《我是传奇》Optimus Prime 预告片
A cinematic video prompt for Grok Imagine to create a movie trailer scene replacing Will Smith with a Tesla Optimus robot.
本页汇集归入“Cityscape Urban”分类的视频提示词示例。调整示例用于自己的项目之前,可先比较生成结果、构图或镜头选择以及原始写法。
926 prompts
主体
A cinematic video prompt for Grok Imagine to create a movie trailer scene replacing Will Smith with a Tesla Optimus robot.
Movie trailer for I Am Legend but replace will smith with tesla Optimus he’s the last robot left standing post humans
A prompt for high-end 3D open-world game sequences featuring a character chase in a Japanese neighborhood with GTA-style HUD.
Create a 30-second realistic AAA third-person open-world game sequence in a lively local Japanese neighborhood. Use the uploaded image as the exact character reference: a young Korean woman in her early 20s with long black hair, pastel-lavender top, white cargo pants and sneakers. Keep her appearance consistent. She notices a delivery cyclist carrying a cardboard package, grabs the package, and runs. The cyclist chases her through the streets. She hides behind a parked kei truck, sneaks out, then accidentally crashes into another delivery worker, sending boxes everywhere. She ignores a “RETURN PACKAGE” prompt and runs again. She crosses a pedestrian bridge, briefly leaves the package beside a bench, grabs it when the cyclist arrives, and continues escaping. She eventually reaches the address printed on the package and realizes she has accidentally delivered it to the correct recipient. The recipient happily takes it while the exhausted cyclist arrives and looks completely confused. She gives him an innocent smile and walks away. Use authentic third-person gameplay graphics, realistic 3D characters, detailed village/neighborhood environment, believable physics and NPC reactions. Include a GTA-style HUD with minimap, health/stamina bars, controller prompts, mission objectives, alert markers and notifications such as “PACKAGE STOLEN,” “THEY FOUND YOU,” “BAD DECISION,” “DELIVERY COMPLETE,” “MISSION COMPLETE,” and “CHAOS +150.” No anime, cartoon, cel-shading, mobile-game graphics, cinematic movie shots, distorted characters, inconsistent objects, gore or unrealistic physics.
A workflow prompt for generating cinematic car chase scenes by combining Blender animations with Seedance 2.5 photorealism.
Create an original photorealistic cinematic car chase using a structured Blender-to-PixVerse workflow. Design two cars, a driver and an urban environment. Create three connected 4-second shots with a rear pursuit, side tracking turn and wide exit. Animate and validate vehicle movement, wheel rotation, steering, driver interaction and camera paths in Blender. Render a 12-second 1280×720 gray-model video. Use PixVerse Plugin and Seedance 2.5 to create cinematic reference images from the corresponding first frames, preserving composition, perspective and vehicle identity. Use those references with the Blender videos to generate each shot while maintaining the original camera movement, trajectories, timing, colors and spatial relationships.
A prompt recreating the nostalgia of early 2000s Korean home videos with handheld camera shake and authentic market settings.
Create a 30-second, 1080p, 16:9 ultra-realistic early-2000s DV home video of a young Korean woman having a spontaneous summer evening around a quiet neighborhood market in Seoul. SUBJECT Young Korean woman, early 20s, naturally pretty, realistic skin, minimal makeup, relaxed expressions. Straight dark-brown shoulder-length hair, loose with a black headband and a few messy strands. Outfit: dusty-rose fitted T-shirt, dark-indigo jeans, white canvas sneakers, cream canvas shoulder bag, thin silver necklace. Keep her face, hair, outfit, body proportions, and accessories identical throughout the entire video. SETTING An older Seoul neighborhood during a warm summer evening. Narrow streets connected to a small local market, aging low-rise buildings, faded painted walls, metal shutters, parked scooters, bicycles, potted plants, handwritten-looking shop signs without readable branding, utility poles, overhead wires, plastic stools, small street vendors, and residential entrances. The area feels lived-in and ordinary rather than picturesque. A few local residents move naturally through the background. Warm sunlight is beginning to fade into early evening. No brands, logos, advertisements, tourist landmarks, modern luxury buildings, polished streets, or commercial-looking locations. CAMERA STYLE Cheap early-2000s consumer DV camcorder footage recorded casually by a friend. Strong handheld shake, imperfect framing, occasional focus hunting, exposure shifts when moving between sunlight and shadow, soft digital detail, slightly faded colors, mild tape noise, subtle compression artifacts, motion blur, accidental zooms, awkward reframing, and natural camera movement. The camera should feel like a friend casually recording the moment rather than a professional filming a scene. No stabilization, gimbal movement, drone shots, cinematic camera choreography, cinematic lighting, shallow-depth-of-field commercial shots, or polished color grading. TIMELINE 00:00–00:06 — LEAVING THE BUILDING She steps out through an old residential entrance carrying her cream canvas shoulder bag. She pauses beside a parked bicycle and checks the time on a small wristwatch. She notices the camera pointing at her and gives the camera operator an amused look. She says: “Are you filming me again?” The camera moves closer slightly. She shakes her head with a small laugh and starts walking toward the neighborhood market. 00:06–00:12 — SMALL MARKET She walks past a tiny neighborhood fruit stand and notices a colorful pile of peaches. She stops, picks up one peach, looks at it, then looks directly at the camera. She says: “Should I get this?” The camera operator responds naturally from behind the camera: “Definitely.” She laughs quietly, buys one, and takes a bite while continuing down the street. 00:12–00:18 — SUMMER MOMENT She reaches a small side street lined with old apartment walls and potted plants. A sudden warm breeze moves the leaves and pushes loose strands of her hair across her face. She tries to fix her hair while still holding the peach. A bicycle passes behind her. She looks toward the bicycle, then back at the camera and says jokingly: “Okay, that was almost dangerous.” She laughs naturally. 00:18–00:24 — STREET CORNER She reaches a small neighborhood corner with a public bench beside an old concrete wall. She sits down for a moment and drinks water from a bottle taken from her shoulder bag. In the background, an older resident slowly sweeps the pavement while another person carries groceries toward an apartment entrance. She watches the street quietly for a few seconds. The camera operator asks: “Tired?” She looks toward the camera with a relaxed smile and replies: “A little.” She takes another sip of water and smiles. 00:24–00:30 — HEADING BACK She stands up, brushes a small piece of dust from her jeans, adjusts the cream canvas shoulder bag across her shoulder, and starts walking back toward the residential buildings. The camera follows from behind with imperfect handheld movement. After a few steps, she turns around while walking backward and looks directly into the camera. She smiles and says: “Hurry up.” She turns forward and continues walking. The camera follows her for another moment before the footage abruptly cuts to black. AUDIO Natural location sound only. Footsteps on concrete, distant traffic, bicycle wheels, birds, summer insects, leaves moving in the breeze, neighborhood market ambience, faint conversations, a distant scooter, plastic bags rustling, street sweeping, water bottle sounds, natural laughter, and subtle camcorder handling noise. Dialogue should sound spontaneous and conversational, with natural pauses and imperfect timing. No music, narration, subtitles, captions, translations, logos, watermarks, or on-screen text. REALISM & CONTINUITY Maintain strict character continuity throughout all shots. Her face, hairstyle, black headband, dusty-rose T-shirt, dark-indigo jeans, white canvas sneakers, cream canvas shoulder bag, silver necklace, body proportions, and overall appearance must remain identical from beginning to end. Natural human reactions and imperfect timing. Background pedestrians should move naturally and remain physically consistent. Objects must not disappear, duplicate, teleport, or change position unnaturally. No duplicated people, disappearing objects, distorted faces, warped bodies, broken hands, extra fingers, plastic skin, CGI appearance, identity drift, hairstyle changes, outfit changes, accessory changes, exaggerated acting, unrealistic facial expressions, or overly cinematic footage. The final result should feel like a genuine forgotten home-video recording from the early 2000s rather than a modern cinematic recreation. 16:9 aspect ratio, 1080p, 30 seconds.
A detailed structured JSON prompt for a 30-second cinematic video of 1990s Manhattan streets, including specific lighting and camera movements.
{ "format": "16:9, 30s, native audio on, cinematic realism, no text overlay, no on-screen subtitles", "style": "1990s Manhattan street cinematography, warm Kodak film-stock emulation, fine grain, soft haze, anamorphic lens flare", "subject_and_action": { "0-6s": "Wide handheld shot drifting forward through a dense Midtown Manhattan sidewalk crowd. Foreground man in a navy suit glances at his wristwatch mid-stride. A woman with curly auburn hair in a beige blazer walks beside him. Steam rises from a hot dog cart with blue-and-yellow striped umbrellas center-frame. Yellow taxis crawl past on the street.", "6-14s": "Camera holds medium-wide as a woman in a bright floral-print top exchanges a glance and smile with a man in a tan-and-white outfit near the food cart. Behind them a man in a gray suit and burgundy tie walks toward camera. Crowd density remains high, all in business attire, natural staggered walking pace.", "14-20s": "Cut to a lower, closer angle at a storefront corner marked 'W 34th St.' Two young men in casual streetwear (backpack, jeans, polo shirts) walk laughing in the opposite direction, foreground, as a yellow taxi speeds through the lower frame in motion blur. Clothing-store mannequins and a neon 'OPEN' sign visible in the window behind them.", "20-30s": "Camera settles at a crosswalk intersection, slightly elevated. A large crowd of office workers crosses on the white-striped crosswalk toward camera, yellow cabs idling in traffic beside them, second hot dog cart with striped umbrellas at right. Camera holds steady as the crowd thins slightly at the end, pulling focus toward the hazy skyline in the deep background." }, "environment": "Dense Midtown Manhattan intersection, tall office towers fading into atmospheric haze, street vendor carts, painted crosswalks, period-accurate signage (kept intentionally generic/non-legible), classic boxy yellow taxi cabs", "camera": "Handheld walking camera, eye-level, slow forward dolly with natural sway; one hard cut at 14s to a secondary angle; deep focus foreground, soft falloff on background towers", "lighting_and_color": "Bright midday sun, warm amber key light, soft shadow edges, slightly desaturated background with punchy yellow/blue saturation on cabs and umbrellas", "audio": "Ambient city traffic hum, overlapping crowd murmur and footsteps, distant car horns, brief bus engine rumble under the 14s cut, no dialogue, no music", "continuity": "Same crowd density, same taxi model/color, same food-cart umbrella design, and same warm color grade held across all four segments", "constraints": "No legible or readable text on any signage, no modern phones or vehicles, no anachronistic clothing, no visible logos, no distorted or duplicated faces" }
A 30-second supernatural sequence prompt set at a Japanese rural railway crossing with surreal rail deconstruction and volumetric fog.
Create a 30-second ultra-realistic Japanese supernatural mystery sequence at a remote rural train crossing during a dense midnight fog. The entire sequence must be one continuous unbroken camera shot with no cuts, no montage, no CCTV inserts, and no teleporting camera. Photorealistic live-action cinematography, thick volumetric fog, wet gravel reflections, practical halogen signal lighting, natural human reactions, believable physics, subtle supernatural surrealism, no violence, no injury, no gore, no blood, no disturbing body transformation, no explicit threat, no subtitles, no watermark, no artificial CGI aesthetic. OPEN WITH AN EPIC IMAGE. The camera begins high above a vast, mist-shrouded Japanese valley at midnight. A full moon occasionally pierces through heavy, moving fog, illuminating miles of dark bamboo forest and winding mountain ridges. Far below, barely visible, a single red signal light blinks at an isolated railroad crossing on a forgotten countryside lane. The camera descends continuously through thick fog and swaying bamboo toward it. The rusted crossing gates, wooden ties, and single set of steel tracks emerge from the gloom. No houses. No traffic. Only the warm, rhythmic amber glow of the crossing signal cutting through the darkness. The camera drops toward track level and glides alongside the weathered wooden fence. Beside the track stands a lone high school student holding a transparent umbrella, waiting for the train. A quiet dinging sound begins. The red signal lights flash in sequence. The mechanical wooden crossing gates lower with a heavy clatter. Everything feels ordinary, routine, grounded. Then the student notices something along the tracks. The steel rails are changing. Not melting. Unraveling. The solid steel splits into thousands of fine, thread-like silver strands that gently lift into the air like weightless spider silk. The effect spreads along the railway line. The heavy wooden cross-ties beneath the rails break apart into fine, glowing wooden fibers that float upward. The coarse gravel ballast beneath the tracks detaches from the earth, stone by stone, suspending itself in midair like liquid droplets. The student steps back in quiet awe. The camera follows seamless and low. Rain begins to drizzle through the fog, but wherever the unraveling wave passes, moisture freezes in midair, forming a dense lattice of suspended, glowing ice crystals. The transformation accelerates. The mechanical signal post fragments into floating metallic dust. The red warning lamps separate from their housings, their light continuing to shine without any physical bulb, suspended in the mist. A bright headlight appears far down the tracks in the fog. A classic electric train approaches slowly. But as it passes through the unraveling zone, the metal train car begins to dissolve into the same silver threads—not destructively, but gently deconstructing into a swirling vortex of glowing geometry. Within seconds, the entire train dissolves, leaving behind no wreckage, only its passengers standing quietly on the air where the carriages used to be, suspended safely above the ground. Then the very ground beneath the crossing dissolves. The topsoil and modern asphalt disintegrate into fine, dark sand that spirals upward into the sky. The camera slowly pulls upward. The modern crossing vanishes completely. But beneath the vanished modern soil, something ancient is revealed. Carved overgrown stone stepways. A massive, moss-covered Torii gate buried for centuries. The original Edo-period pilgrimage path, flanked by hundreds of ancient stone lanterns whose hollow centers suddenly ignite with soft, supernatural blue flame. The camera rises faster now, maintaining its single unbroken shot. The dissolved modern railway stretches for miles through the valley, now transformed into a massive, shimmering river of floating silver threads overhead. And beneath it, completely uncovered across the valley floor, lies the sprawling stone ruins of an ancient sacred highway leading toward a hidden mountain shrine. Then comes the final impossible reveal. The cloud of floating silver threads and suspended gravel overhead begins organizing itself in the night sky. The particles align into a massive, vertical spiral staircase made of solid light and liquid stone, stretching up into the storm clouds toward the moon. Moving along this vertical highway of light are dozens of ancient phantom travelers carrying glowing paper lanterns, quietly descending from the sky toward the newly revealed stone ruins. The student and the suspended passengers look up together in silent wonder from the ancient path below. One floating traveler carrying a massive bronze bell steps off the sky-road onto the top stone archway of the ancient ruin. The camera continues rising into a breathtaking high-altitude aerial view. Ancient stone path illuminated below. Modern railway turned into an ascending highway of stars above. Mountains submerged in ocean-like fog. And an impossible procession of light descending from the clouds. End on the vast aerial image. Atmosphere: hauntingly peaceful supernatural mystery, contemplative and serene, monumental scale, volumetric fog and mist used for depth, authentic rural Japanese infrastructure, slow visual escalation, surreal environmental transformation, strong visual cause and effect, spectacular final reveal.
A hyper-realistic 4K cinematic vlog prompt for Russian winter travel, ensuring character and clothing consistency across urban and cultural scenes.
Create a 30-second ultra-realistic 4K cinematic winter travel vlog in Russia. Use the male traveler from image1 as the exact character reference in every shot. Keep his face, hairstyle, facial hair, skin and body consistent. He wears the same winter outfit throughout: insulated puffer jacket, knitted beanie, scarf, gloves, dark trousers and waterproof boots. Keep colors and design consistent. 0:00–0:02: Cinematic drone pull-back over a snow-covered Russian city with golden domes, frozen rooftops, ice crystals, pale sunlight and morning haze. 0:02–0:05: Handheld selfie vlog. He walks on a snowy cobblestone street, smiles and talks to camera. Visible breath mist and winter lens flare. Whip pan. 0:05–0:08: Russian winter market with colorful stalls, matryoshka dolls and steaming samovars. Focus on objects, rack focus to his face as he picks up a souvenir, slow push-in, warm grade. 0:08–0:10: Macro of his gloved hand holding a lacquered figurine, frost details, bokeh and subtle camera drift. Match cut. 0:10–0:14: Side tracking shot beside a grand ice-covered historic building, icy reflections, speed ramp 60% to 100%. 0:14–0:16: Dutch tilt and tilt-up revealing a frozen cathedral against a grey winter sky. He looks up in awe. 0:16–0:19: Slow-motion wide shot walking beside a frozen river, blowing snow, distant skyline, cinematic letterbox. 0:19–0:22: Handheld selfie close-up holding a steaming hot drink, satisfied expression, warm grade. 0:22–0:25: Fast montage: palace hallway walk, photographing an ice sculpture, snowy bridge thumbs-up. Rapid cuts and motion blur. 0:25–0:28: Golden-hour overlook of the frozen city, slow push-in toward his silhouette. 0:28–0:29: He faces camera, smiles and waves, subtle lens flare. 0:29–0:30: Cut to black screen. Centered elegant white text fades in: “Wizstar AI”. Music fades to silence. Photorealistic, cinematic lighting, realistic snow, natural motion, accurate hands, consistent image1 identity and outfit, no face changes, distortion, cartoon or CGI.
A stunning 15-second FPV drone video of a city fly-through, featuring sharp architectural details and continuous footage.
15-second realistic cinematic FPV video, 16:9. A breathtaking high-speed flight through a bustling modern city. Extreme acceleration, sharp architectural detail, natural motion blur and powerful depth. 0.0–2.5 SEC: Begin high above the skyscrapers, camera aimed steeply downward. Plunge from the sky at tremendous speed between two towers, their glass facades streaking past. 2.5–4.0 SEC: Smoothly pull out of the dive above the street, redirecting into rapid forward flight without touching the ground. 4.0–7.0 SEC: Race along the street, banking hard around building corners and sweeping between structural columns. Camera bobs up and down while maintaining relentless forward momentum. 7.0–11.5 SEC: Enter a busy pedestrian plaza. Slalom through clear gaps between people, rising above shoulder level when space narrows, then dipping into open stretches. Pedestrians move naturally. Maintain visible clearance; everyone remains unharmed. 11.5–15.0 SEC: Rocket through a narrow passage between buildings, skim above a staircase, then bank sharply into a wide avenue. Continue racing forward through the final frame. CAMERA: ONE continuous uninterrupted first-person shot. No cuts, teleporting, pauses, slow motion or third-person views. Camera faces its direction of travel with controlled banking. Solid buildings and people; never pass through objects. No visible drone. AUDIO: Rushing wind, sharp air whooshes during close passes, distant traffic and brief passing crowd sounds. No music or dialogue.
A workflow prompt for creating realistic GTA-style car chase scenes by converting Blender clay models into cinematic footage.
Create an original GTA-inspired car chase with a photorealistic, live-action cinematic finish. Design the driver, two cars and urban environment. Plan three 4-second shots: rear tracking pursuit, side tracking through a sharp turn and a wide exit shot. Build the scene and animation in Blender, including vehicles, wheel rotation, steering, driver movement and cameras. Render the complete 12-second gray-model video at 1280×720 and 24 fps. Then use the PixVerse Plugin with Seedance 2.5 to transform each shot's gray first frame into a photorealistic cinematic reference while preserving composition, perspective, subject positions and vehicle count. Use each cinematic reference together with its corresponding Blender video to generate the final shots while maintaining vehicle identity, colors, camera movement, trajectories and action timing.
A high-intensity cinematic prompt featuring a supercar driving through overturned train carriages with detailed physics and complex camera movements.
【生成要求】 生成一段 10秒、16:9横屏、真人实拍电影级汽车特技视频。画面具有强烈冲击力,动作紧凑,物理反馈清晰。 白红超级跑车高速冲向侧翻的青绿色列车车厢,借坡侧倾,从一侧大窗撞入,横穿车厢,再撞碎对面玻璃窗冲出。赛车落地瞬间,车厢在身后轰然砸下;赛车连续漂移,成功脱险。除新增的2秒破窗慢动作外,其余镜头保持高速。赛车始终向前运动,没有停车、准备起跑或重新调整位置。 【资产锚点与参考规则】 参考视频9月9日:运镜、轨迹、空间关系与节奏参考。 白色红条低矮几何车辆对应图1赛车;青绿色横向长方体对应图2车厢;倾斜几何板对应金属坡板。黄色窗框仅标明穿越位置,最终替换为真实银色金属窗框。 仅使用参考视频8秒,在赛车即将撞破出口玻璃的位置,插入2秒侧面近景慢动作,后续镜头顺延,成片共10秒。 保留对应段落的摄影机位置、景别、车辆路径、车厢翻转方向与运动速度。在此基础上增加真实悬架、轮胎、破碎、碰撞与环境反馈。新增慢动作衔接同一次出窗动作,不重复撞窗。 图1image:赛车外观。 白色低矮宽体超级跑车,红色纵向条纹与侧面红色装饰,黑色座舱玻璃、细长车灯、深色轮毂、红色刹车组件与碳纤维下包围。全片车型、比例、涂装一致。破窗后允许增加少量细小擦痕,车身保持完整。 图2image:车厢外观。 深青绿色现代城市列车,银色金属窗框、大面积侧窗、浅色内饰、座椅、扶手、顶部灯带与底部转向架。车厢内部无人,两侧中央大窗彼此对应,横向穿越区域保持净空。 参考图的摄影棚背景不进入视频。 【视觉风格】 真实汽车特技电影摄影,真实比例、自然光照、细腻车漆与沉重机械质感。雨后明亮阴天,云隙日光照亮飞散的玻璃和水滴,城市整体冷灰,白红赛车和青绿色车厢鲜明突出。 强化近景、中景、远景的运动层次:近处碎片和护栏高速掠过,中间赛车保持清楚,远处建筑形成稳定空间参照。常速镜头使用自然方向性运动模糊;慢动作中玻璃棱面、水珠与车身反射清晰可辨。 冲击通过车体变形、悬架受力、碎片方向、路面反馈和短促镜头震动体现。摄影机始终跟住关键动作,撞击震颤后迅速恢复稳定。 【场景】 东京现代城区的封闭高架道路,邻近高架轨道。深灰沥青上覆盖雨后薄水膜,零散浅水映出车辆与天空。地面有磨损车道线、排水槽、伸缩缝和细小砂砾。 两侧混凝土护栏、金属隔音屏、路灯与弯道反光标记连续排列,提供高速视差。前方宽阔左弯保持通畅,能清楚看见赛车入弯、车尾滑动和恢复抓地的路线。 旁侧轨道可见钢梁、桥墩、轨枕与金属构件。车厢横向翻向道路,底部机械结构暴露,局部松动部件随惯性震动。车厢内部灯带、扶手和窗框随车体旋转,强化空间变化。 远处密集住宅楼、玻璃办公楼与楼顶设备逐层延伸,雨后空气带有轻微透视雾。背景建筑不遮挡赛车、窗洞和逃离路线。道路与车厢内无人。 【画面内容运镜与音效】 [00:00—00:01.21] 镜头1:巨物侧翻,赛车闯入 低机位朝前拍摄。开场只有青绿色车厢向道路和镜头方向侧翻,车体横向压住前方通路。随着翻转,底部钢架与转向架暴露,窗面反射快速变化,松动金属件震颤,少量旧玻璃碎屑和积水从车体上甩落。 白红赛车随后从镜头后方高速闯入,迅速占据前景,轮胎切开路面水膜,两道低矮水雾向后展开。镜头衔接追拍,巨大车厢在赛车前方快速逼近。 音效:沉重金属扭曲声、连续结构震响,引擎由远及近猛然掠过,伴随轮胎排水和风压声。 [00:01.21—00:02.29] 镜头2:压坡腾起,险贴窗框 后侧低位高速跟拍。赛车右侧车轮连续压过金属坡板,坡板瞬间受压震动,边缘弹起少量砂砾和水珠。右侧悬架先压缩,再随车轮离坡释放,右侧车身抬高,整车向左侧倾并短暂腾空。 车头准确对准正在转动的侧窗。窗框边缘与车顶之间的空隙迅速缩小,轮胎仍在高速旋转,车底阴影快速划过路面,呈现明确的前冲惯性。 音效:两次紧密的压板重响、底盘震动、高转速引擎和骤然增强的破风声。 [00:02.29—00:03.29] 镜头3:撞碎入口,冲入狭窄空间 镜头紧随赛车,车头撞上入口大窗。接触处玻璃骤然开裂,随即向车厢内部炸开,形成沿赛车前进方向扩散的碎片流。 赛车冲过入口,玻璃颗粒撞击座椅和扶手,少量碎片从镜头边缘掠过。明亮室外瞬间切换为短促的车厢内光线,顶部灯带与侧面立杆高速划过,强化狭窄空间中的速度感。 对面出口窗仍然完整,窗外道路清晰可辨。车头迅速逼近,在接触出口玻璃前切镜。 音效:尖锐爆碎声、碎片敲击金属与内饰的密集脆响,引擎声在车厢中短暂轰鸣。 [00:03.29—00:05.29] 镜头4:侧面近景,玻璃向镜头外侧爆散 切至出口窗外的斜侧面近景,保留青绿色车厢外壁、银色窗框 and 逼近玻璃的白红赛车。进入2秒高速摄影慢动作,承接同一次出窗动作。 车头撞击玻璃,接触位置出现密集裂纹,裂纹瞬间爬满相邻窗面。紧接着,玻璃被车头向外推开,碎成大量细小颗粒与少量尚未完全解体的片团,沿前冲方向层层喷出。 **玻璃具有清晰的三层纵深:**前景少量碎片从镜头旁快速掠过;中景碎片包围车头与前轮,翻转时闪出冷白反光;背景仍有玻璃从窗框边缘脱落。碎片之间留出空隙,让白红车身始终可见。 车头、前轮、座舱、车门与后轮依次冲出。镜头短距离横移跟住车身,红色涂装从晶亮碎片之间划过。水珠从车身表面甩离,玻璃颗粒擦过车漆,窗框局部弯折,擦碰位置迸出一小束短促火星。 车厢仍在翻转,赛车持续向外前进。后轮完全越过窗框,玻璃碎片仍在身后扩散,随后恢复常速。 音效:玻璃裂纹的细密脆响、拉长的爆碎声、碎片翻飞声与低沉引擎声;末尾风声迅速恢复正常速度。 [00:05.29—00:06.50] 镜头5:重落地,车厢轰然砸下 切至赛车前侧低机位。赛车回正,轮胎依次重压路面,悬架明显压缩,车身下沉后迅速回弹。轮胎挤出扁平水花,车底与湿路短暂逼近,车辆继续向前冲。 紧接着,身后的车厢侧面砸向道路。接触边缘先发生局部挤压,随后沉重车体整体落下,外壳折出凹痕,窗框震动,残余玻璃集中脱落。冲击沿路面扬起低矮水雾、细小砂砾与少量混凝土碎屑。 车厢继续短距离擦地滑动,接触处拖出明亮火星,松动部件震颤回落。摄影机被重击带出一次短促震动,赛车清晰地冲离前景,身后的碎片和水雾形成追赶般的视觉压力。 音效:轮胎落地重响,随后车厢砸地的低频巨响、钢板挤压声、持续刮擦与玻璃雨。 [00:06.50—00:09.25] 镜头6:贴地漂移,水雾甩出弧线 前侧低位跟拍,赛车直接切入左弯。前轮转向,车尾向弯道外侧滑出,车身产生轻微侧向受力倾斜,轮胎牢牢贴住路面。 后轮甩出两道沿弯道展开的薄水雾,外侧水雾更宽,细小水滴被车尾气流拉成长尾。湿路反射随车身旋转快速变化,红色条纹、黑色轮毂和白色车体在连续偏转中保持清楚。 镜头贴近路面,前景车道线、排水口与护栏底部极速后掠,赛车在画面中保持稳定,突出背景与主体的速度反差。漂移后段,车尾逐渐收回,轮胎恢复抓地,悬架轻微回正,赛车顺势加速。 音效:强烈轮胎
A detailed prompt for a high-budget music video featuring three singers in a neon-lit nighttime city.
Create a 30-second ultra-realistic cinematic music video featuring three young adult singers performing an emotional modern song in a neon-lit city at night. The video should look like a high-budget professional music video with realistic humans, precise lip-sync, expressive performances, atmospheric lighting, and sophisticated cinematography. CHARACTERS Character 1 — Female Lead: Young adult woman, early 20s, long black hair, expressive eyes, elegant black-and-silver outfit, confident yet emotional personality. Character 2 — Male Lead: Young adult man, early 20s, dark textured hair, stylish black jacket and white shirt, charismatic and emotionally expressive. Character 3 — Female Vocalist: Young adult woman, early 20s, shoulder-length dark hair, fashionable deep-red outfit, energetic but natural stage presence. Keep their faces, clothing, hairstyles, body proportions, and identities perfectly consistent throughout the video. ENVIRONMENT A futuristic downtown street at night after light rain. Wet pavement reflecting colorful neon signs, glowing storefronts, subtle fog, distant traffic, cinematic bokeh, atmospheric city lights and realistic reflections. SHOT-BY-SHOT 0–4 sec — Opening Extreme close-up of Character 1's eyes. Neon reflections visible in her eyes. Camera slowly pulls back as she begins singing. Rain droplets sparkle in the background. 4–8 sec — Lead Performance Character 1 walks slowly down the wet street while singing directly toward the camera. Smooth backward tracking shot. Her hair moves naturally in the night breeze. 8–12 sec — Male Verse Cut to Character 2 leaning against a neon-lit building. He begins singing his section. Slow cinematic camera orbit around him, with colorful city lights blurred behind him. 12–16 sec — Female Vocalist Character 3 appears walking through the neon street. She sings while looking toward the camera. Smooth side-tracking shot transitions into a close-up. 16–22 sec — Trio Performance All three characters meet in a wide city intersection and perform together. Camera slowly circles around them while they sing. Natural interaction, subtle gestures, believable chemistry. 22–27 sec — Emotional Chorus Rapid but elegant sequence of close-ups: Character 1 singing, Character 2 joining, Character 3 harmonizing. Every mouth movement precisely follows the provided audio. 27–30 sec — Final Shot The three singers stand together in the middle of the wet street. Camera rises slowly upward and pulls away, revealing the glowing city around them. They finish the final lyric together exactly on the beat. End on a dramatic cinematic wide shot. CINEMATOGRAPHY High-end music-video cinematography, anamorphic lens look, shallow depth of field, smooth gimbal tracking, slow-motion accents, cinematic close-ups, controlled camera movement, realistic lens flares, natural motion blur, beautiful bokeh and dynamic composition.
A detailed video prompt mimicking early 2000s MiniDV home video style, featuring a woman walking through Seoul residential alleys with a narrative involving an umbrella.
GIRL / MAIN CHARACTER: Young Korean woman in her mid-20s, black hair in a loose braid, fitted pastel-lilac blouse, wide-leg beige trousers, white flat sandals, thin silver bracelet, small crossbody bag. Natural skin texture, realistic features, consistent identity throughout. LOCATION: Peaceful old Seoul residential lane on a warm evening—narrow concrete street, small houses, potted plants, parked bicycles, a convenience store on the corner, overhead wires, a few trees. STYLE: Photorealistic Seedance 2.5, nostalgic early-2000s MiniDV home video. Handheld shaky camera, imperfect framing, autofocus hunting, faded colors, soft digital image, exposure shifts, motion blur and compression noise. No modern cinematic look. ACTION (timed): 00:00–00:02 — She steps out of her house with an empty cloth bag, locks the door. 00:02–00:04 — She walks down the lane toward the corner convenience store. 00:04–00:07 — She buys eggs and bread at the store, puts them in the bag. 00:07–00:09 — She starts walking back home through the lane, umbrella still hooked over her shoulder. 00:09–00:11 — Suddenly one rib of the umbrella bends outward and it becomes lopsided. She stops and notices it. 00:11–00:13 — She tries pushing the bent rib back into place with her fingers, but it keeps popping back out. Friend filming zooms in awkwardly. 00:13–00:15 — She spots a rubber band near a parked bicycle, picks it up, wraps it tightly around the bent section. 00:15–00:17 — She opens the umbrella slightly to test it—the rib snaps loose again and the umbrella flops sideways. 00:17–00:19 — She stares at the camera, stunned, then bursts out laughing. 00:19–00:21 — She collapses the umbrella completely and holds it firmly under her left arm. The cloth bag with groceries stays in her right hand. 00:21–00:23 — She continues walking home, passes a neighbor watering plants who notices the crooked umbrella and chuckles. She shrugs and grins. 00:23–00:26 — She turns to the camera and says, "Bi-do an oneunde, deurama-네!" ("It's not even raining, and there's drama!"). She laughs. 00:26–00:28 — She reaches her house and unlocks the door. 00:28–00:30 — She walks inside. Friend remains outside filming the closed door. CONTINUITY RULE: From 00:19 onward, the umbrella stays tucked under her left arm and never touches the ground, disappears, duplicates, or reopens on its own. Groceries never disappear from the bag. FINAL FRAME: Closed door, empty lane, no umbrella left on the street. AUDIO: Natural birds, footsteps, distant traffic, bicycles, neighborhood ambience, store chime, dogs barking faintly, evening sounds. No music or narration. NEGATIVE: No disappearing/duplicating umbrella, no umbrella on the ground, no object teleportation, no missing groceries or bag, no identity drift, outfit changes, distorted hands, extra fingers, unnatural movement, CGI look, subtitles or watermark.
A hyper-realistic action video prompt depicting a young woman on a black motorcycle speeding through a modern urban landscape.
Ultra-realistic cinematic action scene of a fierce young woman riding a sleek black superbike at high speed through a modern city street, wearing a fitted black leather racing suit, black gloves, and long flowing dark hair. She leans aggressively over the motorcycle, gripping the handlebars with intense focus. Dynamic low-angle tracking shot, dramatic motion blur, warm cinematic lighting, realistic reflections on the bike, shallow depth of field, urban background, high-speed atmosphere, photorealistic skin and fabric details, professional action photography, 85mm lens, HDR, 8K, ultra-detailed, cinematic color grading, vertical 9:16 composition.
A detailed 30-second timeline prompt capturing the moment a city professional drops their coffee cup in a dramatic 360-degree frozen "bullet time" shot.
Create a 30-second cinematic bullet-time sequence in Wall Street, New York, on a wet, icy street surrounded by towering skyscrapers. The scene must remain visually consistent throughout. 0–5 sec — Establishing Shot: Start at pavement level with an ultra-low wide-angle view. Reveal the narrow financial-district street, reflective icy ground, and skyscrapers towering on both sides. A businessman in a white shirt and black tie begins losing his balance. 5–10 sec — Freeze Moment: Move into a low three-quarter angle as he falls backward. A coffee cup sits near his feet, with coffee bursting outward. At the peak of the fall, freeze the entire scene—the man, coffee, water droplets, ice fragments, clothing, and surrounding atmosphere become perfectly suspended. 10–22 sec — 360° Bullet-Time Orbit: Perform a slow, perfectly smooth 360° camera orbit around the frozen businessman at ground level. Gradually rise slightly during the orbit to reveal different perspectives of his suspended body and the frozen coffee explosion. Only the camera moves; absolutely everything else remains locked in place. 22–27 sec — Dramatic Low Angle: Transition into a low upward-looking angle beneath the frozen action. Frame the businessman against the towering buildings, creating a dramatic urban-canyon composition. Emphasize the suspended droplets and ice particles against the skyline. 27–30 sec — Hero Frame: Complete the orbit and settle into a powerful wide three-quarter shot. Hold the frozen moment completely still for the final seconds, with the businessman suspended mid-fall and the coffee splash surrounding him. Visual Style: photorealistic cinematic realism, cool overcast daylight, dramatic contrast, wet pavement reflections, subtle wide-angle lens distortion, realistic textures, controlled depth of field, premium Hollywood-style cinematography. No unwanted character movement, no background motion, no flickering, no camera jitter, and no independent movement of the frozen elements.
A 30-second high-detail gameplay demo set in Osaka featuring an elderly woman on a bicycle in a AAA open-world style.
30秒の連続映像。大阪を舞台にしたAAA級オープンワールド犯罪アクションゲーム風のプレイ映像。実写映画ではなく、最新AAAゲームの高精細なリアルタイム3DCGとして描く。人物の肌、髪、衣服、道路、車両、建物、照明、影、反射、物理挙動まで、リアルだが明確にゲームCGらしい質感で統一する。主人公の背後から追従する三人称ゲームカメラを基本とし、実際にプレイヤーが操作しているように空間と動きを連続させる。左下に小さな円形ミニマップと体力ゲージ、右上に手配度の星を表示。 舞台は雨上がりの夕方、大阪ミナミを思わせる繁華街。串カツ店、狭い商店街、派手な立体看板、雑居ビル、自動販売機、路上駐輪、電線、濡れたアスファルトが並ぶ。主人公は60歳前後の大阪のおばちゃん。短い紫がかったパーマ、金色のイヤリング、オレンジと黒のトラ柄シャツ、黒いパンツ、赤いスニーカー、斜め掛けバッグ。がっしりした体格で眼光が鋭い。乗り物は銀色の普通のママチャリ。前カゴにはスーパーの買い物袋と長ネギ。顔、衣装、自転車、小物は全編で統一する。 0〜6秒。三人称視点でおばちゃんが串カツ店の屋外カウンターに立つ。串カツを共用ソースに一度浸し、一口食べた直後、その食べかけの串をもう一度ソースへゆっくり浸す。周囲の空気が止まり、店主が絶句。近くの警察官が「二度漬けやないか!」と叫ぶ。右上の手配度が★2へ上昇。警察官がおばちゃんの腕をつかむが、おばちゃんは強く振りほどき、警察官を突き飛ばす。警察官は金属テーブルにぶつかり地面へ倒れる。重量感のある衝撃。手配度が★3になる。 6〜10秒。おばちゃんは買い物袋を拾い、店先のママチャリへ向かう。追ってくる警察官を無視し、袋を前カゴへ放り込み、自転車にまたがって全力で発進。カメラが自然に自転車後方のゲーム視点へ移行。遠くからパトカーのサイレン。 10〜17秒。おばちゃんが大阪の狭い商店街を猛スピードで逃走。現実的なペダリングで必死に加速し、服やバッグが揺れ、前カゴの長ネギが激しく振動する。後方からパトカーと警察バイクが追跡。おばちゃんは路地を急旋回し、追跡車両は急ブレーキ。濡れた路面でタイヤが鳴き、車体がカラーコーンや壁を擦る。逃走中、おばちゃんは歩行者1人にママチャリで接触して転倒させ、別の歩行者の肩をかすめる。周囲から「危ないやろ!」「何さらしてんねん!」と罵声が飛ぶ。おばちゃんも前方を見たまま「どいてや!」と怒鳴る。短くベルを鳴らし、さらに狭い路地へ突入。手配度は★4。 17〜23秒。前方を警察官2人が塞ぐ。おばちゃんは強くブレーキをかけ、濡れた路面で後輪を少し滑らせて停止。すぐにママチャリを降り、前カゴから長ネギを引き抜く。進路を塞ぐ1人目の警察官の腕を長ネギで強く叩き、そのまま顔面へ一撃。警察官はよろめいて倒れる。2人目が接近すると、おばちゃんは長ネギを横薙ぎに振り、肩から首元を打ってひるませ、さらに体当たりして地面へ倒す。ネギは大きくしなり、一部が潰れる。人体には重さがあり、大げさには吹き飛ばない。おばちゃんは乱れた長ネギを持ったまま進もうとするが、路地の出口をさらに別の警察官が塞ぎ、後方にはパトカー。完全に包囲される。 23〜30秒。BGMが静まり、サイレン、警察無線、おばちゃんの荒い呼吸が響く。警察官が慎重に近づき「もう逃げられへんで」と言う。おばちゃんは無言で斜め掛けバッグに手を入れる。警察官が緊張する。おばちゃんが取り出したのは赤い透明包装の小さな飴。肩越しのゲームカメラで、おばちゃんが低い声で「兄ちゃん、飴ちゃん食べる?」と言う。短い沈黙。警察官が飴とおばちゃんを交互に見る。おばちゃんが警察官の手のひらに飴を1個置く。警察官は少し迷い、静かに受け取る。その瞬間、右上の手配度が★★★★から★★★、★★、★、0へ順番に消えていく。サイレンも止まる。警察官は無言で身体を横へずらして道を空ける。おばちゃんは小さくうなずき、ママチャリに戻って乗り込む。警察官の横を通り過ぎながら「ほな」と一言。最後は標準的な三人称ゲーム視点に戻り、折れかけた長ネギを前カゴから突き出したまま、おばちゃんが大阪の街へ走り去る。 全編を通して、人物、街、車、自転車、衝突、衣服、表情、路面反射を最新AAAゲームのリアルCGとして描写する。犯罪ゲームらしい緊張感と重量感を保ちつつ、「串カツ二度漬け→ママチャリ逃走→ネギで警察を突破→飴ちゃんで手配解除」という異常な展開だけがシュールな笑いになる構成。
A cinematic dark fantasy prompt depicting a witch using a massive waterspout to extinguish a village fire with photorealistic effects.
Create a highly realistic cinematic fantasy video set in a medieval European village during a mysterious supernatural disaster. A young beautiful woman with pale skin, long straight black hair, wearing a large pointed black witch hat, dark black cloak and deep burgundy medieval dress, walks through a crowded medieval village while villagers stare at her with fear and suspicion. Wooden half-timbered houses, stone streets, old market stalls, medieval villagers in rustic clothing, atmospheric smoke and fog. She walks toward a massive stone archway and exits into an open courtyard overlooking the village. In the distance, several medieval houses are burning intensely, with huge orange flames and thick black smoke rising into the sky. The witch suddenly becomes supernatural and flies forward above the ground, her dark cloak and dress flowing dramatically in the wind. A gigantic magical water tornado suddenly rises in the middle of the burning village, forming a huge swirling column of water that crashes through the streets and begins extinguishing the flames. Villagers gather and look up in shock as a mysterious flying witch passes through the smoky sky. Show dramatic aerial shots of the medieval village covered in smoke and water, burning rooftops, frightened villagers, and the giant water vortex. End with a cinematic close-up of the young witch standing calmly among the villagers, looking directly toward the camera with an enigmatic expression. Photorealistic, cinematic dark fantasy, medieval Europe, realistic human faces, detailed clothing and architecture, volumetric lighting, natural fire and smoke simulation, realistic water physics, dramatic atmosphere, shallow depth of field, realistic camera movement, smooth motion, film-quality composition, high detail, 4K, anamorphic cinematic look, dramatic lighting, realistic textures, epic fantasy movie style.
A cinematic thriller prompt about a woman walking through a city on a rainy night who realizes she is being followed by a mysterious black car.
Create a 30-second ultra-realistic cinematic urban thriller following a young woman walking alone through a rain-soaked city at night. Show her leaving a crowded subway station → noticing that the street has suddenly become unusually empty → walking faster beneath her umbrella → hearing footsteps behind her → looking back but seeing nobody → turning into a narrow neon-lit street → noticing a mysterious black car slowly following her → entering a small convenience store and looking through the window → seeing the car disappear → stepping outside cautiously → suddenly hearing a loud vehicle approaching → turning around in shock as headlights fill the frame → running toward a crowded main street as the rain continues. Authentic 2026 nighttime city footage, realistic human movement, heavy rain, wet reflective pavement, glowing neon signs, passing traffic, realistic car physics, wind-reactive hair and clothing, atmospheric mist and natural environmental details. Handheld smartphone/cinema-camera style with subtle camera shake, natural autofocus, exposure changes, realistic motion blur and immersive first-person moments. Dark blue-gray atmosphere with contrasting red and orange neon lighting. Build tension gradually with natural pacing and believable reactions. English dialogue only, realistic footsteps, rain, distant traffic, muffled city sounds and subtle breathing. No background music, no CGI, no animation, no VHS aesthetic, no subtitles, no logos or watermark.
A detailed Vlog-style video prompt using reference images for character consistency while depicting a natural walk through a Korean residential area.
REFERENCE RULE: @image is the character identity reference only. Use @image every time the girl is visible. Preserve her exact facial identity, facial structure, eyes, nose, lips, skin tone, natural facial proportions, and recognizable hairstyle characteristics. Do not copy the reference image’s original pose, clothing, background, composition, or lighting. Generate all environments, actions, wardrobe, and cinematography from this prompt. STYLE Ultra-realistic Korean daily-life vlog, cinematic documentary realism, vertical 9:16, 4K, 24fps. Natural handheld smartphone camera, subtle realistic camera shake, authentic Korean neighborhood atmosphere, realistic depth of field, natural skin texture, subtle film grain. Everyday and unstaged, never glossy or commercial. CHARACTER Young Korean woman based on @image. Shoulder-length naturally messy dark-brown hair with soft texture and a few loose strands, minimal natural makeup, realistic skin. Outfit: oversized pale-blue button-up shirt, clean white T-shirt, relaxed beige trousers, white sneakers, small dark crossbody bag. Keep the same face, hair, outfit, accessories, body proportions, and age appearance throughout all 30 seconds. TIMELINE 00–02s @image opens her apartment entrance and steps outside into a quiet Korean residential neighborhood. She adjusts her crossbody bag and begins walking. Soft afternoon daylight falls between nearby buildings. 02–04s Side-following handheld shot. @image walks through a narrow residential lane with brick walls, apartment buildings, potted plants, balconies, utility poles, parked bicycles, and small Korean neighborhood signs. 04–06s She passes a small local shop. She briefly turns her head toward the window, notices something interesting inside, then looks forward and keeps walking naturally. 06–08s Lower cinematic angle focused on her white sneakers moving across the pavement. Tree branches cast moving patches of light and shadow. Her shadow moves correctly with her body. 08–10s She notices a neighbor watering potted plants outside an apartment doorway. She slows slightly, exchanges a subtle polite smile and nod, then continues walking. Keep the interaction casual and understated. 10–12s She arrives at a vending machine. Close-up of her hand selecting a cold bottled drink. The machine dispenses the bottle naturally. She picks it up and checks the condensation on the surface. 12–15s Medium tracking shot as she walks away from the vending machine holding the drink. She gently rotates the bottle in her hand while walking, sunlight reflecting naturally through the transparent plastic. 15–17s She glances down at the drink, then raises it naturally toward her lips and takes a small refreshing sip while continuing forward at the same walking pace. 17–19s Close side-profile shot. She lowers the bottle, exhales softly, and gives a tiny satisfied smile. A light afternoon breeze moves loose strands of hair and the hem of her shirt. 19–21s She passes a small neighborhood bakery-café. Through the glass window, simple pastries, bottled drinks, and everyday customers are visible. She briefly looks inside without stopping. 21–23s She notices a small wooden public bench beneath a leafy tree. She slows down and walks toward it, casually adjusting her crossbody strap. 23–25s She sits naturally on the bench beneath the tree. She places the drink beside her for a moment, relaxes her shoulders, and looks quietly toward the street. 25–27s She picks the bottle back up and takes another short sip. Close-up captures realistic condensation, fingers, bottle grip, subtle swallowing, and natural facial movement. 27–29s She looks across the street at passing cars and pedestrians, then gently smiles to herself. Sunlight moves softly through the leaves above her. 29–30s She stands, picks up her crossbody bag, and resumes walking deeper into the tree-lined neighborhood. Camera slowly follows from behind and slightly to the side, ending naturally as she moves farther down the street. CAMERA & MOTION Natural handheld smartphone/documentary cinematography. Subtle micro-shake, believable operator movement, smooth side tracking, occasional low angle, medium close-up, and gentle rear-following shot. Natural focus pulls and realistic lens behavior. No impossible camera movement, excessive stabilization, drone-like motion, or abrupt geography changes. LIGHTING & COLOR Afternoon only. Soft neutral daylight, slightly cool shadows, gentle warm highlights, realistic skin tones, muted greens, natural concrete and brick colors, restrained cinematic contrast, subtle film grain. No morning light, sunrise, sunset, heavy golden hour, orange cast, HDR, oversaturation, artificial bloom, or excessive glow. PHYSICAL REALISM Accurate walking rhythm and foot contact, realistic arm swing, correct hand-to-bottle interaction, realistic bottle weight, condensation, swallowing, hair movement, fabric movement, shadows, reflections, and object permanence. Environmental elements remain spatially consistent from shot to shot. AUDIO Natural location sound only: footsteps on pavement, distant Korean traffic, bicycle bell, leaves rustling, watering hose, vending-machine beep, bottle dispensing sound, bottle cap click, subtle sipping/swallowing, café ambience, soft neighborhood sounds. No background music, no narration, no dialogue.
A detailed scene breakdown of a cinematic handheld vlog featuring an East Asian couple's urban adventure using an ultra-wide fisheye lens.
Subject A young East Asian woman with long black hair styled in a braid, wearing a white t-shirt with a blue logo, cross earrings, and a necklace, and a young East Asian man wearing a light blue t-shirt with a matching logo, riding and walking together on a vlog adventure. Style Cinematic handheld vlog aesthetic captured through an ultra-wide fisheye lens, featuring natural street lighting, authentic skin tones, and dynamic movement. Camera & Framing Lighting consists of bright outdoor daylight and indoor convenience store illumination. Framing utilizes close-up POV selfie-cam angles, wide tracking shots, and fish-eye booth camera perspectives. Audio Ambient street sounds, laughter, shutter clicks from a photo booth, and casual conversation. Realism Photorealistic 8K rendering with natural fabric textures, organic motion blur, and authentic handheld camera physics. Detailed Scene Breakdown 00:00 - 00:02: Close-up POV selfie shot of the woman smiling outside a doorway, turning around as a young man rides up on a white scooter and waves. 00:03 - 00:04: Medium tracking shot of them walking together down a narrow alleyway lined with green vines, ending with a hand blocking the camera lens playfully. 00:05 - 00:08: Fisheye close-up inside a photo booth where both lean in close, making funny expressions, smiling, and bursting into laughter. 00:09 - 00:11: Medium shot of them standing on a city street at dusk, holding up a strip of printed photo booth pictures and laughing together. 00:12 - 00:14: Medium shot inside a convenience store aisle where the man grabs a bottled drink from a refrigerated cooler while shopping with a red basket.
A prompt for generating hyper-realistic archival footage of 1989 West Berlin street life, featuring period-accurate vehicles and handheld camera motion.
Create a 30-second, 16:9, 1080p ultra-photorealistic archival video of everyday Berlin street life in 1989. The entire video must look like genuine footage recorded in 1989 with an unusually good professional video camera. It should feel like a real archival recording that has been digitized in HD, not a modern recreation, not a movie, and not an AI-generated vintage filter. **MAIN FOCUS:** The video is primarily about ordinary daily life on the streets of West Berlin in 1989. Crowded sidewalks, people walking in different directions, period-correct taxis (Mercedes W123s), Trabants and Wartburgs passing through traffic, buses, storefronts, street vendors, newspaper kiosks, and the constant movement of the city. The camera should feel like someone documenting the everyday routine of Berlin, not showcasing its architecture or politics. **SCENE SEQUENCE:** - **0–5s:** Street-level view from a busy West Berlin sidewalk (e.g. near Kurfürstendamm). A crowd of pedestrians walks past the camera in both directions. Mercedes taxis, Trabants, and older European cars move through the street. Natural handheld camera movement. - **5–10s:** A crowded avenue intersection. People wait at the crosswalk, then begin crossing. Buses, taxis, and traffic move through the frame. The camera slowly pans with the street activity. - **10–15s:** A closer street-level view of everyday pedestrians, storefronts with German signage, newspaper kiosks, and passing cars. People carry shopping bags, talk to each other, and go about their normal routines. Natural, unscripted-looking movement. - **15–20s:** A slightly wider street view showing a busy Berlin avenue filled with pedestrians and traffic. Buildings are visible only as part of the background. A section of the Berlin Wall or period signage may appear naturally in the distance, but the street activity remains the focus. - **20–25s:** Another crowded sidewalk and intersection. Trabants, taxis, buses, pedestrians, and storefronts create a constantly moving urban scene. The camera gently follows the flow of people. - **25–30s:** Final street-level view of a busy avenue, with pedestrians crossing, cars passing, and traffic continuing naturally. End like a real archival recording, without a dramatic cinematic conclusion. **CAMERA & CINEMATOGRAPHY:** Real 1989 professional video-camera footage. Mostly street-level, eye-level, and slightly elevated sidewalk viewpoints. Natural handheld and vehicle-mounted camera movement, slow pans, gentle zooms, slight camera vibration, occasional imperfect framing, and realistic motion blur. The camera should feel operated by a real person filming the city, with small imperfections and natural timing. No modern drone footage, no gimbal-smooth movement, no impossible camera angles, and no dramatic cinematic camera moves. **IMAGE QUALITY:** Surprisingly sharp
A multi-scene cinematic fashion prompt set in Chicago, focusing on hyper-realistic textures and professional camera work.
Seedance 2.5 — Chicago Fashion Film Visual quality: Hyper-realistic live-action fashion film. [character] is beautiful with model-like features. Real natural skin texture, pores, fine facial detail, and realistic light response. No fake skin, no plastic skin, no waxy skin, no overly smooth skin, no animated look, no CGI-looking face. Natural expressions and movement. No facial warping, morphing, or identity drift. Spectacular polished cinematography. Performance: Keep [character] relaxed and natural. Most of the video is candid fashion-film movement rather than posing for the camera. She should only make direct eye contact when it naturally fits the shot. Scene 1: [character] walks directly toward camera beneath the elevated Chicago L tracks, framed symmetrically beneath the dark steel structure. Wide frontal view, urban street activity behind her, confident natural walk. Scene 2: Cut to a side-profile tracking shot of [character] walking through a narrow downtown alley beside a long brick wall covered in graffiti. She continues forward naturally, occasionally adjusting her hair or casually moving one hand as she walks. Scene 3: Cut to [character] crossing a wide downtown Chicago intersection, shown mostly from the side as she walks through the crosswalk. Tall reflective glass buildings, traffic, and city architecture surround her. Scene 4: Cut to [character] outside a modern fashion or streetwear storefront. She casually hangs out with a small group of stylish female friends with model-like features, talking, smiling, and reacting naturally to one another while pedestrians continue along the sidewalk. Keep the same relaxed sidewalk-group composition as the reference. Scene 5: Cut to [character] standing on an elevated Chicago L platform beside a silver train. She waits casually near the train, relaxed posture, looking briefly along the platform before turning her attention forward. Scene 6: Quick cut to [character] walking along a downtown sidewalk beside large glass storefront windows. Then another quick walking transition to a Chicago waterfront promenade, with the downtown skyline dramatically visible across the water. She walks naturally through the environment just as in the reference. Scene 7: Cut to a wide view of [character] standing alone in the middle of an industrial Chicago street lined with red-brick buildings and overhead steel structures. The camera steadily moves closer from the wide shot into a tight portrait of her face. As the camera reaches her, she looks directly into the lens
A creative prompt for a modern travel vlog set in the ancient Maurya Dynasty, featuring historical architecture and realistic handheld camera work.
cinematic, ultra-realistic vlog video of me exploring the ancient Indian Maurya Empire at its peak. Preserve my exact face, identity, and appearance from the reference image. Show me holding the camera and casually vlogging while walking through a bustling Pataliputra, surrounded by grand Mauryan architecture, wooden palaces, stone pillars, markets, elephants, soldiers, merchants, monks, and everyday citizens in historically inspired clothing. Use natural handheld vlog camera movement, authentic reactions, immersive crowd activity, warm golden-hour sunlight, atmospheric dust, realistic textures, shallow depth of field, cinematic lighting, and photorealistic historical detail. Make it feel like I genuinely travelled back in time and filmed a modern travel vlog inside the Maurya Empire. No modern objects, vehicles, buildings, or technology visible except the implied vlog camera
A cinematic anime video prompt set in dark, foggy Victorian London alleys with atmospheric lighting and wet cobblestones.
Cinematic anime clip, 15 seconds. Dark foggy Victorian London alley, wet glistening cobblestones, warm orange gas lamp glow, tall dark brick buildings either side. One location throughout. SHERLOCK: Lean angular white male, sharp dark eyes, light stubble,
A raw, home-video style prompt capturing a young woman walking to a convenience store on a rainy night in Osaka.
Day 1 — “Rainy Convenience Store” Create a 30-second, 16:9, 1080p ultra-photorealistic personal home-video capturing an ordinary rainy evening in the life of a young Japanese woman. The footage should feel spontaneous and genuinely recorded by a friend, not like a commercial or music video. MAIN SUBJECT Young Japanese woman in her early 20s, naturally attractive, realistic skin texture, minimal makeup, relaxed and slightly playful personality. Shoulder-length dark-brown hair worn loosely with natural flyaways and slightly damp strands from the rain. Wearing a muted sage-green lightweight hoodie, relaxed dark denim jeans, white canvas sneakers and a thin silver necklace. Maintain the same face, hairstyle, clothing, body proportions and overall appearance throughout the entire video. SETTING A quiet older residential neighborhood in Osaka during a warm summer evening after rainfall. Narrow wet streets, small residential buildings, vending machines, bicycles under awnings, utility poles, tangled overhead cables, parked scooters, rainwater running beside the pavement, small plants outside homes and a modest neighborhood convenience store. The environment should feel lived-in and ordinary. Avoid famous landmarks, recognizable brands, advertisements or tourist locations. CAMERA / VISUAL AESTHETIC Raw personal footage casually recorded by a friend on a small early-2000s consumer digital camcorder. Handheld movement, imperfect framing, occasional autofocus hunting, slight exposure pumping, mild motion blur, soft digital detail, faded colors, subtle sensor noise, accidental zoom adjustments and realistic camera-handling movements. The camera operator should sometimes react slightly late to her movement. No gimbal, no stabilization, no drone shots, no cinematic lens effects, no polished commercial cinematography. 00–05s — LEAVING HOME She opens the front door of a small apartment building and steps underneath the awning. Rain is falling steadily outside. She checks the sky, pulls her hood loosely over her head and looks toward the camera with a small amused smile. She says: “I thought it stopped raining.” She steps carefully onto the wet pavement. 05–10s — WALKING THROUGH THE RAIN The camera follows beside her as she walks down the narrow residential street. Her sneakers make small splashes through shallow puddles. She passes parked bicycles covered with rain droplets. A scooter moves through the background, briefly spraying water from the road. She adjusts her hoodie sleeve while walking. The camera briefly loses focus on her and focuses on a nearby rain-covered bicycle before recovering. 10–15s — CONVENIENCE STORE STOP She notices a small convenience store ahead. She walks inside while the camera remains just outside the entrance for a moment. Warm interior lighting contrasts naturally with the cool rainy street. She comes back out holding a small transparent plastic bag containing a bottled drink and a
先选择与目标相符的示例,清楚描述主体和预期结果,再补充视频生成所需的构图、镜头、光线、音频、运动或版式细节。生成前请替换产品、品牌、参考素材和对白变量。
打开卡片,对照预览与原始写法,再将原始 Prompt 复制到 Topview AI 或兼容的生成器中。请根据项目调整参考素材、限制条件和风格说明。
请将每条提示词视为经过展示的示例或起点,而不是结果保证。应根据所选模型检查品牌准确性、版权、安全性和生成能力。
可以。媒体主页会链接到独立分类页;每个分类页只保留一种分类条件,使示例范围和搜索意图更加清晰。
当前提示词库包含 Seedance 2.5, Seedance 2.0, Wan 3.0, GPT Image 2, Nano Banana Pro, Gemini Omni, Grok Imagine 的示例,具体可用内容会随媒体类型和筛选条件变化。
当前浏览“Cityscape Urban”主体分类下的视频提示词。