by ByteDance

Seedance 2.0 Prompts

ByteDance's multi-shot video model — write a sequence of shots, and characters speak with lip-sync and spatial audio built in.

video

Create a 15-second high-fashion football shoe advertisement using the uploaded reference images for the gold metallic football cleats, white knee-high socks, and vintage feminine football styling. Keep the footwear design, colors, textures, and proportions consistent throughout the entire video. Environment: An enormous open outdoor football field, covered in lush natural green grass, with a completely open horizon and a beautiful dreamy pastel blue-and-pink sky. The field should feel spacious and untouched. No stadium, no spectators, no buildings, no bleachers, no indoor environment, no close fences. 0–3 sec: Wide cinematic shot of a young adult female footballer standing alone in the middle of the vast open field. She wears the same elegant vintage-inspired outfit from the reference images with white knee-high socks and the gold metallic football cleats. She gently places one foot on a football. Camera slowly moves toward her while sunlight reflects beautifully off the cleats. 3–6 sec: Cut to dramatic close-up shots of the gold cleats. Her foot steps firmly onto the grass, the studs press naturally into the turf, and she tightens the laces. Macro camera movement reveals the metallic texture, stitching, sole, and studs. Make the shoes the visual hero. 6–10 sec: She starts playing football across the completely open field, dribbling the ball quickly and confidently. Use a low-angle tracking camera focused on her feet and cleats as she changes direction, accelerates, and controls the ball. Her flowing outfit moves naturally with her movement. 10–13 sec: She takes a powerful run-up and strikes the football with the gold cleat. Capture the kick in cinematic slow motion, showing the shoe making contact with the ball, grass particles flying naturally, and the ball launching across the open field. 13–15 sec: Premium hero shot. The football rolls to a stop beside her gold cleats. She stands confidently in the background on the vast green field as warm sunlight catches the metallic shoes. Camera slowly pushes toward the cleats and ends on a sharp product-focused close-up. Visual style: luxury sports fashion campaign, dreamy editorial photography, cinematic natural lighting, realistic football movement, realistic grass physics, elegant feminine styling, dynamic camera movement, macro shoe details, shallow depth of field, premium commercial quality, photorealistic, subtle film texture. Important: Keep the gold football cleats identical throughout the video. No changing shoe design, no distorted feet, no extra limbs, no warped football, no artificial CGI appearance. The entire video takes place outdoors on one vast open football field.

Create a 15-second fast-paced, smooth luxury fashion editorial video using the character sheet as the visual reference. Keep the same woman, face, brunette hair, fur jacket, red crop top, distressed denim, chains, makeup, and overall styling consistent throughout. Preserve her playful, confident, slightly mischievous personality. The video should feel like a fashion mugshot mixed with a playful “wanted for beauty” campaign. 0–3s — THE MUGSHOT Start with a sharp full-body mugshot composition in front of the height chart. She looks directly into camera. Quick smooth push-in → she gives a playful wink → instantly cuts to her holding the “WANTED FOR BEAUTY” board. She slowly tilts the board toward camera with attitude. 3–6s — BEAUTY DETAILS Move into a rapid but smooth beauty montage: wink → glossy lips → red nails → lollipop → fur jacket texture → chain details → sunglasses → playful smile. Use smooth snap zooms and seamless whip transitions. Each shot should be very short, around 0.3–0.6 seconds, but transitions should remain fluid and polished. 6–9s — PLAYFUL TROUBLEMAKER Return to the full mugshot. She casually leans toward one side while maintaining her confident stance. Quick smooth camera orbit around her → she puts on sunglasses → looks over the sunglasses directly at camera → gives a mischievous smile. Add subtle camera flash bursts like paparazzi photographers are surrounding her. 9–12s — FAST FASHION MONTAGE Rapidly showcase: fur coat → red top → belt and chains → distressed jeans → lollipop → lips → eyes → sunglasses. Use smooth continuous camera movement between each detail, with quick editorial cuts. Newspaper pages briefly fly across the frame, creating transitions. 12–15s — FINAL SHOT Return to the mugshot setup. She holds the board toward camera. The board now reads: “WANTED FOR BEING TOO BEAUTIFUL” She raises one eyebrow and smiles. Camera rapidly pushes toward her face. A newspaper suddenly sweeps across the lens. CUT TO BLACK. Motion & Editing FAST-PACED but SMOOTH. Use: 0.3–0.6 second cuts smooth snap zooms seamless whip transitions controlled camera orbit quick push-ins and pullbacks subtle speed ramps fashion-editorial motion blur paparazzi flash effects flowing newspaper transitions beat-synced editing Do NOT make it slow, dreamy, jittery, or chaotic. The camera should always feel controlled and fluid, while the editing stays fast. Overall feeling: playful troublemaker + luxury fashion campaign + cinematic mugshot + glossy magazine editorial.

Create a 30-second ultra-realistic fictional home-video featuring an adult Korean man in his late 20s spending a cheerful afternoon in an older Seoul residential neighborhood. CHARACTER: A fictional adult Korean man in his late 20s with medium-to-long dark hair tied in a casual low ponytail, natural masculine facial features, realistic skin texture and a friendly expressive personality. Keep his appearance consistent throughout the entire video. OUTFIT: He wears a bold, fashionable summer outfit consisting of a vivid red fitted T-shirt, high-waisted relaxed-fit white denim shorts, clean casual sneakers, a simple bracelet, small understated earrings and a small shoulder bag. The outfit is youthful, colorful and stylish, appropriate for a warm summer day. SCENE 1 — LEAVING HOME He steps out of an older Seoul apartment building carrying a small reusable shopping bag. He closes the gate behind him, notices the camera and gives a spontaneous smile before walking down the quiet residential lane. SCENE 2 — LOCAL BAKERY He enters a tiny neighborhood bakery, looks through the pastry display and chooses a small baked treat. He pays the shopkeeper with coins, thanks them and walks back outside. SCENE 3 — FRIENDLY ENCOUNTER While walking through the narrow lane, he suddenly sees his adult male friend approaching from the opposite direction. They smile, greet each other warmly and share a quick friendly hug. They chat and laugh for a moment before waving goodbye and continuing in opposite directions. SCENE 4 — FRUIT STAND He stops at a small roadside fruit stall and chooses a peach. He pays the vendor, places it inside his shopping bag and continues walking. SCENE 5 — EVERYDAY NEIGHBORHOOD MOMENT He walks beneath trees while eating his pastry. A bicycle passes nearby, and he naturally steps aside. He looks around at the quiet houses and smiles as the camera follows him from a short distance. SCENE 6 — ENDING He reaches the end of the lane, turns toward the camera and gives a cheerful wave. He smiles naturally and says, “Bye bye!” He then turns around and walks away down the residential street while carrying his bag and peach. The camera stays behind him until he disappears around the corner. CAMERA STYLE: Authentic early-2000s consumer MiniDV home-video footage. Handheld camera shake, imperfect framing, autofocus hunting, automatic exposure fluctuations, soft digital detail, mild digital noise, slight compression artifacts, realistic motion blur and occasional awkward zooms. It should feel like a genuine recording made by a friend or family member, not a professional production. AUDIO: Only natural neighborhood sounds: footsteps, bicycles, distant traffic, bakery activity, casual conversations, birds, children playing and light wind. No music, no narration, no subtitles, no text overlays, no beauty filter, no sexualized posing, no CGI appearance, no cinematic lighting and no polished commercial cinematography.

part A: [Overall Setup] 9:16 vertical screen, 15-second continuous long take. Rural southern China, a sweltering summer afternoon. A rural barbershop by the village road is moving its barbering platform, which had been set up in the sun at the entrance, into the shade of a tree. An old yellow forklift slowly carries the entire barbering setup. The scene is absurd, but the villagers initially act as if it is completely normal. [Environment and Atmosphere] Reference scene reference image ChatGPT Image September 30, 2026 23_24_14 Narrow concrete village road, with a patch of mixed cement and red soil on one side, and two- to three-story self-built houses covered in white tiles on the other. The barbershop wall has faded characters reading “Convenient Barbering,” the rolling shutter door is half open, towels hang by the door, and an electric tricycle is parked under the eaves. On the right side of the frame, an old banyan tree extends low branches, with mottled tree shadows on the ground. In the background are vegetable plots, a low brick wall, utility poles, and crisscrossing wires. At the base of the wall are a broom, plastic buckets, and several empty flower pots. The site shows real signs of use, not deliberately made into a ruined, desolate place. Leaves sway gently, cicadas chirp continuously. Occasionally, an electric bike, motorcycle, or agricultural tricycle passes along the village road, briefly blocking the view. [Shooting Texture] The videographer is sitting in a family car parked across the village road, holding a phone and filming through the front windshield. The dashboard and the lower edge of the windshield remain at the bottom of the frame throughout. The videographer only turns the phone slightly, using small, clumsy digital zooms, without completely cropping out the edges inside the car. Ordinary phone video quality, slight hand shake, compression noise, softness from zooming, delayed focus; exposure fluctuates slightly when panning from sunlight into tree shade. It looks like something a villager casually filmed, with no cinematic color grading, no slow motion, no editing. [Character Lock] The female lead is a preset adult East Asian woman , with facial features, hairstyle, and body shape strictly following the character reference image. Wearing , black pointed high heels, and a thin necklace. She is the barber, standing behind and to the right of the customer, skilled in her movements, with a serious expression, not hinting at the punchline in advance. The customer is a Chinese rural man about 50 years old, stocky, with sun-darkened skin and natural wrinkles on his face, draped in a faded blue-and-white floral barber cape, wearing dark sandals. He wears a naturally fitting short black-brown wig; at the beginning, only ordinary short hair is shown, and his bald head must not be revealed in advance. The driver is a Chinese man about 45 years old, with short hair, wearing an old gray short-sleeved shirt, dark work pants, and cloth shoes. Three middle-aged and elderly villagers sit on plastic stools waiting by the tree: one older man in a white tank top holding a palm-leaf fan; one older woman in a floral short-sleeved shirt; and another older man in a dark short-sleeved shirt holding a transparent lidded teacup. The number of people and their clothing are fixed. [Space and Props] The forklift cab is on the left side of the frame, the mast faces right, and two forks support a reinforced wooden platform about three meters wide and two meters deep. The platform is about one meter above the ground, fixedly connected to the fork carriage, with low guardrails on the rear edge and both sides. The barber chair base is fixed at the center of the platform. The narrow tool rack to the female lead’s right is fixed in place, holding electric clippers, towels, and tool slots. The wooden-framed mirror behind is firmly installed. The female lead holds scissors in her right hand and a comb in her left. On the low banyan branch in the upper right, there is a clearly visible small fork. At the position the forklift’s left rear wheel is about to pass, there is a shallow pit, present from the beginning. The queued villagers are outside the path of movement. [0–4 seconds] The phone slowly pushes in from a wide shot. The female lead uses the comb to lift a small amount of hair at the customer’s temple and cuts the ends. The customer sits relaxed, both feet on the footrest. The older man in the white tank top slowly waves his palm-leaf fan, while the woman in floral clothes and the person beside her chat in low voices. An electric bike passes from right to left, briefly blocking the lower part of the platform. [4–7 seconds] The driver looks back at the tree shade, raises a hand toward the female lead in signal, then slowly reverses. The female lead stops cutting, moves the scissors away from the customer’s head, and waits for the platform to move. The forklift and platform as a whole shift toward the left side of the frame, and the banyan tree’s shadow sweeps across her shoulder and the customer’s cape. The phone pulls back slightly, revealing the wheels and the shallow pit. [7–10 seconds] The forklift’s left rear wheel presses into the shallow pit and climbs out again, and the whole vehicle jolts briefly once. The female lead immediately closes the scissors, raises her right hand away from the customer, and with her left hand along with the comb braces the back of the chair. The customer grips the armrests, toes curling in his sandals. The electric clippers slide a few centimeters on the tool rack and stop after hitting the retaining edge. The older man with the teacup stops drinking and looks up. [10–13 seconds] The driver brakes to a stop, and the platform’s swaying subsides. The phone clumsily pushes in, focus briefly blurs, then recovers. The female lead first looks at the customer, then confirms she is standing steadily; the customer frowns and glares at the driver. The older man in the white tank top laughs once, his palm-leaf fan stopping at his chest. [13–15 seconds] A gust of wind blows from the left side of the frame toward the upper right. The edge of the cape puffs up first, the female lead’s hair strands drift to the right along with it, and the banyan branches and leaves sway. The front edge of the wig on the customer’s head is gently lifted, and the whole piece of hair begins to loosen. The female lead’s gaze shifts to the top of his head, the comb stops midair, and her lips part slightly. End frame: the forklift has stopped, the platform is steady; the female lead’s right-hand scissors are closed, her left-hand comb hovers; the front edge of the wig has just been lifted and has not yet left the top of his head. [On-Site Sound] Cicadas, leaf rustling, forklift diesel idling, reversing alert, tires rolling over soil, slight platform creaks, and passing electric bike sounds. The villagers speak Mandarin with a southern rural accent, the content indistinct, not carrying plot explanation. No music, narration, subtitles, or comedic sound effects. [Quality and Negative Constraints] First the wheel presses into the pit, then the platform jolts, then the characters react. The forks, platform, chair, and tool rack connections must be realistic. Wind direction stays consistent, and the wig must not fly off early in this segment. Forbidden: European and American rural architecture, American road signs, Spanish moss, and Western characters; forbidden: face swapping, outfit changes, extra or missing limbs, scissors touching skin, platform floating, characters falling, forklift overturning, wig duplication, extra people in the mirror. Forbidden: cuts, aerial shots, and camera passing out through the windshield. part B: [Continuation Starting Point] Use the end frame of the first segment September 30(1) , continuing the same in-car phone footage, without repeating the jolt. The old yellow forklift has stopped behind the shallow pit, and the reinforced platform is about one meter above the ground. The female lead is behind and to the right of the barber chair, holding closed scissors in her right hand away from the customer, and a comb hovering in her left hand. The customer sits in the chair, both hands gripping the armrests, the front edge of the short black-brown wig just lifted by the wind. The wind continues blowing from the left side of the frame toward the upper right, and the position of the low banyan branch and the small fork remains unchanged. [Environment and Shooting Texture] 9:16 vertical screen, 15-second continuous long take. Rural southern China on a summer afternoon. The concrete village road, white-tiled self-built houses, half-open rolling shutter door, old characters reading “Convenient Barbering,” vegetable plots, low brick wall, utility poles, and parked electric tricycle all remain consistent. The videographer is still sitting in the family car opposite, filming through the front windshield, with the dashboard and lower edge of the glass always visible. Small digital zoom, following half a beat late, brief softness, ordinary compression noise. The light is sweltering and flat, cicadas continue, no cinematic color grading, no cuts, no slow motion. [Character and Prop Lock] The female lead continues to use the preset adult East Asian character , with , black pointed high heels, thin necklace, and long hair unchanged. Her expression shifts from surprise to suppressed laughter, then tries as much as possible to return to seriousness. The same Chinese rural male customer about 50 years old, sun-darkened and stocky, blue-and-white floral cape, dark sandals; the same driver in a gray short-sleeved shirt; the same three queued villagers: the palm-leaf fan older man, the floral-clothed older woman, and the teacup older man. There is only one wig, short black-brown, with a soft mesh base inside. After detaching, the customer reveals a smooth bald head, with a small amount of sparse short hair allowed on the sides. The image in the mirror must change in sync. The positions of the platform, fixed barber chair, tool rack, mirror, two forks, and low guardrails remain continuous. [0–3 seconds] The wind lifts the front edge of the wig, and the entire wig detaches from the customer’s head, revealing the soft inner mesh, tumbling once toward the upper right. The phone follows upward half a beat late, still keeping the lower edge of the car interior. The wig flies out about one meter along a clearly visible trajectory, its inner mesh catches on the small fork of the low banyan branch, sways twice, and hangs there. The customer first shrinks his neck, then looks up; the female lead’s comb is still hovering midair, her gaze following the wig. [3–6 seconds] The phone pulls back slightly, bringing the wig and the people on the platform into frame together. The female lead, the customer, and the three villagers look up one after another at the same branch. The customer raises a hand and touches his bald head, his palm stops, then he looks at the mirror. The mirror synchronously shows his bare scalp. The female lead glances at the branch, then at the top of his head, her mouth tightening. The palm-leaf fan older man covers his mouth with the fan, his shoulders beginning to shake; the floral-clothed older woman turns her face away and laughs, and the teacup older man lowers his cup. [6–9 seconds] The female lead first puts the closed scissors into the tool slot, then puts down the comb; both tools have complete placement actions. Then she lightly presses the customer’s shoulder, keeping him in the chair. The customer holds the armrest with one hand and points at the wig with the other, turning his head to look at the driver. The driver follows the pointing finger, looks up, seriously studies the height of the branch, nods slightly, lowers his head, and grips the lift control lever. [9–12 seconds] The driver operates only the lift, and the forklift tires remain stationary. Hydraulic sound rises, and the forks steadily raise the entire platform about thirty centimeters. The female lead braces the chair back with one hand and holds the side guardrail with the other. The customer stays seated, extends his right arm upward, fingers spread, gradually approaching the wig. Below, the three villagers look up and wait, and the palm-leaf fan older man simply puts the fan on his lap. The phone adjusts slightly to keep the relationship among the branch, the customer’s fingers, and the rising platform readable. [12–15 seconds] The customer’s fingertip is about to touch the wig when a gust of wind makes the branch tip swing outward, and the wig moves more than ten centimeters farther away. He stretches his arm fully and is still just short, able only to freeze. The female lead looks at his fingertip, then at the wig, presses her lips together and turns her face away, shoulders giving a slight shake. The videographer laughs out loud inside the car, and the phone shakes along with it. An agricultural tricycle loaded with empty vegetable baskets passes from left to right, briefly blocking the lower part of the platform; above, one can still see the customer reaching for the wig, the female lead bracing the chair back, and the banyan branch swaying gently. The video ends naturally. [On-Site Sound] Cicadas, leaf friction, forklift idling, hydraulic lift sounds, and village road vehicle sounds. Villager laughter goes from light to obvious, and the videographer’s laughter is closer to the phone and clearer. The wig has no exaggerated flying sound effect, and the reversal has no music, narration, or subtitles. [Quality and Negative Constraints] The wig must detach from the top of the head, pass through the air, touch the branch, and then be caught by the inner mesh. It must not teleport, duplicate, fly on its own, or turn into an animal. The top of the customer’s head and the mirror reflection must remain consistent. The characters react only after seeing the wig fly away; only after the tools are put down may the female lead brace the chair back with empty hands. The platform, chair, and all fixed objects rise together, and the forklift must not suddenly drive while raising. Forbidden: European and American scenes and characters, face swapping, outfit changes, hands clipping through objects, extra arms, the wig automatically turning back, the customer standing on the chair, characters falling, machinery overturning, or exploding out of nowhere. Maintain a rural everyday feel and restrained awkward comedy performance throughout.

Create a cinematic high-quality 3D animated short film set in a beautiful sunlit forest meadow, featuring two adorable anthropomorphic animal characters: a small fluffy brown beaver-like creature with big expressive eyes, a tiny tuft of hair, soft rounded body, and a dark furry gorilla-like companion. Scene 1 — Peaceful Beginning: Wide cinematic shot of the two cute animals sitting together on lush green grass in a bright forest. The small brown animal happily eats a banana while the dark gorilla-like character watches beside him. Warm golden sunlight filters through the trees, soft depth of field, floating dust particles, beautiful colorful environment. Scene 2 — Funny Reaction: Cut to an extreme close-up of the brown character's face. His expression suddenly changes from happy to suspicious and annoyed. Use exaggerated cartoon facial animation, expressive eyes, subtle head movement, detailed soft fur, cinematic shallow depth of field. Scene 3 — Emotional Gorilla: Extreme close-up of the gorilla-like character with enormous expressive eyes. Tears begin streaming down his face in an exaggerated but adorable emotional reaction. His eyes reflect the surrounding forest and sunlight. Make the moment funny, cute, and emotionally expressive. Scene 4 — Argument: Medium-wide shot of both characters sitting in the meadow. The brown animal becomes angry, his cheeks turning red, while the gorilla reacts dramatically. Exaggerated facial expressions and body language, playful comedy, smooth character animation. Scene 5 — Wooden Bat: Close-up of a large wooden stick/bat entering the frame. The brown character grabs it with determination while the gorilla looks shocked. Use a comedic action-movie style camera push-in and dramatic timing. Scene 6 — Chase/Fight: Dynamic wide shot as the two characters run and playfully fight across the grassy meadow. The brown animal swings the wooden stick while the gorilla dodges and reacts dramatically. Fast but smooth camera movement, comedic choreography, expressive faces, flying grass particles, cinematic motion blur. Scene 7 — Calm After Chaos: Close-up of the brown character looking directly toward the camera with a cute, slightly mischievous expression. His expression gradually changes into a happy smile. Warm sunlight creates a beautiful glowing rim light around his fur. Scene 8 — Fruit Discovery: Wide shot near a large tree. The small animal discovers a colorful pile of fresh fruit and happily sits down beside it. Apples, peaches, grapes and other colorful fruits fill the foreground. Soft sunlight and dreamy forest background. Scene 9 — Hero Fruit Shot: Cinematic close-up of the adorable brown character sitting among the colorful fruit, smiling directly at the camera. Bright blue sky, lush green trees, vibrant fruit colors, soft golden sunlight, highly detailed realistic fur, polished animated-film quality. Scene 10 — Grand Finale: Epic wide cinematic shot of a large group of cute forest animals gathered together around a huge colorful fruit display. Rabbits, small mammals, bears and other adorable animals celebrate together in a joyful festival atmosphere. Colorful fireworks explode in the sky above the forest. Include a festive vertical red banner with Chinese-style celebratory writing in the center. Everyone looks happy and excited. Visual Style: Premium cinematic 3D animation, adorable character design, realistic soft fur, expressive oversized eyes, Pixar-quality feel, vibrant colors, warm natural sunlight, global illumination, realistic shadows, shallow depth of field, detailed environments, smooth facial animation, exaggerated comedic expressions, polished movie-quality rendering. Camera: Use cinematic establishing shots, extreme close-ups, medium shots, tracking shots, slow push-ins, dynamic action camera movement and smooth transitions. Maintain consistent character appearance throughout every scene.

Create a cute, funny, high-quality 3D animated cinematic scene in a cozy modern bedroom during warm morning daylight. A small child is dressed in an oversized fluffy white ghost costume, with only the child’s big expressive eyes, small hands, and bare feet visible. The adorable ghost walks toward a bed where a surprised mother and father are sitting under a beige blanket. Start with a close-up of the cute little ghost standing in the warmly lit bedroom, then show the child slowly walking toward the bed. The parents notice the ghost and react with exaggerated shock and fear, pulling the blanket up while staring at the child with wide eyes and funny facial expressions. The ghost innocently approaches the camera and raises its tiny hands. Use Pixar-quality 3D animation, highly expressive faces, soft realistic fur and fabric textures, warm natural sunlight coming through the window, cozy bedroom environment, cinematic depth of field, smooth character animation, realistic cloth movement, gentle camera tracking, comedic timing, adorable family-friendly atmosphere, detailed lighting, polished animated-movie quality, vertical 9:16 format, 4K.

Created a 15-second cinematic fantasy battle scene in a ruined ancient city at sunset, with dramatic golden skies, burning buildings, smoke, and destroyed stone structures. A powerful blue-clad female warrior with dark hair faces a fierce female fire warrior with pale pink hair and small red horns. The blue warrior controls massive waves of glowing water while the fire warrior creates intense orange flames around her hands and body. Show them charging toward each other with fast, dynamic combat movements, magical energy trails, flying sparks, smoke, and debris. Build the action from a close-up confrontation into a wide cinematic shot of both elemental powers colliding in the center of the battlefield. End with an enormous blue water wave crashing against a giant fire explosion, creating steam, glowing particles, and a spectacular energy shockwave. Use realistic cinematic lighting, detailed characters, smooth camera movement, epic fantasy atmosphere, high-quality VFX, dramatic depth of field, and a powerful movie-trailer style ending.

Created a video, a cinematic cartoon-style kitchen story featuring a curly red-haired woman and a cute fluffy gray cat in a warm, cozy home kitchen. The video begins with the woman entering the kitchen while the curious gray cat stays nearby, creating a playful and innocent atmosphere. The camera then moves closer to the cat as it reaches toward a button on the kitchen counter with its tiny paw. Suddenly, a funny kitchen mishap begins, filling the room with clouds of flour and food flying through the air. The woman reacts with surprise as the cat remains at the center of the chaos, making the scene humorous and energetic. Show dynamic camera movements, expressive facial reactions, detailed character animation, and natural body movement throughout the sequence. Gradually reveal the messy kitchen with flour, food, and ingredients scattered across the counters and floor. End with the woman and the cat sitting together in the messy kitchen, looking innocent and confused after the hilarious disaster. Keep the same characters, appearance, hairstyle, clothing, kitchen environment, lighting, and visual style consistent from beginning to end, with polished cinematic cartoon-quality animation.

Create a 15-second photorealistic skincare video featuring a young Korean woman in a bright, elegant white room. Start with an extreme close-up of her natural face as she gently touches her cheek with her fingertip, showing realistic skin texture and soft daylight. Then show a clear skincare bottle placed on a white marble table as her hand slowly reaches toward it. Continue with her applying skincare gently to her face using both hands, keeping her facial features and appearance consistent. Show her closing her eyes peacefully while softly massaging both cheeks with her fingertips. Finish with a wider shot of her wearing a simple white dress standing beside a large window, while the sheer white curtains move naturally in the sunlight. Keep the movements smooth and realistic, with natural hands, realistic skin, soft cinematic lighting, clean luxury atmosphere, gentle camera motion, and no distortions or artificial-looking details.

Overall style: Hollywood blockbuster, ultra cinematic, Three Kingdoms epic realism, hyper-realistic cinematic style, IMAX-level epic battlefield, Ridley Scott–style war scale, Zack Snyder–style slow motion, authentic Three Kingdoms war atmosphere. Cold blue-toned sky, dust and smoke filling the air, cold metallic reflections, sparks flying, ochre-toned battlefield. Hans Zimmer percussion score, volumetric dust, dynamic camera, hyper realistic armor, dramatic sunset battlefield, IMAX scale, 8K, high contrast, motion debris, war atmosphere. [Core aesthetics and environment] Top-tier Hollywood blockbuster action film quality, 60fps high frame rate. A Three Kingdoms battlefield, with soldiers from both sides locked in fierce combat. The camera switches between high-angle overhead shots and low-angle upward shots, emphasizing the epic battlefield imagery and the brutality of war, along with the intensity of a decisive life-or-death battle — like the climactic sequence of a genuine Three Kingdoms war film. Strong visual hook in the first 2 seconds, stable subject, fluid action, cinematic composition, realistic lighting and shadow, epic feel, strong emotion, highly detailed. No subtitles, no dialogue, no narration throughout. 🚫 Negative prompts (avoid cheap-looking results): cartoon, anime, fake armor, floating weapon, bad anatomy, blurry face, cheap CGI, low detail horse, duplicated limbs, weak impact, soft action.

Create a 15-second ultra-realistic early-2000s Sony MiniDV home video. Subject: Young Korean woman, naturally attractive, realistic skin, minimal makeup, long dark hair loosely tied back. Oversized faded lavender T-shirt, loose gray lounge pants, white socks, thin silver necklace. Preserve identical identity, face, hair, proportions and appearance throughout. Location: Small old Seoul apartment balcony on a sunny summer morning—concrete walls, metal railing, clothesline, colorful laundry, plastic basket, potted plants, neighboring buildings and distant rooftops. Bright, slightly hazy sunlight. Style: Authentic personal early-2000s MiniDV footage with gentle handheld sway, imperfect framing, subtle autofocus/exposure adjustments, faded colors, soft contrast, DV compression and mild digital noise. Smooth continuous motion throughout: no stutter, judder, frame skipping, duplicated frames, stop-motion, excessive motion blur, speed changes, low-frame-rate look, stabilization or cinematic movement. 00–03s: She brings the laundry basket onto the balcony, sets it down and clips the first shirt onto the clothesline. 03–06s: She calmly hangs several more clothes while the camera naturally follows her hands. 06–09s: She unfolds and hangs a white bedsheet; it briefly fills the frame before moving gently in the breeze. 09–12s: She steps back and straightens an uneven sleeve. Neighboring apartments and blue summer sky are visible behind her. 12–15s: She sits on a small plastic chair, drinks water and looks toward the rooftops with a tiny relaxed smile. Camera drifts toward the laundry moving in the breeze and cuts. Audio: Natural ambience only—birds, distant traffic, faint apartment voices, fabric rustling, clothespins, basket sounds, AC hum and gentle breeze. No music, narration or added effects. Goal: An ordinary forgotten early-2000s family recording—warm, mundane, intimate and unstaged. Nostalgia comes from everyday Seoul life and authentic MiniDV image quality, not reduced frame rate.

A young Korean girl shopping in a busy Korean fashion market. Keep the SAME Korean girl, SAME face, SAME hairstyle, SAME outfit, SAME body proportions, and SAME black handbag throughout the entire video. Maintain strong character and visual consistency between every shot. Scene 1 — 0–2 sec: The Korean girl walks through a lively Korean market and stops at a clothing stall. She looks through a large rack filled with beautiful dresses. Show colorful Korean signs, crowded shoppers, warm indoor lighting, and a realistic Korean market atmosphere. Use a smooth medium side-tracking shot. Scene 2 — 2–4 sec: She carefully selects a dress from the rack and examines the fabric and details with her hands. Use a cinematic close-up of her hands and the dress, followed by a subtle close-up of her face reacting positively. Scene 3 — 4–6 sec: She holds the selected dress against herself and checks her appearance in a large mirror inside the shop. Show her reflection clearly. Use a smooth medium shot with shallow depth of field and natural realistic movement. Scene 4 — 6–8 sec: She decides to buy the dress. A Korean shop assistant neatly folds the dress and places it into a clean shopping bag. Show a close-up of the packing process, hands, dress, and shopping bag. Scene 5 — 8–10 sec: The girl leaves the clothing stall carrying the shopping bag in one hand and her black handbag on her shoulder. She walks naturally through the busy Korean market. Use a smooth tracking shot from the front/side. Scene 6 — 10–12 sec: She reaches an AUTOMATIC ESCALATOR going DOWN from the market. She steps onto the moving downward escalator and begins descending while holding her shopping bag. Make it clearly an escalator, NOT normal stairs. Use a rear three-quarter tracking shot following her downward. Scene 7 — 12–14 sec: While riding down the escalator, show a cinematic close-up of the girl looking slightly upward and around at the market. Her hair moves naturally with her movement. Keep the escalator clearly visible behind and beside her. Scene 8 — 14–15 sec: Wide rear shot as she reaches the bottom of the downward escalator and walks away into the busy Korean market crowd, still carrying her shopping bag. End with a smooth cinematic fade-out. Visual style: photorealistic, cinematic Korean fashion-market atmosphere, warm soft lighting, realistic skin texture, natural facial expressions, shallow depth of field, subtle film grain, realistic crowd movement, smooth camera motion, premium commercial look, high detail, 4K quality. Important: Keep the same girl's identity and appearance consistent in every shot. The transition from the market to the escalator must feel continuous and realistic. The escalator must be an AUTOMATIC MOVING DOWN ESCALATOR, not stationary stairs.

15-second cinematic sci-fi action sequence, 16:9, ultra-realistic, vibrant stellar colors, IMAX-quality cinematography, realistic motion, no visible face, no text, no dialogue. A spacecraft cruises through a vast solar system. Ahead, the system's sun burns peacefully. Suddenly another sun appears. Not arriving. Appearing. A second star ignites nearby. The entire system reacts instantly. Asteroids change direction. Planetary rings distort. Comets accelerate. The pilot is caught inside the gravitational chaos. Massive rocks collide and explode into debris clouds. The fighter threads through the destruction while both suns illuminate the scene from opposite directions. The sky becomes blindingly bright. The two stars begin pulling everything apart. Cut.

Create a 15-second ultra-realistic personal home-video featuring the woman from the reference image. Keep her exact appearance, facial features, hairstyle, body proportions, and identity consistent throughout the entire video. Setting: A quiet roadside neighborhood at night during summer. Warm streetlights illuminate the pavement, with dark trees, small roadside shops, parked vehicles, and occasional distant headlights. The environment feels ordinary and slightly imperfect. Wardrobe: She wears a simple white casual dress, natural and slightly loose, with realistic fabric movement. Action: She stands or sits casually by the roadside, holding a small everyday snack in her hand. As she eats, a little piece unexpectedly falls onto her hand. She notices it, tries to catch it with her fingers, then looks toward the camera and laughs naturally. She wipes her hand with a napkin, shakes her head and quietly mutters, "This is going terribly." A moment later, another small piece falls onto her hand. She looks directly into the camera with a defeated little smile and says, "I'm still eating it." Visual style: Shot like a random early-2000s family video. Handheld DV camcorder, imperfect framing, tiny focus mistakes, soft digital noise, mild motion blur, slight lens imperfections, uneven exposure from streetlights, realistic low-light grain. No cinematic composition or polished commercial look. Audio: Natural nighttime roadside ambience—distant traffic, passing motorcycles, insects, soft wind, occasional footsteps, snack-wrapper crinkles, and quiet spontaneous laughter. No music, subtitles, or cinematic sound effects. Keep the acting understated, awkward, spontaneous, and genuinely human. The whole clip should feel like an accidentally recorded silly nighttime moment rather than a scripted performance.

STYLE: Ultra-realistic cinematic travel vlog, natural handheld camera, vibrant Japanese market, authentic Japanese street atmosphere, realistic crowd movement, warm daylight, natural facial expressions, smooth motion, 4K quality, 16:9. SCENE 1: Three girls enter a lively traditional Japanese market. Red lanterns, colorful shop signs, food stalls, and crowds surround them. The camera follows them from behind as they walk into the market, looking excited and curious. SCENE 2: The girls explore the market, looking at traditional Japanese shops and signs. One girl points toward something interesting while the others smile and look in the same direction. The camera moves naturally around them. SCENE 3: They stop at a Japanese street-food stall and excitedly choose different snacks. Show close-up shots of colorful food, steam rising from the stall, and their happy reactions. SCENE 4: The girls walk through the busy market while enjoying their drinks and talking together. They laugh naturally as the camera smoothly tracks alongside them, capturing the lively market in the background. SCENE 5: They enter a small souvenir shop and browse cute Japanese souvenirs. One girl picks up an interesting item and shows it to her friends, making everyone smile and laugh. SCENE 6: At the end, the girls leave the market happily and look back at the colorful street. One girl waves toward the market as the camera slowly pulls back into a wide cinematic shot. CAMERA: Smooth handheld travel-vlog movement, wide establishing shots, medium shots, close-ups, natural motion blur, subtle camera shake, realistic autofocus, cinematic tracking shots. MOOD: Happy, adventurous, friendly, youthful, authentic Japan travel experience. NEGATIVE PROMPT: No text overlays, no subtitles, no watermark, no distorted faces, no extra fingers, no unnatural body movements, no duplicated people, no face changes, no cartoon look.

A cinematic dark fantasy epic video in 8K resolution. Extreme macro close-up of a female warrior's eye, iris reflecting a burning molten celestial orb swirling inside dark storm clouds. Low-angle tracking shot as an East Asian female warrior clad in sleek black leather-and-steel armor walks through shallow water carrying an ornate key. She steps onto a circular stone platform engraved with glowing golden runes, surrounded by mist, cascading waterfalls, and ancient temple ruins. Above, a colossal magma-veined celestial sphere looms within a vortex of swirling clouds. She inserts the key into a moss-covered stone altar, triggering a massive circular runic array that launches vertical high-pressure water geysers into the sky. A giant, majestic white serpentine dragon with fiery orange eyes emerges from the mist. The warrior extends her hand as her eyes glow bright golden, establishing a powerful magical bond. The dragon turns upwards, soaring into the sky and unleashing a beam of pure radiant white energy directly into the celestial orb, causing it to shatter into shockwaves of blinding light. Epic cinematic scale, volumetric fog, photorealistic visual effects, Unreal Engine 5 render style, dark gray and golden color grading, hyper-detailed.

15-Second Realistic Dragon Transformation Prompt Create a 15-second ultra-realistic cinematic fantasy sequence featuring an adult woman in her 20s playing with a small toy dragon beside a crystal-clear river deep inside a lush, mysterious forest. Scene & Character: A beautiful adult woman in her 20s, natural appearance, realistic skin texture, long flowing hair, wearing a simple earthy-toned casual outfit. She is sitting on smooth rocks beside a shallow forest river, playfully holding a small, highly detailed toy dragon in her hands. The environment feels completely real and immersive: dense green foliage, moss-covered rocks, soft sunlight filtering through the trees, floating dust particles, realistic water movement and natural atmospheric depth. 0–4 seconds: Begin with a cinematic medium shot of the woman sitting beside the river, smiling naturally as she plays with the tiny dragon. She gently moves the toy through the air as if making it fly. Use subtle handheld camera movement and realistic environmental sounds. Sunlight creates soft highlights across her hair and the water. 4–7 seconds: She slowly lowers the toy dragon into the shallow river and briefly dips it completely underwater. As the toy touches the water, create subtle but realistic ripples and small waves around it. The woman watches with curiosity. 7–11 seconds — Transformation: The water suddenly begins to glow with a subtle mystical energy. The tiny dragon starts expanding beneath the surface. Its body rapidly grows while maintaining realistic anatomy and physical movement. Scales form naturally across its body, wings unfold, claws emerge, and its long tail sweeps through the water. The transformation should feel physically believable and photorealistic, not cartoonish. Water splashes naturally as the creature grows from a tiny toy into a massive, majestic dragon. 11–15 seconds: The giant dragon rises dramatically from the river, towering above the woman. Water cascades from its enormous scales and wings. It spreads its massive wings and releases a powerful but realistic roar that echoes through the forest. The woman steps back in genuine amazement while maintaining a natural, believable reaction. End with a wide cinematic shot revealing the woman, the giant dragon, the river and the surrounding forest together, creating a breathtaking sense of scale. Visual Style: Ultra-photorealistic live-action fantasy, cinematic Hollywood-level VFX, physically accurate water simulation, realistic dragon anatomy, detailed individual scales, natural skin and hair textures, volumetric sunlight, realistic shadows, atmospheric depth, subtle film grain, high dynamic range, realistic motion blur, full-frame cinema camera look, 35mm lens, shallow depth of field where appropriate, natural color grading, highly detailed environment, seamless character and creature consistency. Important: Keep the woman’s appearance, hairstyle, clothing and facial features consistent throughout the entire video. Keep the dragon’s design consistent during the transformation. The transformation must happen smoothly and continuously, with no cuts during the actual transformation. Avoid cartoon aesthetics, anime, CGI-looking plastic textures, exaggerated facial expressions, unnatural body movements, flickering, morphing artifacts, extra limbs, deformed anatomy, or abrupt scene changes.

FORMAT: 16:9 landscape, 15 seconds, photorealistic live-action, cinematic lifestyle fashion film. CHARACTER CONSISTENCY: Use the uploaded character sheet as the master character reference. Keep the girl’s face, facial proportions, long wavy brown hair, hairstyle, hair clip, gold earrings, body proportions, burgundy pinstriped fitted shirt, wide-leg dark denim, and white sneakers exactly consistent throughout every shot. Do not change her outfit, hairstyle, age, or appearance. SHOT 1 — 0:00–0:05 A cozy rustic café in warm afternoon sunlight. The girl enters naturally carrying a small shoulder bag. Camera follows her from behind at waist height as her long wavy brown hair moves gently while she walks. She approaches a small wooden table near a sunlit window. Camera: smooth handheld tracking shot, natural movement, shallow depth of field. SHOT 2 — 0:05–0:10 She sits comfortably, crosses one leg over the other, picks up a simple white ceramic coffee cup, and takes a relaxed sip. Cut to intimate close-ups of her gold earrings, fingers around the cup, burgundy striped shirt, and flowing hair. Camera: subtle push-in, realistic handheld micro-movement, warm sunlight across her face and hair. SHOT 3 — 0:10–0:15 Side-profile shot as she looks peacefully toward the café window. She notices something outside, gives a tiny natural smile, then stands and walks toward the door. Final shot follows her from behind as she exits into warm daylight, her hair moving naturally. VISUAL STYLE Soft feminine lifestyle aesthetic, cozy European café atmosphere, warm beige and brown surroundings, natural sunlight, realistic skin texture, detailed hair strands, subtle film grain, authentic candid expressions, understated fashion editorial feeling. IMPORTANT: No exaggerated posing, no slow motion, no beauty-filter effect, no outfit changes, no face changes, no additional accessories, no cartoon/CGI appearance. Keep the performance natural and effortless. 16:9 LANDSCAPE • 15 SECONDS • PHOTOREALISTIC • CINEMATIC • NATURAL CAMERA MOVEMENT

Use the character sheet as the visual reference. Preserve the bride’s exact face, hairstyle, dress, body proportions, and accessories throughout the entire video. 16:9 landscape. 0–3 sec — THE ESCAPE A church wedding is happening when the bride suddenly bursts through the giant church doors and sprints down the steps, still holding her bouquet. Her expression is determined but hilariously excited. Her veil and dress fly wildly behind her. Camera rapidly tracks backward in front of her as she runs. A few confused wedding guests appear in the background, realizing what is happening. 3–5 sec — GET TO THE CAR She spots a bright red 1950s vintage car waiting at the curb. She kicks off one white bridal heel while running, then throws herself toward the driver's door. Fast whip-pan follows her movement. 5–8 sec — PEEL OUT She jumps into the car, slams the door, starts the engine and PEELS AWAY at ridiculous speed. Tires squeal, a tiny cloud of smoke appears, and her long white veil gets caught in the closing door and streams dramatically behind the car. The bouquet lands on the passenger seat. 8–11 sec — CHAOS Rapid comedic interior cuts: Bride gripping the steering wheel and laughing → her veil whipping around her face → bouquet bouncing around the passenger seat → her other bridal heel flying through the air → wedding guests running helplessly behind the disappearing car. 11–15 sec — SHE’S FREE Dynamic side tracking shot of the red car racing down a sunny vintage highway. The bride drives one-handed, completely carefree. She looks into the rearview mirror, sees the church disappearing in the distance, grins, then blows a huge pink bubblegum bubble. Final frame: The red car speeds toward the horizon, veil flying behind it. Style: fast-paced physical comedy, playful rebellious energy, 1950s Americana, saturated red vintage car, creamy white wedding dress, warm golden sunlight, cinematic vintage film grain, slightly painterly realism, realistic motion, energetic camera movement, whip pans, quick cuts, exaggerated but believable comedy. Important: No slow motion, no sad mood, no dramatic romance, no dialogue, no text, no extra brides, no face changes, no outfit changes, no distorted hands, no morphing.

Use the provided character image as the strict identity and styling reference. Keep the exact same woman, face, hair, body proportions, makeup, outfit, and accessories throughout the entire video. Photorealistic live-action, not animation or 3D. 0–3 sec Extreme close-up at a vintage vanity. She slowly applies glossy pink lipstick while looking into a small mirror. Warm, dim bedroom lighting, soft film grain, subtle camera movement. Her rhinestone pink flip phone sits beside the makeup. On-screen typography appears briefly: “I was trying to be subtle…” 3–6 sec Fast editorial cuts synced to the beat: — her glossy pink nails tapping the flip phone — pearl earrings being put on — sunglasses picked up from the vanity — a quick close-up of her lipstick and eyes — she snaps the flip phone shut. Text flashes: “oops.” 6–10 sec Camera pulls back as she stands from the vanity, revealing her full outfit. She puts on the oversized pink sunglasses, grabs her small handbag, checks herself in the mirror, then gives the tiniest confident smile. Smooth camera movement, like a real fashion commercial. 10–13 sec She walks past the camera through the bedroom with effortless confidence. Slight slow motion, vintage flash photography effect, soft motion blur, realistic fabric movement and natural body movement. Camera subtly tracks her. 13–15 sec She suddenly stops and turns back toward the camera. Close-up. She lowers her sunglasses slightly, gives a tiny knowing smirk, then the frame freezes like a 1990s fashion magazine cover. Large pink editorial typography: “ICONIC, ACTUALLY.” Visual style: late-90s/early-2000s fashion editorial, vintage Hollywood glamour, pink and black palette, glossy beauty campaign, film grain, subtle imperfections, flash photography, realistic skin and hair, cinematic depth of field, playful but sophisticated, fast-paced editorial cuts. No exaggerated acting, no cheesy posing, no cartoon look, no random outfit/face changes.

15 seconds, ultra cinematic cyberpunk boss battle, AAA game cinematic trailer quality, IMAX 70mm, Unreal Engine 5 realism, dark sci-fi action. Classic Hong Kong kung fu film choreography meets Devil May Cry style combo action: non-stop fighting from the first frame to the last, no pause, no slow motion, no standing poses. Extreme speed, brutal close-quarter combat, relentless chained combos, launcher uppercuts, air juggles, slams, dodge-counters, wire-fu aerial movement, real impact weight, hit-stop micro-freezes of 2-3 frames on every heavy hit, razor-sharp speed ramping. 0–1秒地铁车厢内超低機位，急速推進。武者瞬間爆發，腳下地板凹陷，藍色雷電炸開，身體化作殘影衝出，第一秒即與怪物接戰。 1–2秒 90°荷蘭角，側面高速跟拍。武者瞬移至綠色怪物面前，連續三記重拳擊中胸腹，肌肉受力變形，怪物被打得連連後退，武者貼身追擊，絕不停步。 2–3秒極端俯拍，突然切換仰拍。怪物揮拳反擊，武者側身閃避，瞬間消失，出現在怪物背後，一記重肘轟中脊背，無縫接上掃腿。 3–4秒超廣角低機位，猛烈甩鏡。怪物被擊飛撞碎車廂座椅，金屬支架彎曲，玻璃爆裂，碎片四散，武者凌空飛身追上，毫無間隔。 4–5秒三機位快速交叉剪輯。怪物從殘骸中暴起，抓住武者將其砸向車廂側壁，金屬壁板凹陷，整節車廂震動；武者借力反彈，瞬間反手格擋，立刻還擊。 5–6秒 180°環繞運鏡，極低仰拍。武者蹬牆反彈，空中扭身，一記雷霆飛膝擊中怪物下顎，綠色毒霧爆散，怪物被挑離地面。 6–7秒極端俯拍，超高速追蹤。武者在空中連續追打浮空的怪物，拳腳連環，六道藍綠殘影高速交錯，拳腳碰撞產生衝擊波，怪物像沙包般被打得在車廂內彈飛。 7–8秒荷蘭角，貼身手持攝影。武者閃過怪物利爪，連續左右勾拳，接一記兇猛上勾拳，怪物頭部猛然後仰，武者隨即躍起追擊。 8–9秒車廂盡頭超長焦，急速變焦。怪物釋放綠色能量衝擊波，武者貼地高速滑行從衝擊波下方穿過，沿途地板被撕裂，滑行中直接蹬地彈起，反擊不斷。 9–10秒 360°高速環繞，突然切換仰拍。武者躍起瞬移至怪物頭頂，一記雷霆下劈腿將怪物砸向地面，地板嚴重凹陷，武者落地即接連環重拳。 10–11秒超近景與極端俯拍交替。怪物掙扎反擊，雙方拳拳相撞，拳頭、肌肉、衣物產生明顯的衝擊變形，格擋、拆招、反擊一氣呵成。 11–12秒 45°荷蘭角，急速倒退跟拍。武者被綠色能量轟飛，連續撞穿座椅與扶手，落地翻滾，單手撐地瞬間反彈，毫不停頓地衝回戰場。 12–13秒地板高度超低機位，迎面高速攝影。武者全身雷電爆發，瞬間突破音障，以極限速度衝向怪物，身後形成多重藍色殘影。 13–14秒正面特寫，側面超高速攝影，俯拍交叉剪輯。雷霆重拳擊中怪物胸口，衝擊使其軀幹劇烈後彎，藍色雷電與綠色能量猛烈爆炸，武者連續追擊兩拳一腿。 14–15秒超廣角固定鏡頭，瞬間拉遠。怪物被轟飛撞向車廂盡頭，金屬門板扭曲，玻璃粉碎，強烈衝擊波席捲整節車廂，武者在飛散的碎片與雷光之中落地。 GLOBAL REQUIREMENTS: fighting continues non-stop from 0:00 to 15:00, every hit flows directly into the next, each dodge becomes a counterattack, each landing becomes another attack. Fists, elbows, knees and kicks stay anatomically connected to shoulders, hips and footwork, with real weight and visible muscle deformation on impact. Blue lightning on the warrior, green toxic energy on the monster, sparks, debris and glass shards on every collision. Faces and costumes stay stable and consistent. No slow motion, no waiting, no standing poses, no dialogue, no subtitles, no watermark, no extra limbs, no broken anatomy.

Create a 15-second vertical 9:16 photorealistic cinematic video of a cute orange tabby cat inside a muddy World War-style trench, wearing a realistic olive-green military helmet and holding a small vintage rifle. Start with the camera focused on the dark trench entrance, with stacked sandbags and rough wooden planks clearly visible above. At first, only the top of the helmet slowly appears from the trench. The cat gradually rises into view while holding the rifle naturally with both paws. Keep the cat’s face, fur, helmet, rifle, trench, and background consistent throughout the entire video. Around the middle, the cat looks directly toward the camera with a serious but adorable expression and slowly raises one paw in a small salute. Maintain realistic fur movement, natural paw motion, subtle head movement, and cinematic depth of field. The camera should remain mostly stable with a very gentle handheld cinematic movement. Near the end, the cat lowers its paw and slowly ducks back down into the trench, leaving only the helmet visible. Use realistic outdoor lighting, soft overcast sky, detailed muddy soil, natural textures, shallow depth of field, smooth motion, and no text, watermark, distortion, or extra characters.

Subject & Character: A mysterious and beautiful young East Asian woman standing in a ruined ancient shrine surrounded by endless red spider lilies under a dark stormy sky. She wears an elegant black gothic traditional-inspired dress with red accents, long flowing sleeves, and dark fabric moving naturally with her body. Her expression is cold, melancholic, and hypnotic — a mixture of sadness, loneliness, and quiet confidence. Maintain the original character appearance, face, hairstyle, outfit design, and cinematic atmosphere. ⸻ Action & Choreography: 15-second intense cinematic dance performance. The woman performs a powerful fusion of dark contemporary dance, gothic choreography, and sharp hip-hop inspired movements. Her movements are elegant but explosive: * sudden shoulder hits * sharp arm waves * dramatic body isolations * fast hand gestures like a ritual dance * powerful spins * flowing sleeve movements * low crouching movements * sudden freezes matching the rhythm Her long sleeves and hair follow every movement with realistic physics. The dance feels like a lonely ghost performing a final ritual in a forgotten world. She moves from stillness into explosive motion, expressing grief, anger, and acceptance. ⸻ Camera Direction: Vertical cinematic video 9:16 Use dynamic movie-style camera language: 0-3 seconds * Start with a slow cinematic push-in from a wide shot. * Woman stands motionless in the middle of the spider lily field. * Wind moves her hair and dress. * Rain droplets fall. 3-6 seconds * Sudden beat drop. * Camera rapidly circles around her. * She begins sharp dance movements. * Fast shoulder hits and arm movements. * Red spider lilies shake violently around her. 6-10 seconds * Dynamic handheld camera following her movement. * Low-angle shots showing power and elegance. * Quick cinematic cuts: * close-up of her eyes * close-up of hands * flowing black fabric * footsteps stepping through wet ground 10-13 seconds * She performs a powerful spin. * Camera rotates with her. * Hair and sleeves create a circular motion. * Fog swirls around her like a supernatural force. 13-15 seconds * Music suddenly slows. * She stops moving. * Camera pulls far away. * She becomes a lonely silhouette surrounded by endless red flowers. * A single red spider lily petal falls in front of the lens. ⸻ Environment & Lighting: Dark abandoned Japanese-inspired shrine ruins. Heavy rain, wet stone ground, dense fog. Cold blue cinematic lighting mixed with deep crimson highlights from spider lilies. The atmosphere is: * beautiful * tragic * mysterious * supernatural * elegant horror The environment itself reacts to her dance: * flowers sway with her movements * fog follows her motion * rain splashes with footsteps * shadows move subtly on the walls ⸻ Camera Style: IMAX cinematic photography. Dynamic camera movement: * orbit camera * low-angle tracking shot * fast dolly movement * smooth handheld realism * dramatic close-ups * slow motion moments High-quality cinematic dance film aesthetic. Realistic human motion, natural body physics, detailed fabric movement. ⸻ Visual Style: Silent Hill f inspired atmosphere. Dark Japanese gothic fantasy. Cinematic realism. Cold blue and blood-red color palette. Ultra realistic skin texture. 35mm film grain. High contrast lighting. Moody, emotional, haunting beauty. ⸻ Negative Prompt: static image, boring movement, stiff body, robotic dance, bad anatomy, distorted face, extra limbs, unrealistic physics, cartoon style, excessive visual effects, bright colors, modern nightclub, casual streetwear, comedy expression, low quality, frame interpolation artifacts, watermark, text, logo.

Create a cinematic, ultra-realistic luxury watchmaking commercial. Show a skilled watchmaker in a dark premium workshop carefully assembling an intricate mechanical gold watch. Start with close-ups of tiny gears, screws and moving mechanisms, then show his hands precisely placing the delicate components with professional tools. Slowly reveal the complete watch being polished and placed on his wrist. End with an extreme macro shot of the finished watch and its moving mechanical gears. Dark elegant lighting, realistic metal reflections, shallow depth of field, smooth camera movement, detailed craftsmanship, premium luxury advertisement aesthetic, photorealistic 3D animation. No text, logos or watermark.

Ultra-realistic cinematic medieval battle scene, a brave young woman warrior in an elegant flowing ivory medieval dress with black fitted sleeves, standing on an ancient stone courtyard while fighting a heavily armored knight wielding a large medieval mace. Dynamic combat pose, realistic steel armor reflections, detailed fabric movement, dramatic overhead camera angle, intense action, historical European castle setting, cinematic lighting, realistic skin and hair, atmospheric depth, subtle motion blur, highly detailed textures, epic fantasy atmosphere, photorealistic, HDR, 8K, professional film still, shallow depth of field, vertical 9:16 composition.

Ultra-realistic cinematic scene of a mysterious dark warrior in flowing black armor standing on a wet rooftop during a storm, powerful dynamic pose, water splashing dramatically around him, dark cloudy sky, intense atmospheric lighting, flying water droplets and motion, futuristic city skyline in the background, dramatic action-movie composition, realistic fabric and armor textures, volumetric lighting, shallow depth of field, high detail, HDR, 8K, photorealistic, cinematic color grading, vertical 9:16 composition.

15-Second Sequential Video Prompt 0 to 3 Seconds (The Hook) Visual: Extreme macro shot of a single fresh red strawberry resting on a white marble slab. Suddenly, the strawberry begins to hover and spin rapid-fire in mid-air. Action: The strawberry explodes into a swirling vortex of vibrant red fruit particles, liquid chocolate droplets, and fine powdered sugar clouds. Sound: High-speed comic cartoon swoosh building into a resonant pop sound effect, underlaid with a fast, bouncy acoustic guitar strum. 3 to 6 Seconds (The Transformation) Visual: Fast kinetic camera orbit around the swirling vortex as the floating ingredients instantly snap and condense back together in slow motion. Action: The liquid chocolate coats the fruit particles in mid-air, instantaneously transforming into a multi-layered, glossy gourmet strawberry chocolate tart with golden spun sugar spiraling around it. Sound: Satisfying magic transformation chime blending into a crisp chocolate shell snap sound effect. 6 to 9 Seconds (The Character Dialogue) Visual: Medium shot of the playful pastry chef winking at the camera and effortlessly catching the freshly transformed gourmet dessert on a sleek slate plate with one hand. Action: She holds the plate up toward the lens with a wide, infectious smile and speaks her line naturally with upbeat energy. Sound: Upbeat, clapping pop beat with a warm, cheerful voiceover: "Play with your food!" 9 to 12 Seconds (The Macro Reveal) Visual: Ultra close-up slice shot of a golden fork gently breaking through the top chocolate layer of the tart, revealing rich strawberry cream layers inside. Action: Glaze glistens under bright studio lighting as micro crumbs fall softly onto the slate plate. Sound: Hyper-detailed crisp crunch sound effect followed by a cheerful brass horn accent. 12 to 15 Seconds (The Brand Outro) Visual: Centered hero shot of the completed strawberry chocolate tart resting on the slate plate, surrounded by scattered fresh strawberries and spun sugar threads. Action: A playful pastel yellow graphic wave sweeps softly across the bottom screen as subtle steam/aroma swirls rise from the dessert. Sound: Energetic music track landing on a clean, snappy final kick drum beat with a lingering acoustic chime.

A cinematic 3D Pixar-style animated short of a beautiful young woman with long wavy chestnut-brown hair, large sparkling blue-green eyes, soft rosy cheeks and a gentle smile, wearing a cream sleeveless top and a beige apron with the text "@Logolumos" printed on the chest. She is in a bright, sunlit modern kitchen with warm wooden cabinets, marble countertop, a window with plants, and golden hour sunlight streaming in. Photorealistic lighting, shallow depth of field, ultra-detailed textures, high-end 3D animation quality. Sequence: She cracks a brown egg into a glass bowl already containing several egg yolks. She pours white sugar over the yolks. She simultaneously pours golden oil from a measuring cup and white milk from a glass pitcher into the bowl. She sifts white flour through a metal sieve into the wet mixture. She sprinkles dark cocoa powder onto the flour mound. She whisks everything into a rich, glossy dark chocolate batter. She brushes melted butter onto a rectangular metal baking pan. She pours the thick chocolate batter into the pan with a spatula. She slides the pan into a preheated oven. She looks at her wristwatch with a slightly worried expression while waiting. The cake rises and bakes inside the glowing oven. She opens the oven wearing oven mitts and pulls out the perfectly baked dark chocolate cake. She proudly presents the finished round chocolate cake on a cooling rack, smiling at the camera. Warm, inviting, cozy cooking atmosphere, smooth camera movements, professional food-commercial quality, 8k, highly detailed.

Image 1 SHARON'S REAL FACE — sole source of her features, 100% match, zero drift: soft rounded oval face, warm light-beige skin with tiny freckles and beauty marks, GREEN eyes, dense straight feathered brows, small neat nose, full pink lips, small silver drop earring. Use the uploaded REFERENCE VIDEO Video 1 as the absolute master for timing, camera movement, body motion, pose, facial-expression timing, interaction, transition rhythm, pixel effects, outfit-change effects, framing, and overall choreography. Replace the original woman with Image 2 as the ONLY replacement human identity. From this point onward, refer to her only as THE FEMALE CHARACTER Image 1. CRITICAL REFERENCE PRIORITY: REFERENCE VIDEO controls: exact motion exact timing exact camera movement body choreography pose changes head movement hand movement facial-expression timing interaction with the other man transition timing outfit-change timing pixel effects digital clothing-change effects framing speed ramps movement through the pixels overall visual rhythm THE FEMALE CHARACTER controls: identity @Image 2 face hairstyle head shape skin tone body proportions gender presentation The original woman is NOT an identity reference. She controls motion only. The generated video must follow the reference video as closely as possible, but the woman must be completely replaced by the same female character @Image 1 throughout the entire sequence. ================================================== ABSOLUTE IDENTITY LOCK There is only ONE replacement identity throughout the video: THE SAME FEMALE CHARACTER. Her identity must remain completely stable in EVERY FRAME. This includes: normal frames fast-motion frames motion blur transition frames pixel transformation frames clothing-change frames partially occluded frames close-ups profile angles extreme angles frames where another person crosses in front of her Never restore the original woman's identity. Never reveal the woman's face. Never reveal the woman's body. Never blend the reference video female character with the woman of reference pictures. Never create a temporary female version. Never morph from male to female and back. Even if the transformation lasts only a few frames, those frames must still contain the SAME female character. @Image 2 ================================================== MOST IMPORTANT OUTFIT CHANGE RULE THE CLOTHING TRANSFORMS. THE HUMAN DOES NOT. Every pixel transformation, digital breakup, clothing replacement, color change, texture change, or outfit transition applies ONLY to the clothes. The female character underneath remains physically identical. Correct visual logic: SAME female character wearing Outfit A → pixel effect begins across clothing → clothing breaks into / passes through digital pixels → SAME female character @Image 1 remains underneath → Outfit B forms on the SAME body → SAME female character @Image 2 continues moving Never: female character → pixels → original woman → clothing changes → female character returns. The pixel effect must never act as an identity-change transition. ================================================== PIXEL EFFECT BEHAVIOR Recreate the original reference video's pixel effect as closely as possible. Match: direction density speed size timing breakup behavior digital fragmentation reassembly interaction with the body interaction with the other man moment when clothing changes The pixels should feel integrated into the physical scene. When the other woman passes through the pixel field, preserve that original interaction exactly. Her body should visibly move through / be partially occluded by the pixels in the same way as the reference video. Do not replace this with: smoke magic particles unrelated to the reference light beams portals generic dissolves morphing bodies Keep the distinctive pixel clothing-change effect from the source. ================================================== FACE LOCK DURING PIXEL TRANSITIONS The female character's FACE @Image 2 is permanently locked. If pixels move across the face or temporarily obscure part of it, the visible portions of the face must remain the same identity. When the pixels pass away, the exact same face must be underneath. Never reconstruct hidden facial areas using the original woman. The face before, during, and after every transformation is the same person. ================================================== BODY LOCK DURING OUTFIT CHANGES Keep the female character's body proportions stable continuously. The clothes adapt to her @Image 2 body. Do not reshape her body to match the woman from the source video. Maintain: female shoulder width torso proportions waist proportions arms legs height posture hand size overall silhouette The original woman's body is motion guidance only. The female character performs her movement while remaining physically herself. @Image 1 ================================================== MOTION MATCHING Follow the reference video's @Video 1 movement as closely as possible. Do not reinterpret the choreography. Match: exact body direction exact turns exact head movement exact timing exact pauses exact walking movement exact hand placement exact interaction exact acceleration exact deceleration exact movement through the pixel effect The character replacement should feel like the same footage was filmed with a different actor. Do not invent new gestures. Do not simplify the original performance. Do not change the rhythm. ================================================== FACIAL EXPRESSION Copy the original woman's facial-expression TIMING and emotional beats while keeping the replacement female identity @Image 2 Match: gaze direction eyebrow movement smiles attitude reactio

TITLE: Premium Sparkling Fruit Drink Product Commercial Storyboard FORMAT: • Single-page premium storyboard • 3:4 Portrait ratio • Luxury beverage product campaign • 8 cinematic storyboard scenes • Product remains the central hero • Premium advertising agency presentation HEADER: • Modern luxury typography • Information cards: Duration: 10 Seconds Style: Cinematic Beverage Commercial Product: Sparkling Fruit Drink Audio: Fizz + Refreshing Liquid ASMR • Why This Style Works section • Silver, citrus orange and deep blue aesthetic • Minimal premium decorative accents STORYBOARD: 1. Chilled sparkling drink bottle covered in condensation 2. Bottle cap opening with a burst of carbonation 3. Extreme macro shot of bubbles racing through the drink 4. Sparkling drink pouring into a crystal glass 5. Ice cubes falling into the glass in slow motion 6. Fresh citrus slices creating a dramatic splash 7. Macro shot of condensation and carbonation bubbles 8. Final hero bottle and glass surrounded by frozen splash EVERY PANEL: • Scene number • Duration badge • Camera direction • Visual • Action • Product detail CAMERA: High-speed liquid photography, extreme macro, frozen splash capture, slow-motion pour, dramatic backlighting, condensation close-up, cinematic product hero framing. STYLE: Ultra-realistic beverage advertising, realistic carbonation, detailed water droplets, dynamic liquid splash, premium glass reflections, studio lighting, luxury branding, commercial photography, 8K.

About Seedance 2.0

Seedance 2.0 is ByteDance's video generation model, and its defining trait is that it thinks in sequences rather than single clips. Where most models produce one continuous shot, Seedance can carry a subject through several distinct shots — an establishing view, a cut to a closer angle, a reaction — inside a single generation, with characters whose mouths actually match their lines thanks to native lip-sync, and a soundscape that places audio in space.

That makes it the model to reach for when you want a scene that tells a small story: a two-line exchange between characters, a product reveal cut across three angles, a moment with dialogue that needs to feel spoken rather than dubbed. Reviewers consistently place it among the strongest video models available, and its edge is exactly this director-style shot control.

Multi-shot power cuts both ways, though — a vague prompt gives the model too many decisions, and the cuts drift. Prompts written as explicit shot lists with marked dialogue are what separate coherent sequences from disjointed ones. The gallery below collects tested Seedance prompts with their real outputs, so you can start from a structure that already works.

How to write Seedance 2.0 prompts

1Write the prompt as a numbered shot list — "Shot 1: wide establishing… Shot 2: cut to close-up…". Seedance follows explicit sequence structure far better than one long paragraph.
2Repeat your character's identifying details (clothing, hair, build) in every shot line. Consistent descriptors are what keep the same person on screen across cuts.
3Mark dialogue clearly and attribute it: the woman says: "We leave at dawn." Quoted, attributed lines are what trigger accurate lip-sync.
4Direct the spatial audio — say where sounds come from: "footsteps approaching from off-screen left, crowd noise behind her". Placement cues make the mix feel three-dimensional.
5Give each shot exactly one job: establish, reveal, or react. Cramming two beats into one shot line is the most common cause of muddled cuts.
6Keep the cast small — one or two speaking characters. Every added speaker multiplies the continuity and lip-sync load across shots.

Frequently asked questions

What is Seedance 2.0 best at?

Multi-shot storytelling in a single generation: sequences that cut between angles while keeping the same characters, with native lip-sync on dialogue and spatial audio that places sound in the scene. If your idea needs more than one shot to land, Seedance is built for it.

How do I write Seedance 2.0 prompts for multiple shots?

Structure the prompt as an explicit shot list — number each shot, give it one purpose, and repeat your character descriptions in every shot so identity holds across cuts. The tested prompts on this page show the pattern; copy one and swap in your own story beats.

Does Seedance 2.0 support lip-sync and dialogue?

Yes — lip-sync is native. Put spoken lines in quotation marks and attribute them to a described character, and the generated speech matches the mouth movement. It also renders spatial audio, so describing where sounds originate pays off.

Where can I use these Seedance prompts?

Seedance is available through ByteDance's Dreamina (Jimeng AI) creative platform, and developers can access it via the Volcano Engine API. Copy any prompt from this page, paste it there, and adapt the shot list to your own scene.

Related models

Seedance 2.5

Seedance 2.5 is a next-gen AI video model that generates continuous, synchronized 30-second 4K clips from a single prompt.

Seedream 5

ByteDance's high-fidelity bilingual image model — the best quality-to-cost ratio for high-volume pipelines.

MiniMax H3

MiniMax H3 is a powerful multimodal video generation model that creates up to 15-second 2K videos with native stereo sound from text, image, video, and audio inputs.

Grok Imagine 2

xAI's Grok Imagine 2 — instant photorealistic stills that animate into short video clips with native audio, built into Grok.

Browse AI Video Prompts All models