Architecture Interior için Video promptları

Cinematic photorealistic film still of a young East Asian woman with long straight black hair, cracked round wire-rim glasses, dirty face with orange soup stains, wearing a stained oversized olive green military jacket over a messy white collared shirt and dark clothes, sitting at a rusty wooden desk in an abandoned dilapidated classroom with peeling walls, broken ceiling, chalkboard drawings of schoolgirls behind her, holding a glass laboratory beaker filled with chunky orange tomato soup and greens, melancholic distant expression, looking slightly to the side, golden hour sunlight streaming through torn white fabric hanging over large broken windows, plants growing inside the ruined building, dusty atmospheric haze, shallow depth of field, moody post-apocalyptic survival aesthetic, high detail, 35mm film grain

CHARACTER REGISTRY: Exactly one adult male mountain warrior. He has a compact, broad and extremely powerful build. He wears an original dark gunmetal suit of medieval fantasy plate armor: enclosed pointed helmet, layered shoulder plates, articulated arm protection, heavy gauntlets, reinforced breastplate, leather waist panels, dark trousers, steel greaves and heavy armored boots. His armor is weathered, scratched and wet from the storm. He carries exactly one enormous two-handed warhammer. It has one long reinforced dark-metal shaft and one heavy symmetrical rectangular hammer head. The weapon remains the same length, shape and weight throughout. He controls it with both hands during jumps, climbing and striking. Exactly one colossal organic humanoid giant, more than thirty times the warrior’s height. It has immense muscular shoulders, extremely long arms, huge humanlike hands, coarse charcoal-gray skin, visible pores and scars, a heavy brow, broad nose, powerful jaw and long tangled black hair. It is an organic living titan—not a statue, robot, machine or stone golem. No additional warriors, giants or background armies. ENVIRONMENT: A windswept highland battlefield beneath a violent blue-gray thunderstorm. The uneven ground is covered with dark wet soil, flattened grass and thousands of small pale flowers. Strong wind bends the grass and flowers in irregular waves. A ruined medieval fortress stands on a distant hill at screen-left. Broken towers remain visible through low drifting fog. Lightning intermittently illuminates the fortress and storm clouds. The giant occupies the battlefield’s screen-right side. The warrior begins in the center foreground, running toward the giant. Preserve this geography and screen direction throughout every cut. CHRONOLOGICAL ACTION AND CAMERA: 0.00–3.30 — CHARGE TOWARD THE GIANT Begin immediately with a low rear tracking shot, close behind the armored warrior as he runs powerfully through the wet field toward the colossal giant. He carries the warhammer horizontally across his body with both hands. The heavy hammer head remains toward screen-right while the lower shaft extends toward screen-left. His boots compress the wet ground with every step, throwing soil, crushed flowers and droplets backward only after physical contact. The giant’s legs and enormous right hand enter from the upper-right side of the frame. The giant bends down and extends its open hand toward the charging warrior, intending to scoop him from the ground. The fingers move independently with believable joints and weight. The giant does not instantly grab or teleport the warrior. Camera movement remains low, fast and smooth, emphasizing the extreme difference in scale. The ruined fortress stays visible on the distant screen-left horizon. 3.30–5.80 — LEAP ONTO THE GIANT’S HAND As the giant’s open hand sweeps low across the warrior’s path, the warrior plants his right boot firmly into the ground. His knee compresses, hips lower and rear leg drives upward. He performs one powerful forward jump. Use controlled cinematic slow motion as he rises in front of the giant’s separated fingers. His legs tuck slightly beneath him while both hands raise the same warhammer above his shoulders for balance. The warrior lands with both boots on the back of the giant’s middle and ring fingers. Show clear physical contact: boots touch skin, knees absorb impact, the giant’s flesh compresses slightly and the warrior’s armor reacts to the landing. The giant begins lifting its hand toward its face. The warrior does not float or hang in empty air. Use a dramatic low-angle crane that travels upward beneath the warrior, with the enormous hand filling the background. 5.80–9.00 — RUNNING UP THE ARM Return to fast natural action. As the giant raises its arm, the warrior runs from the fingers across the back of the hand and onto the wrist. His footfalls alternate correctly and visibly grip the uneven moving surface. The giant rotates its wrist and attempts to shake him loose. The warrior lowers his center of gravity, widens his stance and keeps the hammer close to his torso until the arm stabilizes. He then accelerates along the giant’s forearm toward the elbow. Each step follows the arm’s changing angle; his boots do not slide through the skin. Camera tracks beside and slightly below him, rising along the length of the giant’s arm. Near parts of the arm cross the foreground quickly while the giant’s head and distant fortress move more slowly, creating powerful parallax and scale. 9.00–12.00 — CLIMB TO THE SHOULDER The warrior reaches the upper arm as it rises steeply toward the giant’s shoulder. He hooks one forearm and the warhammer shaft against a natural ridge of muscle for leverage, plants his right boot, pushes through his leg and pulls himself onto the shoulder in one connected climbing action. The giant turns its head toward him. Its eye tracks the warrior, its brow tightens and its jaw opens in a deep nonverbal roar. Hair and skin move from the rotation of its head. The warrior remains attached to the shoulder through real hand and boot contact. He climbs diagonally across the upper shoulder toward the base of the giant’s neck. Use a close side-tracking shot that keeps the complete warrior, warhammer and giant’s facial profile readable in the same frame. 12.00–15.00 — FULL HAMMER STRIKE TO THE JAW The warrior reaches a stable position on the giant’s sloped shoulder near its neck. He plants his left boot forward and braces his right boot behind it. Both feet visibly press against the giant’s skin. He rotates his hips away from the target and draws the warhammer backward with both hands. Show the complete preparation before impact: feet plant → knees compress → hips load → torso rotates → shoulders draw the hammer backward → arms guide the heavy hammer head into its starting position. At 13.00 seconds, the warrior releases one complete horizontal two-handed swing toward the giant’s jaw. The power travels continuously from his legs through his hips, torso, shoulders and arms. The hammer head follows one clear uninterrupted arc. It does not jump positions or touch the face before the swing is complete. At 14.00 seconds, enter explicit ultra slow motion for the decisive contact. The rectangular hammer head strikes the side of the giant’s lower jaw with its broad striking face—not the shaft or handle. Show skin and cheek tissue compressing around the impact, the giant’s jaw shifting sideways, loose hair whipping outward and a radial burst of rain, dust and skin debris. The warrior’s arms resist the sudden deceleration. His shoulders recoil while his body continues through a controlled follow-through. No blood, exposed tissue, gore or dismemberment. 15.00–17.30 — GIANT RECOIL AND WARRIOR FALL Return immediately to natural speed. The giant’s head snaps sideways from the impact. Its upper body recoils and the struck shoulder drops sharply. This sudden downward movement removes the warrior’s footing and throws him away from the giant. The warrior falls toward the battlefield while retaining the same warhammer with both hands. He does not float or perform an additional jump. Cut to a ground-level side view. His boots contact first, his knees collapse under the momentum and he rolls once across one shoulder. The hammer head strikes the soil beside him and digs a shallow trench, throwing wet earth and pale flowers outward. The giant’s huge face descends into the upper-right portion of the frame as it struggles to regain balance. It does not crush or intersect the warrior. 17.30–20.00 — RECOVERY AND FINAL STANDOFF The warrior stops his roll in a low kneeling position. He plants the warhammer head into the soil, grips the shaft with both hands and uses it as support to rise steadily to one knee. He then pulls the hammer free and

Create a 30-second, 1080p ultra-realistic early-2000s DV home video of a young Korean woman doing quiet Sunday chores around her home in an older Seoul neighborhood. Purely observational, no dialogue, no narrative arc just rhythmic, textural everyday realism. MAIN SUBJECT Young Korean woman same as , early 20s, natural beauty, realistic skin texture, no makeup, black hair tied up messily in a claw clip, oversized faded T-shirt, rolled-up sweatpants, bare feet or house slippers. Keep her identity, outfit, hairstyle and proportions perfectly consistent throughout. SETTING The front step and small yard/alley outside an older Seoul home. Concrete step, a low gate, potted plants, a garden hose, a trash bin, scattered leaves. Ordinary, lived-in, no landmarks or brand names. SEQUENCE (rhythmic, no dialogue) She sweeps the front step with a short broom, dust and leaves scattering in the light. She crouches down and pours a small amount of dry food into a bowl for a neighborhood cat waiting nearby; the cat eats while she watches briefly. She stands and waters potted plants along the wall with a small watering can, water visibly darkening the soil. She picks up a bagged trash bundle and carries it a few steps to place it by the curb/bin. She wipes her hands on her shirt, looks around the now-tidy step and yard for a moment, then exhales/stretches. She glances toward the camera briefly with a small, tired smile — no words — then turns and walks back inside. Camera holds on the empty, swept step for a beat before cutting to black. CAMERA Raw handheld early-2000s DV camcorder, shaky footage, autofocus hunting, faded colors, exposure shifts, motion blur, soft digital detail, occasional accidental zooms. Observational, documentary-like framing — lingering shots, no cuts within actions. No polished cinematography. AUDIO Natural ambience only — broom bristles on concrete, water pouring, cat eating, distant birds, wind, a far-off scooter or dog bark, plastic bag rustling, faint footsteps. No dialogue, no music. CONTINUITY Broom, watering can and trash bag each remain consistent through their respective actions. Cat stays in frame while eating, doesn't disappear or duplicate. No teleporting or vanishing objects. Smooth, realistic, unhurried movement throughout. NEGATIVE CGI look, plastic skin, identity drift, outfit changes, distorted hands, extra fingers, subtitles, watermark.

生成一段 10 秒、9:16 竖屏的高端美食广告，使用 Gemini Omni 1.1 Flash。结合本段参考视频与五张参考图片，理解食材形态、操作顺序和动作节奏。参考素材用途：视频提供完整备料流程；五张图片分别用于河虾清洗、沥水、韭菜花切段、姜蒜切碎、料汁准备。将它们作为视觉事实，不复制原素材中的人物身份、字幕、标识、旁白或独特版式。统一视觉设定：主料是细小的完整带壳河虾，保留自然的虾须和虾脚，不是大对虾，也不是剥壳虾仁。目标体长约 1.5 厘米、体宽约 0.2 厘米，不含须脚。清洗、沥水等不同镜头里的河虾必须保持相同尺寸，不得忽大忽小。韭菜花使用鲜绿色的细长花茎，可带少量未开放的花苞，切成约 3—4 厘米的小段，不要生成宽大的韭菜叶。姜蒜切碎，搭配少量红辣椒。厨房采用深灰石质台面、浅橡木砧板、小号透明调料碗。只出现成年厨师的双手，不出现人物正脸。左上方柔和暖光，暗部适度压低，食材颜色自然，保留真实水珠和湿润质感。分秒动作：0—3 秒：清洗后的细小河虾在滤网中沥水，水滴自然落入下方容器。河虾数量充足、形态纤细，不出现手捧河虾的展示镜头。3—5 秒：切换到砧板，厨师将韭菜花整齐切成小段。5—7 秒：切近景，姜蒜被切碎，刀具与手部动作自然。7—10 秒：在透明小碗中调好料汁，用勺子轻轻搅匀。调料应通过可见的加入动作形成颜色，不要让清水无缘无故瞬间变成棕色。画面铺满竖屏，不复制参考视频的黑边。保留轻微水声、切菜声和搅拌声，不要对白、音乐或字幕。避免：大虾、粗壮虾身、不同镜头尺寸不一致、畸形手指、悬浮食材、额外器具、突然改变光线、塑料质感。生成一段 10 秒、9:16 竖屏的高端美食广告，使用 Gemini Omni 1.1 Flash，结合本段参考视频和全部五张参考图片。参考素材用途：图 1：食用油进入黑色炒锅。图 2：姜蒜末和少量红辣椒从小碗倒入热油。图 3：灰色生河虾从滤网倒入锅中。图 4：河虾在翻炒中逐渐变为橙红色。图 5：韭菜花在结尾开始入锅。保持工序真实，不复制来源人物、字幕、标识、声音或版式。统一视觉设定：使用细小、完整带壳的河虾，目标体长约 1.5 厘米、体宽约 0.2 厘米，不含须脚。所有镜头里的河虾保持同一尺寸，熟后不能突然变大。单只河虾明显短于 3—4 厘米的韭菜花段，一把锅铲能托起多只小虾。使用圆形黑色碳钢炒锅、金属锅铲、深灰石质台面、低饱和灰砖背景和炉边浅色木砧板。只出现厨师双手。左上方柔和暖光，食物颜色自然，蒸汽适量，镜头运动克制。分秒动作：0—3 秒：少量食用油铺开在预热的炒锅中，姜蒜末和红辣椒从小碗倒入，开始滋滋作响。此时锅中还没有河虾。3—7 秒：沥干的灰色生河虾从滤网落入锅中。厨师用锅铲自然翻炒，通过合理切镜表现烹饪时间经过，再呈现虾壳变为橙红色，不要瞬间魔法变色。7—10 秒：橙红色的小河虾被轻轻翻起、自然落回锅底。结尾从备料碗加入鲜绿色韭菜花，为下一段合炒建立衔接。这一段不要装盘，也不要提前加入料汁。输出一个结果，完整 10 秒，720p，9:16 竖屏铺满画面。只保留轻微炒菜环境声，不要对白、音乐或字幕。避免：畸形手部、悬浮食材、多余配料、夸张火焰、工序倒置、塑料质感，以及河虾尺寸变化。生成一段 10 秒、9:16 竖屏的高端美食广告，使用 Gemini Omni 1.1 Flash，结合本段参考视频和五张参考图片。参考素材用途：图 1：鲜绿色韭菜花已经落在熟河虾上。图 2：锅铲开始翻拌。图 3：食材进行小幅度翻炒。图 4：河虾和韭菜花混合后出现油润光泽。图 5：翻炒时淋入细细的棕色料汁。按照参考素材里的真实动作与顺序组织镜头，不复制文字、标识、声音或人物身份。统一视觉设定：河虾始终是已经炒熟的橙红色完整带壳小河虾，保留细虾须，目标体长约 1.5 厘米、体宽约 0.2 厘米。单只虾短于韭菜花段，所有镜头保持相同尺寸与数量感。韭菜花是鲜绿色花茎和少量未开放花苞，不是宽叶蔬菜。姜蒜末与少量红辣椒已经在锅里，不再添加新的蔬菜。沿用圆形黑色碳钢炒锅、金属锅铲、深灰台面、灰砖背景、浅色砧板与左上方柔和暖光。蒸汽克制，颜色自然，只出现厨师双手。分秒动作：0—2 秒：从韭菜花刚落在橙红色河虾上的状态开始，锅铲将韭菜花翻入河虾中。不要再倒入第二整份韭菜花。2—6 秒：进行两次清晰的锅铲翻拌和一次低幅度翻锅。食材跟随锅铲运动，轻微升起，再在重力作用下自然落回。河虾保持橙红色，韭菜花保持绿色和花茎形态。6—8 秒：从透明小碗中淋入适量浅棕色料汁，形成细而连续的液流，随后立即翻炒。不要出现无来源的液体或突然变色。8—10 秒：将料汁翻匀，让河虾与韭菜花表面形成薄薄的湿润光泽，但锅底不要积成汤。结尾将食材收拢在锅中，等待下一段出锅。这一段不要提前装盘。输出一个结果，完整 10 秒，720p，9:16 竖屏，无黑边。保留轻微滋滋声与锅铲声，不要对白、音乐和字幕。避免：新增配料、畸形手部、食材悬浮、巨大火焰、汤汁过多、工序倒置或河虾忽大忽小。生成一段 10 秒、9:16 竖屏的高端美食广告收尾，使用 Gemini Omni 1.1 Flash，结合本段参考视频和五张参考图片。参考素材用途：图 1：调味完成后的最后翻炒。图 2：金属锅铲翻拌。图 3：小幅度收尾翻锅。图 4：菜品呈现在白色盘子上。图 5：继续将锅中食材转移到盘中。注意：图 5 是装盘动作参考，不是静止成品画面。参考其食材形态、操作顺序和自然落盘动作，不复制原片的关注按钮、字幕、标识、声音或人物身份。统一视觉设定：河虾是细小、完整带壳、已经熟透的橙红色河虾，带自然细虾须，目标体长约 1.5 厘米、体宽约 0.2 厘米。翻炒、装盘和特写中的虾保持同一尺寸，不变成大对虾或虾仁。韭菜花是约 3—4 厘米的绿色花茎段，带少量未开放花苞，混有姜蒜末和少量红辣椒。食材已经裹好薄薄的料汁，不再加新配料或额外浇汁。沿用黑色碳钢炒锅、金属锅铲、深灰石质台面、灰砖背景与浅色木砧板。使用一个素净暖白色浅口陶瓷盘。只出现厨师双手。柔和暖光从左上方照入，食物色彩自然，蒸汽轻微。分秒动作：0—2.5 秒：在锅中进行最后一次轻柔翻拌和小幅度翻锅。河虾保持橙红色，韭菜花保持绿色，表面油润但不汤水淋漓。2.5—6 秒：切换到出锅装盘。将炒锅轻轻倾向白盘，用金属锅铲引导食材自然滑落，清楚呈现食物离开锅、在盘中逐渐形成整齐小丘的过程。不要瞬移、突然出现第二只盘子或大量洒出盘外。6—10 秒：双手与锅铲退出画面。镜头缓慢、轻微推进，呈现完成装盘的韭菜花炒河虾。橙红色小虾与绿色花茎均匀混合，虾壳纹理自然，料汁薄而有光泽。盘子保留适当边缘空间，最后一秒平稳收尾。成品特写开始后，不再继续装盘，不要伸手拿虾、插入筷子或添加新的装饰。输出一个结果，完整 10 秒，720p，9:16 竖屏，无黑边。只保留轻微锅铲、出锅与装盘声，不要对白、音乐或字幕。避免：复制原素材文字、畸形手部、悬浮食材、巨大火焰、大虾、食材变化和突然改变光线。

Create a 12-second, single-take white-model animation in Blender based on the attached reference image https://t.co/oEKq6hDALF, then use PixVerse with Seedance 2.5 to transform the exported animation into a cinematic, Witcher-3-inspired wizard workshop sequence. In Blender, use the reference image to guide the room layout, architecture, furniture, and props. Build an editable low-poly scene with clean meshes and UVs, using simple white or light-gray materials. Include stone walls, wooden shelves, an arched window, a fireplace, books, an astronomical instrument, and an alchemy table filled with potion bottles. Keep the silhouettes readable and the room proportions believable. Animate a low first-person viewpoint with exactly one right hand holding one potion. Begin with the bottle resting near the lower-right edge while the character looks around the workshop and toward the window. Raise the potion naturally, pause to examine it, shift focus onto the bottle, then lower it while turning toward the fireplace and glowing reagents. Leave a small gap between the palm and bottle while maintaining believable fingertip contact. Use smooth changes in speed, gentle curved head movements, subtle breathing, and slight arm lag. Check the complete action at normal playback for clipping, awkward grip, abrupt turns, and excessive shaking. Keep the Blender fireplace simple: use logs, low embers, and flickering light. Avoid solid cones or flame-shaped meshes, which can be interpreted as glowing rocks. Prepare a separate fireplace detail from the reference image to guide the final appearance. Export the complete white-model MP4. Then generate a 12-second video with PixVerse, explicitly referencing the Blender-exported white-model video as the camera, action, and spatial reference, the attached image as the scene appearance reference, and the fireplace detail as the fire reference. Preserve the continuous shot, low viewpoint, single-hand potion action, room layout, and timing. Enrich the scene with weathered stone, carved wood, worn leather, iron fittings, and realistic glass. Combine cool window light and drifting dust with warm fireplace illumination and softly glowing magical liquids. Create natural wood fire with thin, irregular flames curling between charred logs, glowing embers, occasional sparks, and subtle smoke. Keep the hand anatomy, bottle shape, fire movement, and focus transitions consistent throughout. Review the full generated video, especially the hand action and fireplace. Deliver the white-model MP4, the PixVerse-rendered MP4, and the editable Blender project. After acceptance, retain the latest approved versions and move older versions to recoverable storage.

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.

30 seconds | 16:9 | premium travel music video / fashion travel film | 2024–2026 commercial grade | MULTISHOT CORE CONCEPT A young traveler experiences China through an energetic but natural sequence of movement, culture, fashion, food, architecture and landscapes. The film feels like a premium Chinese tourism campaign combined with an elite fashion travel film. The traveler is always physically present in the environment. Every location feels photographed rather than generated. Music drives the edit, but the footage retains the imperfections and spontaneity of real travel photography. CHARACTER ONE TRAVELER — young adult international traveler wearing a contemporary Adidas travel outfit: premium red Adidas jacket, neutral trousers, sneakers, compact crossbody bag. Natural hair, realistic skin texture, minimal accessories. Same face, clothing, hairstyle, proportions and accessories throughout the entire film. Do not invent additional Adidas branding. SETTING Modern and historic China: high-speed railway, Shanghai streets, traditional water-town lanes, Chengdu food streets, ancient architecture, dramatic mountain valleys, elevated viewpoints and vibrant nighttime streets. Real pedestrians, vendors, commuters, vehicles and local activity. Locations feel naturally connected through the journey. STORY — MUSIC-DRIVEN MULTISHOT VISUALS 00:00–02.5 — CLOSE-UP HOOK 85mm close-up of the traveler beside a high-speed train window. Warm sunlight catches the face while reflections of the moving Chinese landscape slide across the glass. Traveler looks outside, then turns toward camera as the first beat begins. 02.5–05 — MOVEMENT 24mm wide shot from the platform as the traveler walks alongside the departing high-speed train. Wind moves the red jacket naturally. The train accelerates through frame. Cut precisely with the music. 05–07.5 — CITY ARRIVAL 35mm handheld follow shot as the traveler exits a busy station into a dense Chinese city street. Real pedestrians cross naturally. Electric scooters, taxis and buses move through the background. Camera operator follows slightly behind rather than perfectly framing the subject. 07.5–10 — STREET LIFE 50mm observational shot. Traveler moves through a crowded neighborhood while a food vendor prepares steaming street food nearby. Traveler briefly stops, watches the preparation and smiles naturally. Steam passes across the foreground. 10–12.5 — CULTURAL TRANSITION 24mm shot following the traveler through a traditional Chinese water-town street. Stone paths, wooden buildings, bridges and hanging signs surround them. People move naturally through the scene. Traveler crosses a small bridge as sunlight breaks through the buildings. 12.5–15 — FOOD / HUMAN MOMENT 50mm close-up. A local vendor hands the traveler a freshly prepared dish. Traveler takes a bite and reacts naturally. Shallow depth of field, warm skin tones, authentic background activity and subtle handheld movement. 15–17.5 — MOUNTAIN REVEAL 24mm deep-focus landscape. Traveler walks up a long stone staircase through dense greenery. Camera follows from behind. As the traveler reaches the top, a vast mountain valley emerges through cool atmospheric mist. 17.5–20 — FASHION MOMENT 50mm side-tracking shot in golden sunlight. Traveler walks along the mountain viewpoint. Red Adidas jacket contrasts strongly against deep green vegetation. Golden rim light catches the hair and shoulders. Natural wind moves fabric. 20–22.5 — LANDSCAPE / SCALE 24mm wide. Traveler becomes small against enormous mountains disappearing into mist. Clouds move slowly through the valley. No artificial drone aesthetic; perspective feels like a real elevated camera position. 22.5–25 — NIGHT TRANSITION 50mm handheld street shot at blue hour. Traveler enters a lively nighttime food district. Warm lanterns, cool ambient light, scooters and pedestrians create layered depth. The music increases in intensity. 25–27.5 — CITY ENERGY 35mm tracking shot as traveler walks beside a modern riverside district. Reflections ripple across the water. Modern towers illuminate behind them while boats move naturally through the frame. 27.5–30 — FINAL REVEAL 24mm wide composition from behind the traveler. They stop briefly at the riverside and look across the illuminated skyline. Camera slowly moves backward rather than flying upward. Traveler then continues walking as the music reaches its final beat. CAMERA 35mm and 50mm for portraits and human moments, 24mm for landscapes, architecture and stairs, occasional 85mm compression on faces. Shallow DOF on close-ups, deep focus on mountain wides. Handheld and physically motivated tracking movement. Natural camera micro-movement, imperfect framing, subtle autofocus adjustment, realistic exposure adaptation and occasional foreground obstruction. No impossible camera movement, no floating drone aesthetic. VISUAL / COLOR SETTING Premium travel music video / fashion travel film, 2024–2026 commercial grade. Look: photoreal cinema, slight filmic grain, mild halation on highlights, teal-cyan skies, punchy crimson reds, deep forest greens, warm skin, crushed-but-not-crushed blacks. COLOR GRADE Cinematic teal-and-warm, greens slightly cyan, red Adidas pops hard against foliage, golden rim on faces in sun, cool mist in mountain valleys. Maintain realistic skin tones and natural environmental color. No excessive saturation or artificial HDR. MOTION 180-degree cinematic shutter, natural motion blur on hair and fabric, 24fps. No soap-opera 60fps look. Movement should retain the subtle imperfections of real location photography. LIGHTING Natural daylight, soft overcast city light, warm direct sunlight, golden-hour rim light, cool mountain mist, practical lanterns and nighttime city illumination. Lighting must originate naturally from the environment. AUDIO Premium contemporary travel soundtrack with subtle modern Chinese-inspired textures. Music drives the transitions and rhythm. Keep authentic location sound underneath: train ambience, station announcements, footsteps, scooters, traffic, vendors, cooking sounds, crowd chatter, wind, birds, distant city noise and riverside ambience. Environmental sound should occasionally become prominent during intimate moments. REALISM No CGI look, no plastic skin, no beauty-filter smoothing, no extra fingers, no warped architecture, no artificial crowd synchronization, no impossible reflections, no floating objects, no exaggerated depth of field. Realistic skin pores, hair strands, fabric texture, water reflections, atmospheric perspective and human movement. BRAND CONTROL The only Adidas branding visible is the existing Adidas trefoil already present on the traveler’s garments. Do not invent additional logos, advertisements, storefront branding or branded products. Do not add watermarks or random UI. EDITING Music-synchronized commercial editing without excessive effects. Cuts are motivated by movement, reflections, steam, architectural shapes, walking direction and changes in light. Use clean match cuts and occasional speed changes only when physically believable. Avoid generic AI transitions, artificial zooms, excessive whip transitions and over-edited montage pacing. CONTINUITY The traveler remains identical throughout all shots. Preserve face, hairstyle, red Adidas jacket, trousers, sneakers, bag and accessories. Maintain realistic weather and lighting progression from daylight → golden hour → blue hour → night. Each location should feel like part of one continuous journey through China. FINAL QUALITY TARGET The final film should look like genuine footage captured by an elite travel filmmaker for a major Chinese tourism/fashion campaign—not a collection of AI-generated beauty shots. The realism comes first; the commercial polish comes from cinematography, col

Ultra-realistic cinematic short film, vertical 9:16. Inside a dark, cozy living room late at night, a young child sits on the wooden floor, carefully assembling a small toy project. Beside the child, a humanoid robot kneels down at the child's eye level, gently assisting with the tiny toy parts. The robot has a realistic white-and-black mechanical body, intricate joints, subtle brushed-metal textures, soft reflections, and expressive mechanical eyes. Its movements are slow, precise, and gentle. The robot carefully picks up a small toy component, examines it, and hands it to the child. The child looks up at the robot with curiosity and trust, then smiles softly as they continue working together. A narrow, dramatic warm flashlight beam illuminates the child's hands, the toy, and the robot's fingers. Cool blue moonlight enters through a nearby window, creating a beautiful contrast between warm and cool tones. Subtle dust particles float through the light. The rest of the room remains dim, creating an intimate, emotional atmosphere. The camera begins with a medium-wide shot of the robot and child sitting together on the floor, then slowly moves closer in a gentle cinematic dolly-in. Cut to a close-up of the robot's articulated fingers carefully placing a toy part. Cut to the child's face, showing genuine curiosity and a subtle smile. End with a close-up of the robot and child looking at the completed toy together. Natural human and robotic motion, realistic hand interactions, accurate object contact, subtle facial expressions, emotionally authentic storytelling, consistent character appearance, physically accurate lighting, realistic shadows and reflections, cinematic depth of field, soft lens bokeh, high dynamic range, film-quality color grading, photorealistic textures, detailed materials, premium science-fiction drama aesthetic, 4K cinematic quality. No dialogue, no subtitles, no text on screen.

VIDEO CONCEPT: A completely natural 30-second personal home-video recording of a young woman doing something ordinary on a quiet apartment rooftop during a breezy afternoon. She hangs freshly washed clothes, discovers that one sock has blown away, and casually runs after it. The moment feels spontaneous, funny, and completely unplanned. FORMAT: 30 seconds • 16:9 • 1080p • photorealistic live-action • raw consumer camcorder footage MAIN SUBJECT A young Turkish woman in her early 20s with long dark-brown hair tied loosely in a low ponytail. She wears a faded white T-shirt, loose olive-green trousers, simple house slippers, and a thin silver bracelet. Keep her face, hairstyle, clothing, body proportions, and accessories completely consistent throughout the entire video. SETTING A modest apartment rooftop in Izmir, Turkey, on a warm breezy afternoon. The rooftop has concrete flooring, metal railings, water tanks, plastic buckets, a simple clothesline, neighboring apartment buildings, satellite dishes, potted plants, and laundry moving in the wind. The environment should feel lived-in and ordinary. No famous landmarks, recognizable brands, advertisements, or tourist imagery. CAMERA / VISUAL AESTHETIC Shot on an inexpensive early-2000s consumer digital camcorder. Handheld and slightly shaky Occasional uneven framing Natural autofocus hunting Slight exposure changes when pointing toward the bright sky Mild digital compression Subtle image noise Natural motion blur Slightly faded colors No stabilization No cinematic lens effects No artificial bokeh No polished commercial look The camera operator should behave like a friend casually filming from a few feet away. TIMELINE 0–5 SECONDS — ROOFTOP The camera steps onto the rooftop. The woman is already standing beside the clothesline with a small plastic basket full of freshly washed clothes. Wind moves several shirts hanging nearby. She looks toward the camera and says casually: “It’s really windy today.” 5–12 SECONDS — HANGING CLOTHES She takes a white shirt from the basket and clips it onto the clothesline. The fabric immediately catches the wind and flutters strongly. She laughs quietly and uses both hands to secure it with another clothespin. The camera moves slightly closer. Natural sunlight reflects off the metal clips. 12–18 SECONDS — THE SOCK She pulls out a small sock from the basket. Before she can attach it, a sudden gust catches it from her hand. The sock flies across the rooftop. She freezes for half a second. Then says: “Oh, come on!” She quickly starts walking after it. 18–24 SECONDS — CHASING IT The camera operator follows her with slightly shaky movement. The sock slides across the concrete floor, pushed by the wind. She reaches down but misses it. The sock moves toward a rooftop corner. She laughs while chasing it. Her ponytail and loose shirt move naturally in the wind. 24–30 SECONDS — CAUGHT She finally catches the sock near the railing. She holds it up toward the camera with an amused expression. She shakes her head and says: “Got you.” She walks back toward the clothesline. The camera remains handheld and slightly imperfect as the recording ends mid-action. AUDIO Only natural location sound: Strong but realistic wind Clothes flapping Plastic basket movement Clothespins clicking Distant city traffic Birds Footsteps on concrete Her natural laughter Quiet neighborhood ambience NO MUSIC. Dialogue should sound spontaneous, slightly imperfect, and naturally recorded from several feet away. REALISM / PHYSICS Wind must affect the environment consistently. Clothes should flutter according to their size and weight. The lightweight sock should move more easily than the heavier clothing. Hair and loose fabric should respond naturally to gusts. The plastic basket should remain grounded unless physically moved. Hands must interact correctly with clothespins and clothing. No impossible wind direction changes, floating objects, duplicated clothes, or objects appearing/disappearing. Maintain perfect continuity of the woman’s face, hairstyle, outfit, bracelet, and slippers. NEGATIVE PROMPT CGI, 3D render, animation, game graphics, plastic skin, beauty filter, AI face, face morphing, identity drift, extra fingers, malformed hands, duplicated people, floating objects, impossible physics, fake wind, excessive slow motion, HDR, oversaturation, cinematic color grading, artificial bokeh, dramatic lighting, studio lighting, perfect stabilization, drone footage, commercial advertisement aesthetic, staged acting, exaggerated expressions, subtitles, captions, logos, watermarks, recognizable brands, background music, wardrobe changes, hairstyle changes, continuity errors. FINAL LOOK The footage should feel like a random afternoon memory captured by a friend on an old family camcorder. The camera should not behave like a professional filmmaker. Small shakes, missed framing, autofocus adjustments, imperfect exposure, ordinary rooftop clutter, and spontaneous reactions should remain visible. Make it feel like a real moment that happened once—not a scene created for a camera.

15-second cinematic sci-fi action sequence, 16:9, ultra-realistic, IMAX-quality cinematography, breathtaking scale, realistic motion, no visible face, no text, no dialogue. A lone spacecraft flies through a dense field of orbital habitats illuminated by a brilliant sun. Everything is bright. Then darkness begins moving across the structures. Not an eclipse. A shadow. The shadow sweeps across stations, ships and habitats at incredible speed. Every vehicle touched by the darkness instantly loses power and drifts lifelessly. The pilot realizes the shadow is chasing him. Entire stations go dark behind the spacecraft. Navigation lights disappear. Cities vanish into blackness. The shadow closes the distance. Closer. Closer. Ahead, a narrow corridor of sunlight remains between two rotating habitats. The pilot commits. The corridor collapses into darkness immediately after the spacecraft passes through. Cut.

@image1 fights three opponents inside a Japanese high school classroom in an intense, highly dynamic one-take action sequence. The classroom is filled with wooden desks, chairs, school bags, a chalkboard, sliding windows, curtains, fluorescent ceiling lights, posters, books, and scattered papers. The camera is extremely dynamic and close to the action, never static — fast-moving, constantly following, circling, ducking, whipping, and pushing through the fight, immersive and physically present. Natural classroom lighting mixed with warm afternoon sunlight through the windows, realistic shadows, practical motion blur, grounded textures, raw cinematic look, no glossy AI finish. [0-2s] Camera whips into the room low and fast — she's already mid-motion, ducking under the first opponent's swing near the chalkboard. [2-4s] She sweeps a chair into his legs, camera circling tight around the impact as he stumbles into a row of desks. [4-6s] Second opponent charges from the side aisle; she vaults over a desk, camera rising suddenly to follow her over the top. [6-8s] Mid-air, she kicks off the desk toward him, papers exploding upward around the impact, camera pushing in close. [8-10s] She slides across a tabletop to close distance, camera tracking low alongside the desk surface, dust catching sunlight. [10-12s] Third opponent grabs a backpack, swings it — she blocks with a raised forearm, camera whipping around to catch the block from behind her shoulder. [12-14s] She grabs the same backpack, deflecting his next strike and shoving him into a toppling desk, camera dropping low as it crashes. [14-16s] First opponent recovers, rushes her from behind; camera spins 180° rapidly to reveal him closing in. [16-18s] She pivots, uses the narrow aisle to redirect his momentum, throwing him into a row of chairs, camera circling the throw. [18-20s] Second and third opponents converge — camera rushes backward ahead of her as she retreats between desks, curtains whipping from the motion. [20-22s] She grabs a fallen chair, sweeping it low — camera drops near floor level to catch the leg-sweep connecting. [22-24s] She rises fast, camera surging upward with her as she catches an incoming strike and redirects it into a desk. [24-26s] Final opponent lunges; she sidesteps using the aisle space, slams him against the sliding window frame, glass rattling, curtain billowing. [26-28s] Camera whips around her as she scans the room, all three opponents down or staggering among overturned desks and scattered papers. [28-30s] She exhales, standing still amid the wreckage, sunlight cutting through dust in the air, camera slowly pushing in on her face for the final beat. Strong choreography, realistic body movement, believable impact, fast reaction timing, close-range combat, continuous motion, handheld urgency throughout, one uninterrupted take feel.

A young, statuesque French female in a Galleria Borghese gallery, wearing a muted fall outfit.

Create exactly 30 seconds of photorealistic 4K AAA third-person gameplay inside a realistic Japanese high school on a bright weekday morning. The sequence should feel like a spontaneous story mission with believable movement, natural NPC behavior, realistic physics, and uninterrupted environmental continuity. CHARACTER: 20-year-old Japanese schoolgirl with medium-length straight black hair, subtle side bangs, natural youthful facial features, white short-sleeve school blouse, navy ribbon, dark grey pleated skirt, black knee-high socks, white indoor sneakers, and a dark blue shoulder school bag. Maintain identical face, hair, body proportions, clothing, footwear, and accessories from beginning to end. OBJECT: A small red classroom key attached to a simple wooden key tag. The key is fully physical, metallic, reflective, and consistently sized throughout the sequence. 0–5s — THE MISSING KEY Inside an emptying classroom, she searches through a desk drawer and realizes the classroom key is missing. She notices the red key tag underneath a stack of worksheets near the window. She reaches for it, but a sudden gust from the open window pushes the worksheets across the desk and the key drops onto the floor. HUD: FIND THE CLASSROOM KEY 5–10s — DOWN THE CORRIDOR She picks up the key and leaves the classroom. A school announcement begins playing through the hallway speakers. She walks toward the main office while checking the key tag against a handwritten classroom number. Students move naturally around her, some entering classrooms, others carrying books and sports bags. 10–15s — WRONG TURN She reaches an intersection and realizes she has taken the wrong corridor. She stops beside a wall map of the school and studies it briefly. A group of younger students rushes past carrying basketballs, causing her to step back against the wall. Once the corridor clears, she turns into a smaller connecting hallway. 15–20s — LOCKED DOOR She reaches a shortcut door but finds it locked. She tries the handle once, then notices a stairwell beside it. She takes the stairs down one level. Her shoes make realistic sounds against each step while sunlight flickers across the stairwell through the tall windows. HUD: TAKE THE SHORTCUT 20–26s — LAST SECOND She exits the stairwell and reaches the classroom wing just as a staff member begins closing a large sliding partition at the end of the corridor. She quickly walks through the remaining opening before it closes, then reaches the classroom door. She inserts the key into the lock, turns it naturally, opens the door, and steps inside. HUD: ROOM UNLOCKED 26–30s — HARD CUT Hard cut to a fixed frontal classroom shot. She places the key on the teacher's desk, removes her school bag, and sits down at her usual seat. The teacher enters a moment later, notices the unlocked room, and gives her a brief approving look. She quietly opens her notebook as the morning lesson begins. HUD: MISSION COMPLETE CAMERA: Use one grounded third-person camera from 0–26s positioned behind and slightly beside the girl. Maintain natural gameplay-style tracking with realistic camera inertia and subtle operator movement. The camera must physically follow the character through classrooms, corridors, stairwell, and doorway. No floating camera, no orbiting shots, no sudden perspective changes, no impossible tracking, and no cuts during the first 26 seconds. At exactly 26 seconds, perform one hard cut to the fixed frontal classroom angle. AUDIO: Natural Japanese school ambience: distant student conversations, footsteps, sliding classroom doors, papers moving, school announcements over speakers, stairway echoes, basketballs bouncing in the distance, door handles, key movement inside the lock, fabric movement, subtle breathing, and morning classroom sounds. No dramatic music or action soundtrack. REALISM LOCK: Natural student behavior, realistic walking speed, accurate body mechanics, believable collisions, physically correct key movement, realistic wind interaction with paper, authentic Japanese school architecture, varied background activity, natural morning lighting, realistic shadows and reflections, detailed skin and hair, physically based materials, and cinematic AAA game rendering. No teleporting, supernatural abilities, impossible shortcuts, parkour, combat, duplicated characters, disappearing objects, changing identity, changing outfit, changing key design, unrealistic physics, exaggerated acting, anime or cartoon style, plastic CGI appearance, floating camera, subtitles, logos, watermarks, or additional cuts.

Main Subject: Young Korean woman, 24, naturally attractive, realistic skin, minimal makeup, long dark hair loosely down. Wearing an oversized maroon hoodie and casual pants. Preserve her exact identity, facial features, hairstyle, body proportions and appearance throughout. Location: Small old Seoul apartment kitchen during a dark, rainy early morning. Slightly worn kitchen counter, simple bowl of food, sauce bottle, wooden cabinets, rain-covered window and blurred neighboring apartment buildings outside. Steady rain can be seen through the window. Lighting & Atmosphere: Cozy, dim blue-hour ambience. Cold blue-gray light from the rainy window mixed with a weak warm kitchen light. Muted colors, soft shadows, slightly underexposed interior and a quiet sleepy atmosphere. Style: Ultra-realistic early-2000s Sony MiniDV home video filmed by another person holding the camcorder. Completely candid and unstaged. Natural handheld shake, imperfect framing, gentle reframing, occasional autofocus hunting, mild exposure shifts, faded colors, soft contrast, authentic DV compression, subtle low-light digital noise and microphone noise. Smooth continuous real-time motion throughout. No stuttering, judder, frame skipping, duplicated frames, stop-motion appearance, excessive motion blur, speed changes or low-frame-rate look. No stabilization or modern cinematic movement. 00:00–00:04: She stands at the kitchen counter preparing a simple bowl of food. She casually squeezes some sauce over it while looking away for a moment. 00:04–00:07: Far too much sauce suddenly comes out of the bottle. She immediately stops squeezing and stares down at the food in silent disbelief. 00:07–00:10: She slowly tilts the bowl toward herself, inspecting the excessive amount of sauce as if trying to figure out whether it can somehow be saved. 00:10–00:13: She looks toward the camcorder with a helpless, slightly miserable expression, then looks back down at the ruined-looking bowl. 00:13–00:15: She gives a tiny defeated sigh, looks directly into the camera and says in a funny, genuinely confused tone, **“What do I do now?”** She gives a small helpless shrug. Audio: Natural location sound only—steady rain against the window, sauce bottle squeezing, subtle kitchen sounds, refrigerator hum, fabric movement and distant apartment ambience. Her spoken line is natural and quiet. No music, narration or added sound effects. Goal: Cute, spontaneous and lightly comedic, like a tiny everyday mistake accidentally captured on an old family MiniDV camera. Her reaction should be subtle and genuinely confused rather than exaggerated. The spoken **“What do I do now?”** should feel like an impulsive reaction to the mistake, not a scripted performance. Motion quality: Keep every movement smooth, continuous and physically realistic. The sauce should visibly come out too quickly and create a believable mess. Avoid sudden camera movements or exaggerated acting. The vintage MiniDV aesthetic

A bright, clean beauty commercial of a young Southeast Asian woman with fair glowing skin, dark hair pulled neatly back, wearing a simple white camisole, standing in a modern bathroom with pastel mint and peach tiled walls, a round gold-rimmed mirror, and a white marble counter. Soft natural lighting, fresh and airy aesthetic, high-end skincare ad look. She smiles at the camera while holding a light-blue Wardah Lightening Gentle Wash tube. Cut to close-up of her hands on the marble counter picking up a Wardah Lightening Serum dropper bottle among other matching light-blue tubes and a cream jar. She pulls the dropper out with a drop of serum falling. Then she gently pats the lightweight serum onto her cheek with her fingertips, skin looking dewy and radiant. Next she holds a Wardah Lightening Day Cream jar, unscrews the white lid, and applies a small amount of white cream to her face with a glowing finish. Final shot: she stands behind the full product lineup arranged neatly on the counter (Gentle Wash tubes, serums, day cream jar, toner) with both hands framed under her chin, smiling softly. Cinematic beauty commercial style, shallow depth of field, soft highlights on skin, clean product packaging in matching powder-blue and white, no text overlay, photorealistic, 9:16 vertical.

Create a 30-second ultra-realistic handheld vlog video, filmed entirely inside a busy Apple-style retail store during the launch of a new iPhone. A young female tech vlogger wearing a pink fitted top and jeans is inside the store, surrounded by display tables with the new iPhones. Other vloggers, influencers, and customers are visible in the background testing phones, filming content, and talking about the launch. She holds the new iPhone in her hand and films herself in an authentic, energetic vlogger style. She occasionally turns the phone toward the camera to show its design, back, and camera system. Dialogue: “Okay, I’m inside the store checking out the new iPhone, and honestly, it looks so cool. I really love the design, the camera is seriously impressive, and the battery life looks really good too. This might actually be a really nice upgrade.” ENDING ACTION: As she finishes speaking, the phone accidentally slips from her hand and falls onto the store floor. She immediately reacts with a surprised expression, quickly bends down and picks it up. She checks the screen carefully, turns it over to inspect the phone, then looks back at the camera and says: “All good!” She then laughs naturally, relieved by what just happened. Style: authentic smartphone vlog, handheld movement, spontaneous reactions, realistic store lighting, busy background, natural facial expressions, realistic physics, detailed phone reflections, cinematic realism but not overly polished. Important: Keep the entire scene inside the store. The phone should visibly fall naturally, remain intact, and look exactly the same before and after the drop. No exterior shots or location changes.

Create a 12-second single-take cinematic wizard workshop sequence. First build an editable white-model scene in Blender based on the supplied reference, including stone walls, wooden shelves, an arched window, fireplace, books, astronomical equipment and an alchemy table. Animate a low first-person camera and one right hand holding a potion. Preserve the natural hand movement, fingertip contact, focus transitions, head movement and arm lag. Export the white-model animation, then use PixVerse and Seedance 2.5 with the Blender video as the motion and camera reference and the supplied images as appearance references. Preserve the room layout, continuous shot and potion action while creating realistic stone, carved wood, leather, glass, firelight, glowing reagents, irregular flames, embers, smoke and sparks.

Main Subject: Young Korean woman, 24, naturally attractive, realistic skin, minimal makeup, long dark hair loosely down. Wearing a simple oversized casual T-shirt and loose lounge pants. Preserve her exact identity, facial features, hairstyle, body proportions and appearance throughout. Location: Small old Seoul apartment bedroom on a quiet rainy morning. Simple wooden furniture, unmade bed, small desk, clothes casually placed around the room and a rain-covered window overlooking blurred apartment buildings. Steady rain outside. Lighting & Atmosphere: Cozy, dim blue-hour ambience. Cold blue-gray light from the rainy window mixed with a weak warm bedside lamp. Dark cloudy sky, muted colors, soft shadows and slightly underexposed interior. Sleepy, intimate rainy-morning atmosphere. Style: Ultra-realistic early-2000s Sony MiniDV home video. Completely candid and unstaged. Natural handheld movement, subtle camera shake, imperfect framing, occasional autofocus hunting, mild exposure shifts, faded colors, soft contrast, authentic DV compression, subtle low-light digital noise and microphone noise. Smooth continuous real-time motion throughout. No stuttering, judder, frame skipping, duplicated frames, stop-motion appearance, excessive motion blur, speed changes or low-frame-rate look. No stabilization or modern cinematic movement. 00:00–00:04: She stands beside her desk casually organizing a few small things, occasionally glancing toward the rainy window. The camcorder watches from a slightly imperfect angle. 00:04–00:07: She suddenly feels a sneeze coming. She pauses, scrunches her face slightly and brings her hand toward her nose. 00:07–00:10: She sneezes naturally into her hand. For a moment she looks a little surprised by how sudden it was. 00:10–00:13: She lowers her hand and looks directly toward the camcorder with a slightly embarrassed expression, realizing she was being filmed. 00:13–00:15: She gives a tiny amused smile and quietly laughs at herself before turning back toward the window. Audio: Natural location sound only—steady rain against the glass, soft room ambience, fabric movement, distant traffic, faint apartment sounds and the natural sneeze. No music, narration or added sound effects. Goal: Feel like a tiny accidental moment captured by a family member on an old MiniDV camcorder. Cute, natural and understated. Her reaction afterward should feel genuine rather than performed. Motion quality: Keep all body and camera movement smooth and continuous. The sneeze should be one natural, fluid movement rather than exaggerated or repeated. The vintage look comes from authentic MiniDV image characteristics, not from a low or inconsistent frame rate.

CONCEPT: Create a 30-second ultra-realistic slice-of-life video about a young woman spending a quiet evening on an apartment rooftop, trying to get an old battery-powered radio working before sunset. The entire story happens in one location. No shopping, no café, no market, no journey, and no walking-home sequence. The charm comes from tiny realistic actions, environmental sounds, and her reaction when the radio suddenly works. FORMAT: 30 seconds • 16:9 • 1080p • photorealistic live-action • authentic handheld consumer-camera footage MAIN CHARACTER A young Moroccan woman in her early 20s with naturally curly dark hair tied loosely with a fabric band. She wears a faded mustard sweatshirt, relaxed dark jeans, white canvas sneakers, and a thin silver necklace. Keep her face, hair, clothing, necklace, age, body proportions, and identity completely consistent. LOCATION An ordinary apartment rooftop in Casablanca, Morocco, shortly before sunset. The rooftop contains: - Concrete walls - Old plastic chairs - Several potted plants - Water tanks - Laundry lines - A small wooden table - A dusty portable radio - Neighboring apartment buildings - Satellite dishes - Laundry moving gently in the breeze Warm late-afternoon sunlight gradually changes as the scene progresses. No famous landmarks or recognizable brands. CAMERA STYLE Recorded by a friend using an older consumer camcorder. The camera should feel physically present on the rooftop. - Handheld movement - Slight natural shake - Imperfect framing - Occasional autofocus hunting - Exposure shifts when pointed toward the sunset - Mild digital noise - Slight compression - Natural motion blur - Ordinary color reproduction - No stabilization - No artificial bokeh - No commercial cinematography SHOT BREAKDOWN 0–5 SECONDS — THE RADIO Start with a close shot of an old dusty portable radio sitting on a small wooden table. The woman enters the frame and picks it up. She turns the power knob. Nothing happens. She taps the side of the radio. She looks at the camera. “Come on…” --- 5–10 SECONDS — TRYING AGAIN She opens the battery compartment. The camera moves closer over her shoulder. She removes the batteries and checks them. One battery is slightly loose. She adjusts it and puts everything back together. A small click. Still nothing. She gives the radio an annoyed look. --- 10–15 SECONDS — THE ANTENNA She pulls the antenna upward. The antenna makes a tiny metallic clicking sound. She rotates the radio toward different directions. The camera follows her movement. Suddenly, a burst of static comes through the speaker. She immediately stops moving. --- 15–21 SECONDS — FOUND IT She slowly turns the tuning dial. Static. More static. Then a faint, completely original radio melody comes through. Her expression changes into a genuine smile. She looks toward the camera. “There.” --- 21–26 SECONDS — SUNSET She places the radio on the table. She pulls a plastic chair closer and sits down. The camera slowly shifts away from her toward the rooftop horizon. The radio continues playing softly. Wind moves the laundry behind her. She quietly listens. --- 26–30 SECONDS — LITTLE ENDING She suddenly reaches over and lowers the radio volume. She looks at the sunset. The camera moves slightly closer from behind. She doesn't say anything. The shot ends naturally on her sitting beside the radio as the sunlight fades. AUDIO Authentic rooftop ambience only: - Wind - Distant traffic - Birds - Laundry fabric moving - Radio static - Dial clicks - Battery compartment clicks - Plastic chair scraping concrete - Quiet original radio melody - Natural breathing NO ADDED BACKGROUND MUSIC. The radio melody must be original and not imitate a recognizable copyrighted song. REALISM / PHYSICS The radio must behave like a real old battery-powered device. The tuning dial should physically rotate. The antenna should extend realistically. The static should change naturally as the radio is rotated. The laundry should respond subtly to the wind. The chair should scrape slightly when moved. Sunlight and shadows should remain physically consistent throughout. Hands must interact naturally with the radio and battery compartment. NEGATIVE PROMPT CGI, 3D render, animation, plastic skin, beauty filter, artificial face, face morphing, identity drift, extra fingers, malformed hands, duplicated people, floating objects, impossible radio mechanics, fake static, unrealistic antenna movement, teleportation, object duplication, excessive HDR, oversaturated colors, heavy cinematic grading, artificial bokeh, fake film grain, studio lighting, perfect stabilization, drone footage, commercial advertisement aesthetic, exaggerated acting, subtitles, captions, logos, watermarks, recognizable brands, copyrighted music, wardrobe changes, hairstyle changes, continuity errors. FINAL LOOK The final footage should feel like someone casually filmed a quiet evening on a rooftop and happened to capture a small moment that felt worth remembering. Don't force emotion. Don't make the sunset overly dramatic. Keep the imperfect camera movement, ordinary rooftop clutter, realistic wind, slight autofocus mistakes, and natural pauses. Simple moment. Real environment. Genuine reaction.

SCENE CONTEXT A 30-second realistic AAA third-person stealth-action game sequence set in a Japanese corporate office at exactly 5:00 PM on a bright weekday afternoon. The player character, NAGI, has finished her work and must reach the elevator without being stopped by her boss and given another assignment. ACTIVE REFERENCES [@Image1] = NAGI’s facial identity, if a character reference is supplied. Use only her facial appearance as the identity reference; replace any school clothing and background with the adult office character and environment specified below. NAGI: Japanese woman, 25, long straight black hair with blunt bangs, white short-sleeve office blouse, charcoal tailored trousers, black leather belt, white minimalist sneakers, employee ID clipped to her waistband, small black work tote held close to her body. Voice: light, breathy adult female voice, speaking Japanese in a hushed whisper. Keep her face, hairstyle, outfit, proportions, and accessories identical throughout. CAST SEPARATION Four distinct adult office characters appear, each with a different silhouette, age, and hairstyle so they read as separate people: TEAM LEADER: man in his 40s, 170 cm, average build, full head of short black hair parted at the side, thin metal-framed glasses, white dress shirt with a loosened navy tie. Appears only beside the first desk cluster, checking his watch. PAPERWORK COWORKER: woman in her 20s, 160 cm, slim, brown hair in a high ponytail, beige cardigan over a white blouse, carrying a thick stack of printouts. Appears only in the printer aisle. BOSS: man in his 60s, 160 cm, stout and round-shouldered, completely bald with a shiny scalp and a fringe of white hair above the ears, round gold-rimmed glasses, charcoal three-piece suit with a company lapel badge, carrying a blue assignment folder. Appears at the corridor T-junction and remains in that connected corridor during the whiteboard sequence. OFFICE ASSISTANT: man in his early 30s, 182 cm, lean and broad-shouldered, thick full black hair swept back, short beard, navy shirt with rolled sleeves, dark trousers, no glasses. Pushes the mobile whiteboard from the meeting-room alcove toward the elevator lobby. The BOSS is the only bald character in the entire video. The OFFICE ASSISTANT keeps a full head of thick black hair and a beard, stands more than 20 cm taller than the BOSS, and is clearly a different, much younger man. LOCATION MAP One unbroken spatial route the camera travels with her: Her workstation → low desk partition → printer aisle → corridor T-junction → meeting-room alcove with mobile whiteboard → elevator lobby → elevator interior. Keep the route compact and physically traversable within the 27-second continuous section. Foreground: polished linoleum floor, office desks, steel filing cabinets, rolling chairs, and reflective glass meeting-room partitions. Background: window wall on camera-right overlooking neighboring office buildings, dust suspended in the sunbeams. Light enters from camera-right along the office route. ELEVATOR GEOMETRY The elevator entrance is at the end of the office corridor. The call button is on the wall beside the entrance. The elevator is empty when NAGI enters. Inside the elevator: brushed-metal rear wall, side handrails, softly illuminated ceiling, control panel beside the doorway. No rear exit and no mirror creating a second NAGI. NAGI enters facing the rear wall, then turns to face the open elevator doors. For the final reverse shot, the camera is positioned INSIDE the elevator, immediately beside the doorway, looking inward at NAGI. The brushed-metal rear wall is behind her. The elevator doors close behind the camera, allowing her face to remain visible throughout the final shot. FIRST FRAME / BLOCKING First frame is already in motion: NAGI darts in from lower-left toward camera-right, work tote clutched to her chest, and drops into a crouch-slide behind a low desk partition beside her workstation. Camera behind her right shoulder. Game HUD fully visible from frame one. A small desk clock reads 17:00. FORMAT MODE One continuous unbroken take from 0.0s to 27.0s with no cuts of any kind, then a single HARD CUT at 27.0s to one final locked reverse shot that runs to 30.0s. Exactly one cut exists in the whole video, at 27.0s. The camera does not cut anywhere else. OPTICS One lens for the continuous section: 47° third-person over-the-shoulder framing as the baseline, breathing in to 29° on reaction beats and out to 63° for the boss encounter and moving-whiteboard concealment. All FOV changes in that section happen as smooth continuous zoom breathing, never as a jump. The final shot after the cut is a fixed 29° frontal framing of NAGI, no drift. CAMERA For the continuous section, the camera is a physical object flying with her. Chest-height, 1.5 meters behind NAGI, slightly camera-right of her spine, swinging with a soft spring delay half a beat behind her turns like an analog-stick gameplay camera. It dips to knee height when she crouches, rises when she stands, slides sideways along the filing cabinets with her, swings wide to corridor-left to reveal the boss encounter, drifts behind her for the moving whiteboard, and follows her through the open elevator doorway. The camera travels through open space around desks and partitions. It never clips through furniture, walls, the whiteboard, or elevator doors. After the cut, the camera is repositioned inside the elevator beside the doorway, looking inward at NAGI — locked off, eye level, completely static, no movement. ACTION [Beat 1 — 0.0s to 6.0s] NAGI crouch-slides behind the low desk partition, back flat against it, chest heaving. She leans out 20 cm to peek at the TEAM LEADER checking his watch beside the adjacent desk cluster, then pulls back. She whispers in Japanese: {定時だ…捕まったら終わり。} HUD flashes 【5:00 PM — SHIFT OVER】 and the mission banner 【OBJECTIVE: REACH THE ELEVATOR UNDETECTED】. The TEAM LEADER turns toward a ringing desk phone. NAGI slips behind his back, staying below the desk-partition line, and moves into the printer aisle. The camera follows without stopping. [Beat 2 — 6.0s to 12.0s] The camera stays with her beside the steel filing cabinets. NAGI presses her spine flat against the cabinets and shuffles sideways at 2 km/h, sneakers rolling heel-to-toe in silence. The camera tracks sideways with her at the same speed. The PAPERWORK COWORKER walks past the end of the row carrying a thick stack of printouts, scanning the office for someone available to help. NAGI holds her breath, pupils tracking the coworker without moving her head, and whispers: {来ないで…こっち見ないで。} The minimap vision cone sweeps past NAGI’s marker and turns away. HUD shows 【SNEAKING MODE】. The PAPERWORK COWORKER exits frame-left. NAGI exhales, crouches beneath the edge of the last desk, and slips into the corridor with the camera still on her shoulder. [Beat 3 — 12.0s to 18.0s] The BOSS steps around the T-junction two meters in front of her, blue assignment folder in hand. He catches a brief glimpse of movement. A red exclamation marker snaps above his bald head with a sharp alert sting. The HUD edge pulses red: 【ALERT】. He starts saying in Japanese: {なぎさん、追加の仕事が…} The camera swings wide to corridor-left as NAGI reacts in one motion: hugs her tote tightly against her ribs, drops below his eye line, pivots around the corner of a tall filing cabinet, and slips into the adjacent meeting-room alcove. The cabinet fully blocks his view before he can finish approaching her. She whispers: {今だけは無理…！} HUD prints 【EVASIVE MANEUVER】 and 【BREAK LINE OF SIGHT】. The BOSS takes a step toward the place where he last saw her, looking around the cabinet. NAGI has already moved to the far side of a mobile whiteboard in the alcove. The camera falls in behind her again. [

Main subject: A hauntingly beautiful Eastern woman in a tattered crimson wedding gown and red veil, her silver hair disheveled. The background is the ruins of a collapsed ancient Chinese building, under a grey sky with light rain falling. Story storyboard (0–15 seconds): 0–5s — Close-up and struggle: Camera slowly pushes in on the woman's face in close-up. Her eyes are unfocused, tears mixing with rain as they slide down her cheeks, yet an eerie smile plays at the corner of her mouth — her expression twisting between anguish and madness. 5–10s — Stumbling and shattering: Camera follows her footsteps as she staggers unsteadily through the ruins, the hem of her wedding gown sweeping over rubble and dead branches with a soft rustling sound. 10–15s — Despair and descent: Wide-angle shot pulls back as she collapses into a sitting position amid the ruins, the red veil slipping off to reveal her pale face. She tilts her head back toward the grey sky, her laughter fading as tears continue to fall. Style and atmosphere: Cinematic quality, dark gothic style, high contrast, striking red-and-black visual impact, oppressive, despairing, surrealist, 8K resolution, exquisite detail. Negative: Low quality, stutter, face/body collapse, over-bright, excessive gore, stiff motion, watermark, T-pose, bright palette, flashy VFX, rigid camera, lack of speed/blur, weak kills.

Tribute to sacred Hearts of Jesus and Mary Church, Scranton Pennsylvania, circa 1925, parish of Polish Immigrants

Create a 12-second single-take white-model animation in Blender based on the supplied wizard workshop reference. Build the stone walls, wooden shelves, arched window, fireplace, books, astronomical instrument and alchemy table filled with potion bottles. Animate a low first-person viewpoint with exactly one right hand holding one potion. Begin with the bottle near the lower-right edge, look around the workshop and toward the window, raise the potion naturally, pause to examine it, then lower it while turning toward the fireplace and glowing reagents. Export the white-model MP4. Then use PixVerse with Seedance 2.5, referencing the Blender video for camera, action and spatial layout and the supplied images for appearance. Preserve the continuous shot and timing while adding weathered stone, carved wood, worn leather, realistic glass, cool window light, warm fireplace illumination, glowing magical liquids, natural flames, embers, sparks and smoke.

Create a high-energy cinematic multishot action sequence featuring the female ninja warrior from the attached character sheet fighting masked demon-robot creatures inside an ancient ruined fortress. STYLE: Hollywood blockbuster, ultra-realistic, dark fantasy + futuristic sci-fi, massive cinematic scale, high-detail VFX, realistic physics, dramatic volumetric lighting, sparks, smoke, dust, debris, powerful energy effects. Wide aerial shot of a gigantic abandoned fortress surrounded by darkness and storm clouds. The camera rapidly dives through the ruins toward the female ninja standing alone. Suddenly, dozens of masked demon robots emerge from the shadows, surrounding her from every direction. Their eyes ignite simultaneously. Cut to an extreme close-up of her eyes — completely calm. A demon robot lunges toward her. She instantly disappears in a burst of energy. WHIP-PAN → CLOSE SHOT: she reappears behind the creature and delivers a devastating Kantara strike. The weapon releases a powerful energy arc, slicing through multiple robots. Fast cuts: - low-angle kick - spinning Kantara strike - robot smashed into a stone pillar - sparks exploding into camera - ninja sliding beneath a massive attack The remaining robots attack simultaneously. She leaps into the air. BULLET-TIME 360° CAMERA: time slows dramatically as she rotates through the center of the attacking creatures, performing multiple precise Kantara strikes. Energy trails form a glowing circular pattern around her. Suddenly— TIME EXPLODES BACK TO FULL SPEED. All robots are simultaneously blasted backward. Everything becomes completely silent. Smoke slowly clears. The ninja lands in a powerful stance. Hundreds of sparks fall around her. She looks forward as if the battle is over. Then— BOOM. The ground beneath her cracks. She slowly looks down. A massive red energy symbol begins glowing beneath the battlefield. The ninja realizes the truth. The demon robots were not attacking her to kill her — they were distracting her while completing a ritual. The destroyed robots suddenly begin connecting together mechanically, forming a gigantic underground machine. The camera rapidly pulls upward. The entire fortress begins shaking. A gigantic Demon King Robot rises from beneath the fortress, towering above the ninja. Its enormous masked face emerges through smoke and fire. One glowing eye opens. The ninja looks tiny compared to it. She slowly raises her energized Kantara. FINAL SHOT: extreme low-angle behind the ninja, enormous Demon King towering in the background. The Demon King releases a deafening roar. She charges directly toward it. CUT TO BLACK JUST BEFORE IMPACT. CAMERA & EDITING Fast cinematic cuts, aggressive whip-pans, low-angle hero shots, extreme close-ups, aerial establishing shots, dynamic tracking, handheld impact movement, orbi