled in a neat slick-back, distinct square face contour, sword-like eyebrows slanting towards the temples, eyes sharp like electricity, wrinkles at the corners of her eyes like badges of time, a confident smile on the corner of her mouth, wearing a black leather jacket over a white printed T-shirt (large black letters "YOLO" on the chest) + black cargo pants + white high-top sneakers, a thick gold chain necklace around her neck, silver bracelet on her wrist, holding up a microphone with both hands, strong drum beats of the BGM start, the old woman's eyes sharpen, and her lips open to start Rap. 3-7 seconds: Medium shot + close-up switch, the old woman starts rapping, with an extremely strong sense of rhythm, her silver hair flying with her head-nodding movements, one hand holding the microphone, the other hand making gestures to match the rhythm—index finger pointing at the camera, palm cutting the rhythm up and down, making hip-hop gestures, movements are smooth and flowing, eyes sharp and looking directly at the camera, wrinkles vividly jumping with her expression, lips opening and closing rapidly to spit out lyrics: [Rap Lyrics] "Eighty-year-old legs, can jump better than you! Silver hair flowing, this is my pride! Don't call me old, my Flow is better than yours, when you were playing rap, I was listening to disco!" (Fast speed, strong rhythm, fierce attitude) Quick cuts: facial close-ups, hand movements, full-body swaying, side silhouettes, synchronized with the BGM beat. 7-11 seconds: Dance segment, the camera pulls back to show the full body, the old woman starts dancing—first the classic hip-hop bounce, then a neat street dance freeze, followed by a body wave transmitting from the shoulders to the toes, and then a quick footwork workout, movements are clean and sharp, silver hair flies under the neon lights, the leather jacket flutters in the air, she continues to Rap while dancing: [Rap Lyrics] "Legs and feet are nimble, speed is not slow, my lyrics are carved in time! You play with phones, I play with beats, eighty years of life, written into this verse!" (Faster rhythm, stronger tone) Low-angle upward shot + 360-degree surrounding shot, capturing the old woman's cool and fierce dance moves. 11-15 seconds: Climax ending, the old woman makes a cool turn, her silver hair arcs in the air, she faces the camera and makes a "shush" gesture with her finger, then her lips move closer to the microphone, singing the last line in a low, magnetic voice: [Reality Lyrics] "Time never defeats a beauty, I just changed the way I experience youth..." (Slow rhythm, deep emotion, lingering finish) The camera slowly pushes in for a close-up of the old woman's eyes, the wrinkles at the corners of her eyes are all stories, her gaze is still sharp yet with a hint of kindness, the BGM abruptly stops at the climax, the frame freezes on the old woman's cool yet slightly gentle smile, vignetting + neon purple light halo.
No. 6: Cinematic Street Racing Sequence for Seedance 2
📖 Description
A detailed, multi-shot prompt designed for Seedance 2 to generate a cinematic street racing sequence at night, focusing on intense driver focus, dynamic camera work, and explosive acceleration, structured with specific time segments for scene progression.
📝 Prompt
cinematic street racing sequence at night, a focused driver inside a high-performance car grips the steering wheel, intense eye focus, city lights reflecting on windshield, tension building before sudden acceleration
camera: rapid multi-angle system with seamless transitions, interior close-up → over-the-shoulder → exterior tracking → low ground shots, ultra dynamic camera movement, whip pans + speed ramp transitions + motion blur masking cuts, continuous flow illusion
(0-2s) interior close-up on driver, hand tightens on gear shift, subtle breathing, dashboard lights glowing
(2-4s) over-the-shoulder shot, road ahead stretching into neon-lit city, engine vibration building
(4-6s) extreme close-up on finger pressing NOS button, instant ignition reaction
(6-8s) explosive acceleration, camera snaps to exterior side tracking shot, car launches forward with violent speed surge
(8-10s) ultra low ground shot near asphalt, wheels spinning at extreme velocity, environment streaking past
(10-12s) high-speed chase through tight streets, sharp turns, camera whip pans between angles, reflections and light trails enhancing speed
Dense urban night environment, wet asphalt reflecting neon lights, tunnel passages, street lights streaking, high-speed city atmosphere
Ultra realistic, fast and furious inspired energy, photorealistic lighting, intense motion blur, high contrast neon reflections, cinematic depth of field, extreme sense of speed, fluid transitions, no distortion, no stretching
A prompt for a dizzying high-altitude shot of a city at sunset from the edge of a skyscraper, featuring handheld camera motion.
📝 Prompt
Vertical 9:16 aspect ratio, high-altitude overhead shot with realistic cinematic texture, warm twilight city light, slight atmospheric haze shrouding the city, 14mm wide-angle lens providing intense high-altitude pressure, natural shaking sensation of a handheld selfie stick throughout, urban skyscraper clusters filling the entire background, set in an extreme scene at the edge of a high-rise rooftop.
A comedic video prompt set in a rustic farmhouse where a hen flies above a lounging girl and lays an egg directly into her open mouth.
📝 Prompt
Generate a comedic style video. The background is set in a quaint farmhouse courtyard. The background music is light, playful, and rhythmic instrumental music. No voiceover or subtitles are needed. Video storyboard description: 1-2s: A beautiful girl in a white silk camisole dress lies lazily on a bamboo lounge chair with her mouth open. 3-5s: A hen flutters its wings and lands on a bamboo pole above her. Sound effect of a chicken flying. 6-8s: The hen lays an egg that falls vertically and lands precisely in the girl's open mouth with a dropping sound effect. 8-10s: A close-up of the girl's face, eyes wide with shock, holding the egg in her mouth. 10-12s: She takes the egg out, looks at it in confusion. The video ends with a dramatic 'thud' sound. 9:16.
A creative prompt for a high-quality 2D anime scene where a character's emotional tears flood a karaoke room, complete with shot-by-shot progression.
📝 Prompt
15 seconds. Japanese full-color anime. High-density 2D animation with a 500-million-yen budget scale. Detailed background art, smooth in-betweens, movie-quality cinematography processing. To keep the visual variety, develop appealingly by changing composition, camera angle, screen size, and character distance. No subtitles, no watermarks, no BGM. Ambient sound included.
[Video Composition] After watching the end of an emotional movie, the water level in the room rises from the protagonist's tears. While crying, the protagonist continues to watch while floating on a swim ring; at the climax, the tears turn into a waterfall and flow out the window. Once the viewing is over, the water recedes and the room is dry as before.
[Must include somewhere in Shot 5-7] As the end credits roll, the water recedes and all the drinks in the room have turned salty.
Shot 1 (The Single Drop Hook): Long corridor of a karaoke shop. A single tear from the protagonist watching the end of an emotional movie falls to the floor with a sound like a pool dive. Expression with eyes full of tears.
Shot 2 (Flooding): Tears won't stop, and the water level rises to ankles and knees. Slippers drift away like small boats. Protagonist stares at the screen while sobbing.
Shot 3 (Continuation): Protagonist floats on a swim ring while continuing to watch through tears. Messily crying but eyes are glued to the screen.
Shot 4 (Underwater): Camera goes underwater. Amidst floating daily necessities, wailing is heard from above the water surface. Sobbing with a trembling voice.
Shot 5 (Breach): At the climax, tears become a waterfall and flow out of the window. A rainbow appears. Large tears falling in chunks.
Shot 6 (Drying Up): The moment the viewing ends, the water recedes quickly. The room is mysteriously dry. The protagonist is still sniffing.
Shot 7 (Aftermath): With bright red eyes, the protagonist blows their nose and says in a damp voice, "I'm watching it a second time."
A high-paced cinematic video prompt for Seedance 2.0 featuring a speedboat racing through neon-lit canals and escaping through closing flood gates.
📝 Prompt
Night. In a futuristic city of narrow neon-lit canals, a small speedboat races at high speed through twisting waterways while trying to escape through the maze. The canals are tight and visually dramatic, with glowing signs, reflective glass buildings, wet concrete walls, low bridges, dock platforms, moored boats, floating barriers, and large flood gates built into the canal system. Neon reflections ripple across the dark water and mist hangs low over the surface. Wide opening shot: the speedboat blasts into a narrow canal at high speed, skimming over the water between glowing buildings. Neon lights reflect across the boat and the water as the route ahead narrows. Tracking shot: the boat powers through a series of sharp turns between canal walls and dock structures. It leans hard into the turns, throws up spray, and barely clears a low bridge overhead. Warning lights begin flashing farther ahead as a flood gate system starts activating. Side shot: the chase becomes more dangerous. One flood gate begins lowering across the canal while the boat rushes toward it. The driver steers through a tighter side channel, misses a moored boat by inches, and cuts back into the main canal. More low bridges and tight corners force fast direction changes. Final 5 seconds: the action becomes extreme. Multiple flood gates begin closing in sequence ahead. The speedboat accelerates into a final burst, skims under a very low bridge, threads through a narrow gap between canal walls, and shoots through a half-open flood gate just before it slams shut behind. Spray explodes across the frame as the boat lands hard back into the water and keeps racing forward. Final moment: the speedboat bursts into a wider canal stretch at full speed while neon reflections, mist, and the sealed flood gate glow behind it in the night. Style: hyper-realistic, cinematic, fast-paced, intense, stressful, clear readable action, strong sense of speed and danger, futuristic canal city, neon reflections, dark water, low bridges, sharp turns, closing flood gates, dynamic but readable camera movement, no text, no logos, no cartoon style, no slow motion, no famous celebrity faces, no recognizable actors, no movie-star resemblance, no public-figure likenesses, no clear facial close-ups. Keep proportions. Keep style and features. Aspect ratio 16:9.
A high-intensity cinematic prompt for a Formula 1 pit stop during a rainy night race, featuring detailed smoke and motion effects.
📝 Prompt
A Formula 1 car screams into the pit lane during a night downpour — the crew swarms in choreographed chaos, tire smoke blooming, rain hammering under the floodlights. Shot in slow motion from ground level: wheel guns blazing, water spraying off the bodywork, the car launching away in a rooster tail of spray. Photorealistic rain, smoke and motion VFX, high-gloss broadcast look.
A stylized anime prompt for a hauntingly calm tea ceremony where a ghostly figure slowly appears in an abandoned room.
📝 Prompt
Stylized anime haunted tea ceremony beat: an elderly woman pours tea inside an abandoned tatami room, steam rising from the cup and slowly forming the shape of a long-lost guest. Dust floats in golden afternoon light, paper doors rattling gently though no wind enters the house. Slow push-in across the floor, tea reflections rippling with impossible memories, the woman’s calm face mirrored in the porcelain cup. The ghostly figure leans closer and the silence holds one beat past comfort.
A detailed multi-shot narrative prompt featuring a giant crocodile attacking a boat near a massive dam, culminating in a dramatic spillway release.
📝 Prompt
LOCATION: A massive concrete dam in bright stormy daylight, a wide grey-green reservoir behind it, a small maintenance boat on the water near the dam wall, a glass control room perched on top of the dam, the huge dry spillway ramp and turbine house far below.\n\nShot 1 (0–3s) — THE HOOK: Water-level tracking shot. A mega crocodile the size of a bus has its jaws clamped on the maintenance boat's stern, dragging it backward through the reservoir toward the dam wall, the hull groaning, gear sliding off the deck. The lone worker aboard clings to the rail, screaming into his radio: "IT'S PULLING ME INTO THE WALL! I'M JUMPING!"\n\nShot 2 (3–6s): Inside the control room on the dam crest. The control officer, headset on, hands already spread across the floodgate console for the scheduled release, looks down through the glass at the croc hauling the boat toward the gates. His eyes flick to the access ladder on the wall. Into the radio: "JUMP NOW! LADDER'S TEN METERS TO YOUR LEFT! SWIM!"\n\nShot 3 (6–9s): Handheld from the dam wall. The worker dives off the boat and swims hard for the ladder, hauling himself up the rungs as the croc crushes the empty boat flat in its jaws behind him — then turns, gliding straight along the wall, directly over the massive submerged spillway gates.\n\nShot 4 (9–13s) — BULLET TIME PAYOFF: The officer slams every gate lever at once. Bullet time — all the spillway gates blast open together, and the reservoir tears downward in slow motion, a monstrous whirlpool ripping the croc under, its body twisting and dragged through the gates, fired down the concrete spillway inside a white cannon of floodwater — and slammed straight through the turbine house wall below. Impact. The building detonates, water and fire exploding outward together.\n\nShot 5 (13–15s): Time snaps back. The flood thunders down the spillway through the burning wreckage, spray and smoke boiling up the dam face as the worker clings to the ladder above, staring down.
An intense, multi-shot action sequence for Seedance 2 featuring a massive crocodile attacking a wind farm construction site and a dramatic cinematic payoff.
📝 Prompt
LOCATION: A coastal wind farm construction site in bright harsh daylight, giant white turbine towers along the cliffs, a massive crawler crane mid-lift with a 70-meter turbine blade hanging from its hook, scattered containers and a fenced transformer station humming at the site's edge, sea wind whipping dust. Shot 1 (0–3s) — THE HOOK: Ground-level tracking shot through the site. A mega crocodile the size of a bus has its jaws clamped on the rear of a worker's ATV, dragging it backward across the gravel with the worker still on it, wheels spinning, gear flying. He clings to the handlebars, screaming into his radio: "IT'S GOT MY QUAD! SOMEBODY DO SOMETHING!" Shot 2 (3–6s): High shot from inside the crane cab. The crane operator, hands already on the slew levers mid-lift, the enormous white blade hanging off his hook, looks down at the croc dragging the ATV directly across his lift zone. His eyes go from the blade to the croc to the transformer station behind it. Into his radio: "GET OFF THE QUAD! ROLL LEFT! NOW!" Shot 3 (6–9s): Low handheld at ground level. The worker kicks free of the ATV and rolls hard across the gravel behind a container. The croc shakes the empty quad apart in its jaws, then rises up on its hind legs to full height, bellowing at the fleeing man — fully exposed in the open lift zone. Shot 4 (9–13s) — BULLET TIME PAYOFF: The operator slams the slew levers full over. Bullet time — the crane whips around and the 70-meter blade sweeps across the site in slow motion like a giant sword, dust curling off its edge — and scythes into the rearing croc's body, slicing through and smashing the monster off its feet, hurling it through the transformer station fence. Impact. The transformers erupt in a chain of explosions, arcs of lightning and fire ripping upward around the broken body. Shot 5 (13–15s): Time snaps back. Sparks rain across the site, the blade still swinging overhead, the worker rising from behind the container to stare at the burning, arcing wreckage.
A cinematic action prompt for Seedance 2.0 featuring a young Japanese woman performing parkour across Tokyo landmarks, ending with a super-powered climb to the top of Tokyo Tower.
📝 Prompt
Subject: A 20-year-old young Japanese female with black long hair in a high ponytail, wearing a white sports tank top, denim miniskirt, and white sneakers. At night, she is parkouring in downtown Tokyo. She first greets the camera, then immediately runs across a Tokyo bridge, jumps over car roofs, very quickly leaps onto an apartment balcony, then onto a supermarket billboard, jumps to a cell signal tower, and finally to the base of Tokyo Tower. Using her superpowers, she runs from the bottom to the top in just 2 seconds. She stands at the top, the camera circles around, overlooking the brightly lit night view of Tokyo. The action is cool and thrilling, featuring low-angle follow shots, high-difficulty sports photography, and camera shake.
A prompt designed to generate realistic, shaky smartphone footage of friends hanging out at the beach with quick cuts and natural lighting.
📝 Prompt
Super casual real smartphone home video footage, sunny beach day outing with friends, natural mobile phone camera with slight authentic handheld shake, normal frame rate with smooth natural motion, rapidfire montage with constant quick jump cuts every 1-2 seconds like scrolling through phone memories, unpolished authentic phone recording of mixed group laughing, playing in sand, snacking and clicking pictures, pure raw home video feel, no cinematic polish or heavy effects.
Use the provided reference photo as the strict ONLY visual reference for the main woman. Maintain her exact appearance with zero deviation: [her described features]. Generate a mixed group of friends of all ages around her on the beach.
0-2.5s: Shaky handheld rapid cuts main woman laughing with friends near the shoreline, wind in her hair, quick flashes of feet in sand and waves.
2.5-5s: Abrupt jump cuts close-up of her smiling with sunglasses pushed up, then group splashing water and clicking selfies.
5-7.5s: Fast shaky she sits on a beach towel chatting animatedly, snacks and drinks scattered around, natural sunlight flare.
7.5-10s: Quick cut close-up big warm smile toward camera, playful wave, then jump to group building a small sandcastle together.
10-12.5s: Abrupt edit everyone gathered near a beach umbrella, passing chips and cold drinks, casual toast with cans.
12.5-15s: Final rapid transition main woman relaxed, sitting among friends, soft smile, calm beach memory ending with gentle phone sway.
Natural smartphone video quality, slight real handheld shake, smooth normal frame rate motion, authentic casual interactions and physics, stable main character consistency, unpolished home phone recording, no pro stabilization or effects.
A detailed multi-shot cinematic prompt for a high-stakes escape through a collapsing library with intense fire and smoke effects.
📝 Prompt
Hyper-realistic cinematic action sequence, 15 seconds, aspect ratio 16:9.
Night. Inside a vast grand old library, one person runs through a towering maze of bookshelves while the building begins falling apart around them. The library is dramatic and atmospheric, with tall wooden shelves, rolling ladders, upper balconies, iron railings, chandeliers, reading tables, scattered books, dust, and warm firelight spreading through the space. Smoke thickens in the air as the danger grows.
Wide opening shot: the person runs through the main library floor between towering shelves while fire spreads in the background. Sparks drift through the air, smoke gathers near the ceiling, and the upper balconies shake as the structure starts failing. Tracking shot: the person sprints past long shelves as one row begins collapsing behind them like dominoes. Books fly outward, ladders fall, and the collapsing shelves send dust and debris across the floor. The person keeps moving toward a staircase or balcony route ahead.
Side shot: the escape becomes more dangerous. The person climbs a rolling ladder or narrow staircase to an upper balcony while another line of shelves crashes down below. The balcony shakes, a railing bends, and burning debris falls into the path. The person runs along the upper level, using the railing for balance.
Final 5 seconds: the action becomes extreme.
A section of the balcony ahead begins breaking apart while more shelves collapse below in a chain reaction. The person accelerates, crosses the unstable balcony, jumps to the final platform or doorway, lands hard, and pushes through the exit just as another row of shelves crashes down and firelight bursts behind.
Final moment: the person reaches the safer exit corridor or outer landing while the burning library behind continues collapsing in heat, smoke, sparks, and falling books.
Style: hyper-realistic, cinematic, fast-paced, intense, stressful, clear readable action, strong sense of danger and urgency, grand old library atmosphere, collapsing bookshelves, ladders, balconies, smoke, firelight, falling debris, dynamic but readable camera movement, no text, no logos, no cartoon style, no slow motion, no famous celebrity faces, no recognizable actors, no movie-star resemblance, no public-figure likenesses, no clear facial close-ups. Keep proportions. Keep style and features. Aspect ratio 16:9.
A complex sci-fi architectural visualization prompt featuring a floating skyscraper with an interactive holographic interface.
📝 Prompt
A futuristic luxury residential skyscraper floating on a massive rock above a dark cloudy sky, glowing with warm lights. The camera flies toward the twin towers as a transparent sci-fi HUD interface appears with digital data panels, graphs, and scanning reticles selecting a penthouse unit. A holographic window labeled “LUXUMY LOGON” opens, showing a luxury living room preview; a cursor clicks and the camera seamlessly zooms through the glass into the real penthouse interior. Inside, seven elegantly dressed guests relax on plush sofas with drinks, surrounded by floor-to-ceiling windows, a city skyline at dusk, warm lighting, a modern fireplace, and ultra-modern minimalist décor. Cinematic, futuristic, high-end architectural visualization, photorealistic.
A visually stunning drone-style tracking sequence showing a city with multiple gravity planes where vehicles travel on walls and ceilings.
📝 Prompt
Cinematic tracking sequence highlighting the impossible localized gravity planes of the cuboid city.
0-4s: Wide establishing shot. Slow push-in toward the central void. Traffic flows simultaneously on all four inner walls, defying standard downward gravity.
4-8s: Dynamic FPV dive. Camera swoops into the center and aligns with the left vertical wall. Gravity shifts; cars drive past the lens as if the wall is the floor.
8-12s: Camera tracks a yellow taxi approaching a 90-degree internal corner. The taxi seamlessly rolls onto the inner ceiling. Camera rolls 90 degrees to keep the car grounded in frame.
12-15s: Camera pulls straight back through the suspended Brooklyn Bridge structure, exiting the cube to re-establish the wide shot above the tiny motionless observer.
Style: Photorealistic 8K, macro lens depth of field, smooth drone cinematography, stark studio lighting.
A high-action cinematic prompt featuring a loyal bodyguard protecting a client in a gritty warehouse with teal lighting and dynamic movement.
📝 Prompt
A cinematic 15-second action sequence set inside a dark, gritty industrial warehouse at night, featuring moody teal-green lighting, chain-link fences, metal scaffolding, peeling green walls, and floating dust particles. A powerful, elegant East Asian Boss Lady wears a sleek black pantsuit with long flowing black hair and a calm, commanding expression. Standing beside her is a handsome, athletic male bodyguard in an all-black tailored suit with a heroic presence. As multiple attackers rush in, the bodyguard instantly steps in front of the Boss Lady, protecting her with lightning-fast punches, powerful kicks, evasive movements, and cinematic takedowns. The Boss Lady remains composed and confident, watching as her protector defeats every attacker. The sequence ends with the bodyguard standing protectively beside the Boss Lady as they walk forward together in slow motion, dust swirling around them. Handheld and tracking camera shots, dramatic low angles, realistic fabric movement, cinematic motion blur, ultra-detailed choreography, film-quality lighting, emotional heroism, 4K ultra-realistic cinematic masterpiece.
A detailed environment prompt for a rainy Tokyo street at night with realistic reflections and cinematic lighting.
📝 Prompt
Main scene: Roadside in Tokyo late at night, torrential rain, wet asphalt surface full of puddles and reflections, cold neon street lamps and blue light from buildings reflected in puddles, damp and hazy rain-mist atmosphere, dark cinematic film texture, IMAX wide aspect ratio, 8K ultra-clear, ARRI.
A highly detailed prompt for a 15-second 2D hand-drawn anime video showing the step-by-step preparation of Mapo Tofu with professional animation quality.
📝 Prompt
15-second Japanese 2D hand-drawn anime cooking video, 12 scenes, generated with text only (no reference images or storyboard images).
Art Style: Clean full-color Japanese 2D hand-drawn anime cooking animation. Soft pencil-like lines, gentle cell shading, warm hand-drawn background, a cozy home kitchen with the warm light of the stove flame, warm lighting that makes it easy to see the cooking, shadows visible under tools and ingredients, rich steam animation, glossy highlights on red chili oil and thickened sauce, natural timing of hand movements, stable hands and utensils.
Protagonist: The cooking process of Mapo Tofu in a wok. The color narrative is one-way only—from white tofu to a glossy reddish-brown simmering sauce. Only hands, ingredients, and tools are shown. No faces, eating scenes, or character reactions.
Scene Composition (one main action per scene; tofu corners stay sharp until the end, no crumbling or restoring):
1 (0.00–1.25) Close-up: Silken tofu is placed on an open palm and a knife carefully cuts it into even cubes. The blade is slow, hands stable and safe. A quiet, precise process cut.
2 (1.25–2.50) Top-down: Tofu gently slides from the palm onto the cutting board, arranged in neat white rows.
3 (2.50–3.75) Medium side-view: Ground pork sizzles in a heated wok, broken apart with a ladle until crumbly, and fat becomes transparent.
4 (3.75–5.00) Close-up highlight: The moment Doubanjiang and Douchi touch the meat, deep red chili oil blooms across the wok. A vivid explosion of color in one direction.
5 (5.00–6.25) 45-degree angle: Minced garlic, ginger, and chopped green onions are mixed in. Everything shines in the red oil.
6 (6.25–7.50) Side view: Soup is poured from a bowl, the reddish-brown liquid level rises, and it begins to simmer with small bubbles.
7 (7.50–8.75) Top-down view: White tofu gently slides from the cutting board into the simmering red sauce. Corners intact, floating softly.
8 (8.75–10.00) Close-up: The back of the ladle slowly and carefully pushes the tofu, coating it in sauce without breaking a single piece.
9 (10.00–11.25) Close-up highlight: Slurry is swirled in, the sauce visibly thickens and becomes glossy, enveloping each piece of tofu. A satisfying moment of texture change.
10 (11.25–12.50) Side close-up highlight: Large, slow bubbles form and pop on the thickened, glossy surface, with steam wafting up. A visual where you can hear the "bubbling" even without sound.
11 (12.50–13.75) 45-degree angle: A final swirl of chili oil and a pinch of ground Sichuan peppercorns are scattered. The grains settle on the glossy sauce.
12 (13.75–15.00) Top-down view: The finished Mapo Tofu simmers quietly in the wok—white, sharp-edged tofu peeks through the glossy reddish-brown sauce, steam rises, and green onions pop. A short, beautiful, warm final cut with a natural tempo, no dramatic slow-mo or excessive zoom.
Camera: Moves like a person around a stove, changing distance, angle, and height for each scene—close for tofu cutting, side for wok work, top-down for the finish. The camera stays calm within each scene. Do not show the finished product until scene 12.
Physical Continuity: Consistent size of wok, ladle, cutting board, and tofu between scenes. Maintain ingredient continuity. Tofu does not crumble, increase, or restore while simmering. Sauce color only darkens in one direction. Steam always goes up. Realistic gravity and liquid flow. Natural recipe order. No sudden state changes.
Prohibited: Finished product at start, repeating finished plate, title text, captions, subtitles, logo, watermark, readable labels, live-action, photo-real, 3DCG, claymation, plastic toy style, game render, ultra-realistic food photos, AI morphing, flickering, distorted hands, extra fingers, floating utensils, floating ingredients, restoring crumbled tofu, impossible knife movements, reverse cutting, disappearing wok, shape-shifting pan, unrelated ingredients, raw ingredients appearing after heating, reversed cooking order, sauce color lightening, revealing finished product before final scene, messy background, faces, eating characters, character reactions, person taking a bite, dialogue, narration, BGM.
A cinematic prompt for a 10-second music video in a neon-lit dark dance studio with continuous dynamic camera movements.
📝 Prompt
A cinematic 10-second music video filmed in a dark modern dance studio with smooth grey reflective floors, black walls, and horizontal neon tubes. Continuous dynamic camera movements, primarily medium shots and close-ups, never pulling too wide. The female lead is always moving, with no frozen or static poses.
A multi-shot video prompt for a high-end fashion influencer video. It uses a reference image for character consistency and details camera work, lighting, and specific movements across three shots in a dark purple studio.
📝 Prompt
Duration: 15 seconds\n\nAspect Ratio: 9:16 Vertical\n\nReference: Strictly use the adult female protagonist in the reference image, maintaining clear facial features, hairstyle, makeup, body proportions, and the entire outfit consistently throughout; it must be the same person with no costume changes.\n\nOverall Style:\n\nHigh-end influencer fashion short film, cold, charming, and confident. Dark gray studio with a black mirrored floor, dark purple and gold contour lighting, and soft beauty main lighting. Skin texture is realistic and delicate with slight film grain. Strong rhythmic feel with natural movements.\n\nSHOT 1 | 0—5s | Face Close-up & Eye Contact\n\nSubject: Female protagonist from the reference image.\n\nAction: Starts with an extreme close-up of the protagonist's face. She first slightly turns her face away, then slowly moves her eyes to stare directly into the camera, blinks gently, slightly raises an eyebrow, and has a faint, charming smile; one hand naturally brushes a stray hair by her ear, her body leans slightly towards the camera with a confident, attractive gaze.\n\nEnvironment: Background is blurred into soft dark purple bokeh.\n\nCamera: 85mm portrait lens, eyes are sharp and clear with shallow depth of field. The camera slowly pushes in and orbits the face about 15 degrees, capturing eye highlights and real skin details.\n\nConstraints: No facial deformation, no exaggerated pouting, no vulgar suggestive actions.\n\nSHOT 2 | 5—10s | Pull back for full body reveal\n\nAction: The protagonist raises her hand to sweep past the camera naturally, creating a smooth transition. The camera quickly and steadily pulls back from the face to a full-body shot. She walks forward two steps in high heels, stops with a cross-step, puts one hand on her waist, and slightly shifts her weight; she then turns into a side profile to show overall body proportions and clothing silhouette, before turning back to look at the camera.\n\nCamera: Seamless transition from 85mm close-up to 35mm full-body lens, slight low angle but maintaining an upscale feel. Camera follows and retreats; a fashion photography flash effect appears the moment she pauses.\n\nSound: Clear high heel footsteps, camera shutter sounds, and low-tempo fashion electronic beats.\n\nConstraints: Always maintain full integrity of the reference image's clothing, stockings, high heels, and their pattern details; display the overall look, do not focus on a single body part for too long.\n\nSHOT 3 | 10—15s | Orbital showcase & wrap-up\n\nAction: The protagonist continuously completes three natural model poses (front, side, back), with quick and smooth speed changes between movements. The camera orbits her about 270 degrees; her skirt, hair, and stray hairs show realistic slight swaying. At the end of the orbit, she quickly turns back to the front, walks toward the camera, leans in slightly, raises an eyebrow and blinks with a playful half-smile, and finally taps the camera lens with her finger as the screen cuts to black.\n\nCamera: 50mm lens stable orbit, mirrored floor creates soft reflections; finally zooms in quickly to a facial close-up, accurately focusing on both eyes.\n\nStyle: High-end, cold, charming, with a viral influencer showcase feel. Actions are rich but not messy; the character maintains command of the camera.\n\nNegative Constraints:\n\nForbidden: Identity changes, face swaps, clothing changes, lace pattern drifting, stocking seam movement, fluctuating body weight, exaggerated proportions, limb distortion, extra hands/feet, extra fingers, finger fusion, melting features, plastic skin, over-smoothing, sliding walk, high heel clipping, abnormal clothing transparency, exposure, vulgar poses, close-ups of private parts, up-skirt shots, camera angle drift, character teleportation, sudden background deformation, excessive slow motion, flickering, subtitles, text, logo, watermark.
A high-quality cinematic prompt for a rainy Tokyo night scene featuring a red sports car and a female lead in a crime action style.
📝 Prompt
Base theme: Deep night in Tokyo, continuous pouring rain, large puddles on the road, cold blue and pink neon lights covering the city, IMAX 8K film texture, ARRI dynamic tracking shot, strong motion blur, a layer of rain-mist lens flare, realistic live-action crime action film style, bright red high-performance sports car, a jade mascot hanging from the center console, and a glamorous female lead in a short skirt.
A cinematic FPV drone prompt for a high-speed flight through a chaotic dystopian battlefield with mechs and neon effects.
📝 Prompt
Immersive first-person flying camera perspective, no visible drone or flying device. The camera launches at insane speed across a colossal dystopian cyborg battlefield at night, flying only centimeters above shattered metal, burning wreckage, and rivers of glowing energy. It violently snap-rolls between the legs of towering combat mechs, knife-edges through collapsing steel structures, dives beneath gigantic walking war machines, then instantly climbs through exploding industrial ruins. Swarms of autonomous combat drones streak overhead while colossal cybernetic titans exchange devastating energy blasts that illuminate the battlefield. The camera constantly changes direction with brutal FPV precision,rapid S-turns, vertical dives, barrel rolls, power loops around gigantic reactor towers, split-S reversals, wall-hugging passes through ruined megafactories, and razor-close proximity flights beneath collapsing bridges. Neon holograms flicker through dense smoke as thousands of laser tracers, plasma arcs, sparks, and electrical storms fill the sky. Gigantic cybernetic creatures emerge from the darkness while endless ranks of futuristic soldiers and armored exosuits advance across the battlefield beneath towering ruined skyscrapers. The camera threads through impossibly tight gaps as collapsing buildings, burning aircraft, and massive mechanical debris crash around it, then rockets into a colossal mechanical canyon formed by fallen war machines. At the climax, the battlefield opens into an unimaginably vast cybernetic wasteland where a planet-sized artificial intelligence core rises above the horizon, surrounded by colossal rotating rings, lightning storms, and endless mechanical cities stretching to infinity. Continuous POV shot, no cuts, relentless acceleration, extreme high-speed FPV racing, aggressive banking, rapid altitude changes, barrel rolls, corkscrews, split-S maneuvers, power loops, knife-edge turns, realistic inertia, cinematic motion blur, volumetric smoke, dynamic lighting, neon reflections, hyper-detailed dystopian environments, surreal cyberpunk architecture, blockbuster sci-fi VFX, IMAX quality.
A cinematic video prompt for Seedance 2.0 that creates a cozy Ghibli-style anime cooking sequence with detailed macro shots of dough preparation and warm kitchen lighting.
📝 Prompt
Anime cooking short film, Ghibli food aesthetic, warm golden kitchen light, potted plants in background, cozy apartment kitchen, 16:9. A series of rapid close-up macro shots: hands punching down a ball of risen dough, fingers stretching the dough wide
A stylized animated sequence of Erling Haaland eating lasagna in a Manchester City kit while his mirror reflection acts independently.
📝 Prompt
An animated, stylized video featuring professional footballer Erling Haaland sitting at a dining table at night, wearing a Manchester City home kit. He is enthusiastically eating a large plate of lasagna, puffing out his cheeks to an extreme, comical degree as he chews.
To his right, a large wall mirror reflects his image. As he eats, his reflection suddenly develops a mind of its own, making bizarre, exaggerated facial expressions, gasping with wide eyes, and violently banging its hands against the glass from inside the mirror. The real Haaland notices the erratic behavior of his reflection, stops mid-bite, and stares back with a mixture of confusion and shock before returning to eating his meal with stuffed cheeks. The setting is a cozy apartment room with a city skyline visible through the window and a Manchester City poster on the wall.
A complex, multi-shot narrative video prompt depicting a family's desperate escape from a collapsing house during a massive earthquake.
📝 Prompt
Subject: Daniel, a 42-year-old father in a grey henley and dark jeans; Maya, his 17-year-old daughter with tied-back curly hair, a red jacket, and black trousers; Noah, his 8-year-old son with brown hair, in a yellow T-shirt and blue pajama trousers.
Action: The family scrambles to escape their collapsing suburban house and crumbling neighborhood during a massive earthquake.
Context: Inside a suburban home during breakfast, then outside on the driveway, street, and overlooking a collapsing city skyline.
Cinematography: 24 fps, grounded live action, transitioning from a locked 24mm wide kitchen shot, to a low handheld shot, to a lateral tracking shot, to an 18mm rising crane shot, and finally a low 14mm backward tracking shot. Cut to between shots.
Style & Ambiance: Photorealistic, gritty, Kodak Portra 400 film look, cinematic lighting filtered through thick rising dust, gravity-based structural collapse with realistic physics, no slow motion, no explosions, debris and ground falling inward.
Dialogue: "Dad!", "Run!", "I've got you."
On-Screen Text: No text, subtitles, or captions are visible on screen.
SFX: Low-frequency geological rumble, plates and glass shattering, timber snapping, crumbling concrete, car alarms, distant panic.
Timestamped Sequence: [00-02s] Shot 1: Inside a kitchen, a subterranean groan rises. Water trembles, the lamp swings, and a sudden sideways jolt throws Daniel, Maya, and Noah down. Plates shatter. / [02-05s] Shot 2: Cut to a low handheld shot. A massive crack splits the floor, isolating Noah on a tilting slab. Maya crawls across the shifting boards, grabs Noah's wrists, and pulls him clear. / [05-08s] Shot 3: Cut to a lateral tracking shot. Daniel braces a falling ceiling beam while Maya drags Noah outside. Daniel yells "Run!". Maya sends Noah out, then pulls Daniel clear as the roof collapses behind them. / [08-11s] Shot 4: Cut to an 18mm crane shot rising above the street. The road arches like a wave and folds inward. Power poles lean and cars slide as houses rotate and sink into a deep trench. / [11-15s] Shot 5: Cut to a low 14mm tracking shot moving backward. Daniel carries Noah while Maya pulls him. The driveway breaks, Daniel falls as a slab tips. Maya grabs his forearm and pulls them over the edge. They collapse behind a retaining wall as their house and street vanish in dust. Daniel embraces them.
A detailed prompt for a character-consistent countryside video, styled like a nostalgic early-2000s handheld camcorder recording.
📝 Prompt
One original female character with identity perfectly locked across the entire video. The same face, hairstyle, body shape, clothing, and accessories remain completely consistent. She has short chestnut hair tucked behind one ear, wears a mustard-yellow oversized hoodie, black athletic shorts, white crew socks, vintage running shoes, and a simple digital wristwatch.
Location: a quiet countryside railway crossing at sunrise. Empty train tracks stretching into the distance, open grassy fields, wildflowers, old wooden fences, a small railway signal, morning mist, scattered birds, and distant hills. No houses, no streets, no vehicles, no city elements, no shops, and no crowds.
The camera feels like an old consumer camcorder from the early 2000s. Unpredictable handheld movement, accidental zooming, exposure constantly adjusting, delayed autofocus, washed-out colors, visible digital noise, tape compression artifacts, soft image quality, slight motion blur, and completely unstabilized footage. It should feel like an amateur family recording, never cinematic.
She begins sitting on the railway platform edge, tying her shoelaces while looking toward the empty tracks. She stands and slowly walks through tall grass, brushing wildflowers with her fingertips. A gust of wind lifts her hoodie as she laughs naturally. She discovers a paper airplane on the ground, unfolds it, smiles with curiosity, and gently tosses it into the air. The camera struggles to keep focus as it drifts away.
She then stands beside the crossing signal, closes her eyes for a brief moment, taking in the morning breeze. In the final shot she walks away across the open field, turns once with a bright genuine smile, gives a small wave without speaking, and the recording suddenly stops mid-motion as if the camcorder battery died.
Natural audio only: birds singing, insects, distant wind across the fields, grass rustling, soft footsteps, occasional railway signal clicking, and ambient countryside sounds. No music, narration, artificial effects, or post-production audio.
A structured multi-shot action prompt for a desert military ambush featuring a giant scorpion attack on a relay post.
📝 Prompt
A rocky ridge above an army camp in bright daylight, a small radio relay post with an antenna mast standing at the top. A giant scorpion, armored with a whipping stinger tail, bursts up from the rocks near the relay post and grabs the operator. Lower on the ridge slope, a gunner is already loaded, posted there to watch this signal ridge every day. Sound: cracking rock, scraping armor, shouting, the scorpion's hiss, radio voices.
Shot 1 (0–3s) — THE HOOK: Low shot at the relay post. The giant scorpion bursts up from between the rocks, claws snapping around the operator's arm, its tail whipping over its back near the antenna mast. He shouts into his radio: "IT'S GOT ME AT THE RELAY POST!"
Shot 2 (3–6s): Lower on the slope, the gunner lifts the bazooka onto his shoulder, tracking the scorpion up near the ridge line — but holds his fire, the operator still too close. He calls on the radio: "Slide down the slope! Now!"
Shot 3 (6–9s): The operator wrenches free and slides down the loose rock slope away from the relay post. The scorpion turns and climbs onto the open ridge line above him, alone now, claws snapping against the empty sky.
Shot 4 (9–13s) — BIG SLOW-MOTION MOMENT: The scorpion stands alone on the open ridge now. The gunner fires from lower on the slope. Bullet time — the bazooka kicks back, smoke bursting from the tube, the rocket streaking up the ridge in slow motion, dust and loose rock hanging in the air.
Shot 5 (13–15s): Time snaps back. A massive blast tears through the scorpion at the top of the ridge, fire and rock scattering against the sky. The operator lies flat lower on the slope, safe, as smoke drifts off the ridge line.
A multi-shot narrative prompt featuring a giant crocodile attacking a mechanic at an army vehicle repair shed, including specific shot breakdowns and synchronized audio cues.
📝 Prompt
An army vehicle repair shed in bright daylight, a wide open doorway leading out into a dusty yard, tools and fuel drums stacked along the walls inside. A mega crocodile, huge as a truck, drags a mechanic out of the shed toward the open yard. At the shed's corner, a gunner is already loaded, posted there to watch this repair yard every day. Sound: scraping metal, groaning tools, croc hissing, shouting, radio voices.
Shot 1 (0–3s) — THE HOOK: Low shot at the shed doorway. The mega crocodile drags the mechanic by his overalls out through the open doorway, tools clattering off a workbench as he claws at the ground. He shouts into his radio: "IT'S DRAGGING ME OUT OF THE SHED!"
Shot 2 (3–6s): At the shed's corner, the gunner lifts the bazooka onto his shoulder, tracking the crocodile through the doorway — but holds his fire, the mechanic still too close. He calls on the radio: "Roll behind the drum! Now!"
Shot 3 (6–9s): The mechanic twists hard and breaks free, rolling behind a stacked fuel drum at the edge of the yard. The crocodile drags itself fully into the open shed doorway, alone now, no one near it, jaws snapping at empty air.
Shot 4 (9–13s) — BIG SLOW-MOTION MOMENT: The croc stands alone in the open doorway now. The gunner fires. Bullet time — the bazooka kicks back, smoke bursting from the tube, the rocket streaking straight at the doorway in slow motion, dust rising off the ground.
Shot 5 (13–15s): Time snaps back. A massive blast tears through the shed and the crocodile together, fire and twisted metal bursting out through the doorway. The mechanic peers out from behind the fuel drum as smoke rolls across the yard.
A multi-shot action prompt describing an alien attack at a military motor pool, including specific shot timing and slow-motion effects.
📝 Prompt
An army motor pool yard in bright daylight, rows of parked trucks and jeeps, tool racks along one side, open ground between the vehicles. A mechanic lies working under a truck when a tentacled alien — brownish-black and slimy — wraps around his legs and drags him out into the open yard. At the yard's watch post, a gunner is already loaded, covering the motor pool the way he does every shift. Sound: dragging tools, wet tentacles slapping, shouting, the alien's low roar, radio voices.
Shot 1 (0–3s) — THE HOOK: Low shot across the yard. The alien's slimy tentacles wrap around the mechanic's legs and drag him out from under the truck, tools scattering across the ground. He claws at the dirt and shouts into his radio: "IT'S GOT ME! PULLING ME OUT!"
Shot 2 (3–6s): At the watch post, the gunner drops behind his weapon, tracking the alien across the open yard — but holds his fire, the mechanic still too close. He calls on the radio: "Roll under the next truck! Get clear!"
Shot 3 (6–9s): The mechanic twists hard and rolls sideways under a parked jeep nearby, breaking the tentacle's grip. The alien, empty-handed, slides forward into the open middle of the yard, rearing up tall and alone among the parked trucks, tentacles spread wide.
Shot 4 (9–13s) — BIG SLOW-MOTION MOMENT: The alien stands alone in the open yard now, fuel drums stacked nearby. The gunner opens fire. Bullet time — the long burst rips across the yard in slow motion, muzzle flashes lighting the parked trucks, dust kicking up as it tears into the alien and the drums behind it.
Shot 5 (13–15s): Time snaps back. The fuel drums ignite together with the alien in one huge fireball across the motor pool, fire rolling between the parked trucks. The mechanic peers out from under the jeep as smoke drifts over the yard.
A seamless cinematic video prompt designed for a 15-second one-take shot with ultra-slow motion and a 90s aesthetic.
📝 Prompt
Generate a seamless continuous one-take video using the reference images. No dialogue, hard cuts, fade transitions, or opacity changes at any moment. Use ultra slow motion with a relaxed summer atmosphere and nostalgic ’90s visual aesthetic. Connect every scene naturally using only smooth camera movement transitions. Add matching transition sound effects and keep the cinematic ambient audio flowing continuously without interruption. No music. Maintain visual consistency, coherent motion, and realistic cinematic lighting throughout. 15 seconds, 16:9 aspect ratio, 720p resolution.
A high-intensity prompt for generating a professional kitchen scene featuring an intense chef, flaming woks, and rapid close-ups of culinary skill.
📝 Prompt
A cinematic, action-packed cooking scene in a professional kitchen featuring an intense animated male chef with a fierce expression. He slams a blazing hot wok onto a roaring gas flame, pours in oil that erupts into white smoke, and ignites dramatic fire as he tosses the wok. Rapid close-ups show expert knife skills slicing fresh bok choy, carrots, cucumbers, and red bell peppers before the vegetables are tossed high into the flaming wok and coated with a rich dark sauce. The glossy stir-fry is plated elegantly on a white dish, ending with a close-up of the chef tasting it with a focused, critical expression as flames flicker in the background. Ultra-realistic, cinematic lighting, dynamic camera angles, slow motion, high detail, 4K.
A detailed RAW-style photography prompt for Seedance 2.0 aimed at achieving a realistic, unretouched smartphone selfie aesthetic with an East Asian subject.
📝 Prompt
STYLE: unretouched RAW-style photography, authentic UGC smartphone selfie aesthetic, shot on front-facing phone camera, slight wide-angle distortion, natural ambient light, visible facial microtexture (skin pores, fine lines, natural texture, subtle imperfections), true-to-life color grading, candid amateur framing. LAYOUT: arm-length front camera angle slightly above eye level, subject fills most of the frame, casual slightly tilted composition. SUBJECT: original young adult woman in her early-to-mid 20s, East Asian features, long straight vividly blue-dyed hair reaching lower back, side-parted with face-framing strands, small silver hairclip above right temple, large expressive dark gray-blue eyes, delicate facial structure, soft confident smile, one arm extended holding the phone, fair skin with natural flush on cheeks. ENVIRONMENT: gym locker room, bright fluorescent light, lockers and bench in background. DETAILS: y2k style — baby pink cropped cardigan, low-rise flared jeans, butterfly hairclips, tinted sunglasses on head; realistic dyed-hair texture with slightly darker roots, flyaway strands, natural skin shine on nose and forehead, slight motion blur on extended arm. NEGATIVE: no beauty retouching, no Instagram filters, no CGI, no 3D render, no anime, no illustration, no over-retouched skin, no doll skin, no porcelain skin, no airbrushed skin, no skin blur, no glossy plastic finish, non-photorealistic output rejected, no studio lighting, no professional camera look
A cinematic travel vlog prompt for a video featuring a woman's journey on a Japanese train with varied scenic transitions.
📝 Prompt
Train Window Travel Diary
A cheerful young woman (@ image) starts her day by boarding a Japanese bullet train with her camera. She sits beside the window, filming beautiful scenery as cities, rivers, mountains, and rice fields rush past. She arrives at different stations throughout the journey, steps out to capture famous landmarks and local streets with her camera, then happily shows every photo on the camera display. The vlog feels peaceful, cinematic, and adventurous, ending with her waving goodbye from the train window as the train departs.
A detailed storyboard for a 15-second 3D animation commercial where a character experiences magical environment transitions by putting on sunglasses.
📝 Prompt
A 15-second continuous single-take 16:9 widescreen video in 3D animation style. Warm, soft, natural lighting throughout. Opening (0s–3s): A cozy sunlit modern living room. A young girl in a bear-patterned pajama set sits cross-legged on a beige sofa reading a book. A pair of black sunglasses rests on the wooden coffee table in front of her. She puts down the book, reaches forward, picks up the sunglasses, and slowly puts them on. Camera: medium shot, static, warm morning light through the windows. Magic transition 1 (3s–6s): The instant the sunglasses settle on her face, the living room background seamlessly dissolves and transforms into a bright tropical beach — turquoise ocean waves rolling in, tall palm trees swaying, warm golden sunlight. The girl is now on the beach in her pajamas, looking around in delighted surprise. Camera: same medium shot angle, girl centered. Magic transition 2 (6s–8s): She slowly slides the sunglasses down to the tip of her nose and peeks over the rim. Instantly the tropical beach snaps back into the cozy living room. She looks around, amused. Camera: medium close-up on her face, eyebrow raised, playful expression. Magic transition 3 (8s–12s): She pushes the sunglasses back up onto her eyes. The living room instantly transforms into a majestic snow-covered mountain landscape — large white snowflakes drifting slowly down from a pale sky, pine trees in the background. She reaches out one hand, palm up, and a single large snowflake lands gently on her fingertip. She watches it with a soft smile. Camera: medium shot slowly pushing in slightly. Magic transition 4 (12s–15s): She takes the sunglasses off completely. The snowy mountain fades and the cozy living room returns. She glances at the sunglasses in her hand, then gently places them back on the wooden coffee table. Camera rapidly pushes forward in a crash zoom, ending on an extreme close-up of the black sunglasses resting on the wood grain surface. Hold. Clean negative space on upper right for brand logo.
Author:Ima Studio | Source:Link | Published: Jul 19, 2026
Cinematic Shadow Horror Scene
A high-quality cinematic horror prompt for Seedance 2.0 featuring a man whose shadow detaches and attacks him on a dark residential street.
📝 Prompt
STYLE Ultra-realistic live-action cinematic horror, photorealistic, Hollywood-quality filmmaking, grounded realism, natural human movement, realistic skin textures, subtle film grain, high dynamic range, dramatic cinematic lighting, dark atmospheric mood, suspenseful psychological horror, realistic physics, immersive storytelling. CHARACTER A handsome young adult male with short dark hair, realistic facial features, expressive eyes, wearing a black jacket over a dark gray T-shirt, dark jeans, and sneakers. Natural body proportions, realistic skin texture, authentic facial expressions, no exaggerated acting. ENVIRONMENT A quiet empty residential street at night. Warm orange streetlights illuminate the pavement, parked cars line the roadside, dim houses in the background, light fog drifting through the street, wet asphalt reflecting the streetlights, gentle night breeze moving leaves, realistic urban atmosphere. CAMERA STYLE Shot on an ARRI Alexa 65 with anamorphic lenses. Smooth cinematic camera movements, realistic handheld stabilization during intense moments, shallow depth of field, natural motion blur, cinematic framing, subtle lens breathing, dramatic composition. LIGHTING Warm sodium-vapor streetlights, soft moonlight fill, realistic shadows, volumetric fog, subtle rim lighting, high contrast without crushing blacks, natural reflections on wet pavement. TIMELINE 0.0–4.0s | Scene 1 – The Walk Wide establishing shot of the quiet street at night. The handsome man walks alone at a relaxed pace down the empty road. Long realistic shadow stretches behind him from the streetlights. The camera slowly tracks behind him at waist height. Ambient night sounds only. The atmosphere feels calm but unsettling. 4.0–8.0s | Scene 2 – The Shadow Escapes As he casually walks past a concrete wall, his shadow suddenly tears itself away from the pavement with an unnatural ripping motion. Instead of following him, the shadow rapidly climbs onto the wall beside him while his real body continues walking. The camera pushes in as he notices the impossible movement. He abruptly stops, slowly turns toward the wall, his face frozen in disbelief and fear. 8.0–12.0s | Scene 3 – The Shadow Attacks The shadow peels away from the wall and rapidly transforms into a solid three-dimensional pitch-black humanoid version of himself with a featureless matte-black body. It lunges forward and violently grabs his shoulders. He screams in absolute terror, struggling desperately to break free before pulling away and trying to run. Handheld camera movement increases the intensity while maintaining realistic motion. 12.0–16.0s | Scene 4 – Surrounded As he runs, multiple identical shadow figures silently emerge from walls, parked cars, lamp posts, and the ground itself. They completely surround him in a circle. He spins in panic, breathing heavily, screaming uncontrollably. He covers his face
A detailed storyboard for a Pixar-style animation about a tiny ghost whose attempts to be scary result in making unexpected friends.
📝 Prompt
Style: Pixar-quality 3D animation, ultra-cute, expressive characters, soft cinematic lighting, vibrant autumn colors, cozy Halloween atmosphere, exaggerated facial expressions, smooth animation, whimsical music, heartwarming comedy, highly detailed environments, shallow depth of field, 4K. 0:00–0:05 — The Big Scare Attempt Camera: Slow dolly through a charming neighborhood decorated with pumpkins, glowing lanterns, and colorful autumn leaves before stopping at a tiny floating ghost hiding behind a tree. Action: A tiny, round white ghost with oversized sparkling eyes and rosy cheeks peeks out nervously. It takes a deep breath, puffs up to look intimidating, and jumps in front of a couple walking down the sidewalk, shouting a tiny "Boo!" Instead of screaming, the couple smiles warmly. One whispers, "Aww... look how adorable!" The ghost freezes in confusion, embarrassed as its cheeks blush pink. 0:05–0:10 — Trying Harder Camera: Fast, playful cuts following the ghost around the neighborhood. Action: The little ghost tries everything it can think of: It wears a spooky vampire cape. It makes a silly scary face. It rattles tiny chains. It floats upside down while yelling another "Boo!" Everyone who sees it laughs affectionately. An old lady gently pats its head. A dog happily chases it, wagging its tail. The ghost lets out a tiny sigh. 0:10–0:15 — Total Failure Camera: Medium shot following the ghost as it slowly floats away, shoulders slumped. Action: Sitting alone on a park bench beneath glowing lanterns, the ghost sadly watches other Halloween decorations. A small tear forms in its eye. It whispers quietly, "Maybe I'm just not scary enough..." 0:15–0:20 — An Unexpected Friend Camera: Low-angle shot as a little girl notices the lonely ghost. Action: She slowly walks over with a warm smile and gently opens her arms. The ghost looks surprised. She gives it the biggest hug. The ghost's eyes become wide with happiness. 0:20–0:25 — Everyone Joins In Camera: Wide shot revealing more children running toward the ghost. Action: One by one, the kids gather around, giving the tiny ghost hugs, high-fives, and gentle pats. The ghost laughs for the very first time. Its body begins glowing with a soft golden light. Tiny glowing hearts float gently around everyone. 0:25–0:30 — The Happiest Ghost Camera: Slow pull-back as the neighborhood glows under the moonlight. Action: The once-shy ghost happily floats above the children while everyone waves goodbye. Instead of saying "Boo," the ghost smiles brightly and says, "Hiiiii!" Everyone laughs. The final shot freezes on the ghost's joyful smile as tiny glowing hearts drift into the night sky. End Card: "Sometimes being kind is the greatest magic of all. 👻❤️"
A highly detailed prompt for creating a nostalgic 1970s-style Japanese television commercial for instant ramen, featuring specific scene directions, character consistency, and retro film aesthetics.
📝 Prompt
1970s Japanese TV commercial-style live-action video, 15 seconds. 16mm color film texture, faded reddish warm tones, film grain, soft focus. Only these 4 characters appear: a mother in her 30s wearing an apron, a father in his 40s in a tank top, an elementary school boy, and an elementary school girl. The same 4 people throughout. No other people appear. Do not increase the number of people. Everyone continuously breathes, blinks, and sways; no stationary figures.
[Shot 1 | 0-5s] Apartment living room, evening. A family of 4 (mother, father, boy, girl, only 4 people) around a low table. Tatami mats, CRT TV, floral thermos, round fluorescent lighting. Two children hold chopsticks and beg 'I'm hungry,' and the mother stands up smiling. The father lowers his newspaper and laughs.
[Shot 2 | 5-10s] Cut to kitchen. No people shown. Foreground: Soy sauce ramen simmering in an aluminum saucepan with rising steam. Chopsticks lift the noodles, swaying glossy curly noodles. Green onions and naruto. On a dry counter next to the stove in the background, an orange retro instant noodle package stands. The package has 'MARUFUKU' written in large, white-outlined thick brush letters. Keep the package away from the pot, soup, and steam; never put it in the pot. Keep it dry and still.
[Shot 3 | 10-13s] Cut to a close-up of the boy at the table. He slurps noodles vigorously and smiles happily with a full mouth. The remaining 3 family members (mother, father, girl) are blurred in the background, laughing.
[Shot 4 | 13-15s] Final shot. The family of 4 smiles at the camera. In the center, a large red brush-lettered logo with white outlines saying 'MARUFUKU Shoyu Ramen' appears prominently. Write the text exactly as specified without distortion or different characters. Showa-era CM end card style. The logo remains still once displayed.
[Audio] Cheerful Showa CM jingle with flute and marimba. Sounds of slurping noodles, simmering pot, and family laughter. The jingle concludes in Shot 4 with a bright male narration: 'Marufuku, Shoyu Ramen!'
A comprehensive prompt for recreating a 1970s era Japanese parliamentary speech with authentic period broadcast aesthetics and precise movement instructions.
📝 Prompt
[Scene Setting]
Early 1970s, Japan's National Diet, House of Representatives Chamber. A policy speech at an extraordinary session.
Standing at the rostrum is a Prime Minister around 60 years old. Gray hair neatly parted 70/30, wearing a dark suit with a white pocket square and a legislator's badge on the lapel.
He possesses a calm dignity and is answering questions grandly with a manuscript before him.
[Lip-sync/Dialogue]
Japanese, Male, 60s, a low, relaxed, and resonant voice.
The heavy oratorical style characteristic of Showa-era politicians. Stretching word endings and pausing at punctuation.
"The stability of the people's lives is the greatest mission assigned to politics.
The government intends to exert its full efforts toward price stability and economic development."
[Movement Instructions — Everyone on screen must move constantly. No static figures]
- Prime Minister (Speaker):
* Synchronize mouth movements accurately with the dialogue.
* Head sways slightly while speaking, and shoulders move up and down with breathing.
* At "it is the greatest mission," raises and waves the right hand in an emphatic gesture.
* Looks down at the manuscript at sentence breaks, then raises his head to look forward.
* Natural blinking frequency.
- Background Legislators (Assign individual movements to everyone):
* Legislator on the left: Flipping through materials and leaning forward to take notes.
* Legislator in the center background: Nodding while whispering with the person next to them, changing head direction.
* Legislator on the right background: Removing hand from chin, adjusting posture, and touching glasses.
* Everyone continues breathing, blinking, and making subtle posture changes, ensuring no one is frozen like a mannequin.
[Camera/Visual Style]
- Bust shot from slightly below front. Not perfectly fixed; always include very slight drift and shake like a handheld broadcast camera.
- 1970s NHK Diet broadcast style: Black and white, scan lines, film grain, flicker, and CRT-specific vignetting.
[Audio]
- Slightly muffled sound through a microphone, chamber reverberation.
- Ambient sounds: Murmurs, paper flipping, throat clearing.
- Sparse shouts of "No objection!" and distant applause occur at the end of the dialogue.
A highly detailed 15-second video prompt for Seedance 2.0 featuring a female character performing a playful dance in a park. The video includes complex AR magic effects, such as a floating head avatar that transforms into a heart shape and seamless character-layer animations.
📝 Prompt
Duration: 15 seconds
Aspect Ratio: 9:16 vertical screen
Structure: Fixed camera, continuous long shot, no cuts throughout.
Overall Style: Photorealistic character combined with light and cute AR magic effects—sweet, playful, and nonsensical, similar to creative confession short videos. All abnormal changes must be presented as obvious digital stickers, masks, and elastic layer animations, without showing any realistic physiological details.
SUBJECT:
The protagonist 100% matches the input reference image. Face, hairstyle, body shape, clothing, shoes, and accessories remain exactly as in the reference image throughout, with no redesign of the outfit. The flying AR avatar must also maintain the same face, hairstyle, and head accessories as the protagonist.
ENVIRONMENT:
A sunny summer day at an outdoor park plaza with light gray paved ground. Dense green trees are on the left background, a dark wooden pergola on the right, and a large area of pure blue sky above. Strong natural sunlight shines from the top right, casting the character's shadow toward the bottom left.
CAMERA:
Fixed low-angle slightly upward shot, 24mm full-body wide angle. The protagonist is always centered in the frame with feet fully visible; sufficient space must be left in the blue sky above. The camera does not push, pull, pan, zoom, or follow the AR avatar; all distance changes are produced by the effect layers actively moving toward or away from the lens.
SHOT 1 (0:00–0:05.8) — AR Avatar Bouncing and Kissing Toward the Lens
0:00–0:00.4
The protagonist smiles happily at the camera, doing a light jog-in-place dance to the beat: knee lifts, cross steps, light front kicks, with arms swinging naturally. Movement begins from the first frame.
0:00.4–0:02.2
The protagonist's face layer seamlessly switches to an independently flying circular AR avatar, bouncing upward into the blue sky from its original position. A smooth, clean dark elliptical mask is used at the original position simultaneously, clearly expressing it as mobile short video cutout magic.
The AR avatar bounces along a clear trajectory:
High point directly above → waist height on the right side → near the right knee → kicked up by the lifted knee → flying back above the body.
The main character continues the knee lifts, cross steps, front kicks, and hands-on-hips dance moves, appearing to bounce a cute avatar balloon with their knee. The avatar maintains normal size, clear features, and a happy expression, without random teleportation.
0:02.2–0:02.4
The AR avatar returns accurately to its original position, the mask disappears, and the protagonist returns to the full frame, shrugging with a smile for half a beat.
0:02.4–0:04.0
The protagonist bends their knees and swings their hips left and right, raising hands to shoulder height, performing pushing motions with palms. The face layer switches to the flying AR avatar again, moving strictly in sync with the palm rhythm:
Flying right out of the frame → returning from the left → crossing the screen to the right → being flung left out of the frame again.
The avatar carries natural motion blur, but features, hairstyle, and accessories remain stable.
0:04.0–0:05.4
The main character continues pointing to the sky, side-stepping, twisting the waist, lifting knees, and doing small steps. The AR avatar reappears from the top right, tumbling and rotating above the person, circling to the top left along a large arc, then gradually flying toward the camera.
0:05.4–0:05.8
The AR avatar approaches quickly along the lens axis, enlarging into an extreme close-up of the face. The protagonist naturally closes their eyes, cheeks slightly puffed, lips pursed, blowing a cute kiss to the lens.
Multiple bright red semi-transparent lipstick kiss marks spread outward from the mouth, with the center kiss mark being the largest. The kiss marks appear only as 2D AR stickers and do not change the character's facial structure.
SHOT 2 (0:05.8–0:10.8) — Heart-Shaped Avatar and Comedic Passing
0:05.8–0:07.6
The extreme close-up AR avatar flexibly transforms into a photorealistic heart-shaped outline about three times the size of a normal head: two arcs at the top, tapering to a point at the bottom. It still maintains the same real face of the protagonist, eyes closed, continuing the sweet blowing-kiss expression.
The main character turns to face away from the camera, feet apart, leaning forward and swinging hips left and right to the beat; arms are naturally extended downward to the sides.
The giant heart avatar, as an independent AR layer, bounces regularly between the area directly above the person and the height of one hip/thigh:
Above → low side position → above → slightly descending → floating up again.
0:07.6–0:09.1
The heart avatar begins to tumble and rotate while smoothly shrinking back to normal size and flying high into the sky.
The main character rises from the leaning position, completing the turn, cross steps, hip twists, and arm extensions. The shrunken avatar rotates synchronously in the high sky, gradually descending to return accurately to the original position; the dark mask disappears simultaneously.
The protagonist is restored to full frame, smiling happily at the camera, raising both arms in celebration for half a beat.
0:09.1–0:10.8
The protagonist first shrugs playfully, then leans back significantly and twists shoulders quickly, triggering the AR avatar flight effect again.
The avatar slides to the person's right, then moves down along the waist, finally stopping in front of the lifted thigh and loose clothing, creating a visual comedic point of the 'avatar entering the clothing layer.' The avatar overlaps only in the foreground and does not blend with the clothing texture.
Subsequently, the AR avatar flies quickly out of the frame, and the original position continues using a clean dark elliptical mask, leaving space for the next heart magic.
SHOT 3 (0:10.8–0:15.0) — Heart Within a Heart and Layer Liftoff
0:10.8–0:11.4
The main character stands in the center of the frame, first quickly rubbing hands in front of the chest and abdomen, then extending arms left and right with fingers spread, as if summoning a new confession effect.
0:11.4
A bright pink, full, and thick 3D jelly heart suddenly appears in the center of the blue sky. The front of the heart is embedded with the same pink heart-shaped face of the protagonist, showing a sweet smile.
The heart must be a romantic AR design with a smooth and soft surface, not using realistic textures.
0:11.4–0:12.5
The protagonist's arms initiate elastic cartoon deformation, extending continuously from the shoulders to about three times their normal length toward the top left and right.
The arms first form a giant V-shape, then curve inward from the top. Shoulder, elbow, wrist, and five-finger structures remain clear. Hands approach at the top center of the frame, with fingers lightly crossing to form a heart notch.
The two extended arms encircle to form a giant outer heart, with the pink heart avatar suspended accurately in the center, creating a clear 'heart within a heart.' Hold this composition for about half a second.
0:12.5–0:13.1
Hands gradually separate, and arms smoothly shrink back to normal length. The pink heart avatar descends, color returns to natural, the outline returns to a normal head, and it accurately returns to the character's original position; the dark mask disappears simultaneously.
0:13.1–0:13.8
The complete protagonist raises arms in a V-shape, smiling happily at the camera, rotating in place with their footsteps: front → back → turning back to front. The movement is light and fluid.
0:13.8–0:14.1
The protagonist does a wide side lunge, arms held straight above the head, with the overall frame fully extended vertically.
The character image at the waistline switches into two independent AR layers: the 'upper character layer' (including head, arms, and top) shoots up vertically like a spring and quickly flies out the top of the frame; the 'lower character layer' (including bottom, legs, and shoes) remains standing in place.
This process must look like an obvious short video paper-cut animation, without showing any realistic internal details.
0:14.1–0:15.0
The camera remains completely fixed, retaining only the AR layer of the lower clothing and shoes.
The soles of the shoes always contact the ground. The lower layer performs two spring-like stretches and compressions according to the rhythm of 'pull high → press low → pull high → press low,' with the amplitude gradually decreasing.
Keep a low, wide stance for the final 0.3 seconds. The upper character layer does not return, ending directly on the bright park scene without fading or turning to black.
PERFORMANCE:
The protagonist maintains a happy and playful performance state throughout. Smiles and looks directly at the lens when in full character; expression is relaxed during AR avatar bouncing; eyes close naturally and lips purse when blowing a kiss; sweet smile when the heart avatar appears. The main character's dancing must not pause due to effects.
AUDIO:
Playful and light pop dance music, with the beat strictly synchronized with avatar bounces, horizontal flights, kisses to lens, heart appearances, and character layer liftoffs. Add soft 'whoosh, pop, spring rebound' comedy sound effects. No dialogue, no subtitles.
CONSTRAINTS:
All effects must be clearly presented as AR stickers, masks, paper-cut layers, or elastic animations. The original styling of the protagonist and the reference image remains stable throughout. There is only one avatar layer and one main character layer. Fixed single shot, fixed background, fixed lighting; all deformation processes are smooth and continuous, without showing realistic physiological expressions.
---
Negative:
Horror atmosphere, realistic injury expression, physiological details, a second avatar, character duplication, face drift, feature distortion, transparent avatar, avatar sticking to clothing, extra arms, extra fingers, fused fingers, disconnected arms, arms passing through each other, broken layer edges, heart turning into a realistic object, clothing changes, shoe changes, disappearing accessories, jumping background, camera pushing/pulling, camera tracking the avatar, sudden cuts, sudden scene deformation, plastic CG skin, anime rendering, subtitles.
An ultra-detailed prompt for an authentic 2026-style vacation video of a young Japanese woman on a beach, featuring timeline-based actions and camera physics.
📝 Prompt
A young Japanese woman in her early 20s with effortless natural beauty, warm expressive eyes, realistic sun-kissed skin, minimal makeup, and black straight hair tied in a loose low ponytail wears an oversized sand-beige linen shirt over a muted seafoam ribbed tank top, ivory drawstring linen pants, delicate gold necklace, silver hoop earrings, carrying cream canvas sneakers while walking barefoot on a quiet Japanese Pacific beach during golden hour. Maintain identical identity, facial features, hairstyle, clothing, body proportions, skin tone, and accessories throughout the video. The location features untouched sand, gentle Pacific waves, driftwood, rocky shoreline, weathered seawall, distant fishing boats, native grasses, and a small lifeguard tower with no crowds or commercial activity. Capture everything like a genuine 2026 vacation video using a handheld full-frame mirrorless camera with natural micro-shake, autofocus breathing, slight missed focus, rolling shutter, exposure shifts, authentic lens flare, imperfect framing, and realistic depth of field—no gimbal, drone, cinematic tracking, or slow motion. Ultra-realistic documentary style with lifelike skin texture, natural body language, realistic clothing physics, HDR lighting, soft highlight roll-off, accurate skin tones, airy pastel colors, and zero AI artifacts. Audio includes only ocean waves, seabirds, coastal wind, footsteps, fabric movement, distant fishing boats, and quiet ambient sounds. Timeline: 00:00–00:03 walks barefoot through shallow waves carrying sneakers and smiling as autofocus briefly hunts. 00:03–00:06 crouches to examine seashells, smiles, and gently returns one to the sand while the camera awkwardly reframes. 00:06–00:09 walks beside the seawall sipping iced tea as wind moves her shirt and sunlight sparkles across the water. 00:09–00:12 sits on driftwood watching the ocean, brushes hair behind her ear, then laughs naturally at a friend's joke. 00:12–00:15 softly says "Kirei da ne" ("It's beautiful, isn't it?"), continues walking along the shoreline, glances briefly toward the camera, and the recording ends unexpectedly mid-step as if the friend accidentally stopped filming.
A detailed video prompt for a high-intensity action sequence featuring an Asian female assassin in a silk dress fighting bodyguards in a luxury hotel lobby.
📝 Prompt
A cinematic action sequence with brutal Korean stunt choreography. An Asian female assassin wearing a flowing black silk slip dress with a white underlay and black high-heeled stilettos is fighting five unarmed, muscular male bodyguards in suits. Maintain character consistency. Scene: A luxurious marble hotel lobby at night with crystal chandeliers and warm ambient lighting.
A realistic fashion-lifestyle video prompt for a woman in a hijab performing a mirror selfie in a minimalist, sunlit bedroom.
📝 Prompt
Ultra-realistic cinematic mirror selfie video of a beautiful young woman wearing a white hijab, a pastel lime cropped jacket, white wide-leg pants, white sneakers, and a beige shoulder bag. She walks confidently toward a full-length wooden mirror in a modern minimalist bedroom with warm neutral tones, a wooden bed, soft blankets, woven wall décor, indoor plants, and natural morning sunlight streaming through the window. She gently smiles while holding her smartphone, making subtle head movements and natural blinking. Smooth, stabilized camera motion, realistic body movement, soft fabric physics, shallow depth of field, luxury lifestyle aesthetic, warm color grading, 4K HDR, photorealistic, elegant, Instagram Reel/TikTok fashion content, 9:16 vertical.
A professional-grade automotive commercial prompt for a sleek sports sedan, emphasizing studio lighting, close-ups, and smooth camera movements.
📝 Prompt
A cinematic ultra-luxury car advertisement featuring a sleek premium luxury sports sedan in metallic black. The video opens with an extreme close-up of the LED headlights turning on, followed by dramatic reflections across the sculpted bodywork under premium studio lighting. The camera smoothly showcases the car from multiple cinematic angles: a front hero shot highlighting the bold grille, a low side tracking shot emphasizing the aerodynamic profile, a rear three-quarter angle revealing the signature taillights, a close-up of the alloy wheels spinning slowly, and detailed macro shots of the luxury interior including the leather seats, steering wheel, digital dashboard, and ambient lighting. Midway, the car rotates gracefully on a glossy reflective floor while soft light glides across the paint, emphasizing every curve. The final hero shot features the car centered under dramatic lighting with a slow cinematic push-in, showcasing its premium design and craftsmanship. Ultra-realistic, photorealistic, luxury automotive commercial, 8K HDR, premium studio lighting, shallow depth of field, smooth cinematic camera movements, glossy reflections, minimalist luxury aesthetic, no people, no text, no watermark, 10 seconds, vertical 9:16, high-end automotive advertisement style.
A specialized camera control prompt for creating smooth 360-degree orbiting shots around a subject with gimbal-like stability.
📝 Prompt
The camera smoothly orbits a full 360 degrees around her. Smooth orbiting camera movement, gimbal stability, subject kept centered.
The camera smoothly orbits a full 360 degrees around her. Smooth orbiting camera movement, gimbal stability, subject kept centered.
A wholesome behind-the-scenes video prompt of a Korean idol recreating her childhood photo in a dressing room setting.
📝 Prompt
Cozy idol dressing room at an MV filming studio, midday. A cheerful Korean female idol (@ image) films a heartwarming behind-the-scenes vlog entirely on her phone with natural handheld selfie shots, smooth close-ups, and authentic backstage energy. Smiling brightly, she greets the camera and excitedly says she's going to recreate one of her favorite childhood photos. She holds up a small printed childhood picture to the lens, showing her younger self with an adorable pose and expression. Standing in front of the vanity mirror, she carefully recreates the exact same pose, facial expression, hairstyle, and body language while laughing at how cute it looks. The vlog features cinematic close-up shots of the childhood photo in her hands, her playful attempts to match every tiny detail, and warm reactions as she compares the old and new versions. She then places the childhood photo beside her face so both can be seen together in the frame, smiling proudly before showing a side-by-side comparison to the camera. Unable to stop laughing, she giggles at the resemblance, thanks her fans for growing up with her, gives a sweet finger heart and a warm wave, then grabs her phone and happily heads out toward the filming set, ending the vlog with nostalgic, wholesome, and genuine idol energy.
A complex video prompt designed to simulate unpolished, authentic smartphone footage of a backyard gathering with realistic handheld motion and rapid jump cuts.
📝 Prompt
Super casual real smartphone home video footage, backyard family and friends gathering, natural mobile phone camera with slight authentic handheld shake, normal frame rate with smooth natural motion, rapidfire montage with constant quick jump cuts every 1-2 seconds like scrolling through phone memories, unpolished authentic phone recording of mixed ages people eating, drinking and chatting, pure raw home video feel, no cinematic polish or heavy effects.
Use the provided reference photo as the strict ONLY visual reference for the main woman. Maintain her exact appearance with zero deviation: short dark hair with undercut, gold hoop earrings, black zip-up hoodie over black "nasty" crop top, black cargo pants, pink sneakers, body type, face and proportions. Generate a mixed group of family and friends of all ages (men, women, grandparents, young adults) around her in the backyard. Perfect character consistency on the main woman only.
0-2.5s: [Shaky smartphone handheld rapid cuts] Main woman laughing with family and friends in sunny backyard, holding drink and plate, quick flashes of casual eating and chatting near the table.
2.5-5s: [Abrupt jump cuts] Close-up flashes of her taking a sip and smiling, then group passing food and drinks, grandparents laughing with younger family members.
5-7.5s: [Fast shaky] She chats animatedly while eating with friends and relatives, expressive happy face, natural backyard table full of food and drinks visible.
7.5-10s: [Quick cut close-up] Warm big smile looking toward the person filming, friendly gesture, then jump to her laughing with a grandparent and friends while holding a drink.
10-12.5s: [Abrupt edit] Group moment around the table, family and friends eating, drinking and toasting casually, mixed ages having fun together.
12.5-15s: [Final rapid transition] Main woman centered with the group, soft happy smile and relaxed pose next to grandparents and friends, calm casual backyard memory ending, slight natural phone sway.
Natural smartphone video quality, slight real handheld shake, smooth normal frame rate motion with no low fps or choppy artifacts, authentic casual family interactions and physics, stable main character consistency, charming unpolished home phone recording, no pro stabilization or effects.
A complex technical prompt for generating a side-by-side comparison of vertical space shooter games across three different AI models, focusing on UI consistency and temporal stability.
📝 Prompt
[Slot Execution Instructions] No replaceable slots are configured. Bracketed sections like [Project Overview] and [Output Checklist] are fixed column names, not slots. Execute directly according to these specifications without inquiring. Do not alter the game genre, model names, 3-column layout, art style, shot count, target duration, or audio design. [Global Highest Priority: Complete Action and Duration Adaptation] This rule takes precedence over all other generation, editing, and compositing requirements. Target Duration: The final Master duration is approximately 28 seconds. Fable 5, Kimi K3, and GPT-5.6 Sol are three parallel tracks playing simultaneously, each running for about 28 seconds. Their durations must not be added together; the Master is not 84 seconds. Sequential Generation: Prioritize generating a continuous 28-second clip for each column in a single pass. If limited by the model's single-generation duration, use last-frame continuation to produce sequential segments. The next segment must seamlessly connect from the last frame of the previous one, inheriting the spaceship, enemies, barrages, items, background scrolling, and HUD visual style. Unified Speed Multiplier: If the total duration of the raw sequential footage in a column exceeds 28 seconds, it is strictly forbidden to crop the clips, delete intermediate actions, or only keep the first few seconds. You must apply a unified speed multiplier (speed_factor = Total Duration / 28) to compress the entire continuous track. Action coverage must be 100%, preserving the sequence from the first frame to the final frame. Continuity: Do not use hard cuts, black/white flashes, or cross-dissolves to mask discontinuities. If a segment fails to inherit the state, it must be regenerated. Audio Resync: After video retiming is complete, resync and produce the BGM and game sound effects. Use pitch-preserving time stretching if original audio must be retained; never delete video actions to match audio length. [Project Overview] Duration & Framerate: Approx. 28 seconds, ~30fps. Aspect Ratio: Horizontal 16:9 (Reference: 1212×720 or proportional HD). Theme: Side-by-side comparison of vertical space shooter games generated by three AI models: Fable 5, Kimi K3, and GPT-5.6 Sol. Art Style: White minimalist tech display frame, deep blue-black space interiors, retro arcade style, cyber neon, vector HUD, and slight CRT glow. Fixed Constraints: Single continuous shot with no camera movement or montages. No real people, live-action devices, or watermarks. Only use doubao or keling 2.6 if video models are required. [Three-Column Detailed Differences] The three game windows are identical in size and alignment, separated by light gray vertical lines. Headers and HUDs are locked as stable graphic layers in post-production. Fable 5 (Left): Minimalist near-black space with sparse stars. Cyan triangular wireframe spaceship firing thin cyan bullets. Magenta geometric wireframe enemies with low density and weak explosion feedback. Top HUD displays score, WAVE, and 3 hearts. Kimi K3 (Center): Traditional arcade style. Deep blue-purple gradient sky. Blue solid spaceship with exhaust flames firing vertical yellow bullets. Magenta, purple, and orange geometric enemies dropping items and showing +100/+200 points upon destruction. Top HUD displays SCORE, LEVEL (advancing 1–6), and heart lives. GPT-5.6 Sol (Right): High-density neon style. Scrolling perspective grid with a planet in the upper right. Fast-moving cyan-white glowing spaceship firing dense yellow-white bullets. Neon-colored enemies entering in scattered, diagonal, or full-row formations, causing massive bullet hells and intense particle explosions. Top HUD displays SCORE, SECTOR, and heart lives. [Storyboard Rhythm] This is a single continuous shot with escalating combat intensity: 00:00–00:08: Simultaneous base shooting. Center column enters Level 2; Right column adds colored enemies and barrages. 00:08–00:20: Intensity increases. Center column reaches Level 4; Right column forms complete formations and drops power-up items; Left column maintains a minimalist pace. 00:20–00:28: Climax. Center column reaches Level 6; Right column unleashes massive bullet hells and multi-row enemy arrays. The video ends abruptly while intense combat is still ongoing. [Standard Execution Steps] Setup Parameters: Initialize fixed specifications (16:9, 28s, 1 shot, 3 parallel tracks, no cropping) in project_spec.json. Video Generation: Generate the three vertical game tracks independently. Maintain strict state inheritance using continuity_state.json at every continuation point to track spaceship, enemies, and UI. Retiming & Assembly: Combine all sequential clips per column and apply the calculated speed_factor to compress each full timeline to exactly 28 seconds. Embed the three tracks into the static white tech frame. UI & Audio Post-Production: Overlay and lock the Logos, titles, and HUD layers. Create a retro electronic arcade audio track with fast synth pulses and 8-bit game SFX (lasers, explosions, level-ups) synchronized to the retiming. Quality Control: Inspect all continuation points to ensure 100% action coverage, stable layouts, and continuous HUD numeric progression. [Output Checklist] project_spec.json, storyboard_final.json, duration_map.json, continuity_state.json, run_log.json assets/ (Static UI, frames, and sprites) source_clips/ (Un-trimmed raw clips) and clips/ (Full sequences and retimed 28s tracks) audio/ (SFX tracks and final mix) final/master.mp4 (Final composite video)
A theatrical anime action prompt where a small girl's stumble causes planetary-scale physical phenomena in a school gym.
📝 Prompt
[Main Character] 2nd-grade girl with a black bob. [Setting] Nighttime school gymnasium. [Style] 15s Japanese full-color anime. High-density 2D animation with 500M yen budget scale. Dense background art, smooth in-betweens, cinematic post-processing. Variegated compositions and angles. No subtitles/watermarks. [Plot] A modest stumble causes planet-level physical phenomena. Aerial shots show the scale while the girl stays deadpan. [Specifics] Must include a shot in a crater where she sits in a shy pose, the floor woodgrain becoming concentric rings. Shot 1: A stumble in the gym sends real shockwaves. Shot 2: Aerial view shows city-wide impact. Shot 3: The girl continues daily actions indifferently. Shot 4: A second stumble overlaps the first. Shot 5: Animals evacuate as she remains oblivious. Shot 6: She clears her throat and the city rewinds to normal. Shot 7: Fixes her bangs and walks off saying 'nothing happened'.
A complex 11-shot cinematic action sequence featuring a schoolgirl transformation into a monster and a subsequent tactical battle in a classroom.
📝 Prompt
Shot 1 (0–3s) — girl collapsed, sick. Low static shot, black-bob girl in white sailor uniform slumped on the floor between the desk rows of a cool grey-teal classroom, overcast daylight through the tall windows on the right, overturned desks and scattered notebooks near her, sweat soaking her bangs, hand pressed to her stomach, breath ragged.
Shot 2 (3–5s) — close-up transformation burst. Rapid three-frame cut: spine cracking through torn fabric, jaw distending into fangs, a second eyelid tearing open on her collarbone — hard cuts, no transition, wet cracking sounds, cold blue-grey light on wet tissue.
Shot 3 (5–6.5s) — wide reveal, monster stands. Fast vertical tilt up her growing mass as the uniform shreds and a horned white-boned skull with one massive central eye rises to full height, floor tiles cracking under her weight, guttural roar against the pale walls and green chalkboard.
Shot 4 (6.5–7.5s) — arrival from the hallway. Camera in the dim corridor, blue-haired girl and black-haired boy sprinting toward the wooden classroom door on the left, scythe and hammer in hand; they burst through into the grey daylight room and freeze, eyes wide at the sight.
Shot 5 (7.5–8.5s) — boy's first strike, low angle. Low dutch-angle shot, boy charging first, hammer swinging in a wide arc into the monster's leg; camera whip-pans as the impact throws him sideways through a desk into the corkboard wall, papers scattering off the pins.
Shot 6 (8.5–9.5s) — close-up slow-mo, girl's counter. Close-up slow motion, blue-haired girl vaulting past the wreckage, scythe blade connecting across the monster's forearm, hot pink ichor spraying in thick suspended arcs against the cool window light.
Shot 7 (9.5–10.5s) — mid-fight dialogue, both hit. Wide shot, monster backhands the girl toward the cracking chalkboard as the boy is simultaneously swatted into a row of desks on the other side; camera holds a static two-anchor frame catching both impacts in the same beat.
Boy (Japanese, groaning): 「まだやれる…お前は?」 (Translation: "Still good… you?") Girl (Japanese, pushing up): 「当然。」 (Translation: "Obviously.")
Shot 8 (10.5–11.5s) — boy re-enters, close-up. Close-up on the boy's gritted face as he rises and charges back in, hammer rising into a two-handed grip, eyes locked on the monster's exposed rib-plating.
Shot 9 (11.5–12.5s) — slow-mo, hammer impact. Extreme close-up slow motion, hammer connecting into the plating, bone-white shards and hot pink fluid bursting outward frame by frame, monster staggering off-balance.
Shot 10 (12.5–13.5s) — flanking, orbit shot. Fast orbiting camera around both fighters as they flank the staggered monster from opposite sides, scythe hook and hammer both rising for the final blow.
Shot 11 (13.5–15s) — scream and kill, slow motion.
A heartwarming video prompt for Seedance 2.0 featuring a girl rescuing a kitten in a narrow alley, designed with a retro DV camera aesthetic.
📝 Prompt
The girl and her friend walked into a narrow residential alleyway when they first heard the persistent meowing of a kitten coming from above. She stopped in her tracks, followed the sound around a pile of plastic crates and old flower pots, and discovered a small orange-and-white kitten huddled on top of a fixed storage cabinet by the outer wall, too afraid to jump down. She turned a short plastic stool that had been upside down against the wall right side up and pushed it under the cabinet. After crouching down and gently patting the seat, the kitten jumped down using the lower step; the girl breathed a sigh of relief and crouched on the ground as it scampered over to her shoes. Her friend’s camcorder was a split second too slow to capture the moment she broke into a smile.
An intense, hyper-realistic cinematic action sequence prompt for Seedance 2.0 featuring explorers on a collapsing rope bridge.
📝 Prompt
Canyon Rope Bridge Break
Hyper-realistic cinematic action sequence, 15 seconds, aspect ratio 16:9.
Daytime. Two explorers cross a long rope bridge suspended over a deep canyon. The canyon is vast and dramatic, with steep rock walls, strong wind, dust in the air, and a rushing river far below. The bridge is old and unstable, made of wooden planks, rope handrails, and thick support ropes tied into the cliff on both sides.
Wide opening shot: the two explorers move quickly across the rope bridge high above the canyon floor. The bridge sways in the wind and the height feels dangerous from the start.
Tracking shot: as they move farther across, one of the support ropes suddenly snaps. The bridge jerks violently. Wooden planks shift under their feet and the rope handrails twist. The explorers lose balance, grab the ropes, and try to keep moving.
Side shot: more ropes begin snapping one by one. The bridge twists sideways and starts hanging at a steep angle. Some planks break loose and fall into the canyon. The explorers cling to the bridge and begin climbing upward along the ropes and planks toward the cliff side while the whole bridge swings hard in open air.
Final 5 seconds: the action becomes extreme. The bridge swings and slams against the cliff wall. One explorer nearly slips free, the other grabs them and helps pull them upward. They climb the tilted bridge like a hanging ladder, reach the rocky ledge, and scramble onto the cliff just as more planks and ropes break away below them.
Final moment: both explorers pull themselves onto the narrow cliff ledge, breathing hard, while the ruined rope bridge hangs and swings beside the canyon wall.
Style: hyper-realistic, cinematic, fast-paced, intense, stressful, clear readable action, strong sense of height and danger, deep canyon, swinging rope bridge, snapping ropes, falling planks, dust and wind, dynamic but readable camera movement, no text, no logos, no cartoon style, no slow motion, no famous celebrity faces, no recognizable actors, no movie-star resemblance, no public-figure likenesses, no clear facial close-ups. Keep proportions. Keep style and features. Aspect ratio 16:9.
A whimsical animation prompt where a playful clay cat transforms a grayscale world into a vibrant paradise with each step, featuring Pixar-quality lighting and handcrafted textures.
📝 Prompt
Create a whimsical, cinematic claymation-style animation of a playful black-and-white cat transforming a grayscale world into a vibrant paradise. As the cat flips, runs, and lands, each step splashes rainbow paint and colorful confetti, bringing grass, flowers, rivers, trees, houses, mountains, and the sky to life. The camera follows with smooth dynamic movements, revealing a charming floating island filled with smiling celestial characters, lush vegetation, and colorful details. End with the cat proudly holding a red flower in a fully transformed, cheerful miniature world. Pixar-quality lighting, handcrafted clay textures, smooth animation, vibrant colors, and magical storytelling.
A comedic video prompt for Seedance 2.0 showing a girl at a bus stop dealing with a flyer stuck to her shoe, captured with a nostalgic DV aesthetic.
📝 Prompt
A roadside bus stop during the day. A girl stands up from a bench to walk forward, unaware that a thin flyer is stuck to the sole of her shoe. As she takes a step, the paper drags behind her shoe, making a small rustling sound. She turns around to discover it and tries to shake it off twice with one foot, but it remains stuck. Finally, she looks down, stifling a laugh. The friend's old DV camera first captures her shoes and the ground, then pans up slightly delayed to a close-up of her embarrassed expression.
An atmospheric 8K prompt of a narrow Tokyo alleyway during heavy rain, featuring neon reflections and film textures.
📝 Prompt
Main scene: A narrow residential alley in Tokyo at late night, torrential rain, the water on the road reflecting the neon of faded Japanese shops on both sides, dense rain forming a hazy mist, dim light in the alley with only scattered street lamps casting hard side light, damp walls covered in water stains, 8K IMAX film texture, ARRI.
A highly atmospheric 8K prompt for a rainy Tokyo night scene with neon reflections and IMAX film quality.
📝 Prompt
Main scene: Roadside in Tokyo city at late night, torrential rain, wet asphalt road surface full of water reflections, cool-toned neon street lights and blue building lights reflected in puddles, damp and hazy rain fog atmosphere, dark cinematic film texture, IMAX wide aspect ratio, 8K ultra-clear, ARRI.
A sophisticated stop-motion animation prompt for Seedance 2.0 that produces a hand-painted 2D look of a blizzard-swept Kazakh yurt camp with wolves and riders.
📝 Prompt
Style: STOP-MOTION ANIMATION — stepped, frame-by-frame motion brought to a HAND-PAINTED 2D . True 12 frames per second, ANIMATED ON TWOS: 12 distinct hand-painted drawings per second, each pose held two frames then snapping to the next, never gliding. Constant painterly BOIL — brushstrokes and outlines subtly alive frame to frame. NO smooth interpolation, NO motion blur, NO morphing, real frame-by-frame animation not AI slop. Style from <<<image_1>>>, the yurt camp from <<<image_2>>>, the wolves from <<<image_3>>> — lean steppe wolves, coal-black with cold sheen, pale eyes. THE HERDSMAN from <<<image_4>>> (on foot). RIDER 1 from <<<image_5>>> riding HIS horse from <<<image_6>>> — keep this man and this horse together as one consistent pair. RIDER 2 from <<<image_7>>> riding HIS horse from <<<image_8>>> — a second consistent pair. Never mix the riders onto each other's horses. Atmospheric motion (blowing snow, blizzard haze) moves SMOOTHLY; figures, horses and wolves step on twos with secondary action. DIRECTOR'S NOTES: 1. THE SCENE — dusk, a blizzard rising over the Kazakh yurt camp. Wolves have come down on the herds. Panic erupts: THE HERDSMAN screams the alarm, men run, RIDER 1 is the first into the saddle and the first to tear out into the storm, RIDER 2 right behind him shouting orders. 2. RISING ENERGY — the sequence builds from dread to chaos: the dark wolf shapes at the herd, then the scream, then the explosive mounting and gallop. Each shot more energy than the last. 3. RIDER 1 IS THE LEAD — give RIDER 1 a clearly readable beat: he is the first to vault into the saddle of his horse (<<<image_6>>>) and the first to spur out of the camp, leading the charge, grim and silent, his face readable for a moment so the audience will know him again. RIDER 2 mounts shouting and follows. 4. AGGRESSIVE HANDHELD — the camera is in human hands in a panic: constant restless motion, jerky corrections, vertical bounce from running steps, buffeted by wind gusts, the horizon never level, never gimbal-smooth, never tripod-locked. Raw documentary chaos. 5. REAL PHYSICS — horses wheel and rear with weight, men vault into saddles with effort, snow is kicked up by hooves and boots as bursts of loose powder (drawn snow-spray effects on twos), cloth and manes whip in the wind with follow-through. 6. SECONDARY ACTION on twos on everything: chapan skirts and fur hats whipping, horse manes and tails streaming, breath-vapor of men and horses torn off by wind, harness straps swinging. 7. LIGHT — failing dusk in a blizzard, dim cold blue-grey storm light, soft and diffuse, no rays, no beams, no god rays; one or two struggling torch flames as small warm accents whipping in the wind. Correct neutral white balance, NOT a blue filter, muted desaturated, the wolves near-black masses. SHOT 1 — WIDE, ~35mm, aggressive handheld, the yurt camp at dusk in driving snow. COMPOSITION: the pale domed yurts low across the LOWER-RIGHT third, the churning panicked herd a dark restless mass on the LEFT third — and along the far edge of the herd, low dark wolf shapes from <<<image_3>>> flowing fast between the snow-veils, barely readable, a dark current, varied in tone and stride, never mirrored, never cloned. Blizzard haze drifts smoothly, figures and animals on twos. The herd wheels and screams. Energy rising. HARD CUT to SHOT 2 — MEDIUM, ~35mm, aggressive handheld running with him: THE HERDSMAN (<<<image_4>>>) bursts between the yurts toward camera, stumbling in the snow, waving an arm, his chapan and fur hat whipping with follow-through, breath-vapor tearing away, screaming raw over the wind, lips on twos: "Wolves!! WOLVES!!!" Figures scramble behind him, a torch flame struggling and whipping. Snow bursts from his boots as drawn powder on twos. HARD CUT to SHOT 3 — MEDIUM, ~50mm, aggressive handheld in the chaos, on RIDER 1: he reaches his horse (<<<image_6>>>) at a run, the horse wheeling with real weight, and VAULTS into the saddle in two hard stepped poses, grim and silent, his weathered face readable for one beat in the torch-glow — then he wrenches the horse around and spurs it, the first one driving out into the storm, snow bursting from the hooves, his chapan and the mane streaming with follow-through. Behind him RIDER 2 (<<<image_7>>>) swings up onto his own horse (<<<image_8>>>), shouting hoarse over the wind, lips on twos: "Save the horses!!" HARD CUT to SHOT 4 — WIDE, ~35mm, aggressive handheld, the edge of the camp: RIDER 1 already a dark mass at full gallop tearing toward the UPPER-LEFT into the blizzard, leading; RIDER 2 and one or two further silhouetted riders breaking after him from the LOWER-RIGHT, hooves drumming, powder bursting, manes tails and chapans streaming on twos, the pale yurts falling behind in the snow-haze, the dark storm ahead as the negative space they ride into. Camera buffeted, horizon tilting. The hoofbeats swallowed by the wind. End. Audio: NO MUSIC — the roar of the blizzard wind, panicked horses screaming and stamping, the herdsman's raw cries, men shouting, drumming hooves fading into the storm, distant wolf snarls under the wind. No subtitles. Natural diegetic sound only, absolutely no music. Constraints: stop-motion stepped cadence on twos at 12fps with painterly boil, figures horses and wolves stepping pose to pose never gliding, NO smooth interpolation NO motion blur NO morphing, blizzard haze and blowing snow smooth while all living things and drawn snow-spray effects step on twos, hand-painted oil look from <<<image_2>>> not photoreal not 3D, four shots with hard cuts rising in energy — wide wolves-at-the-herd, medium the screaming alarm "Wolves!!" from THE HERDSMAN <<<image_4>>>, medium RIDER 1 <<<image_5>>> vaulting onto his horse <<<image_6>>> grim and silent his face readable one beat and spurring out FIRST while RIDER 2 <<<image_7>>> mounts his horse <<<image_8>>> shouting "Save the horses!!", wide the riders tearing out into the storm RIDER 1 leading — each rider stays on his own horse the pairs never mixed, AGGRESSIVE HANDHELD constant restless jerky motion vertical bounce wind-buffeted horizon never level never gimbal-smooth, REAL PHYSICS horses wheeling and rearing with weight men vaulting with effort snow kicked as loose powder bursts, SECONDARY ACTION on twos chapans fur hats manes tails harness breath-vapor all whipping with follow-through, dusk blizzard dim cold storm light soft no rays no beams torch flames as small warm whipping accents, correct neutral white balance not a blue filter muted desaturated, wolves from <<<image_3>>> varied never mirrored never cloned, spoken Kazakh in Latin transliteration pronounced as written not Russian-accented, NO MUSIC only storm and voices.
An incredibly detailed technical prompt for Seedance 2.0 featuring a masked woman walking through a bright, saturated beach environment with specific camera optics and spatial blocking.
📝 Prompt
SCENE CONTEXT Scorching midday beach, aggressively bright and saturated. Turquoise water, red beach umbrellas, children's plastic toys scattered across the sand, a sand castle built near the shoreline path. Into this she walks — entirely in black, long dark hair, white-painted face — moving through the crowd toward an empty lounger ahead. ACTIVE REFERENCES <<<image_1>>> — the woman: long straight black hair falling to the waist, pale white-painted face with elongated white eye corners giving an otherworldly mask quality, black feather-trimmed jacket, black tulle midi skirt with ruffled floral rosettes, black leather combat boots. Reference controls face identity, hair, and full outfit throughout. Reference does not control beach environment or lighting color. <<<image_2>>> — the beach location: wide white sand beach, clear turquoise water, beach chairs, people in summer clothes, bright open midday sky. Reference controls environment, color saturation, and atmospheric brightness. <<<image_3>>> — the black umbrella with black lace fringe trim: folded and closed, tied shut, tucked firmly under her left arm with the lace tip pointing slightly downward behind her. Reference controls umbrella design. In this scene it stays closed under her arm for the entire shot. LOCATION MAP Wide white sand beach, hot and bright. Children's plastic toys scattered on the sand surface in the foreground and midground — small buckets, shovels, a toy boat. A sand castle approximately knee height sits in the path directly ahead of her, built on the right side of the walking corridor. A large inflatable pink flamingo is visible on the sand 3 to 4 meters to screen-right, clearly legible in the frame. An empty beach lounger sits in the midground approximately 15 meters ahead of her, slightly left of center. People — adults seated, a child running — are present between her and the lounger. FIRST FRAME AND SPATIAL BLOCKING First frame: low angle close shot, camera positioned at sand level looking up the length of her legs. Her black combat boots are in the foreground filling the lower frame, walking toward camera. The sand surface between her steps shows scattered plastic toys — a small bucket at screen-left, a plastic shovel near her right boot. The sand castle is visible ahead of her boots in the near midground. She enters already in motion. FORMAT MODE Single continuous take, 8 seconds, horizontal cinematic format. OPTICS SEGMENT 1 — 0.0s to 3.0s 65° diagonal field of view, wide low-angle lens character, camera at sand level approximately 1.5 meters ahead of her boots, angled upward slightly. Her boots, lower skirt hem, and the sand surface with toys are the primary elements. The inflatable flamingo is readable at the right edge of frame. Lens lock: 65°, no drift. SEGMENT 2 — 3.0s to 8.0s 45° diagonal field of view, normal cinematic eye-level lens character, camera cuts to a position 4 meters to her screen-left side, at eye level. Her full figure is visible — face, body, umbrella under arm — as she continues walking and passes through the crowd toward the lounger. Lens lock: 45°, no drift. CAMERA SEGMENT 1: Camera locked at sand level, static. She walks toward it. SEGMENT 2: Camera locked at eye level to her left, static. She walks through the frame left to right, past camera, continuing toward the lounger. No pan. She crosses through the static composition. ACTION TIMING 0.0s to 1.5s Her black boots advance across the sand, navigating around a plastic bucket and stepping past a toy shovel. Her pace is deliberate and unhurried. The sand castle is directly ahead of her path — she does not deviate. Low angle reads her boots large against the bright beach background. 1.5s to 2.5s Her right boot makes full contact with the sand castle. She steps directly onto it — not a stomp, not dramatic, simply the natural consequence of walking without diverting. The castle collapses under her boot: the packed sand walls crumble outward, the small turrets fall. She does not stop. She does not look away yet. Then her eyes drop to the sand beneath her for one beat — she looks down at what she crushed with a faint expression of contempt, not guilt, the white-painted face briefly visible angled downward. In this downward glance the closed black umbrella tucked under her left arm becomes clearly visible — the folded black canopy pressed against her side, lace tip trailing behind her elbow. 2.5s to 3.0s She raises her gaze back to forward and continues walking. The inflatable pink flamingo is visible at screen-right, large and vivid pink. CUT. 3.0s to 8.0s Eye level shot. She walks in front of seated beachgoers — people in swimsuits on towels and loungers who glance at her briefly and look away. She passes them without acknowledgment. The closed umbrella under her left arm is clearly visible — black fabric, the lace fringe at the tip moving very slightly with her stride. The empty lounger is visible ahead and she moves toward it with complete certainty. She arrives at its edge, stops, looks at it for one beat, then looks out toward the water. PHYSICS Combat boots on dry packed sand: each step has slight resistance, the sand compressing under the boot sole with visible displacement. The sand castle collapse is physically accurate — the walls of packed sand crumble outward from the point of contact, the top structure falls and scatters, loose sand fans away from the boot. Her tulle skirt hem swings with a slow natural arc from her stride. The umbrella stays completely still under her arm — it is gripped firmly, no bounce, no sway. LIGHTING Harsh overhead midday sun producing short hard shadows on the sand. The plastic toys cast small bright shadows. The sand castle held its own small shadow before she destroyed it. She, in all black, absorbs the direct sun without reflecting it — her figure reads as a dark void in the saturated scene. Her white face catches the full overhead sun and reads pale and precise against the warm beach environment. AUDIO Full beach ambient: radio from a distance, children's voices nearby, gentle wave sound, faint wind. Her boots on the sand — dry compressed footfalls. At the moment of the sand castle impact: a brief muffled crunch as the packed sand gives way, small and unremarkable. Then her footsteps continue. No music. POSITIVE LOCKS She does not avoid the sand castle — she walks through it without stopping or changing pace. Her downward glance is brief and contemptuous, not apologetic. The umbrella stays closed and tucked under her left arm for the entire shot without exception. The inflatable pink flamingo is visible and clearly pink in Segment 1 at screen-right. Her face identity, hair, and full black outfit stay identical to the reference throughout. The beach stays fully saturated and bright — no desaturation in this scene.
A detailed cinematic prompt for creating a realistic Korean idol backstage vlog with a vintage camcorder aesthetic and natural handheld motion.
📝 Prompt
FORMAT: 16:9
VIDEO CONCEPT: "Hidden Rooftop Break"
A highly realistic self-recorded backstage vlog captured entirely by a Korean female idol using a consumer camcorder. The footage should feel genuinely accidental and unscripted, like personal footage never intended for broadcast. Natural hand movement, realistic autofocus behavior, occasional slight framing mistakes, authentic walking motion, believable exposure adaptation, and smooth physical interactions with the environment. No glitches, no duplicated limbs, no warped objects, no facial distortion, no sudden appearance/disappearance of people or items.
VISUAL STYLE
Early digital camcorder realism. Soft detail, mild sensor noise, subtle compression artifacts, natural skin texture, realistic indoor-to-outdoor exposure transitions, accurate lighting physics, authentic motion blur. No cinematic effects, no artificial lens flares, no beauty filters, no exaggerated color grading.
CHARACTER
HANA, Korean female idol in her twenties. Long dark hair, natural makeup, clear skin, expressive eyes, slim figure. Wearing a comfortable oversized zip-up hoodie over her stage outfit, in-ear monitors around her neck.
LOCATION
Upper maintenance level of a large music-show building. Emergency stairwells, rooftop access doors, ventilation units, concrete walls, safety railings, distant city skyline, evening sunlight. Occasional staff members pass naturally in the background.
The recording starts mid-walk inside a quiet stairwell.
HANA pushes open a rooftop access door and steps outside into the evening air.
She immediately smiles at the camera.
"I come up here whenever I need two minutes of peace."
She walks toward the railing overlooking the city. Wind lightly moves her hair and clothing.
The camera naturally turns to reveal the skyline, traffic below, and the glowing broadcast building behind her.
"Most people downstairs don't even know this spot exists."
She leans casually against the railing while watching the sunset.
For several seconds there is no dialogue. Only distant traffic, faint wind, and venue sounds below.
She notices a small airplane crossing the sky and instinctively points the camera toward it.
"I always get distracted up here."
A vibration from her phone in her pocket causes her to laugh.
She checks the message briefly.
"Yep... they're looking for me."
She starts walking back toward the rooftop door.
Before entering, she turns around one last time and records the sunset.
"Five minutes of freedom. That's all I needed."
She opens the door and re-enters the building.
The atmosphere immediately changes from quiet rooftop ambience to busy backstage noise.
Crew members move through the hallway ahead.
Someone calls her name from off-screen.
She laughs and begins walking faster.
"Okay, okay, I'm coming!"
The recording continues naturally while she heads down the stairwell, then ends abruptly as if she simply stopped recording and put the camera away
A multi-shot video prompt for a stylized 'paint battle' integrating live-action urban footage with 3D anime characters, featuring fluid simulations and speed ramping.
📝 Prompt
SHOT 1 (-00:01) — Opening Impact (Real residential area / Image9 road). EFFECT: Speed ramp (deceleration) + strong motion blur + paint splash composite. Whip pan frame-in. Intense blur and neon yellow paint streaks cross the screen. Yellow-haired Image1 character lands at a crosswalk. Paint splashes radially upon landing, spreading as liquid on asphalt. Low-angle wide camera with a slight shake. Exit: Paint drop hits lens, turning the screen yellow for transition.
SHOT 2 (-00:03) — Three-way Confrontation (Real boulevard / Image8). EFFECT: High-speed dolly-in + three-part sequential focus. Blue-haired Image3 on the left, pink-haired Image2 on the right, yellow-haired Image1 in the center-back facing off. Low dolly move forward. Rack focus to each character every 0.5s as they ready paint weapons. Lighting matches real background and cel-look 3D characters. Exit: Pink flashes a spray, rainbow paint smear covers the screen.
SHOT 3 (-00:05) — Paint Battle Explosion (Real alley / Image4). EFFECT: Speed ramp (accel -> decel) + paint fluid simulation + camera shake. Blue Image3 and yellow Image1 duel in an alley; blue and pink paint splashes on old wooden houses, restoring saturation to the street. High-speed tracking follow. 30% speed at the pass-by to show paint trajectories in slow motion. Exit: Sudden speed recovery, whip pan blur smear.
SHOT 4 (-00:07) — Signature Effect: Color Erosion (Real trackside path / Image7). EFFECT: Color wave + low-speed drone climb. Yellow Image1 slams paint roller weapon down. Rainbow waves spread concentrically, painting the greenway, rusted tracks, and poles in vivid colors as they erode. Vertical climb from 1m to 8m to capture the spread. Neon liquid texture. Exit: White bloom overexposure.
SHOT 5 (-00:09) — Stone Bridge Clash (Real river and bridge / Image6). EFFECT: Slow motion (20-25%) + enhanced water reflection. Blue Image3 and yellow Image1 cross paths on a bridge. Yellow backflips to dodge; blue paint hits the river creating rainbow ripples. Detailed depiction of droplets and hair. Low angle near water. Exit: Sudden speed return, 15-degree Dutch angle rotation.
SHOT 6 (-00:11) — Pink's Counterattack (Real suburban street / Image5). EFFECT: Digital zoom punch + strobe flash + camera jitter. Pink Image2 kicks a pole and fires dual sprays in the air. Punch-in zoom with high-frequency jitter and flashes. Pink/cyan ribbons run along power lines. Strobe feel emphasizes speed. Exit: Ribbons cross camera for match cut transition.
SHOT 7 (-00:13) — Climax Trio (Return to Image9 crosswalk). EFFECT: Time-slice orbital + three-color simultaneous impact. 180-degree high-speed orbital around the trio (40% speed). All three fire upward. Three pillars of paint collide in a giant rainbow firework explosion. Sharp character/paint against blurred background. Exit: Flash swallows frame.
SHOT 8 (-00:15) — Landing & Resolution. EFFECT: Scale out + paint rain. Slow pull-back. Rainbow paint falls like rain, completing the colored intersection. The three stand back-to-back in poses. Final frame: Static view of the colored town with subtle paint dripping.
A cinematic video prompt simulating a handheld MiniDV camcorder recording of a K-pop singer's backstage journey.
📝 Prompt
A worn handheld MiniDV camcorder records an authentic backstage diary. The footage feels accidentally captured rather than directed. Slightly unstable hands, occasional focus breathing, imperfect exposure adjustments, brief moments where the subject drifts partially out of frame, realistic motion blur during fast movement. The camera remains entirely first-person and is always held by the idol herself.
The image carries genuine early-digital camcorder characteristics: soft detail, subtle tape grain, mild compression artifacts, natural indoor lighting, gentle highlight clipping from overhead fixtures, and realistic color shifts caused by automatic white balance.
SUBJECT
YUNA, a Korean pop singer in her twenties. Long dark hair tied loosely into a low ponytail, natural radiant skin, minimal touch-up makeup after rehearsals, expressive eyes, fashionable oversized hoodie layered over her performance outfit, wireless microphone pack clipped at her waist.
LOCATION
The quiet upper level of a large concert venue shortly before a live broadcast. Empty seating sections, concrete walkways, production offices, catering carts, equipment storage rooms, security checkpoints, distant stage lights glowing below. Crew members occasionally pass through the background without interacting with the camera.
SCENE FLOW
The recording begins abruptly as YUNA opens a heavy backstage door and steps into a long arena corridor.
She lowers her voice and smiles.
"Everyone's downstairs getting ready. I escaped for five minutes."
She continues walking through the mostly empty upper concourse while casually talking to the audience. The camera briefly drifts toward the enormous arena bowl visible through an opening.
She pauses near a railing overlooking the venue floor. Far below, technicians adjust lights while music echoes through the building.
"It always looks so different before people arrive."
A sudden burst of stage lighting illuminates the arena. She reacts naturally and laughs.
Continuing her walk, she discovers a forgotten catering cart and jokingly inspects the snacks.
"I think performers and staff survive entirely on these."
She steals a small snack and keeps moving.
While talking, an announcement comes through the venue speakers requesting performers to report for final preparation.
She freezes dramatically.
"That's definitely for me."
The camera swings toward the arena entrance tunnel where staff members are gathering.
The pace quickens as she starts jogging through the corridor, breathing lightly and laughing at the same time.
Near the end of the tunnel she slows down, turns the camera back toward herself, and gives a quick wave.
"Okay, this is the last calm moment before everything gets crazy."
She flashes a playful smile and disappears through the entrance tunnel as crowd noise, stage effects, and production activity grow louder in the background. The recording ends naturally without a clean outro, as if she simply
Futuristic Special Forces Subway Action Video Prompt
An action-packed video generation prompt for Seedance 2.0 featuring a silver-haired operative in tactical combat within an abandoned subway.
📝 Prompt
A futuristic special forces operative with short silver hair, tactical exosuit, carbon armor plates and twin combat blades, calm and focused expression
- enters an abandoned subway station occupied by heavily armed mercenaries, camera gliding behind her through flickering lights and drifting smoke;
- launches into close-quarters combat, seamlessly combining knife techniques, evasive rolls and disarming maneuvers while explosions ripple through the tunnels, handheld transitions alternating with elegant slow motion;
- Defeats the final squad leader before a train crashes through the station, ending with her walking calmly through the dust as sparks rain from the ceiling
Ultra-realistic tactical action, grounded choreography, cinematic lighting, practical VFX, blockbuster pacing.
A commercial-style video prompt for a young creator reviewing wireless earbuds, combining natural interaction with sleek product hero shots.
📝 Prompt
A young creator walks into a bright living room holding a pair of sleek wireless earbuds still inside their charging case. Looking directly into the camera, they smile and say, 'These have honestly become my everyday essential.' They open the case, put the earbuds in, and instantly transition into a quick montage of working on a laptop, making coffee, and taking a short walk outside while music plays. Close-up shots highlight the earbuds' premium design and secure fit. The creator finishes by holding the charging case toward the camera and says, 'Great sound, all-day comfort, and I barely need to recharge them.' End with a clean product hero shot on a table and on-screen text: 'Upgrade your everyday audio.' Natural facial expressions, smooth handheld camera movement, cinematic depth of field, authentic UGC feel, high-quality audio, realistic lighting, premium commercial quality.
A comprehensive multi-shot video prompt for Seedance 2.0 that creates a Pixar-quality 3D animated scene of creatures discovering a jungle treasure.
📝 Prompt
montage, multi-shot 3D animated feature film, Don't use one camera angle or single cut, vibrant glossy CGI render, Pixar-quality stylized animation, expressive cartoon character performance, subsurface-scattered fur and skin, cinematic lighting, sharp focus, high detail texture, depth of field mastery, dappled bright daylight, lush saturated jungle palette
In a lush overgrown jungle temple bathed in dappled bright daylight, three goofy creatures stand among giant mushrooms and mossy ancient ruins. A big shaggy orange horned monster with a rolled bedroll on his backpack bounces with excitement, a small round blue scaly dragon with little dorsal spikes clutches a glowing old treasure map in his clawed hands, and a towering mossy tree-creature with a goofy wide-eyed grin looms behind them. A tiny green creature peeks from the ferns in the foreground. The look is stylized 3D animated feature quality — vibrant, glossy, soft and warm, with playful expressive character animation.
Shot 1: Medium shot with a smooth playful push-in, the shaggy orange monster bounces on his feet and waves both furry arms overhead with a huge toothy grin, green eyes sparkling. Bursting with excitement he says: "Okay — today's the day, I can feel it in my fur!"
Shot 2: Close-up, the little blue dragon holds the old map up close as the parchment glows warm gold under his clawed fingers, his eyes darting across it then snapping wide. He taps the map and whispers: "Wait... the lost chamber — it's real."
Shot 3: Wide shot, the whole trio reacts together as the blue dragon thrusts a claw dramatically toward the overgrown temple, the orange monster gasping with joy and the towering tree-creature beaming behind them, while the tiny green creature pops up out of the ferns with wide eyes. They all gasp: "WHOA!"
Shot 4: Medium tracking shot bouncing along with them, the excited trio surges forward in a huddle, the orange monster sprinting in place and kicking up leaves and petals, the dragon clutching the map to his chest. The orange monster shouts back gleefully: "Last one there hatches a rotten egg!"
Shot 5: Close-up insert, the tree-creature's giant mossy foot slowly lifts off the ground to reveal a glowing golden treasure chest squashed into the moss right underneath it, soft light spilling out around it.
Shot 6: Wide shot, the orange monster and blue dragon screech to a frozen halt and stare slack-jawed at the chest under the tree-creature's foot, a beat of stunned silence, the tiny green creature face-palming in the ferns. The tree-creature gives a sheepish little wave and grins: "...Was it important?"
Total: 15s / 6 shots / 16:9
A 15-second cinematic video prompt for Seedance 2.0 following a stylish student through a premium supermarket run.
📝 Prompt
Create a realistic 15 second "Luxury Grocery Run" lifestyle video featuring a stylish Korean college student with long silky black hair, radiant skin, and a fresh natural look. Bright premium supermarket with modern minimalist interiors, clean product displays, warm natural lighting, cinematic handheld camera, ultra realistic photography.
The video opens with her grabbing a shopping basket at the entrance and smiling toward the camera before walking into the fresh produce section.
She carefully picks strawberries, avocados, fresh flowers, yogurt, pasta, and sparkling water while comparing products. Cinematic close ups capture her hands selecting fruit, placing items into the basket, and colorful shelves filled with premium groceries.
She stops at the bakery, chooses a fresh croissant, then walks through the snack aisle while laughing after discovering a new product. Smooth tracking shots follow her as she pushes the basket through the bright store.
She pays using a contactless card at the self checkout, packs everything into reusable shopping bags, and exits the store into warm afternoon sunlight.
The video ends with her walking home carrying the grocery bags while sipping an iced coffee, smiling confidently as the camera slowly pulls back to reveal a clean modern city street.
Style: premium lifestyle vlog, realistic grocery shopping content, cinematic handheld and gimbal camera movement, elegant transitions, bright natural lighting, photorealistic, shallow depth of field, luxury social media aesthetic, 4K HDR, 16:9 widescreen, no subtitles, no text overlays.
A comprehensive cinematic video prompt for a high-end travel vlog featuring iconic Dubai locations, luxury supercars, and professional camera aesthetics.
📝 Prompt
Style:Ultra-realistic luxury travel vlog, indistinguishable from footage shot on a Sony FX3 with a 24mm cinematic lens. Natural handheld camera movement with subtle stabilization, authentic lighting, realistic skin texture, true-to-life colors, cinematic HDR, and shallow depth of field. The video should feel like a premium travel influencer's Instagram Reel, not AI-generated.
Main Character (Maintain Perfect Consistency):
A beautiful woman, 24–27 years old, warm olive skin, long dark brown wavy hair, expressive brown eyes, natural makeup, slim elegant build. She wears a stylish white linen shirt with matching wide-leg trousers, white sneakers, a beige luxury crossbody bag, black sunglasses, a gold watch, and minimal jewelry. Keep her face, hairstyle, outfit, accessories, and body proportions identical in every scene.
Scene Timeline (14 Seconds)
0.0–2.5s | Luxury Hotel Morning
Inside a five-star suite overlooking the Burj Khalifa. She opens the curtains, sunlight floods the room, picks up a coffee, and walks toward the balcony. The camera follows naturally from behind with subtle handheld movement.
2.5–5.5s | Supercar Drive
Match cut to her driving a white Lamborghini Huracán through Downtown Dubai. Smooth tracking shots alternate between inside the car and low-angle exterior shots as palm trees and modern skyscrapers pass by.
5.5–8.5s | Rooftop Infinity Pool
She relaxes in a rooftop infinity pool overlooking the Burj Khalifa. She adjusts her sunglasses, smiles naturally, and trails her fingertips through the water. Golden-hour reflections shimmer across the pool.
8.5–11.0s | Luxury Yacht Cruise
On a luxury yacht sailing through Dubai Marina. She walks along the teak deck while the breeze gently moves her hair. The camera circles around her as the skyline glows in warm evening light.
11.0–14.0s | Sunset Finale
She stands at the bow of the yacht, watching the sun set behind the Dubai skyline. The camera slowly rises into a cinematic drone pullback, revealing the yacht surrounded by golden water with the Burj Khalifa on the horizon. Fade smoothly to black.
Visual Requirements
Ultra-photorealistic 4K HDR
24fps cinematic motion
Natural handheld camera movement
Warm golden-hour lighting
Realistic human movement and facial expressions
Authentic Dubai landmarks and atmosphere
Luxury travel influencer aesthetic
Perfect character consistency across all scenes
No AI artifacts, flickering, morphing, warped hands, extra fingers, or facial changes
No text, subtitles, logos, or watermarks
Final look:A seamless, premium luxury travel vlog that feels like it was filmed by a professional content creator spending one unforgettable day in Dubai.
Author:Jasmine Ai | Source:Link | Published: Jul 18, 2026
The Forgotten Kite Video Prompt
A Seedance 2.0 prompt that uses a storyboard as a visual reference to generate a consistent anime-style video.
📝 Prompt
TITLE
The Forgotten Kite
REFERENCE
Use the uploaded storyboard as the main visual reference.
Keep the girl, outfit, kite, town, stairs, ocean view, and lighting consistent in every shot.
Do not add extra characters.
Do not change the story.
Keep full
A man falling backwards from a rooftop into a kaleidoscopic abyss of floating crystals and cosmic nebulas.
📝 Prompt
A man standing on the edge of a rooftop at night overlooking city lights, suddenly falling backwards into an abyss. As he falls, the world fractures into floating crystals, shattered glass reflections of himself, cosmic nebulas in blue and purple, and a wormhole of molten light and dark energy. Cinematic slow motion, screams, arms outstretched, hyper-detailed particles, kaleidoscopic mirror effect, 4K filmic, dramatic lighting, emotional and surreal tone.
A visceral stop-motion animation prompt for Seedance 2.0 that describes a brutal wolf attack sequence during a blizzard, focusing on physics and camera motion.
📝 Prompt
Style: STOP-MOTION ANIMATION — stepped, frame-by-frame motion brought to a HAND-PAINTED 2D look, a moving oil painting, NOT clay, NOT puppets, NOT 3D. True 12fps, ANIMATED ON TWOS: 12 distinct hand-painted drawings per second, each pose held two frames then snapping to the next, never gliding — even at full gallop the action steps pose to pose with the strobing cadence of hand-drawn animation. Constant painterly BOIL. NO smooth interpolation, NO motion blur, NO morphing, real frame-by-frame animation not AI slop. Style from <<<image_1>>>, the wolves from <<<image_2>>>, RIDER 1 from <<<image_3>>> riding HIS horse from <<<image_4>>> — the same lead rider and the same horse as one consistent pair throughout, never another horse, never another man. The dusk snowfield from <<<image_5>>>. Blizzard haze and blowing snow drift SMOOTHLY; figures, horses, wolves and drawn snow-spray effects step on twos with secondary action. DIRECTOR'S NOTES: 1/ THE SCENE — full-gallop chase in the dusk blizzard, brutal and fast. RIDER 1, the lead rider, chases a sprinting wolf, leans low off the saddle in the manner of a kok-boru player reaching for the ulak, seizes the wolf by the scruff — and the wolf twists and savages his arm. A second wolf hits him from his blind side. He is torn from the saddle at full speed and the pack swarms him. Savage, dynamic, with REAL PHYSICS and a visible causal chain — every wound has its on-screen cause. 2/ REAL PHYSICS AND CAUSALITY — the horse (<<<image_4>>>) gallops with true four-beat weight; RIDER 1 hangs low off the side of the saddle, one hand braced, reaching down; the wolf is a heavy animal — when seized it twists its WHOLE body mid-stride, and that twisting weight plus the clamping bite WRENCHES the rider off balance; the bite is shown on screen: jaws clamp and crush onto his forearm, tearing sleeve and flesh, dark blood — cause before effect, always; the second wolf launches from his blind side and slams full-body into his chest like a missile; torn from the saddle at gallop speed he hits the snow HARD and TUMBLES with momentum, rolling over and over, loose powder snow bursting around each impact (drawn snow-spray effects on twos), the riderless horse galloping on; the pack converges as a fast dark stream and swarms over him, a savage thrashing dark mass. 3/ BRUTALITY STAGED, NOT LINGERED — the violence is fast, hard and physical: the crunching bite, the dark blood across the snow, the swarming pack. Show the savagery through motion, dark mass and sound, not slow anatomical detail. 4/ AGGRESSIVE HANDHELD CHASE CAMERA — racing alongside at gallop, violently jolting with the speed, whipped by wind, jerky corrections, the horizon tilting and never level; on the fall a hard DUTCH TILT as the world goes over with him. Never gimbal-smooth, never tripod-locked. 5/ SECONDARY ACTION on twos — RIDER 1's chapan skirts and fur hat whipping with follow-through, the horse's mane and tail streaming, the wolves' fur rippling along their backs, harness swinging, breath-vapor of horse and man tearing off in the wind, snow bursting from hooves as drawn powder on twos. 6/ LIGHT — deep dusk in a blizzard, dim cold blue-grey storm light, soft, no rays, no beams, no god rays, the figures dark masses against the pale snow. Correct neutral white balance, NOT a blue filter, muted desaturated; the blood a dark muted red, stark on the snow but never glossy, never bright. SHOT 1 — FULL-GALLOP TRACKING, ~35mm, aggressive handheld racing alongside. COMPOSITION: RIDER 1 on his horse a large dark mass driving in from the RIGHT third, the sprinting wolf low ahead of him on the LEFT third, both tearing diagonally through the frame left-and-deeper — the diagonal of the chase as the line of dynamics; the pale storm-lit snowfield from <<<image_5>>> streaking past as negative space. RIDER 1 drops LOW off the side of the saddle in a kok-boru lean, one hand braced on the saddle, the other arm stretching down for the wolf's scruff, his chapan and the horse's mane whipping on twos, hooves throwing bursts of powder. He bares his teeth, hoarse over the wind, lips on twos: "Ustadym!.." His fist closes on the wolf's scruff — HARD CUT to SHOT 2 — CLOSE DYNAMIC, ~50mm, aggressive handheld slammed in tight: the wolf, seized, TWISTS its whole heavy body mid-stride in one violent stepped motion — and its jaws clamp CRUSHING onto RIDER 1's forearm, on screen, tearing through sleeve and flesh, dark blood whipping across the snow and the wolf's muzzle. His raw scream tears over the wind. The wolf's twisting weight and the bite WRENCH him sideways off his balance, his body dragged half out of the saddle, his fur hat ripping away with follow-through. Cause and effect brutal and readable, all stepping on twos. HARD CUT to SHOT 3 — MEDIUM WIDE with a hard DUTCH TILT, ~35mm, aggressive handheld: from his blind side a SECOND wolf launches — a dark missile — and slams full-body into his chest. Torn from the saddle at gallop speed RIDER 1 hits the snow HARD and TUMBLES, rolling over and over with real momentum, powder snow bursting at each impact as drawn effects on twos, the horizon tilted and reeling, his riderless horse (<<<image_4>>>) galloping on into the storm. And then the pack pours in — a fast dark stream of wolves from <<<image_2>>> out of the storm, varied coats, converging from all sides and SWARMING over him, a savage thrashing dark mass on the pale snow, dark blood spreading, snow scattering, his cries swallowed by the blizzard and the snarling. The dark mass of the pack traps and frames him. Hold one brutal beat in the howling wind. End. Audio: NO MUSIC — the roar of the blizzard, pounding gallop, the wolf's snarl and the wet crunch of the bite, the rider's raw scream, the heavy tumbling impacts, the converging snarls of the pack, the wind swallowing everything. No subtitles. Natural diegetic sound only, absolutely no music. Constraints: stop-motion stepped cadence on twos at 12fps with painterly boil even at full gallop, every action stepping pose to pose never gliding, NO smooth interpolation NO motion blur NO morphing, blizzard haze smooth while all figures animals and drawn snow-spray effects step on twos, hand-painted oil look from <<<image_1>>> not photoreal not 3D not glossy, three shots with hard cuts — full-gallop tracking with the kok-boru lean and the grab "Ustadym!..", close dynamic of the twisting wolf and the crushing on-screen bite with dark blood and the scream, dutch-tilted wide of the second wolf's full-body slam the hard tumbling fall at speed and the pack swarming him as a savage dark mass — RIDER 1 from <<<image_3>>> and his horse from <<<image_4>>> the SAME consistent pair in every shot never swapped, REAL PHYSICS AND VISIBLE CAUSALITY every wound caused on screen the wolf's twisting weight wrenching the rider the bite before the blood the slam before the fall the momentum carrying the tumble, AGGRESSIVE HANDHELD racing jolting wind-whipped horizon never level hard dutch tilt on the fall never gimbal-smooth, SECONDARY ACTION on twos chapan hat mane tail wolf fur harness breath-vapor all whipping with follow-through, wolves from <<<image_2>>> varied in coat tone size and stride never mirrored never cloned, deep dusk blizzard dim cold storm light soft no rays no beams, correct neutral white balance not a blue filter muted desaturated dark muted blood never bright never glossy, brutality fast hard and physical staged through motion dark mass and sound not lingering gore, spoken Kazakh in Latin transliteration pronounced as written, NO MUSIC only storm hooves snarls and screams.
A unique prompt for an architectural diorama assembly video, featuring a large-scale harbour island coming to life with satisfying miniature physics.
📝 Prompt
Create a **15-second cinematic miniature-diorama formation video** in a **1:1 square format**. Use **@reference_image** as the exact visual reference for the completed harbour island. The final island layout, coastline, harbour structure, architecture, lighthouse, roof colours, bridges, canals, piers, terrain, and overall appearance should closely match the reference image. The video shows an enormous harbour town rapidly assembling across an entire island surrounded by a bright blue sea. The visual style should feel like a **premium handcrafted architectural diorama, luxury collector model, and highly detailed practical film miniature**—not a cheap toy. Preserve the charm, organised beauty, and satisfying construction quality of a miniature world while making the island feel expansive and cinematic. Bright, clear daylight, sparkling blue water, white waves, red, blue, and white rooftops, wooden piers, stone seawalls, bridges, canals, a lighthouse, hillside neighbourhoods, and multiple harbour districts. The harbour island itself is the main subject. No prominent human characters. ## SCENE 1 — ISLAND FOUNDATION **0.0–3.0 seconds** Begin with a high, wide aerial view showing the entire empty island surrounded by a vast blue sea. The island should already feel large and expansive, not like a small tabletop model. The coastline, bays, cliffs, hills, harbour entrances, canals, breakwaters, multiple docks, bridges, main roads, stone terraces, and layered town districts rapidly emerge from the terrain. Landforms rise smoothly while roads, waterways, harbour walls, and structural outlines assemble with precise, satisfying movements. By the end of the scene, the complete large-scale foundation of the island and harbour is clearly visible. **Camera:** High aerial wide shot, slowly descending and pushing toward the main harbour. **Motion:** Fast, precise miniature construction with pieces locking naturally into place. ## SCENE 2 — HARBOUR TOWN ASSEMBLY **3.0–6.5 seconds** Maintain a wide cinematic composition as the camera gradually descends toward the harbour. Wooden piers extend across the water. Stone streets, stairs, railings, warehouses, fishing huts, canal-side buildings, and rows of houses with red, blue, and white roofs rapidly assemble. Narrow roads climb from the waterfront toward the hillside neighbourhoods. Buildings should form in organised layers, with walls, roofs, doors, windows, chimneys, balconies, and small architectural details snapping smoothly into position. Do not move too close. The harbour, hillside town, lighthouse area, and open sea should remain visible to preserve the island’s scale. **Camera:** Wide forward-moving aerial shot with a gradual descent toward the waterfront. **Motion:** Rhythmic, premium assembly animation with wood, stone, and architecture fitting together cleanly. ## SCENE 3 — HARBOUR DETAILS **6.5–10.0 seconds** Use a seamless cinematic transition into a medium-wide harbour-level view. Multiple piers, small boats, sailing vessels, mooring ropes, wooden crates, fishing equipment, compact cranes, streetlights, flags, bridges, canals, and stone seawalls appear in rapid succession. Detailed wooden planks form across the docks. Stone joints assemble along the quay. Boats lower gently into the water while ropes connect naturally to the piers. This should be the most satisfying construction moment, with the entire harbour district rapidly becoming rich, organised, and highly detailed. Avoid focusing only on tiny objects. Continue showing the wider harbour district growing in density and complexity. **Camera:** Smooth harbour-side tracking movement with layered foreground, midground, and background. **Motion:** Fast detail formation with clean mechanical clicks, sliding components, and natural placement. ## SCENE 4 — LIGHTHOUSE AND FINAL DISTRICTS **10.0–12.5 seconds** Transition toward the lighthouse and hillside town while maintaining a wide view of the island. The lighthouse tower assembles upward from its stone foundation. Its windows, railings, roof, lantern room, and rotating light mechanism lock into position. Additional hillside houses, bridges, windows, streetlights, boats, rooftops, harbour districts, and flags complete the island. Reveal the multiple harbour sections, the bay leading toward the open sea, and the fully developed town climbing across the hills. The completed harbour should now closely match **@reference_image**. **Camera:** Gentle orbit around the lighthouse before beginning to pull away. **Motion:** Final architectural components assemble with elegant, precise movements. ## SCENE 5 — THE DIORAMA COMES ALIVE **12.5–15.0 seconds** The completed harbour island comes to life. Sunlight sparkles across the water. Small boats gently rock with the waves. Flags and ropes move in the coastal breeze. The lighthouse beam slowly rotates. Windows and streetlights softly illuminate across the town. Tiny waves move against the seawalls and wooden piers. End with a grand, wide aerial pullback revealing the entire completed harbour island: the hillside town, lighthouse, bridges, canals, multiple piers, harbour districts, surrounding bay, and open sea. The final image should feel charming, alive, premium, expansive, and cinematic. **Camera:** Large cinematic aerial pullback into a complete island-wide hero shot. **Ending:** The harbour remains subtly animated rather than becoming completely still. ## VISUAL STYLE Premium handcrafted miniature diorama, luxury collector model, highly detailed architectural miniature, practical film model quality, realistic painted wood and stone, precise handcrafted textures, subtle miniature scale depth of field, cinematic daylight, bright blue sea, clean white waves, rich coastal colours, polished professional craftsmanship, large-scale island composition, charming but realistic, highly detailed, sharp, cinematic and visually satisfying. ## CAMERA AND EDITING Prioritise wide-angle compositions that continuously communicate the scale of the island. Use: * High aerial opening * Smooth descending push toward the harbour * Medium-wide waterfront tracking * Gentle lighthouse orbit * Grand aerial pullback for the final reveal Include two or three seamless cinematic transitions during the 15-second video. Use layered foreground, midground, and background compositions so the harbour, hillside town, lighthouse, bay, and open sea can frequently appear together. The pacing should be fast, energetic, and focused on the satisfying formation process. Avoid long static shots, repetitive straight-line camera motion, or extreme close-ups that make the environment appear like a tiny cheap toy. ## SOUND DESIGN Include bright, uplifting cinematic background music with a subtle sense of adventure and discovery. The music should support the excitement of the harbour being completed without becoming overly dramatic. Add detailed sound effects: * Small construction clicks * Wooden pieces locking together * Stone blocks sliding into position * Soft mechanical assembly sounds * Water movement * Gentle waves * Harbour ropes moving * Flags fluttering * Wooden ships creaking * Distant seagulls * Subtle lighthouse machinery No dialogue. No narration. ## NEGATIVE PROMPT Small island, tiny enclosed tabletop scene, cramped harbour, only a few houses, limited environment scale, cheap toy appearance, glossy plastic materials, low-quality craft project, rough handmade construction, narrow composition, empty harbour, dark cloudy weather, muddy water, oversized humans, human characters as the main subject, full-size people walking through the miniature, excessive macro shots, extreme shallow depth of field, chaotic building placement, incorrect island layout, design that does not match @reference_image, repetitive linear camera motion, long static shots, frozen ending, text, captions, subtitles, logos, branding, watermark.
A detailed cinematic video prompt for a 15-second medieval battle sequence, featuring drone shots and combat choreography in a narrow mountain pass.
📝 Prompt
The Last Stand
Duration: 15 seconds
Style: Ultra-realistic cinematic, historical medieval warfare, photorealistic, 9:16 vertical, 4K, 60fps, realistic combat, dramatic lighting, movie-quality visuals, no fantasy, no magic.
0–3s:
A sweeping drone shot reveals a narrow mountain pass at dawn. A lone medieval warrior in battle-worn steel armor stands with a longsword and round shield, facing dozens of enemy soldiers marching toward him through the rocky valley. Cold wind blows his torn cloak as dust drifts across the ground.
3–6s:
The camera moves to a close-up of the warrior's determined face. He tightens his grip on the sword, plants his feet, and raises his shield. The enemy breaks into a full charge, their footsteps echoing through the mountains.
6–10s:
The first attackers reach him. He blocks heavy sword strikes with his shield, counters with swift, realistic sword movements, and forces enemies backward. Steel clashes, sparks fly, dust rises, and the narrow pass prevents the army from surrounding him.
10–13s:
The warrior breathes heavily, his armor scratched and covered with dirt. More enemies continue advancing. He refuses to retreat, taking another defensive stance while the camera circles around him in dramatic slow motion.
13–15s:
The camera pulls back to reveal the lone warrior still standing against the overwhelming army, silhouetted by the rising sun. The enemy hesitates for a brief moment as the screen fades to black.
Cinematic Keywords: Ultra-realistic, historical accuracy, practical armor, realistic sword fighting, volumetric lighting, dramatic sunrise, mountain battlefield, handheld camera, cinematic slow motion, high-detail textures, immersive sound design, 8K quality, masterpiece.
Author:Luca Ai | Source:Link | Published: Jul 18, 2026
Robot MMA Octagon Battle
A high-intensity robot MMA fight in an octagon, featuring weapon collisions, muzzle flashes, and fire effects.
📝 Prompt
Inside a high-end professional MMA octagon arena, Ares and Titan's combat escalates as they fight with heavy metal weapons on the floor. Ares swings a massive glowing red steel axe at Titan. Titan parries with a heavy rusted steel sword, generating an explosive shower of brilliant sparks. Titan fires rapid forearm cannon rounds, muzzle flashes illuminating the cage. Massive bursts of real orange flames and embers erupt from the concrete floor behind them.
Shot from a handheld ringside third-person POV camera angle, panning quickly to follow the weapon swings, with dramatic natural camera shake on impacts, capturing a highly realistic, intense raw broadcast feel.
- 0–5s: Ares sweeps the glowing red axe in a heavy arc; Titan parries with a rusted steel sword, creating a brilliant burst of dynamic sparks, handheld camera shaking with impact.
- 6–10s: Titan raises his forearm cannon, firing a rapid barrage of bullets with intense muzzle flashes; bullets spark off Ares's crimson armor shields.
- 11–15s: Large real flames erupt from the concrete floor in the background, casting dramatic orange reflections as both robots clash weapon-to-weapon in the center, sparks and embers flying.
Photo-realistic cinematic style, 8k resolution,
A detailed video script for a scene involving a character in an airplane cabin who experiences turbulence and a sudden dragon encounter.
📝 Prompt
CHARACTER : [REFERENCE IMAGE] wearing casual clothes, seated relaxed, natural expression
LOCATION
Inside an airplane cabin during flight, the camera positioned inside the cabin facing toward a passenger window, the character seated in the window seat beside it, soft diffused daylight coming through the window, muted cabin interior tones, outside the window a vast bright sea of clouds stretching to the horizon as the plane cruises high above the cloud layer
STYLE
Cinematic single continuous shot, mostly static handheld feel from inside the cabin framing the character and the window, ARRI Alexa Mini LF, Cooke S7/i anamorphic prime, shallow cinematic depth, desaturated cool palette, Kodak Vision3 250D grade, fine natural 35mm grain, deep shadow falloff, photorealistic
SHOT
Shot 1
Character sits relaxed in the window seat laughing warmly, glancing out at the bright sea of clouds, at ease and enjoying the flight.
Shot 2
Suddenly the plane hits violent turbulence, the whole cabin jolts and shakes hard, the character's laugh drops into panic, gripping the armrest and looking around alarmed.
Shot 3
Out through the window beside the character, flocks of birds burst upward out of the cloud layer flying up and away, the character turns their head to face the window at their side, leans in close to the glass wide-eyed, and extends their arm sideways toward the window pressing a finger toward the glass at the birds outside while shouting "hey what is that", their gaze and pointing hand both aimed at the window and the sky beyond it.
Shot 4
The sky outside the window rapidly darkens as heavy storm clouds roll in and forks of lightning flash across the gloom, and from the clouds an enormous dragon head bursts upward very close alongside the aircraft, rising and gliding up just outside the window at close range, followed by several more dragons breaking up out of the cloud layer nearby and flying tight beside the plane, their massive scaled bodies filling the view outside the glass, the camera slowly zooming in past the character toward the window.
Shot 5
One of the dragons suddenly lunges at the aircraft, rocketing in fast and slamming its enormous open jaws straight at the passenger window, the whole plane pitching and rocking violently from the impact, the cabin shaking hard as the character and other passengers scream in terror voicing "that dragon", the gaping maw driving in against the glass until the dark interior of the mouth completely fills and swallows the entire frame, the image going fully black from the inside of the dragon's jaws.
AUDIO
Steady muffled airplane cabin drone and engine hum throughout. Shot 1 light and calm with the character's warm laughter. Shot 2 a sudden deep turbulence rumble, rat
A comprehensive video generation script for Seedance 2.0 featuring a Ming Dynasty ghost romance. The prompt includes specific lighting instructions, character descriptions, and a three-act structure transitioning from spooky to romantic to a comedic twist.
📝 Prompt
45-second vertical short drama, 9:16 aspect ratio, cinematic feel, late Ming Dynasty Liaozhai style, movie-grade lighting.
Scene: An abandoned Lanruo Temple at the end of the Ming Dynasty, spooky and terrifying at night, with broken walls, spider webs everywhere, and the three characters 'Lanruo Temple' mottled on a dilapidated stone tablet, under pale moonlight.
Characters:
Scholar Ning Caichen <<<Image1>>>: 25 years old, frail and handsome, wearing a light blue scholar's robe and a square cap.
Xiaoqian <<<Image2>>>: Sweet female ghost, long straight black hair to her waist, snow-white skin, wearing light pink tulle ancient costume, with a delicate temperament.
Laolao <<<Image3>>> (Tree Demon): A half-man half-woman monster, initially in a black robe with long black nails, later transforming into an exaggerated American drag queen (bold blue eyeshadow, bright red lips, exaggerated fake eyelashes, tight sequined drag queen outfit).
Style: Poignant and romantic ghost movie style, contrast between cold blue tones and warm yellow candlelight, extreme detail, ending with a sudden comedic turn.
Part 1 (0-15s):
0-3s: Outside the abandoned Lanruo Temple at night, spooky, dilapidated stone tablet engraved with 'Lanruo Temple'.
3-6s: Scholar Ning Caichen is in a dim, old wing room, lighting a candle and writing in an account book with a brush.
6-9s: Suddenly there is a knock on the door, and the scholar opens the wing room door.
9-12s: Xiaoqian is standing at the door crying for help, saying in Chinese: 'Sir, save me! There's a monster chasing me!'
12-15s: The scholar quickly pulls Xiaoqian's hand into the room and closes the door.
Part 2 (15-30s):
15-18s: In the dim wing room, Xiaoqian suddenly pins the scholar against the wall, with ambiguous eyes, whispering in Chinese: 'Sir... you are so kind...'
18-21s: The scholar blushes with shy resistance: 'Miss... this, this is not in line with etiquette...'
21-24s: Xiaoqian leans in closer, breathing like an orchid, urging in Chinese: 'Tonight it's just the two of us... what are you afraid of, sir?'
24-27s: The scholar gradually can't resist, breathing fast, their faces very close, the atmosphere extremely romantic.
27-30s: The scene shifts outside the room, where Laolao is waiting impatiently, saying in a sinister voice: 'What are these two young people doing?'
Part 3 (30-45s):
30-33s: Laolao's monster appearance with black robe and long black nails transforms into a glamorous drag queen after a puff of black smoke.
33-36s: The drag queen knocks on the door affectedly, Xiaoqian opens the door impatiently and asks: 'Who is it?' Seeing the drag queen, she immediately flees as black smoke.
36-39s: The scholar (bare-chested and muscular, slightly sweating, wearing only white ancient sleeping pants soaked in sweat) comes to the door and sees the glamorous drag queen, his heart instantly racing.
39-42s: The scholar looks around guiltily and asks in Chinese: 'Is Xiaoqian... gone?'
42-45s: The drag queen pretends to be shy and says: 'Yes, she's gone~' The scholar suddenly grabs the drag queen's waist and kisses her passionately. Xiaoqian hides on a tree branch, looking at everything with a confused and shocked expression (Xiaoqian's inner monologue: 'How can this be?'), the frame freezes at a funny and weird moment.
A cinematic prompt designed to mimic the imperfect, natural look of a handheld iPhone selfie video with realistic camera movements.
📝 Prompt
Handheld iPhone filming oneself, or occasionally leaning the camera against a vanity mirror. Only selfie/first-person perspective. Natural hand shake, imperfect framing, delayed focus, clumsy zooming, slight loss of subject, face occasionally cropped. The camera itself never appears. Natural lighting, high-definition pixel quality, soft contrast, realistic skin tones.
Style: Casual
A technical video prompt for a rap music video, emphasizing precise lipsync coordination, character consistency, and nighttime cinematic lighting.
📝 Prompt
@Image1 is the performer — preserve her exact identity: cornrow braids, septum ring, statement earrings, sculptural white designer top, dark indigo denim. @Audio1 is the finished master track — the only audio; no invented music, no new vocals.
SHE RAPS THE VOCAL ON CAMERA — PRECISE LIPSYNC IS THE TOP PRIORITY. Mouth articulates every syllable of @Audio1 exactly on time; face visible and sharp through every vocal line, no cutaways mid-word.
LIPSYNC MAP:
0.0–0.5 instrumental.
0.5–2.8 "I'm standing on the edge / Say it with your chest / Or keep it on the deck" + "Hey!"
3.2–6.7 "I walk in, whole room gets tense / I don't need luck, I'm the consequence / If you really want to test my intent / Come correct, come correct or get bent" + "Woo!"
7.5–13.7 same hook verbatim second time, escalated.
14.5–15.0 instrumental hold.
Music-video route: performance, night drive exterior. Director thesis: she raps in the beams of a single car's headlights on an empty wet asphalt lot — minimal, cinematic, all attitude.
Visual world: empty asphalt lot at night after rain, one matte black sedan parked with headlights on, wet ground mirroring the beams, distant sodium streetlights, light steam rising off the asphalt. Palette: headlight white, sodium amber, wet black, bone white top blazing in the beams, indigo. No neon signage, no particles.
Shot flow:
0–2.8s she leans against the car hood in silhouette; on the first word she pushes off and steps into the beams — medium shot, she raps straight down the lens, double shadows fanning behind her.
2.8–3.2s on "Hey!" hard cut to a low wide: her figure blazing between the headlights.
3.2–6.7s backward-dollying medium as she stalks toward camera through the beams rapping, each snare hitting with a sharp head isolation, wet ground doubling her figure; finger to lens on "come correct".
7.5–10s cut on the kick to a tight close-up lit only by headlight glow: second hook with bared teeth intensity, breath faintly visible in the cold air, jaw snapping every consonant.
10–13.7s slow orbital around her in the beams, steam drifting through the light, she raps while carving angular vogue lines with one hand, earrings flaring.
13.7–15s on "Woo!" she stops dead center of the beams, arm high, frozen; the headlights flick to high-beam for the final frame, hold.
Performance rules: cold, cocky, unbothered; articulation crisp and readable; never smiles. Continuity: same woman, same wardrobe, same lot and car. Audio intent: @Audio1 only, mouth locked to it; faint idle engine and wet-ground foley under the track. Quality bar: expensive cinematic rap video, no AI gloss, no glow effects.
A detailed cinematic video prompt for a luxury art gallery heist, featuring a detective confronting thieves in a high-stakes chase sequence.
📝 Prompt
An exclusive luxury art exhibition inside a modern gallery, attended by wealthy collectors, celebrities, and journalists. Priceless masterpieces line the elegant white walls under dramatic spotlights. An undercover detective, dressed in a sharp black suit, quietly observes the crowd while disguised as a guest. A sophisticated team of professional thieves secretly replaces priceless original paintings with flawless replicas using magnetic frames and hidden compartments. The detective notices a tiny discrepancy in one painting just as the thieves prepare to leave. He confronts them, triggering a fast-paced chase through the gallery filled with shattered glass, dramatic close-quarters combat, and narrow escapes between priceless artworks. The detective corners the leader at the rooftop exit, recovers the stolen masterpieces, and arrests the thieves as police flood the gallery. Ultra-realistic, cinematic thriller atmosphere, luxury modern architecture, dramatic lighting, dynamic camera movements, expressive performances, premium Hollywood-quality cinematography, suspenseful orchestral soundtrack, slow-motion action, 4K, HDR, high detail, realistic physics, no subtitles, no text, no watermark.
A high-density 3D toon battle prompt between a spear-wielder and a large-axe wielder, featuring complex weapon physics and 8 distinct cuts.
📝 Prompt
[Genre] High-density 3D toon/cel-look. A fast-paced spear vs axe combat sequence in a vast open-world city plaza. Emphasize depth, weapon weight, speed, and recoil. [References] @1 for spear-wielder features/gear; @2 for axe-wielder features/gear. Maintain character consistency; no merging or role-swapping. [Character Adaptation] Adjust lighting and atmosphere to match both characters while keeping their unique identifying colors. Maintain tails/wings only if in reference. [Style] Theatrical key animation, multi-layer cel shading, delicate outlines. sunset lighting. No photorealism. [Weapons] Exactly one spear and one axe. Weapons are rigid bodies; no melting or duplication. 0.1s hit-stops on impact. [Setting] Open-world city plaza with stone paving, arches, and distant towers. No crowds/subtitles. [Camera] 8 cuts following causal action. No aimless orbiting. [Action] Cut 1: Axe user slams floor to spark and start swing. Cut 2: Spear thrust parried by axe handle. Cut 3: Low axe sweep; spear user jumps over. Cut 4: Tail or spear butt attack countered by axe handle. Cut 5: Mid-air spin parry by spear wielder. Cut 6: Overhead axe slam dodged by sliding. Cut 7: Multi-hit combo exchange. Cut 8: Simultaneous deep lunge.
A cinematic portrait prompt blending modern iPhone photography style with ancient Dunhuang cultural elements and a mystical atmosphere.
📝 Prompt
Realistic portrait photography, iPhone 16 Pro close-up shooting style, no phone visible in the frame. A young adult East Asian female sits partially on a flying dance carpet with Western Regions charm. The background consists of mottled Dunhuang murals, earthy yellow sandstone, swaying lotus candlesticks, pipas, and colorful ribbons. The atmosphere is gorgeous, exotic, mysterious, yet real and natural.
A professional broadcast-style prompt for an announcer delivering a weather report with natural pauses and studio ambience.
📝 Prompt
Clean broadcast audio. Soft studio ambience. Dialogue is clear and prominent. Background music is very low. She smiles warmly, briefly glances toward the weather map, then looks back into the camera and speaks in a cheerful, calm, professional voice: 'Hello everyone. Today will also be sunny nationwide, and summer-like blue skies will spread. In some places, the maximum temperature will rise to around 35 degrees, so please hydrate frequently and be very careful of heatstroke.' Natural conversational pacing with small pauses between sentences. Slight smile throughout. Authentic Japanese TV announcer delivery. A woman speaks toward the camera. 'Hello everyone. Today will also be sunny nationwide, and summer-like blue skies will spread. In some places, the maximum temperature will rise to around 35 degrees, so please hydrate frequently and be very careful of heatstroke.'
A surreal and cinematic prompt describing an elegant woman in a desolate landscape where crimson roots erupt from the earth, blending high fashion with dreamlike nature.
📝 Prompt
A cinematic, high-fashion close-up and medium shot of an elegant East Asian woman wearing a striking white and red abstract-patterned cloak with a high, ruffled collar, standing in a barren, desolate landscape under a dim, overcast sky. She interacts with a massive, ancient tree with dark, gnarled bark and deep crimson, leaf-covered branches. The ground is dry and cracked, and suddenly, thick, vein-like crimson roots or tendrils erupt from the earth, surrounding her and growing upward towards the sky in a dramatic, surreal sequence
A character interaction prompt focused on subtle facial expressions and a sarcastic tone for lip-sync video generation.
📝 Prompt
① Version with no acting specifications
Fixed camera, no cuts. A woman speaks while looking at the other person. Dialogue: "That's amazing. I never would have thought of that."
② Happy version
Fixed camera, no cuts. The woman has just been told about a major achievement her best friend accomplished on her own and is truly impressed from the bottom of her heart. She says this while facing her best friend. Dialogue: "That's amazing. I never would have thought of that."
③ Sarcastic version
Fixed camera, no cuts. The woman knows that a colleague stole her idea and took credit for it, and she is inwardly exasperated and contemptuous. She says this to the person's face, pretending to praise them on the surface. Dialogue: "That's amazing. I never would have thought of that."
A comprehensive multi-scene video script for Seedance 2.0 to generate a premium beverage advertisement with a vibrant summer theme.
📝 Prompt
Create a premium beverage commercial featuring the same young woman throughout the entire sequence. Maintain identical facial features, shoulder-length blonde beach-wave hair, glowing skin, natural makeup, and body proportions in every scene. She wears a stylish pastel pink crop top, matching pleated mini skirt, white sneakers, gold hoop earrings, and delicate bracelets. Bright summer atmosphere, luxury lifestyle aesthetic, vibrant pink color palette, premium commercial cinematography, ultra-realistic storytelling.
The video opens with her smiling brightly into the camera while holding an ice-cold pink mixed berry juice bottle beside her face. She gently rotates the bottle as condensation sparkles in the sunlight. She playfully taps the bottle, winks, and says, "Ready for something refreshing?"
A cinematic macro hero shot showcases the chilled bottle surrounded by fresh strawberries, raspberries, dragon fruit, and ice cubes. Tiny droplets glisten as sunlight reflects across the bottle. She twists the cap open with a satisfying pop, and slow-motion captures sparkling juice swirling inside before she takes a refreshing sip and smiles naturally.
She strolls through a colorful flower market filled with blooming pink flowers, fruit stalls, cafés, and cheerful summer energy. Smooth tracking shots capture her laughter as she samples fresh fruit, greets friendly vendors, and carries the juice bottle in her hand.
The scene transitions to a scenic rooftop picnic decorated with pastel cushions, flowers, fairy lights, and fresh fruit platters. Her friends arrive, everyone laughs, chats, and clinks their juice bottles together while enjoying the sunset.
As upbeat energy builds, they dance together in an open garden surrounded by blooming flowers and fluttering petals. Handheld and gimbal shots capture authentic laughter, spinning movements, and joyful summer moments.
Near golden hour, the group runs through a beautiful flower garden with sprinklers creating sparkling water droplets. Slow-motion shots capture sunlight shining through the mist as she raises her juice bottle toward the camera with a radiant smile.
Final cinematic hero shot: she stands among blooming pink flowers with her friends behind her, holding the chilled juice bottle toward the viewer.
She smiles warmly and says, "Taste the joy!"
The camera slowly pulls back to reveal the vibrant summer garden, golden sunset, blooming flowers, and friends celebrating together. Premium beverage advertising, ultra-realistic commercial cinematography, dynamic camera movement, shallow depth of field, realistic liquid physics, vibrant pink fruit color palette, joyful storytelling, 4K HDR, 16:9 widescreen, natural ambient sounds only (birds, breeze, footsteps, laughter, bottle opening, ice clinking, water splashes), no background music, no subtitles, no logos, no watermarks, and no on-screen text.
A storyboard-style video prompt for a biscuit advertisement, featuring crispy close-ups, slow-motion crunches, and cozy family scenes.
📝 Prompt
(15 sec Ad Video – Zeera Biscuits)
Scene 1 (0–3s):
Close-up shot of crispy golden Zeera biscuits placed on a wooden table. Light steam tea cup beside it. Soft morning sunlight.
👉 Text on screen: “The perfect start to the morning…”
Scene 2 (3–6s):
Slow-motion biscuit break — crunch sound — zeera (cumin seeds) visible inside. Crumbs falling in cinematic style.
👉 Sound: Satisfying crispy crunch
Scene 3 (6–10s):
Young person dipping biscuit into chai ☕, smiling. Cozy home vibe.
👉 Text: “Real taste in every bite”
Scene 4 (10–13s):
Pack shot of Zeera Biscuits rotating with glowing light effect.
👉 Text: “Crispy • Tasty • Classic”
Scene 5 (13–15s):
Final frame: Family enjoying tea with biscuits together ❤️
👉 Text: “Zeera Biscuits – The best partner for every tea”
A comprehensive lifestyle video prompt following a woman's journey to a premium Japanese hair salon, focusing on consistent character details and realistic environment.
📝 Prompt
Create an ultra-realistic cinematic lifestyle video featuring the same young East Asian woman throughout the entire sequence. Maintain identical facial features, long soft ash-brown wavy hair, glowing skin, body proportions, and outfit in every shot. She wears a fitted white ribbed crop top, a flowing red pleated skirt, white sneakers, and carries a cream canvas shoulder bag. Bright summer morning, modern Japanese neighborhood, premium hair salon with warm lighting, realistic reflections, elegant interiors, and a relaxed lifestyle aesthetic.
The video opens with her checking herself in the bedroom mirror before lightly styling her hair. She smiles naturally, picks up her cream tote bag, grabs her phone and keys, and leaves the apartment.
She walks through a peaceful Korean street lined with cafés, flower planters, and boutique stores. The camera follows her with smooth handheld tracking as sunlight filters through the trees and a gentle breeze moves her hair.
She arrives at a stylish Japanese salon, warmly greeting the receptionist before browsing a hairstyle lookbook with the stylist. They chat, laugh, and agree on a soft layered haircut.
She relaxes in the shampoo chair while her hair is gently washed and massaged. Close-up shots capture flowing water, shampoo bubbles, warm lighting, and her peaceful expression.
The stylist carefully trims her hair, blow-dries it with smooth cinematic movements, and finishes with soft curls and a healthy glossy shine. She smiles while watching the transformation in the mirror.
After the haircut, she admires the final look from different angles, takes a quick mirror selfie, thanks the stylist with a warm smile, and leaves the salon feeling confident.
Outside, she walks through the sunny streets with her refreshed hairstyle flowing naturally in the breeze. She stops at a café window, catches her reflection, smiles happily, then looks toward the camera and gives a small friendly wave as the camera slowly pulls back to reveal the vibrant Japanese street.
Natural ambient audio only: footsteps, city ambience, café chatter, salon conversations, scissors cutting hair, hairdryer, running water, shampoo bubbles, hairbrush sounds, door chimes, birds, gentle breeze, distant traffic. No background music, no subtitles, no logos, no watermarks, and no on-screen text. Premium commercial-quality cinematography, smooth handheld and gimbal camera movement, realistic skin texture, detailed hair physics, natural expressions, physically accurate lighting, shallow depth of field, warm golden atmosphere, 16:9 widescreen, 4K HDR.
An 8K IMAX style prompt for a traditional 2D hand-drawn animation featuring a toddler in a violent blizzard with undulating wolf forms on the horizon.
📝 Prompt
Style: 8K IMAX, traditional hand-drawn 2D animation, animated on twos at 12 frames per second — each drawing held for two frames then replaced, choppy stepped motion cadence, hand-painted oil-brush texture, brushstrokes shifting and redrawn from frame to frame, line jitter, no 3D render, no game engine, no CGI smoothness.
DIRECTOR'S NOTES — non-negotiable for every frame and every cut:
1. CHARACTER REFERENCE IS ABSOLUTE — face from <<<image_3>>> and wolf design from <<<image_4>>> exactly 1-to-1, no deviation, reference always overrides text.
2. MICRO-ACTING ON TODDLER FACE — every frame of her close-up shows constant micro-expressions: involuntary blinks as distinct held closed-eye frames on twos, sustained hard squints under gusts, eyelid flutter between blinks, brow gathering, chin quivering, lip pressed and trembling, jaw small and tight, nostrils flaring with shallow breath, tiny scared saccades searching the white air, eyes welling but no tears fall. When the first wolf howl rises offscreen, her eyes snap open wide for a single held frame in pure shock, eyelids freeze, breath catches in her small throat, lip parts slightly.
3. WOLVES NEVER APPROACH — they appear ONLY as a distant dark cloud creeping along the far horizon, never close, never as individual animals, only an undulating dark band of forms — appearing and vanishing as the buran sweeps across the lens.
4. BURAN NEVER PAUSES — rolling white-out waves continuously in every frame.
CHARACTER TAGS:
- THE TODDLER = small girl from <<<image_3>>>.
- THE WOLVES = animals from <<<image_4>>>.
- THE FOREST = location from <<<image_1>>>.
Cinematography Lubezki / Deakins, fully handheld in human hands breathing with operator, anamorphic wide lens, shallow depth, never tripod never dolly never crane never aerial, eye level or below.
The 12 principles of animation throughout: anticipation, follow-through and overlapping, slow in slow out on head turns, arcs, secondary action, exaggeration, solid drawing.
Lighting: night, no light source, no moon, no stars, no rim, no contre-jour, no key light. Flat dim diffuse ambient grey glow only, no direction. Flat painted shapes, no gradient shading.
Atmosphere — violent buran continuous: hurricane gusts driving snow horizontally, visibility roughly 3 meters around the camera, rolling waves of denser blizzard sweeping the lens, snow piled on the toddler's cap and shoulders, wind never drops.
Audio: roaring buran wind continuously as dominant bed, crunching snow, shallow ragged child's breathing, plus two long wolf howls rising from offscreen distance — one howl in the first half of the scene, a pause, then a second howl from a different point along the horizon answering the first in the second half. Distant low growls and panting from the dark mass barely audible under the wind. No dialogue. No music. No subtitles.
SHOT 2A — TIGHT CLOSE-UP handheld on THE TODDLER's face, exact face from <<<image_3>>>, every feature 1-to-1, identical features identical hair identical cap. Camera very close at her eye level, breathing with operator, vertical sway, her small face filling the frame off-center, negative space of white-out, focus locked on her eyes, background dissolved into pure white-out blur. Flat painted shadow only, no light direction. Snowflakes catch on her dark lashes and on the fur of her cap, snow piling on her shoulder.
MICRO-ACTING in this shot, drawn frame by frame on twos as held poses: she squints hard against the wind, eyelids fluttering, then a held closed-eye frame for two frames, then snapping open, then a sustained hard squint when a gust hits held for three frames, anticipation as her tiny brow gathers before each squint, slow in slow out on every eye closure. Chin quivers visibly between beats, lower lip pressed and trembling, jaw small and tight, nostrils flaring with each shallow ragged breath, eyes welling at the corners but no tears fall.
Then the first wolf howl rises from offscreen — her eyes snap wide open for a single held frame in pure shock, eyelids freeze in that wide pose for two frames, breath catches in her small throat (visible by held still chest), lip parts slightly. Her gaze then shifts in tiny scared saccades searching the white air on arcs, head turns a fraction toward the sound on a slow arc. The second howl answers from a different direction — she flinches, brow tightens, another sharp involuntary blink as a held closed-eye frame. A wave of buran sweeps across the lens partly obscuring her face, she does not move. Painting style identical to references. Animated on twos.
HARD CUT to SHOT 2B — VERY WIDE LOW handheld looking out across the snowy expanse beyond THE FOREST treeline, the operator crouched in snow at knee height looking out toward the far horizon, camera in their hands with visible breath sway, the nearest dark pine trunks framing the edges as flat silhouettes.
Far in the distance at the very edge of visibility along the horizon, THE WOLVES move as a single body — a dark moving mass like a black cloud creeping along the snowline, never approaching, never resolving into individual animals, only an undulating dark band of forms — exact wolf design from <<<image_4>>> readable only as silhouettes, exact coal-black fur with cold steel-blue sheen, faint pale yellow eye pinpricks barely visible.
A rolling wave of buran sweeps across the lens — the dark cloud of wolves vanishes completely into white-out, holds white for two beats, then ghosts back into view as a faint dark band shifting along the horizon. The second wolf howl rises from a different point along the horizon, the dark band shifts in response stretching laterally. Another wave of buran swallows them again. The camera stays low and still, operator only breathing. Painting style identical to references. Animated on twos.
Constraints: two distinct shots with hard cut between them not one continuous take, TIGHT CLOSE-UP on toddler then HARD CUT to VERY WIDE on wolves, THE TODDLER's face matches <<<image_3>>> exactly 1-to-1 with constant frame-by-frame micro-acting drawn as held poses on twos, THE WOLVES remain a distant dark cloud along the horizon throughout and never approach or resolve into individual close animals, reference always overrides text, buran rolling waves present in every frame, no dialogue, camera handheld eye level or below, no light source, flat painted shadow only, no 3D look.
A high-quality theatrical anime action prompt featuring a cyborg and a robot companion in a fast-paced battle across a coastal aero-city.
📝 Prompt
1:1 square, 15 seconds, high-quality theatrical anime-style high-speed action. The setting is a bright afternoon futuristic coastal aero-city. High-speed cuts between the blue sky, sea, huge white deck, glass corridor outer walls, aerial transit routes, connecting bridges, terminal rooftops, 3D structures between buildings, and observation decks. Avoid enclosed spaces or monotonous combat in the same location.
[Reference Image] Use [image_name] only to fix the appearance of one cyborg woman and one partner robot. Prioritize the upper body views of the woman and the full robot; face, head, arm weapons, back, and leg parts are supplementary. Do not reproduce outlines, white backgrounds, headings, multiple views, expressions, or details of face/legs/weapons as intro cuts or compositions. Animate the two in a completed anime world from the start. The woman and robot are allies in the same battle but act independently in the first half to middle, converging on the same large enemy only at the end. Maintain face, hairstyle, body type, armor, weaponry, back structure, and color scheme; no costume/armor/unit changes, transformations, merging, giantization, duplication, or color swaps. Enemies are graphite-colored non-humanoid small drones and one large graphite unmanned aerial vehicle at the end. Aerial traffic in the background is civilian and does not participate in combat.
[Field of View & Movement] Wide to ultra-wide based. Do not make it feel cramped even at 1:1; leave sky, sea, city, architecture, and margins. Close-ups are used only momentarily. Movement should not be photorealistically smooth but shown as a chain of: strong stance -> short tension -> screen occlusion -> strong pose at another point -> contact -> short hit stop -> large reaction. Avoid long runs or flights; use arcs, diagonal crossings, sudden reversals, vertical differences, X-shapes, S-shapes, and jumping between buildings. The camera also uses bold diagonal dives, sudden climbs, crossings, gaps between buildings, and quick reversals.
[Effects] Effects should not be blue light lines, beams, lasers, or auroras. Use primary and accent colors from @image1 as opaque color planes with clear outlines, thick stroke marks, long sweeping tail-like threads, flying color chips, and diagonal color blocks. Every movement, appearance, or impact must be accompanied by a fast-feeling effect like dragged paint.
[Composition] 0.0-1.5s: Ultra-wide view of the coastal city. Drones invade from multiple directions. The woman from the corridor wall and the robot from the lower deck deploy separately. The robot parries a blow in an arc, sending shockwaves through the city. 1.5-3.3s: Woman's part. Color planes cover the foreground, switching between the corridor, transit way, and rooftop. She shows only key poses of stance, slash, and landing reaction with strong thread effects. 3.3-5.1s: Robot's part. Uses deck edges and bridges for crescent trajectories and heavy hits to blow away drones. 5.1-6.9s: Woman's part. Vertical space between buildings. Appears instantly from different angles after occlusion, changing height for continuous attacks. 6.9-8.7s: Robot's part. Uses high structures for wall reversals and diving through drones. 8.7-10.2s: Large UAV enters. Huge shadow crosses the terminal. Woman and robot jump in from different directions to converge on the enemy. 10.2-12.2s: High-speed combo climax. Robot breaks armor in an arc; viewpoint flips for the woman to appear from above and slash the weak point. No long grappling. 12.2-15.0s: Large unit explodes not as a fireball but as opaque color planes and sharp fragments. Camera moves through debris to the observation deck. The two land at different times and re-accelerate away. The city responds with celebratory smoke and functional restoration. Ends with a full city view and tracks stretching into the distance.
[Audio & Forbidden] High-density theatrical anime BGM. Strong dynamics for impact, slashes, and destruction. Avoid cheap TV anime style, constant speed movement, long slow motion, UI, subtitles, or merging weapons.
A detailed cinematic prompt for a music video sequence featuring a rapper in a classic NYC deli, with precise lip-sync mapping and dynamic crash zoom transitions.
📝 Prompt
@[Image 1](image_1) is the performer — preserve her exact identity: cornrow braids into long dark curls, silver chain-drop earring, gold pendant necklace, washed-green denim corset top, glossy lips. @[Audio 1](audio_1) is the finished master track — the only audio; no invented music, no new vocals.
SHE RAPS THE VOCAL ON CAMERA — PRECISE LIPSYNC IS THE TOP PRIORITY. Mouth articulates every syllable of @[Audio 1](audio_1) exactly on time; face visible and sharp through every vocal line, no cutaways mid-word.
LIPSYNC MAP:
0.0–0.5 instrumental.
0.5–2.8 "I'm standing on the edge / Say it with your chest / Or keep it on the deck" + "Hey!"
3.2–6.7 "I walk in, whole room gets tense / I don't need luck, I'm the consequence / If you really want to test my intent / Come correct, come correct or get bent" + "Woo!"
7.5–13.7 same hook verbatim second time, escalated.
14.5–15.0 instrumental hold.
Music-video route: performance, NYC deli counter + street hybrid. Director thesis: corner-store cash-out — she raps from the bulletproof-glass deli counter out to the curb where her girls hold court on a double-parked old-school sedan. Black girlie hustle vibe.
Visual world: classic uptown NYC corner deli at dusk — plexiglass counter carousel, snack racks, lotto machine glow, storefront plastered with faded posters; outside, a burgundy 90s sedan double-parked at the curb, streetlight just flicking on, brownstone corner behind. 3 background dancers: Black girls in uptown glam — fur bucket hat with a puffer vest and hoops, long braids under a fitted cap worn backwards with a cropped jersey, trench worn open over a matching knit set; all with name rings and gold chains. Palette: deli warm yellow, dusk blue street, burgundy car paint, denim green, gold. No neon effects, no particles.
Shot flow (crash zooms stitching inside and outside):
0–0.5s static frame through the deli's plexiglass at her face lit by lotto-machine glow, waiting.
0.5s CRASH ZOOM IN through the plexiglass to her mouth on the first word — she raps through the carousel window, tapping the counter.
2.8–3.2s on "Hey!" hard cut outside: the three girls sit up in unison on the sedan — hood, roof, trunk.
3.2–6.7s she shoulders out the deli door rapping, bell jingling, camera pulling back to the curb; CRASH ZOOM punches on "tense" and "consequence"; the girls slide off the car and fall in step, hitting synchronized hip-cock freezes on every snare along the fender line; finger to lens on "come correct".
7.5s CRASH ZOOM IN on the kick to a tight close-up leaning back against the sedan door — second hook doubled, streetlight warm on her cheekbones, jaw snapping consonants.
10–13.7s slow orbital around the car: she raps from the hood while
A complex three-part martial arts duel featuring steel war-fans against a stone hammer, including destruction and slow-motion impacts.
📝 Prompt
PART 1 — CLASH BEGINS (0:00–0:15)
Cut 1 (0:00–0:05) — Fast drone-in, both students already squared off, empty hands raised, wind gusting. Quick alternating close-ups on their eyes, no dialogue yet.
Cut 2 (0:05–0:08) — ACTION STARTS. Both sprint toward each other, shouting in sync:
Girl: "STEEL—!"
Boy: "—OR STONE!"
Fast handheld push-in, dust kicking up under their feet.
Cut 3 (0:08–0:11) — Both rip weapons from behind their bodies mid-sprint — girl's twin steel war-fans snap open (metallic RING), boy's massive stone-headed hammer swings into frame. Whip-pan cuts between them, full speed.
Cut 4 (0:11–0:15) — Boy laughs, hammer cocked back:
Boy: "Stone crushes steel, sweetheart!"
Girl smirks, doesn't slow down:
Girl: "Not today."
Low tracking shot chasing her sprint.
PART 2 — THE STRIKE (0:15–0:30)
Cut 5 (0:15–0:18) — Boy swings the stone hammer down in a massive overhead arc, roaring with effort:
Boy: "HAAAH!"
Handheld shake with the swing's force.
Cut 6 (0:18–0:22) — SLOW-MOTION STRIKE #1: Girl pivots low, both steel fan-blades scissor together and clash directly into the stone hammer-head. Sparks and rock dust erupt. Camera orbits the impact 180° in slow motion. No dialogue — just the grinding stone-on-steel shriek.
Cut 7 (0:22–0:25) — Full speed: the stone head cracks and shatters into flying rock shards. Boy's eyes go wide:
Boy: "WHAT—"
Cut 8 (0:25–0:30) — Shockwave sends him flying backward, tumbling through dirt and stone fragments. Fast cuts: tumble — dust — skid to a stop. Girl stalks forward, fans still crossed, unshaken.
PART 3 — FINISH (0:30–0:45)
Cut 9 (0:30–0:33) — Boy pushes up on one elbow, dazed, blazer torn, dust on his face:
Boy: (coughing, defiant) "...Not bad."
Cut 10 (0:33–0:36) — Girl closes the distance fast, plants one fan-blade in the dirt beside his head — SLOW-MOTION STRIKE #2: blade sinks into the earth, wind blast throws his hair back, dust ring bursts outward around the impact point.
Cut 11 (0:36–0:40) — Full speed. Girl straightens, fans crossed over her shoulders, hair whipping, staring down at him with total control.
Boy: (smirking despite himself) "...Guess I lost."
Cut 12 (0:40–0:45) — Low-angle hero shot, wind roaring, girl's eyes locked on camera:
Girl: "K.O."
Hard cut to black on final syllable.
A single continuous cinematic shot tracking a butterfly through a forest before a parrot strikes, ending in extreme macro bullet-time.
📝 Prompt
Photorealistic cinematic, one single continuous unbroken shot from start to finish — absolutely no cuts, no edits, no transitions, one fluid uninterrupted camera move, 16:9. Bright daylight in a lush green forest, sunlight filtering through the canopy, leaves and tree trunks softly blurred.
The shot begins directly behind a vivid colorful butterfly fluttering fast and dynamically through the forest, the camera chasing close behind its wings as it weaves between trees, shafts of light and foliage — erratic, lively and kinetic.
Without any cut, in the same fluid motion, the camera keeps racing with the darting butterfly deeper through the trees. Then, at the midpoint, a parrot suddenly bursts in from the side and snatches the butterfly out of the air, biting down and clamping onto the edge of one of its wings in its beak — and the camera sweeps with the strike in one continuous move.
Still unbroken, the camera drives in onto the moment of capture and explodes into a dramatic bullet-time effect: time nearly freezes as the parrot's beak bites and clamps onto the butterfly's wing in an extreme macro close-up, the wing bending and creasing in the beak's grip, and the camera sweeps slowly around the frozen instant — shimmering powder and tiny iridescent scales scattering off the pinched wing and hanging suspended motionless in mid-air, the delicate wing membranes and veins razor-sharp, the parrot's beak texture and eye in crisp detail, the butterfly caught mid-flutter — hyper-detailed.
One seamless continuous camera move — chase from behind, racing through the forest, into the parrot's strike, ending in a bullet-time orbit around the catch. Flowing and dynamic, collapsing into near-frozen bullet time only at the macro catch. Shallow depth of field, strong motion blur on the chase resolving into crisp frozen detail, bright natural daylight, dappled forest light, high dynamic range, ultra-detailed photorealistic textures — wing scales, powder, feathers, foliage — 4K, high-end wildlife documentary look. Pacing over 10 seconds: about 4–5 seconds of dynamic butterfly flight, the parrot striking around the midpoint, then the rest in bullet-time macro of the parrot biting the wing. 10 seconds, single continuous take.
An intense, hyper-realistic cinematic prompt depicting a lighthouse keeper's struggle against a violent storm to reactivate an emergency beacon.
📝 Prompt
Hyper-realistic cinematic action sequence, 15 seconds, aspect ratio 16:9. Night.
On a remote rocky coast during a violent hurricane, a lighthouse keeper climbs the outside of a tall lighthouse to reach the emergency beacon at the top. The storm is brutal and the situation is urgent. Heavy rain lashes the tower, hurricane-force wind pushes hard against the keeper, and giant waves crash violently into the rocks and the base of the lighthouse.
The exterior is simple and clear: wet stone walls, narrow metal ladder sections, exposed railings, a small exterior platform near the top, and the dark emergency beacon housing above.
Wide opening shot: the lighthouse keeper steps out onto the exterior of the lighthouse in the middle of the hurricane and immediately begins climbing upward. Rain blasts sideways, wind whips clothing, and huge waves explode against the base of the tower below.
Tracking shot: the keeper climbs higher along the outside ladder and narrow metal steps while the storm intensifies. The tower shakes from the force of the sea. Lightning flashes across the sky. The keeper nearly loses grip once, slams against the wall, recovers, and keeps climbing. The beacon above is dark, making the danger feel more urgent.
Side shot: the keeper reaches the upper exterior section near the beacon platform. A massive gust hits hard. The keeper clings to the ladder, almost gets pulled away, then forces upward again. Water pours down the stone, the metal steps are slick, and another giant wave crashes into the lighthouse below, shaking the whole structure.
Final 5 seconds: the action becomes extreme. The keeper pulls onto the tiny top platform while the hurricane is at full force. The platform rattles, the railing bends slightly under pressure, and the beacon housing swings or shakes in the wind.
The keeper struggles across the platform, grabs the beacon assembly, and fights to secure or reconnect it while lightning flashes and spray blasts upward. At the last possible second, the beacon powers back on and cuts through the storm with a powerful beam. Final moment: the lighthouse beacon shines through the hurricane while the keeper clings to the top platform, waves smashing below and rain whipping across the frame.
Style: hyper-realistic, cinematic, fast-paced, intense, stressful, clear readable action, strong sense of height and danger, violent hurricane, heavy rain, powerful wind, crashing waves, shaking lighthouse, dynamic but readable camera movement, no text, no logos, no cartoon style, no slow motion, no famous celebrity faces, no recognizable actors, no movie-star resemblance, no public-figure likenesses, no clear facial close-ups. Keep proportions. Keep style and features. Aspect ratio 16:9.
A cinematic video prompt for Seedance 2.0 depicting the mechanical failure and collision of a massive orbital construction system in space.
📝 Prompt
Colossal orbital construction system, synchronized assembly breaks down, turning massive moving parts into lethal, unpredictable motion.
Wide shot: perfectly timed mechanical arms moving huge segments into place.
Micro-delay: one segment arrives early, barely noticeable at first.
Collision: misaligned parts slam together, throwing off timing across the system.
Cascade: surrounding arms react too late, desynchronizing the entire structure.
Hard dive: small ship enters the assembly zone as motion becomes chaotic.
Near-crush: two massive plates slam shut just after the ship passes through.
Timing gamble: pilot commits to a gap that’s already closing.
Whip movement: a mechanical arm swings unpredictably across the path.
Close scrape: ship rolls sideways, barely avoiding full impact.
Moving maze: structure still assembling, but incorrectly, paths shifting constantly.
Critical moment: a full segment drops into the escape vector.
Last-second slip: ship squeezes through a narrowing gap as components collide behind.
Rhythm collapse = danger, everything still moving with force but no coordination.
A detailed video generation prompt for creating a theatrical robot anime-style launch sequence, including characters, mechas, and cockpit views.
📝 Prompt
15-second, 480p, 16:9 widescreen video. A theatrical robot anime-style launch sequence utilizing the 'character', 'manned robot', and 'cockpit' from the attached reference images.
A highly technical cinematic prompt for a 15-second sequence showing a character transforming into armor mid-flight, with detailed instructions on lighting, skin texture, and cinematography.
📝 Prompt
Style: IMAX 8K. Photorealistic no 3D rendering, no game engine, no video game cinematic aesthetics. Cinematography: Emmanuel Lubezki × Roger Deakins. Lighting: Natural light only backlight, camera placed on the shaded side, slight atmospheric haze present throughout the scene. Main light comes only from the sky and windows. Colors: 60:30:10 distribution dominant / secondary / accent. Camera: Real cinema lens. Motion blur with a 180° shutter. Skin: Pore-level realism visible peach fuzz, asymmetrical moles, capillary redness, pore shadows consistent with scene lighting. Acting: Hollywood level micro-pauses before reactions, precise gaze direction, wet and lively eyes with light reflections, breathing visible through chest movements. Physics: Gravity and inertia respected each mass has a realistic weight, correct contact shadows. No floating objects. Composition: Rule of thirds + golden ratio. Every character is in motion from the first frame. Continuity: Characters, props, and environment stay identical from one shot to another. No identity drift. Technical: Fluid motion at 24 frames per second. 8K details. No shaking. Audio: Ambient sound effects only. No music. No subtitles. SUBJECT <<<580cbf5c-4d9d-48b4-bd6d-ca414ac81650>>> matches the reference image 100%. The can <<>> is held in his right hand. At the end of the sequence, he is fully transformed into <<<13ce0872-5dbd-4f81-9d78-bb440b750841>>>: the armor assembles in real time while he is in mid-flight, and <<<13ce0872-5dbd-4f81-9d78-bb440b750841>>> matches the reference 100%. White balance: 6500 K. MULTI-SHOT fast cinematic editing with energy that builds progressively throughout the entire 15-second sequence. LOCATION <<<781dadcd-7026-4651-a9a2-181c3fc22064>>> serves only as a style reference, not a fixed shot. Use this reference for visual style, mood, architecture, and lighting: a large deserted New York-style avenue under intense midday sun. Seedance must freely generate the rest of the scenery: new buildings, new sections of the avenue, and new camera angles. The character actually moves through space from one shot to another. He must never remain frozen in the location or framing of the reference image. Do not reproduce the reference image identically. ACTION SHOT 1 (0:00–0:02) Extreme close-up, from chin to forehead. <<<580cbf5c-4d9d-48b4-bd6d-ca414ac81650>>> brings the can <<>> to his lips and takes a long sip. His Adam's apple goes down and then up twice. Jump cut. SHOT 2 (0:02–0:04) Same close framing. The can goes back down quickly. His eyes snap open, sharp and perfectly attentive (natural skin and iris details, no lighting effects). The zygomatic muscle contracts: a genuine wide smile appears in less than a second, the corners of the lips moving from about 2 mm to 8 mm. The sternum rises during a deep breath. He is bursting with energy. Jump cut. SHOT 3 (0:04–0:06) Wide low-angle shot. <<<580cbf5c-4d9d-48b4-bd6d-ca414ac81650>>> explodes forward in a sprint at 30 km/h, following exactly the direction he was already looking. He runs straight down the avenue. He never looks back. With each stride, his sneakers hit the cracked asphalt violently, kicking up small clouds of dust about 10 cm high. Jump cut. SHOT 4 (0:06–0:08) Tracking shot following the run. Arms move at about 90°. The tracksuit jacket floats behind him for about 15 cm. The smile remains. Eyebrows are raised. Mouth is slightly open and relaxed. The stride lengthens. Ground contact time decreases. His speed increases. Jump cut. SHOT 5 (0:08–0:10) Two final strides. Knees compress to about 110°. The right foot slams into the asphalt. The ground cracks in a radius of about 20 cm. He is propelled upward at 65 km/h. Jump cut. SHOT 6 (0:10–0:13) Mid-flight in the urban canyon of <<<781dadcd-7026-4651-a9a2-181c3fc22064>>>. Played at 24 frames per second, normal speed. No slow motion. He never stays frozen. His entire body continues to move during the jump: torso pivots, legs continue their movement, arms deploy, head turns to follow the arrival of the armor. While he flies and rotates in the air, different pieces of armor emerge from the urban environment and converge on him. The chest plate locks during rotation. The pauldrons close as his shoulders move. The gauntlets lock onto the forearms as his arms extend. The shin guards attach to the legs in motion. The helmet descends, then the visor snaps shut as his head returns forward. The entire transformation takes place in a single fluid and violent sequence. The body stays constantly in motion. A sharp metallic click accompanies the closing of the visor. Jump cut. SHOT 7 (0:13–0:15) <<<13ce0872-5dbd-4f81-9d78-bb440b750841>>> slams into the ground in <<<781dadcd-7026-4651-a9a2-181c3fc22064>>> in a crouching position. Both armored feet hit the asphalt simultaneously. A dust wave of about 80 cm radius spreads. He stands up. He opens and then sharply closes his armored fists: first the left, then the right. He then looks down at his chest plate. A slight muffled laugh is heard behind the closed visor. Sharp cut to a black screen. CAMERA Extremely dynamic handheld camera. Never static. Never locked. Strong natural operator shakes in each shot (4 to 8 cm bounces), without stabilization. Very pronounced Dutch Angle throughout the video: tilt between 12° and 20°, varying from shot to shot and gradually increasing. Shot 1: FOV 18°, extreme close-up, 15° tilt, violent micro-shakes. Shot 2: FOV 18°, reverse tilt at about 18°, nervous camera. Shot 3: FOV 84°, low angle, 12° tilt, brutal start of the run. Shot 4: FOV 84°, camera physically following the character, 16° tilt, strong bounces synchronized with strides, motion blur during pans. Shot 5: FOV 63°, 20° tilt, rapid upward tilt during the jump. Shot 6: FOV 63°, extremely dynamic handheld camera. The operator turns around the character in mid-flight with 6 to 8 cm bounces, quickly reframing each armor piece as it locks, tilt varying from 18° to 8°. No slow motion. Shot 7: FOV 63°, strong impact at landing, 14° tilt, camera recoils by about 8 cm under the impact then regains a slight respiratory movement while inspecting the armor. STYLE Dominant: light gray asphalt and urban canyon (60%). Secondary: navy blue/cream outfit gradually evolving into chrome armor (30%). Accent: smile, dust, chrome reflections, and blue LED on the visor at landing (10%). White balance: 6500 K. No light effects in the eyes. Eyes are only lit by natural sunlight. CONSTRAINTS
A high-energy 80s B-movie style transformation sequence featuring a muscular warrior and a tiger, complete with neon lights and disco energy.
📝 Prompt
Intense fast-paced 80s B-movie transformation sequence with campy disco energy, vibrant pink neon club lighting mixed with explosive golden power effects, rapid-fire editing full of quick cuts and jump cuts for maximum intensity, dynamic handheld camera with constant movement and energy, practical effects focused, over-the-top yet grounded in cheap 80s low-budget aesthetic.
Use the provided reference image as the exact visual reference for the main muscular warrior’s face, wild blonde hair, body, gold sequined outfit with red cross emblem, pink feather details and jewelry. In the final transformed state he additionally wears cheap tacky 80s disco sunglasses with colorful horizontal stripes.
0-4s: Rapid-fire opening montage - quick successive cuts: close-up of warrior’s intense face, cut to hands gripping the glowing power device, cut to his large yellow cat companion looking nervous, cut to surrounding crowd of 80s extras and background actors in flashy outfits reacting with surprise, cut back to warrior beginning to raise the device with raw building power.
4-8s: Rapid-fire power-up sequence - fast montage of quick cuts: warrior dramatically raises the device overhead, energy starts surging, cut to him pulling out and putting on the cheap disco striped sunglasses, cut to his muscles visibly swelling and gold sequins activating with intense sparkle, cut to pink feathers whipping wildly, multiple angles of wind and sparks hitting him, background secondary actors moving and watching in awe.
8-12s: Peak rapid-fire transformation montage - series of intense quick cuts: golden-pink lightning exploding around warrior (hair becoming even more voluminous, full outfit glitter activation), cut to sunglasses reflecting the dramatic light, cut to the cat companion undergoing organic photorealistic transformation into a large majestic tiger (natural fur texture shifting, real muscle and bone structure expanding organically, authentic animal movement and eye reflections, no CGI appearance), cut to crowd gasping and cheering, cut to red cross emblem blazing brightly.
12-15s: Rapid-fire climax and settle - fast final cuts: warrior in full powered heroic pose wearing the disco sunglasses, commanding stance, cut to the photorealistic tiger standing powerfully beside him with natural fur and real presence, cut to surrounding 80s secondary actors cheering and reacting, quick wide shots of the duo side-by-side as energy and glitter settle, ending on a strong held composition with crowd in frame.
Photorealistic, hyper-realistic tiger with authentic fur texture, organic animal physics and natural muscle movement (no CGI look), ultra-detailed sequin reflections and feather physics, realistic practical energy effects, perfect motion blur on all rapid cuts, flawless character consistency, coherent 80s lighting and color grading, stable intense action, professional cinematic quality.
A highly detailed cinematic video prompt for Seedance 2.0 that generates a photorealistic scene of an elderly man in safety gear roller skating and falling. It features comprehensive instructions for natural lighting, skin realism, and physics-based motion.
📝 Prompt
Style: IMAX 8K. Photorealistic, no 3D rendering, no game engine. Lighting: Natural light only, backlighting, camera placed on the shaded side, slight atmospheric haze throughout the scene. The main light comes only from the sky and windows. No artificial lighting. Colors: 60:30:10 distribution (dominant / secondary / accent). Camera: Real cinema lens. Motion blur with a 180° shutter. Skin: Pore-level realism, visible fuzz, asymmetrical moles, capillary redness, pore shadows consistent with the set lighting. Acting: Hollywood level, micro-pauses before reactions, precise gaze direction, lively eyes with catchlights, visible breathing through chest movements. Characters never stay still: they react constantly. Physics: Gravity and inertia respected, each mass has a realistic weight, correct contact shadows. No floating objects. Composition: Rule of thirds + golden ratio. Every character is in motion from the first frame. Continuity: Characters, props, and sets remain identical from one shot to another. No identity drift. Technical: Fluid movement at 24 frames per second. 8K details. No shaking. Audio: Ambient sound effects only. No music. No subtitles. Character: OLD MAN (<<<5571b746-cf71-4d00-856a-e63dfbc65ea5>>>), late sixties, metal-rimmed glasses slightly crooked under a shiny red sports helmet also slightly displaced, black chin strap still attached, gray mustache, white t-shirt pulled up showing his belly, red gym shorts, black elbow and knee pads, striped high socks, and flame roller skates (<<<12af3151-dc95-4411-83d7-e8a4d1fa8c04>>>). Scene: At the bottom of the slope (<<<46231bd6-1653-4ded-b50e-69c0ff113a83>>>), at the level of the white stripes of the crosswalk, near the fire hydrant. The old man arrives at maximum speed, impossible to control. SHOT 1: Lateral tracking shot, 35mm lens, fast pan to keep him in the frame. A wheel catches a crack in the sidewalk. His whole body tips forward beyond the point of no return: his arms deploy like those of a surprised bird, one leg kicks back, his glasses leave the bridge of his nose. He lets out a muffled cry. His body language evokes a comedy of blunders, but with perfectly realistic weight and physics. SHOT 2: Wide angle at asphalt level.
A complex single-shot prompt featuring an in-camera transition from a burning pirate ship deck to an endless sunlit desert through an explosion effect.
📝 Prompt
SCENE CONTEXT One continuous shot with an in-camera transition of location AND wardrobe. Eduardo fights his way along the wrecked, burning deck of his galleon under incoming fire: an explosion bursts on his LEFT — he dodges away and is knocked down; he struggles back to his feet — a second explosion on his RIGHT — he ducks and shields behind debris; then he breaks into a sprint for the sterncastle cabin door. The ship explodes — a white flash, dust and smoke flood the entire frame, wiping the world out. The dust thins and settles — and the world behind it has changed: the same man now stands in an endless sunlit desert, dressed as a desert wanderer, dunes to the horizon, the ship gone. ACTIVE REFERENCES <<<d0ae923b-03a5-4f69-9046-5fce5e0d62c6>>> — lean pirate captain, dark curly hair falling free from under a dusty mustard-yellow cloth bandana, a small white shark tooth pinned to the front of the bandana above his temple, thin moustache, gold hoop earrings, cream linen shirt under a worn brown leather waistcoat, cloth sash and leather belts. 100% matches the reference; he is the runner on the deck in the first half, BEFORE the dust. <<<da4fc251-a627-4ff4-b2da-c9d32266862a>>> — the SAME man as <<<d0ae923b-03a5-4f69-9046-5fce5e0d62c6>>> (identical face: dark curly hair, thin moustache, same features) transformed into a desert wanderer: layered sand-beige nomad robes, a loose hood and shawl draped over his head and around his neck, rust-red sash accents, a leather shoulder strap, wrapped gloves and bound desert boots. 100% matches the reference; he is the man revealed in the desert AFTER the dust settles. <<<9470010f-91ae-4b0f-b10d-9f3f29f55e3e>>> — Eduardo's galleon: pale square sails, tall wooden sterncastle. 100% matches the reference; already battle-damaged in this shot — burst bulwark, smoldering rigging, debris on the deck. <<<673b2d64-5cc7-4653-9320-86c1a404fd7b>>> — calm bright sea, glittering sun path, hazy horizon. Controls water and sky in the first half only. <<<7e338f88-dd41-44d4-b787-65a48471fd9c>>> — endless pale-gold sand dunes, sharp wind-cut ridgelines, hazy white sky. 100% matches the reference; it is the world after the dust settles. LOCATION MAP First half: the main deck of <<<9470010f-91ae-4b0f-b10d-9f3f29f55e3e>>> on <<<673b2d64-5cc7-4653-9320-86c1a404fd7b>>> — a wrecked corridor of splintered planks, fallen spars, torn rigging and small fires between the mainmast and the sterncastle cabin door at the stern. The cabin door is the destination, background-center. Sea and smoke beyond the broken rail. Second half, revealed by the settling dust: <<<7e338f88-dd41-44d4-b787-65a48471fd9c>>> — a rippled sand slope in the foreground where Eduardo stands, a high dune ridge midground, rows of dunes dissolving into white haze at 2 km. Sun high in both worlds. FIRST FRAME / BLOCKING First frame: deck level behind <<<d0ae923b-03a5-4f69-9046-5fce5e0d62c6>>>, MS — he is already moving away from camera down the wrecked deck toward the sterncastle cabin door in the background-center, smoke streaming across the frame, small fires burning left and right, the deck listing. FORMAT MODE One continuous shot — the camera does not cut on its own. The location transition happens INSIDE the shot, hidden in the dust whiteout. PHASE 1 — the gauntlet: handheld follow behind Eduardo working down the wrecked deck toward the cabin door. An incoming round EXPLODES on his LEFT — a burst of flame, planks and spray — he flinches away to the right and is knocked off his feet onto the deck. He struggles up, heavy and unsteady, one hand pushing off a fallen spar — and a second round EXPLODES on his RIGHT — he ducks hard, shielding his head behind a broken mast stump, debris raining over him. PHASE 2 — the sprint and the blast: he shoves off and breaks into a desperate sprint at 12 km/h for the cabin door. Two steps before the door, a hard white flash floods from screen-right, overexposing the frame for two frames. The shockwave hits — Eduardo is thrown off his stride, the camera kicks 5 cm — and a wall of grey-brown dust and smoke rolls over him and the lens, filling 100% of the frame. Hold 1.5 seconds inside the moving dust, faint orange glow pulsing, then fading to neutral bright haze. PHASE 3 — the settle: the dust thins from 100% to 0% over 3 seconds, brightening to clean white daylight — and it uncovers <<<7e338f88-dd41-44d4-b787-65a48471fd9c>>> with <<<da4fc251-a627-4ff4-b2da-c9d32266862a>>> standing alone on the rippled sand slope: the same man, now in the layered sand-beige nomad robes and hood, in the same body position the blast left him in — half-crouched, arms still shielding his head. He slowly lowers his arms and straightens, sand streaming off the robes, the hood settling around his face, and turns a full slow circle taking in the dunes. Silence. Hold on him small in the wide desert to the end. OPTICS 47° neutral through the run and the blast, easing to 63° as the dust settles so the desert reads wide around him. Focus rides Eduardo throughout; during the whiteout the frame is pure particulate with no fixed plane. CAMERA Handheld chase behind him in phase 1, footstep energy visible. The blast kicks the camera hard and buries it in dust. As the dust settles the camera steadies to a slow drift, settling 8 meters behind and slightly above him, level horizon, watching him turn. ACTION THE GAUNTLET IS DESPERATE AND PHYSICAL, IN STRICT ORDER: LEFT EXPLOSION → DODGE RIGHT → KNOCKED DOWN → A HARD, CLUMSY STRUGGLE BACK TO HIS FEET → RIGHT EXPLOSION → DUCK AND SHIELD BEHIND THE MAST STUMP → SHOVE OFF → FULL SPRINT TO THE DOOR. EACH EXPLOSION VISIBLY MOVES HIS BODY: THE FIRST THROWS HIM DOWN, THE SECOND FOLDS HIM BEHIND COVER. THE FINAL BLAST INTERRUPTS HIM MID-STRIDE — BODY THROWN FORWARD AND DOWN INTO A BRACE. IN THE DESERT HE RISES SLOWLY: ONE BEAT ON HIS KNEES FEELING THE SAND UNDER HIS HANDS, THEN STANDING, WRAPPED BOOTS SINKING IN THE LOOSE GRAINS, ROBES SWAYING WITH THE MOVEMENT, A SLOW 360° TURN, CHEST HEAVING FROM THE SPRINT THAT NO LONGER HAS A SHIP UNDER IT. PERFORMANCE DURING THE RUN: JAW CLENCHED, EYES FIXED ON THE CABIN DOOR. AFTER THE SETTLE: CONFUSION IN THE BODY BEFORE THE FACE — HANDS TESTING THE SAND, A SLOW BLINK AGAINST THE BRIGHT LIGHT, BREATH STILL RAGGED, EYES SCANNING A HORIZON WITH NOTHING ON IT. PORE-LEVEL SKIN REALISM, GRIME AND DUST CAKED ON THE SWEAT, SUN CATCH-LIGHTS. PHYSICS THE LISTING DECK TILTS HIS MOVEMENT; DEBRIS HAS WEIGHT AND STOPS HIS FOOT WHEN HIT. THE TWO DECK EXPLOSIONS THROW REAL SHOCKWAVES — PLANKS LIFT, FLAME FLASHES THEN ROLLS INTO SMOKE, AND EDUARDO'S FALLS CARRY TRUE BODY WEIGHT, HARD CONTACT WITH THE DECK, NO BOUNCE. THE FINAL SHOCKWAVE ARRIVES BEFORE THE DUST — CLOTH AND HAIR SNAP FLAT FIRST, THEN THE CLOUD SWALLOWS. DUST HANGS AND SETTLES WITH REAL PARTICULATE BEHAVIOR, FINE GRAINS RAINING OUT LAST. DESERT SAND IS LOOSE: BOOTS SINK TO THE ANKLE, STREAMS POUR OFF HIS SHOULDERS WHEN HE RISES, HIS FOOTPRINTS MARK WHERE HE STANDS. HEAT SHIMMER WOBBLES THE FAR RIDGE. THE NOMAD ROBES MOVE WITH REAL CLOTH WEIGHT, HEMS DRAGGING LIGHTLY ON THE SAND. LIGHTING PHASE 1: HIGH SEA DAYLIGHT 5600K, HARDENED BY FIRE-GLOW ACCENTS FROM THE DECK FIRES AND SMOKE SHADOW SWEEPING THE DECK; EACH OF THE TWO EXPLOSIONS THROWS A BRIEF WARM FLASH FROM ITS SIDE OF THE FRAME. PHASE 2: TWO FRAMES OF WHITE-HOT OVEREXPOSURE, THEN DIM ORANGE-LIT DUST FROM INSIDE THE CLOUD. PHASE 3: THE LIGHT CLEANS AS THE DUST THINS — FLAT BRIGHT 5600K DESERT LIGHT THROUGH THIN HAZE, SOFT SHADOWS IN THE DUNE HOLLOWS, WHITE SKY, MILD SILVER BLOOM AT THE HORIZON. AUDIO PHASE 1: BOOTS ON BROKEN PLANKS, FIRE CRACKLE, GROANING TIMBERS, WIND — THEN BOOM LEFT, RINGING EARS, HIS GRUNT AS HE HITS THE DECK; SCRABBLING BOOTS, RAGGED BREATH; BOOM RIGHT, DEBRIS PATTE
A descriptive prompt for Seedance 2.0 depicting a calm girl emerging from turbulent water in a flooded office, featuring realistic physics and 35mm grain.
📝 Prompt
The video opens on the surface of churning green-gray water, filmed in an extreme close-up: the water splashes and ripples violently, sprays of water erupt, faint reflections of fluorescent neon lights appear on the surface, while the camera already begins a slow zoom out from the very first frame. A thick, pronounced 35mm film grain texture is present on every frame from the beginning. The rendering is in superb 4k ultra-high definition, with an exceptional level of detail on every drop of water. As the camera continues to pull back, a young girl simultaneously emerges from the water from the depths. She breaks through the surface with realistic water physics while the zoom out is already underway. Water streams down her face and hair in wide sheets suspended in slow motion, while droplets explode around her and remain briefly suspended in the air, until her head stabilizes above the waterline, wearing bright blue swimming goggles. Her emergence and the zoom out take place in one continuous motion, without interruption, without pause, never in two distinct stages. Once out of the water, she adopts a perfectly calm, impassive, and totally detached expression. Her gaze remains fixed behind her goggles, never reacting to the chaos surrounding her. She blinks naturally, makes subtle head movements, and breathes normally, appearing fully alive, never frozen or rigid. The camera never stops and there are no cuts: a single fluid and uninterrupted zoom out, pulling back while gradually rising. Her face naturally becomes smaller as the spectacular scene unfolds around her. As the field widens, people cross the scene dramatically right in front of her. A man bursts into the frame, throwing up a huge arcing wall of water. Another person dives in front of the lens, sending a spray of splashes toward the camera. Others struggle through the raging waters between her and the lens, while hands and bodies continuously churn the water. Huge splashes explode in all directions, sheets of water curve and hang in slow motion, foam and spray fly everywhere. The final reveal shows that the young girl is floating peacefully exactly in the center of a flooded office breakroom, lit by fluorescent neon lights, in the heart of totally epic chaos. Churning green-gray water, knee or waist-deep, surges violently through the entire room. Dozens of office workers, soaked in their professional attire, panic around her with natural and spectacular movements: some climb onto vending machines or cabinets, others take refuge near ceiling tiles, a man in a gray suit wades through the water dragging a chair, while others dive, fall, splash, or help each other up. A computer screen floats adrift, overturned beige chairs and waterlogged sheets of paper are swept away by the current, while water gushes from the wall sink in the form of a huge roaring waterfall along the back wall. Despite all this, she remains the only perfectly still, calm, and untouched point in the center of this frantic commotion. The zoom out ends on a perfectly balanced medium-wide shot, where the young girl remains clearly visible and well-highlighted in the center of the image. She maintains a normal human size: close enough that her calm face remains perfectly legible. She should not appear tiny, lost in the distance, or drowned in the scene. She remains the obvious focal point throughout the video, the true eye of the storm. All movements must be natural and physically believable: realistic water dynamics, authentic human movements, true inertia, and natural weight. Nothing should appear rigid, floating, or robotic. On the contrary, everything must be energetic, powerful, and spectacular. The floodwater swirls, surges, and explodes in sprays of splashes. The waves hit and reflect the harsh neon light. Panicked people struggle, dive, climb, and move with realistic force. Hands emerge from the surface, debris is carried away, the waterfall from the sink roars continuously, while the neons reflect off thousands of suspended droplets. All faces remain anatomically correct, stable, and realistic at all times. Human proportions are natural, features are sharp, and expressions of fear or panic are believable and perfectly legible. No face melts, distorts, or stretches. No eyes, mouth, or other facial features show any anomaly or distortion. No strange morphing effects should appear when the characters move. The color palette remains deliberately cold and institutional: seafoam green walls, cream tones, desaturated blue-green, aggressive white fluorescent light, and highly reflective green-gray water. A thick, pronounced 35mm analog film grain is present on every frame from start to finish, uniform and alive, running through both highlights and shadows, like a real scanned film. The image should never look clean, smooth, or digital. The rendering is in highly detailed 4K, revealing every splash, every drop, and every ripple. Lighting comes solely from the ceiling neon lights. At the center of this epic panic reigns a totally absurd calm. The whole thing is filmed in a single continuous cinematic zoom out, from the agitated surface of the water to a wide shot revealing the full extent of the chaos, with fluid camera movement, spectacular slow-motion water, a photorealistic rendering, and an extremely high level of detail.
A high-quality 2D anime animation prompt for a comedic 'anger meter' gag in a Japanese classroom setting.
📝 Prompt
[Video Style]
15 seconds. Japanese full-color anime. High-density 2D animation on a 500-million-yen budget scale. Meticulous background art, smooth in-betweens, and movie-quality post-processing. Develop attractively by varying composition, camera angles, screen size, and character distance to avoid repetitive visuals. No subtitles, no watermark, no BGM. Environment sounds included.
[Visual Composition] An 'Anger' meter appears above the main character's head, and the needle rises due to the person in front of them. The needle goes past the limit, making a full circle, and the meter explodes with sparks. The character remains surprisingly quiet, creating a comedic gap. All text on the meter is correctly written in Japanese.
[Highlight (Must be included in Shots 5–7)] The exploded needle sticks into the chalkboard, pointing exactly to the total stroke count of the kanji '怒' (anger), transitioning into a lesson.
Shot 1 (Meter Hook): After-school classroom. An 'Anger' meter floats above the protagonist's head, and the needle starts to rise slowly. Their eyebrow twitches.
Shot 2 (Cause): Every time the person in front speaks or acts, the needle jumps up. The protagonist's smile begins to twitch.
Shot 3 (Warning): The meter flashes a red light and emits a small warning beep. People nearby start to notice. The protagonist desperately tries to maintain a smile.
Shot 4 (Patience): The protagonist remains smiling. However, the needle is trembling just one step away from the limit. Sweat on the temple; only the eyes are not smiling.
Shot 5 (Breakthrough): The needle exceeds the limit and makes a full circle. Cracks appear in the meter's glass. The protagonist's smile completely freezes.
Shot 6 (Explosion): The meter explodes with sparks. Components flutter like confetti. The protagonist has a blank, dazed expression.
Shot 7 (Restart): A brand new meter pops back up over their head. The protagonist says blankly, 'I was told it was unmeasurable.'
A highly technical 3D anime video prompt for a wire-action combat sequence in a futuristic urban intersection, featuring detailed character consistency and movement physics.
📝 Prompt
[Role of Reference Images]
Maintain a single identity based on the character in the reference images throughout. References are for face, contour, age, eyes, hair, costume, and atmosphere only. Do not recreate the background or pose of the reference image. Start with a new urban fantasy action scene.
[Character Locking]
One person throughout. No changes in face, hair, or costume. Only expressions and actions change. One weapon only. Include a retractable wire mechanism in both sleeves. Use two wires for the initial launch, then only one for upward movement.
[Visual Style]
High-quality 3D cell-look animation. Cinematic high-density key animation, delicate acting, and transparency in lighting. Convert the reference art style into a 3D animated look.
[Setting Adaption]
Fixed at a high-density urban fantasy intersection at night. The environment adjusts to the character's style (e.g., Japanese, Gothic, Mechanical). The enemy is a large black humanoid combat mech.
[Action and Camera]
The protagonist crouches on a wall, shoots two wires to form a V-shape, and launches like an arrow. Fast side-tracking camera follows the horizontal flight. Cuts through the mech's knee joint with a hit-stop effect, then shoots a new wire to swing upward. [Incomplete]
A realistic smartphone-style video prompt of a woman accidentally slipping and falling in a European square, resulting in a lighthearted comedic moment.
📝 Prompt
Create an ultra realistic 8 second continuous smartphone video in 16:9 landscape format.
A lively European pedestrian square on a bright afternoon after light rain, with wet dark-gray stone pavement reflecting the sky, elegant historic white buildings, outdoor cafés, trees, and pedestrians naturally moving in the background. The camera is positioned beneath a large stone archway at eye level, using a mostly steady handheld wide shot with subtle natural movement.
0.0–2.2 seconds: On the far left, a young man wearing a beige jacket, black pants, and black and white sneakers casually leans against a stone column while looking at his phone. A bright neon green soccer ball rests beside his shoe. From the center background, a stylish blonde woman wearing sunglasses, a light cream floral summer mini dress, white sneakers, and a small white shoulder bag walks confidently toward the camera.
2.2–4.3 seconds: As she reaches the foreground near the soccer ball, her sneaker suddenly loses traction on the damp pavement. Her foot slides forward unexpectedly. She throws both arms outward, twists her body, and desperately tries to regain balance. Her long blonde hair swings naturally and her small bag slips from her shoulder. The soccer ball remains beside the man and barely moves.
4.3–5.8 seconds: She loses balance completely and falls onto her hip and backside in a believable, harmless comedic fall, extending one leg forward while catching herself with one hand. Use accurate body weight, realistic gravity, natural clothing movement, subtle motion blur, and physically correct contact with the pavement. No painful impact and no visible injury.
5.8–8.0 seconds: She sits upright on the pavement, initially shocked and embarrassed, then begins laughing at herself. The man immediately puts away his phone, steps away from the column, bends toward her, and reaches out his hand to help her stand. Nearby pedestrians briefly glance toward them. End as she smiles and reaches for his hand.
Photorealistic real life footage, authentic facial reactions, realistic human anatomy, natural skin texture, detailed fabric physics, genuine street ambience, light footsteps, a soft shoe scrape sound, a small impact sound, distant crowd chatter, and spontaneous laughter. Single uninterrupted take, no cuts, no slow motion, no dramatic cinematic effects, no staged acting, no subtitles, no logos, no watermark.
A cinematic multi-shot sequence using reference images to maintain consistency of a Kazakh nomadic camp, featuring realistic nature motion and handheld camera work.
📝 Prompt
Style, palette, texture and mood from <<<image_1>>>. Location from <<<image_1>>> — same yurts, mountains, meadow, river. 2D animation in the style of <<<image_1>>>.
MOTION RULE: atmospheric elements (clouds, mist, cloud-shadows, smoke, river, grass) drift SMOOTHLY; animals move with natural animated life; mountains, yurts and solid ground stay completely still.
CAMERA: handheld from the hand — slow calm breathing sway, faint organic drift, tiny micro-corrections. Alive and observed, unhurried. NOT jittery, never gimbal-smooth, never tripod-locked. Eye level. Natural available light only, wide anamorphic lens kept close to the yurts.
SCENE ALIVE: meadow grass and wildflowers ripple in waves of wind across the valley; herd of horses and sheep by the yurts graze and shift — heads lowering and lifting, tails and manes swishing, ears flicking, some stepping and turning, sheep milling; smoke curls from camp; river flows and glints; low cloud and mist drift across the snow peaks veiling them; large soft cloud-shadows slide slowly over the valley, light shifting shadow-to-glow. Never a frozen postcard.
SCENE: Kazakh nomadic summer camp on a green mountain pasture — felt yurts left, herd of horses and sheep beside them, flowering meadow, pale river winding down the right, vast snow-capped mountains rising in the distance. Soft directional daylight, warm on peaks, cool valley shadow.
SHOT 1 — WIDE, handheld. Thirds, not centered: yurts on lower-left power point close to camera; meadow sweeps right to the river in the right third; snow mountains fill the upper half; low horizon, camp small against colossal peaks.
HARD CUT to SHOT 2 — MEDIUM WIDE, handheld, closer on yurts and herd. Largest yurt on the left third, dark doorway the focal point; horses and sheep strung lower-center to right; slice of distant mountain upper-right.
HARD CUT to SHOT 3 — VERY WIDE EXTREME LONG SHOT, handheld. Camp tiny in the lower-left corner; enormous snow mountains fill the upper two-thirds; river a thin thread down the right; horizon very low, settlement minuscule at the foot of the range. Big-versus-small at its extreme.
AUDIO (all shots): gentle mountain wind through grass, calls of the herd, soft bleating, thin trickle of the river, wide calm hush. No music, no dialogue, no subtitles.
~15s, three distinct shots with hard cuts, cinematic handheld landscape film, composition by rule of thirds throughout.
A complex action prompt involving a young adventurer encountering a giant spider in a dense jungle, featuring detailed blocking and multi-shot timing.
📝 Prompt
SCENE CONTEXT\nA boy hangs upside down by both ankles from a thick green jungle liana, eyes open, staring at a hairy spider hanging centimeters from his face. He screams, knocks the spider straight down to the ground with his left palm, then draws a machete and cuts himself free, dropping a short distance onto his back.\n\nACTIVE REFERENCES\n<<<29eea5d1-f12e-4b02-9913-44ee8009d290>>>: teenage boy, adventurer, bare-headed, disheveled hair, small backpack on his shoulders, compass pendant on a cord around his neck, a sheath fixed on the FRONT of his belt. 100% matches the reference. Voice: a raw panicked male scream.\n<<<77add297-8f10-438e-b207-c29d11a6ef91>>>: the boy's machete, carried in the sheath on the front of his belt. 100% matches the reference.\n<<<025fc600-2e47-4d28-8324-9721baa3f065>>>: hairy spider, 10–12 centimeters across, weighing 50–70 grams, clearly smaller than the boy's head. 100% matches the reference.\n<<<d459ca81-643a-40b1-bcb3-dc2f4c860210>>>: dense green daytime jungle. 100% matches the reference.\n\nLOCATION MAP\nLocation <<<d459ca81-643a-40b1-bcb3-dc2f4c860210>>>: dense green jungle, daytime. Foreground: thick living lianas and the hanging boy — his ankles bound by a thick GREEN LIANA, a living jungle vine with rough green plant bark and small leaves along its length, anchored 2 meters up; his inverted head hangs close above the jungle floor. Midground: massive tree trunks, hanging vines, low bushes at ground level frame-left, shafts of sunlight through the canopy. Background: deep layered jungle fading into haze at 30 meters. The jungle floor beneath him is soft leaf litter. Sunlight comes from high above through the leaves, soft and diffused. Camera positions vary per shot, always on the shadow side.\n\nFIRST FRAME / BLOCKING\nFirst frame: close-up, inverted — <<<025fc600-2e47-4d28-8324-9721baa3f065>>> hangs on a silk thread at the left edge of frame in sharp focus, and behind it, soft and slightly blurred, the upside-down face of <<<29eea5d1-f12e-4b02-9913-44ee8009d290>>> with eyes WIDE OPEN, locked on the spider. His hair hangs toward the bottom of the frame, confirming he is inverted. His arms are straightened and hang straight toward the ground, elbows unbent — hands and wrists stay below the bottom frame edge.\n\nFORMAT MODE\nTimed multishot, cuts only at the specified points, the camera does not cut on its own.\n0.0s to 4.0s — SHOT 1, CU 29°, inverted framing: <<<025fc600-2e47-4d28-8324-9721baa3f065>>> hangs on its silk thread in sharp focus
-Click%20to%20View-lightgrey){kind=icon}
-Click%20to%20View-lightgrey){kind=icon}
