Rainy Cafe Terrace Two-Angle Split Screen Video

1Medium Shot / Eye LevelSlow Push-InA young male barista stands behind the counter of a modern industrial-style café. Morning sunlight streams through large glass windows, creating soft volumetric light rays. He wears a black turtleneck sweater with a gray apron, giving the scene a premium and calm atmosphere. Lo-fi electronic beat begins; subtle café ambience2s 2Extreme Macro / Low AngleStaticBottomless portafilter extraction begins. Rich espresso flows down like molten lava, layered with thick golden crema. Amplified espresso extraction sound1s 3Close-Up / Side ViewSlight TrackingThe steam wand froths milk inside a stainless steel pitcher. White steam surrounds the pitcher while the milk spins into a silky microfoam texture. Crisp high-pressure steam “hiss” sound1s 4Close-Up / Top-Down AnglePush-InThe barista begins pouring latte art. Smooth white milk flows precisely onto the espresso surface, gradually forming a galloping horse pattern. The coffee reflects warm amber highlights with ultra-detailed liquid. intensifies slightly; delicate pouring sound3s 5Close-Up / Eye LevelRack FocusThe finished latte is gently placed on a wooden counter. The camera first focuses on the perfect horse latte art, then slowly shifts focus to the barista’s satisfied smile in the background. Soft ceramic cup “clack” sound; music fades gently3s Pacing Simplified the workflow into the essential visual sequence: Extraction → Milk Frothing → Latte Art → Final Reveal Faster rhythm optimized for: TikTok Instagram Reels Xiaohongshu AI-generated short-form videos Visual Focus Key visual highlights: Golden espresso crema Silky milk texture Galloping horse latte art reveal Emotional rack-focus ending AI Video Generation Keywords cinematic coffee shop macro latte art espresso extraction shallow depth of field warm sunlight volumetric lighting creamy milk texture ASMR coffee sound cinematic rack focus ultra realistic cozy industrial café 85mm lens soft amber tones high-detail liquid simulation

写实奇幻短片。女主的脸严格参考特写，身材、发型和服装严格参考 {{Mixed 1}} 全身。她全片只穿参考图中的灰蓝色风衣、白色圆领上衣、深蓝色牛仔裤和黑色短靴，右耳银色圆形耳钉始终存在。透明雨伞严格参考 {{Mixed 2}} 撑开，八根银色伞骨、5毫米黑色包边、银色中杆和黑色J形手柄不得改变。路口建筑位置、斑马线方向、红色交通灯、粉紫色橱窗光和湿地面反光严格参考 {{Mixed 3}} 。\n\n女主全片左手持伞，左手始终握住黑色J形手柄，右手只负责打响指和触碰气球。镜头始终位于道路西侧并朝东拍摄，不越过斑马线中轴，不发生跳轴。场景中增加约20名普通行人和6辆汽车，行人服装为低饱和灰、蓝、棕色，不得出现与女主相同的灰蓝色风衣。红色气球只有一个，直径约35厘米，系着一根80厘米长的白线。\n\n0至6秒，镜头高度1.6米，35mm镜头，稳定器跟拍。女主从画面底部中央进入，沿斑马线向东直走4米，速度约每秒0.7米。她左手撑伞，右臂自然摆动。背景行人和车辆正常通过，地面没有新的雨滴，环境声为轮胎压过湿路面、脚步声和远处交通声。\n\n6至10秒，女主在斑马线中央停下，身体仍面向东方。镜头移动到她右前方约2米处，改用50mm中景。她抬起右手，用拇指和中指打一次响指。响声出现的同一帧，所有背景行人、车辆轮胎、衣角和水面波纹停止运动。一个红色气球停止在女主右前方约1米、离地1.6米的位置。女主和她的头发、风衣下摆仍可正常运动。\n\n10至13秒，镜头以每秒0.5米的速度向右平移，保持女主腰部以上中景。女主朝气球走三步，左手继续持伞。13秒结束时，女主站在气球左侧，右手食指伸出，指尖距离气球表面约5厘米。\n\n13至16秒，镜头继续向右平移，不切镜。女主右手食指向前移动5厘米并触碰气球一次。接触点先出现直径约3厘米的透明区域，随后透明区域在1.5秒内均匀扩展到整个气球。气球外形、直径和位置保持不变，只把红色橡胶材质变成无色透明玻璃材质。变化完成后，气球内部出现一尾约8厘米长的金色小鱼，小鱼面向画面右侧，摆尾一次。白色气球线保持原状。\n\n16至21秒，女主收回右手，向后退半步，抬眼观察透明气球。镜头停止平移，保持50mm中景。透明气球、金色小鱼、女主和雨伞的位置连续，背景仍完全静止。\n\n21至25秒，女主再次用右手打一次响指。响声出现的同一帧，背景行人和车辆恢复原来的运动方向与速度。透明气球垂直上升约1.5米，气球内部的金色小鱼化成一个直径2厘米的金色光点，从气球右侧穿出。\n\n25至30秒，镜头以连续运动升高到离地6米，镜头向下倾斜约35度，仍保持斑马线中轴和女主位于画面中央。女主站在原地抬头，透明伞从高处看是完整圆形。金色光点沿画面右上方飞出，在29秒时熄灭。30秒停在女主与斑马线的高位全景，不黑场。\n\n全片保持女主脸部、耳钉、发型、服装、身高、雨伞结构和左右手分工连续。禁止女主换脸、换装、换手持伞、雨伞伞骨增减、红色气球复制、透明气球尺寸变化、金鱼出现在气球外、人物穿模、汽车穿过人物、镜头跳轴、突然切镜、字幕、文字、logo和水印。38:Tf3a,Realistic fantasy short film. The female lead's face strictly follows the close-up, while her body, hairstyle, and clothing strictly follow {{Mixed 1}} full body. She wears only the grey-blue trench coat, white crew-neck top, dark blue jeans, and black ankle boots from the reference image, with silver round stud earrings in her right ear throughout. The transparent umbrella strictly follows {{Mixed 2}} opened, with eight silver ribs, 5mm black piping, a silver center pole, and a black J-shaped handle that must not change. The intersection building positions, crosswalk direction, red traffic light, pink-purple window light, and wet ground reflections strictly follow {{Mixed 3}}.\n\nThe lead holds the umbrella in her left hand throughout, always gripping the black J-shaped handle, while her right hand is only for snapping fingers and touching the balloon. The camera is always on the west side of the road shooting east, not crossing the center axis of the crosswalk or jumping the axis. The scene includes about 20 ordinary pedestrians and 6 cars; pedestrian clothing is low-saturation grey, blue, and brown, and must not include the same grey-blue trench coat as the lead. There is only one red balloon, about 35cm in diameter, tied with an 80cm white string.\n\n0-6s: Camera height 1.6m, 35mm lens, stabilizer tracking. Lead enters from bottom center, walking east 4m along the crosswalk at ~0.7m/s. Left hand holds umbrella, right arm swings naturally. Pedestrians and cars pass normally, no new raindrops, ambient sound of tires on wet road, footsteps, and distant traffic.\n\n6-10s: Lead stops at crosswalk center, still facing east. Camera moves to ~2m in front and to her right, 50mm medium shot. She raises her right hand and snaps her thumb and middle finger. At the same frame as the snap, all pedestrians, car tires, clothing edges, and water ripples stop moving. A red balloon stops ~1m in front of her right side, 1.6m above ground. Lead, her hair, and trench coat hem move normally.\n\n10-13s: Camera pans right at 0.5m/s, keeping medium shot from waist up. Lead takes three steps toward the balloon, left hand still holding the umbrella. At 13s, she stands to the left of the balloon, right index finger extended, tip ~5cm from balloo

UGC handheld video in an Indonesian home desk setup, hands-only casual creator style. Person shows a white Harvestside Arabica Instant Coffee pouch and a Diamond Fresh Milk carton clearly to camera, using the provided product images as faithful references for the coffee pouch and milk carton. Make iced kopi susu in a clear glass with visible ice on a cozy desk. Natural morning lighting, realistic phone camera, slight handheld movement, cozy bookshelf background, authentic Indonesian UGC, no studio look, no polished commercial lighting. Sequence for an 8-second 9:16 Seedance 2.0 video: First 1.5 seconds: hands hold both products close to camera with readable labels. Next 2 seconds: the Harvestside coffee pouch is standing upright on the desk, opened neatly at the resealable zip top. A small spoon scoops instant coffee powder from inside the pouch and adds it into the clear glass with ice. Do not pour coffee directly from the pouch, do not tear or rip the pouch, and do not show the pouch as a drink container. Next 2 seconds: pour Diamond Fresh Milk from the carton into the glass, creating a creamy coffee swirl. Final 2.5 seconds: close-up of the finished iced kopi susu on the desk with both product packages beside the glass. Soft upbeat morning lo-fi music background, natural ambient home mood, clean wholesome beverage preparation. Keep product labels faithful to the reference images.

Use Image A and Image B as the two main characters in all shots. Image A{{image A }}: preserve her exact anime illustration identity, hairstyle, face, blue flower hair accessory, outfit, proportions, and overall design. Image B{{image B }}: preserve her exact anime illustration identity, hairstyle, large striped ribbon, twin-bun hairstyle, face, gothic striped outfit, proportions, and overall design. Both characters must remain anime-style illustrations with crisp clean line art, cel-shaded flat colors, expressive anime eyes, and zero photorealism on the characters. All other elements — the SNS-worthy cafe interior, marble tables, glass parfait cups, fruit, cream, gold leaf, desserts, plates, drinks, windows, lighting, other customers, plants, reflections, and background architecture — are fully photorealistic. Setting: a trendy Instagrammable cafe in the afternoon. Soft natural sunlight through large windows, pastel decor, marble tabletops, elegant dessert displays, hanging plants, glass shelves, warm bokeh lights, stylish customers in the background, cozy but luxurious atmosphere. The mood is cute, fashionable, cheerful, and dreamy. Seating layout must remain fixed in every shot. Image A always sits on the viewer-left / camera-left side of the table, closer to the window side. Image B always sits on the viewer-right / camera-right side of the table, closer to the cafe interior side. They are seated side by side on the same elegant sofa bench, not facing each other across the table. The ultra-luxury oversized parfait is placed on the marble table directly in front of them, centered between Image A and Image B. Do not swap their seats. Do not change their left-right positions. Do not make Image A appear on the right side. Do not make Image B appear on the left side. Maintain the 180-degree rule throughout the video. The camera may push in, pull back, tilt, or gently slide sideways, but it must never cross to the opposite side of the table. Avoid full orbit shots around the table because they may reverse the characters’ positions. The main dessert is an ultra-luxury oversized parfait placed between the two girls: a tall crystal glass filled with many colorful layers of strawberry jelly, vanilla cream, chocolate mousse, fresh strawberries, blueberries, melon, peach slices, macarons, wafer sticks, glossy sauce, whipped cream, edible flowers, sparkling sugar, and delicate gold leaf. The parfait should look huge, premium, photorealistic, and extremely SNS-worthy. 15-second cinematic video, 24fps, smooth motion, clear emotional flow, character consistency across all shots. Shot 1 [CAFE ENTRANCE — DISCOVERY] Image A and Image B enter a beautiful SNS-worthy cafe together. They look around with sparkling eyes, impressed by the stylish interior and dessert display case. The camera tracks backward in front of them as they walk inside. Other customers and cafe staff move naturally in the photorealistic background. Their expressions show curiosity and excitement. Cut to Shot 2 [TABLE SEAT — THE PARFAIT ARRIVES] The two girls sit side by side on the same elegant sofa bench at a marble cafe table near a large sunlit window. Image A is on the viewer-left / camera-left side, closer to the window. Image B is on the viewer-right / camera-right side, closer to the cafe interior. A waiter places an ultra-luxury oversized parfait in the center of the table directly in front of them. Image A leans forward with delighted surprise. Image B’s eyes widen softly, looking amazed. Close-up on the enormous parfait sparkling under the cafe lighting, then cut to their happy faces. Cut to Shot 3 [SNS MOMENT — TAKING PHOTOS] Image A and Image B excitedly admire the parfait before eating. Image A gently adjusts the angle of the parfait slightly, while Image B holds up a smartphone to take a cute photo. The parfait glows beautifully with fruit, cream, macarons, edible flowers, and gold leaf. The camera slowly pushes in and gently slides from left to right without crossing the table axis, keeping Image A on the viewer-left and Image B on the viewer-right at all times. Their mood is playful, stylish, and excited. Cut to Shot 4 [FIRST BITE — SWEET HAPPINESS] Both girls pick up their spoons and take their first bite of the parfait. Image A smiles softly with a calm, elegant expression. Image B reacts with a bright, adorable smile, clearly enjoying the sweetness. Close-up on spoons scooping cream, fruit, jelly, and chocolate layers from the parfait. Their hands should remain natural and correctly drawn. Focus on their expressive anime eyes and joyful reactions. Cut to Shot 5 [CAFE JOY — SHARING THE MOMENT] The two girls continue eating the luxurious parfait together, laughing gently and chatting. Image A points at a cute macaron decoration on top of the parfait. Image B happily reacts and leans in slightly while smiling. The camera pulls back into a wide cinematic shot: the two anime-style girls seated at the center of a dreamy photorealistic cafe, surrounded by warm sunlight, pastel decor, desserts, and soft bokeh lights. End with a gentle crane-out while keeping the camera on the same side of the table so Image A remains on the left and Image B remains on the right. Emotional tone: cute, cheerful, luxurious, stylish, friendly, dreamy, and SNS-worthy. Focus on the girls’ expressions at every beat: curiosity, surprise, delight, sweetness, and relaxed happiness. Keep Image A and Image B visually consistent in every shot. Do not change their outfits, hairstyles, accessories, proportions, or core design. Do not make the characters photorealistic. Avoid outline jitter, flicker, warped hands, extra fingers, extra limbs, distorted faces, melting desserts, or inconsistent character details. The parfait must remain photorealistic, tall, luxurious, colorful, and visually delicious throughout the video. Background customers should move naturally and realistically, without drawing attention away from the two girls and the parfait.

SCENE CONTEXT A young Japanese man carries an exhausted young woman in his arms through the rain into an old wooden watchtower shelter. He lays her on a wooden bench, then removes his own coat and wraps it around her so she won't feel the cold, before moving to guard the door — staying alert until he finally rests too, a respectful distance kept throughout. Photorealistic, cinematic movie-scene quality, real Japanese actors, not anime/illustrated. ACTIVE REFERENCES <<<image_3>>>: young Japanese man, damp black hair, dark coat over tunic, protective carrying posture, real human skin texture. 100% matches reference. <<<image_1>>>: young Japanese woman, damp dark hair, kimono-style travel robes, eyes closed, limp and shivering in his arms. 100% matches reference. <<<image_2>>>: wooden Japanese watchtower interior. 100% matches reference, consistent across all shots. LOCATION MAP - Old sliding wooden door, ajar, rain/wind leaking through. - Narrow window slit, storm-grey light, occasional lightning flicker. - Paper lantern (chochin) hanging from a beam — main light source. - Rough wooden walls, old crates, straw mat in corner. - Worn wooden bench where she's laid down. - Puddle near door threshold, lantern reflection. FIRST FRAME He steps through the doorway carrying her, her head against his chest, both drenched, rain visible behind, lantern light on their faces. FORMAT MODE Four-shot sequence, HARD CUTs at 3.5s, 7.5s, 11.0s. Handheld only for carry shot. Photorealistic, natural skin/fabric physics. No subtitles, no music. OPTICS & CAMERA Shot 1 (carry): 50° FOV, 1.5–2m, gentle handheld follow as he enters. Shot 2 (lay down): 56° FOV, 1–1.3m, push-in as he lowers her onto the bench, faint shiver visible. Shot 3 (coat cover): 60° FOV, 2m, three-quarter angle as he removes his coat and wraps it around her, tucking the edges in. Shot 4 (guard, then sleep): 63° FOV, low near door, crane-up to high three-quarter — him now coatless at the door, staying alert, finally closing his eyes to sleep, her warm and undisturbed on the bench. ACTION TIMING 0–3.5s: he carries her in through the rain, her head lolling against his chest. 3.5s CUT. 3.5–7.5s: he lays her on the bench, a small shiver crossing her. 7.5s CUT. 7.5–11.0s: he takes off his coat, wraps it snugly around her. 11.0s CUT. 11.0–15.0s: coatless, he sits guard at the door, alert despite the cold, then eyes close as he finally falls asleep — she stays warm, a clear gap kept between them. PHYSICS Real dead-weight in the carry, wet hair swaying. Coat drapes and settles naturally around her. His bare tunic shows subtle cold response — slight shoulder hunch — through the guard shot. LIGHTING Cinematic low-key, warm lantern glow vs cool blue-grey storm light through the window/door. Faces stay readable, natural film grain, never flat or CG-looking. AUDIO Rain, footsteps, effortful breath72:Tb63,SCENE CONTEXT A youn

[PROJECT TYPE] Text-to-video. 30-second cinematic action sequence. Intense kung fu battle. [Global Setting] Traditional Chinese temple courtyard at dusk. Stone ground, red lanterns, ancient pillars. Dramatic atmospheric lighting. Gritty realistic combat cinematography. [Character 1 Master Martial Artist] Age 35-40, lean muscular build, traditional black kung fu gi, intense focused eyes, weathered face. Precise controlled movements. Absolute master of combat. [Character 2 Multiple Opponents] 3-4 trained fighters in red/dark gi attacking simultaneously. Skilled but facing a master. Brutal choreography. [Scene Description] [Opening, 0–3s] Wide shot of temple courtyard. Master stands alone, perfectly still, centered. Opponents circle him from all angles. Tension building. Rain begins falling. The master's breathing is calm and controlled. Opponents tense, ready. Silence before the storm. [First Exchange, 3–9s] FIRST OPPONENT ATTACKS fast combination of kicks and punches. Master sidesteps with minimal movement, pure efficiency. Counter-strike master's hand snaps out HARD, opponent staggers backward violently. Second opponent presses in from different angle. Master blocks incoming kick with explosive impact (sparks from boot contact on stone). Sweeping kick from master opponent flies backward, crashes into pillar. HARD impacts, no mercy. Fast-cut action, realistic combat sounds. [Escalation, 9–18s] Multiple opponents attack SIMULTANEOUSLY now coordinated assault. Master becomes ABSOLUTE WARRIOR. Rapid-fire strikes and blocks. Every movement is purpose-driven and brutal. One opponent launches spinning kick master catches the leg mid-spin and THROWS them across the courtyard (hard slam on ground). Another attacks master's palm strike connects with chest , opponent drops gasping. Third opponent attempts combo master weaves through each strike with minimal energy expenditure, then delivers devastating elbow strike to the face. Blood. Gritty realistic impacts. Master is untouched, breathing controlled. Opponents are outmatched completely. [SLOW-MOTION PEAK, 18–24s] Final standing opponent makes last desperate attempt launching powerful overhead strike. Time slows to 40% speed. Master's hand rises in perfect defensive position. Slow-motion shows the IMPACT the sound echoes, slow and resonant. Master's muscles tense absorbing the strike. Master's face shows absolute concentration. Then master's OTHER hand moves in slow-motion palm strike aimed at opponent's chest in devastating counter. Slow-motion shows the movement trajectory, the focus, the power building. Impact happens in slow opponent's body recoils violently. Return to normal speed. [Final Moment, 24–30s] Last opponent flies backward, crashes hard against stone wall, crumples to ground. All opponents are down. Master stands in center of courtyard, completely untouched, breathing steady. Rain falling on his face. His expression is calm but intense. He takes one slow controlled breath. Stone ground is marked with impact points. Red lanterns flicker in wind. Master's presence is absolute and undeniable. Final frame: master looking directly forward, absolute confidence and skill. [Audio] Rain falling. Tense atmospheric buildup. Master's controlled breathing. Opponent footsteps and positioning. HARD impact sounds (realistic, meaty, brutal — not cartoonish). Bone-on-bone cracks. Heavy breathing from opponents. Master's breathing calm throughout. During slow-motion: all sounds deepen and stretch (impact becomes resonant). Final moment: just rain and master's steady breathing. [Visual Style] — Cinematic realistic martial arts — Dynamic camera angles (tracking, close-ups, wide shots) — Slow-motion on key impacts — Rain and atmospheric lighting — Blood and gritty realism — Precise choreography showing skill — Temple setting cinematic framing — Master dominates completely [Tone] Serious, brutal, masterful. This is a display of absolute martial skill. Respect for the combat but no mercy. Dark and gritty. The master is unstoppable. [Consistency] — One master throughout (untouched, calm) — Multiple opponents (becoming increasingly desperate) — Temple courtyard location — Rain constant — Action escalates then peaks — Master's superiority clear — Realistic brutal combat

A young East Asian woman riding a bicycle through quiet city streets, casually exploring the neighborhood, cinematic, natural daylight, realistic, smooth camera movement.

Girl from the attached ref images is break dancing on a flattened cardboard box on a bustling NYC sidewalk in 1993

Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.

A cheerful and attractive American female influencer is filming a UGC-style video in a cozy, sunlit bedroom, speaking directly to the camera while casually going through her morning routine. The video feels natural and unfiltered, like a real moment from her day rather than staged content. She speaks in clear English with a natural American accent, using a calm, friendly, and relatable tone. She is wearing a soft, minimal lounge outfit—like an oversized sweater and shorts—with natural, no-makeup makeup and slightly messy hair. She smiles gently, occasionally adjusting the camera or sipping from a mug while talking. She says: "I don’t know who needs to hear this, but you don’t have to have your life together by 9am. Some days I wake up slow, take my time, and honestly… those days feel the best." The room is softly lit with natural sunlight coming through a window. Background is minimal—bed, plant, maybe a mirror. Camera shot: handheld, slightly shaky front-facing camera, medium close-up. Overall style: cozy, real-life, soft aesthetic. Language: English Accent: American Tone: calm, comforting, relatable Speaking speed: slow to natural

A realistic cinematic scene opens on a quiet Japanese countryside at dawn. Mist clings to rice paddies. A bullet train appears as a distant silver streak on the horizon. The camera launches forward at impossible speed, racing alongside the train, matching its velocity. The camera then punches through the window glass in one seamless motion and enters the cabin interior. Inside, everything is calm. A woman sits by the window, sipping tea, completely still. Steam rises slowly from her cup. The camera drifts past her face, catches the blur of the landscape reflected in her glasses, then exits through the opposite window. Outside again, the camera spirals around the full body of the train at high speed before pulling far back to reveal the train crossing a massive bridge over a turquoise river valley. End on a wide aerial shot, the train now small again, disappearing into a mountain tunnel. Silence except for a single distant horn echo.

Ultra-cinematic anime realism scene of a beautiful anime girl sitting alone beside the window inside a moving night train during heavy rain. Soft neon reflections from Tokyo city lights glow across the wet train windows while raindrops slowly slide down the glass. She has long dark flowing hair, expressive emotional eyes, and wears a cozy oversized hoodie with headphones around her neck. The atmosphere feels melancholic, peaceful, and deeply cinematic. The train interior is dimly lit with warm ambient lighting, creating contrast against the cold blue rain outside. Camera slowly pushes toward her face as she quietly watches the city pass by. Reflections flicker across her eyes while distant lightning softly illuminates the cabin. Detailed anime realism style, emotional storytelling, shallow depth of field, smooth camera motion, realistic rain physics, cinematic composition, ultra detailed textures, soft film grain, volumetric lighting, dreamy atmosphere, Makoto Shinkai-inspired visuals, high motion quality, masterpiece anime cinematography. 15-second sequence with: 0–5s: Side profile close-up with rain on window 5–10s: Camera pans outside showing neon city reflections and passing trains 10–15s: Emotional close-up as she gently smiles while thunder lights up the scen