MiniMax Hailuo 3 提示詞與案例

A Two-Character Scene Driven by Exact Dialogue

14s · 含音訊

cinematic sci-fi suspense video. A realistic spaceship crew in full futuristic uniforms follows a mysterious distress signal and boards a dark, abandoned spacecraft drifting in space. Flashlights cut through darkness as they move cautiously through narrow metallic corridors. Warning lights flicker, metal creaks, and their boots echo on the floor. One crew member says, "Signal's coming from deeper inside." They enter a large chamber filled with hundreds of empty cryogenic pods, all open and abandoned. Another crew member says nervously, "Where did everyone go?" They approach a final closed door at the far end. The captain slowly opens it, and instead of another ship compartment, it reveals a completely normal present-day elementary school classroom in bright daylight. Children sit at desks, backpacks on the floor, colorful posters on the walls, and a teacher at the front turns to the crew and scolds them: "You're late again. Take your seats." The astronauts stand frozen in confusion at the doorway. Realistic tone, smooth camera movement, strong suspense buildup, with the final reveal clear, sudden, and absurd. Include realistic audio: radio static, low ship hum, footsteps, pod machinery ambience, door hiss, then ordinary classroom sounds and the teacher's voice.

Starship Bridge — The Hyperspace Jump

10s · 768p · t2v · 含音訊

integrated_multimodal_description: [Shot 1] Cinematic, medium wide shot, pushing in slowly. In the cavernous, dimly lit bridge of a starship, sleek metallic consoles with glowing amber displays flank a massive, curved observation window. A female captain, in her late 40s with an athletic build and short silver-streaked black hair, stands in the center midground. She wears a structured, high-collared dark navy military tunic with silver chest insignias. Her back is to the camera, silhouetted against the cool, ambient starlight pouring through the thick glass. She stands perfectly still with her hands clasped tightly behind her back. Outside the window, a massive armada of jagged, dark grey dreadnoughts hovers in tight formation against a deep purple space nebula. The fleet's massive rear thrusters begin to glow with an intense, escalating bright blue light. [Shot 2] At 00:04.500, the camera cuts to a close-up of the captain's face and shakes strongly. The brilliant blue-white light from the fleet's gathering energy reflects vividly in her dark eyes. Suddenly, a blinding white flash floods through the window, completely washing out the background as the fleet jumps to hyperspace. The sheer spatial force violently jolts the bridge, causing the captain from Shot 1 to stagger slightly forward, her shoulders tensing as she visibly braces herself against the physical tremors. As the intense white light fades abruptly, leaving only the dim, empty expanse of the purple nebula reflected on her starkly lit skin, her jaw clenches, and she slowly closes her eyes in the newly emptied space. overall_soundscape: A low, resonant hum of the ship's ambient life support systems serves as the baseline, soon drowned out by an audible, escalating, high-pitched electronic whine as the fleet outside charges its hyperdrives. A massive, deafening, bass-heavy boom and sharp crackle erupts during the blinding flash, accompanied by the loud metallic creaking, rattling, and deep thuds of the bridge's bulkheads vibrating under immense physical stress. The intense roaring impact then cuts abruptly back to a hollow, echoing room tone, leaving only the faint, steady hum of the isolated bridge. non_diegetic_music: Cinematic space-opera orchestral score, slow tempo, featuring a solitary, mournful French horn melody over deep, sustained string dissonances that build rapidly in volume and intensity, swelling to a massive orchestral peak before snapping immediately into silence right after the jump.

A Morning Begins from Bed to a Seaside Terrace

15s · 含音訊

Create a 15-second ultra-realistic cinematic lifestyle vlog video, vertical 9:16, featuring the same young woman throughout the entire video. Preserve her facial identity, facial proportions, hairstyle, skin tone and overall appearance consistently in every shot. She wears the same outfit throughout: fitted white V-neck T-shirt with a small subtle logo, blue denim jeans, natural makeup, long softly wavy brown hair. 0:00–0:01 — Wake-up: Close-up inside a beautiful bright bedroom. The woman is lying comfortably on the bed, slowly wakes up, stretches naturally and opens her eyes. She is NOT filming a vlog yet and does not hold a phone or camera. Soft morning sunlight enters through the curtains. 0:01–0:02 — Gets up: Medium shot. She sits up on the bed, smiles softly, fixes her hair and gets ready to start her morning. Natural, effortless movement. 0:02–0:03 — Walks to window: She walks toward the large glass balcony door/window. Camera follows her naturally from behind/side. 0:03–0:04 — Seaside reveal: She opens the curtains/door and looks outside. Reveal a breathtaking blue ocean, coastal hills, flowers, balcony and beautiful morning sunlight. She smiles happily while taking in the view. 0:04–0:05 — Steps outside: She walks out onto the seaside terrace. Gentle ocean breeze moves her hair naturally. Wide cinematic shot showing the beautiful surroundings. 0:05–0:06 — VLOG START: Only now she starts filming herself in handheld selfie-vlog style. She looks into the camera with a bright natural smile and says: “Good morning!” 0:06–0:07 — Show the view: She turns the camera away from herself and slowly pans across the stunning ocean, coastal mountains, flowers and terrace. Smooth handheld vlog movement. 0:07–0:08 — Back to selfie: Selfie shot. She looks into the camera and happily says: “This place is just perfect!” 0:08–0:09 — Location reveal: Wide cinematic shot of the cozy seaside terrace with wooden table, chairs, plants and flowers overlooking the ocean. 0:09–0:10 — Walk to table: Medium tracking shot as she walks toward the table, enjoying the view. Her hair and T-shirt move gently in the sea breeze. 0:10–0:11 — Sit and relax: She sits at the seaside table, smiling peacefully and enjoying the ocean view. A refreshing orange-colored juice is placed on the table. 0:11–0:12 — Juice close-up: Cinematic close-up of her hand picking up the glass of fresh orange juice. Beautiful ocean bokeh in the background, natural sunlight reflecting through the glass. 0:12–0:13 — Vlog toast: Selfie shot. She raises the juice toward the camera with a cheerful smile and says: “Cheers to good days!” 0:13–0:14 — Happy close-up: Beautiful close-up of her smiling naturally at the camera, ocean and warm sunlight softly blurred behind her. 0:14–0:15 — Ending: Camera moves from her toward the sparkling ocean and peaceful coastal landscape. Warm sunlight, gentle waves and a relaxing cinematic ending. Overall Style Ultra-realistic, cinematic travel vlog, natural handheld camera movement, realistic human motion, smooth transitions, soft morning sunlight, realistic ocean waves, gentle wind in hair and clothes, beautiful coastal atmosphere, premium lifestyle aesthetic, natural expressions, authentic vlog feeling, shallow depth of field, cinematic composition, realistic skin texture, high detail, 4K quality.

The Secretary’s Office-Scandal Trap

15s · t2va · 含音訊

1960年代，香港邵氏復古電影風格：戴黑粗框眼鏡、頭髮微捲及肩的霸總生氣地按住女秘書(粉紅色廉價套裝、明顯腮紅、淡藍色眼影)的肩膀，質問女秘書道"昨晚，妳到底去了哪裡？"。女秘書開始眼眶泛淚，推開霸總的雙手，然後轉身拭淚哭泣著說"總裁這是我私人的事情，不用你管!"。總裁快步接近女秘書，然後將女秘書的身體按壓在復古的竹製躺椅上，總裁認真地對女秘書說"對不起，我錯了。"然後總裁開始親吻女秘書的臉頰。女秘書一邊假裝喘氣，一邊從總裁的背後拿高了手機喀擦一聲拍照。下一個畫面是香港街道的路人，手中拿著報紙(上面有總裁親吻流淚女秘書的自拍照 新聞標題寫著"OFFICE SCANDAL")。下一個畫面是圍著時尚花頭巾的女秘書(改穿米色連身風衣、黑色高跟鞋)自信地"哼"一聲，從書報攤拿了一份有相同頭版照片的報紙，然後得意地看著鏡頭比了個"shh"的手勢。畫面fade into black.

A Fairy-Wand Role Reversal by the Pool

15s · t2va · 含音訊

美國喜劇reality show: 豪宅的泳池邊，20歲金髮藍眼的紅色比基尼美女與60歲灰髮憔悴的清潔婦正在激烈地爭吵，美女說"醜死了，你這死老太婆!"，清潔婦也不甘示弱說"整天只會換男人，不正經!"。這時畫誇張眼影妖后造型的drag queen飛過，便將手中的仙女棒往美女與清潔婦的頭上各點一下，結果美女迅速老化變成70歲皮膚鬆垮的老女人，清潔婦則迅速變成年輕的20歲美麗模樣。變年輕的清潔婦自信地說"啊，我現在感覺好多了!"就脫掉制服，露出夏季連身華麗黑色窄裙與高跟鞋，然後自信地離去，留下崩潰且一臉錯愕的老女人無助地看著鏡頭哭著吶喊:"不!!!!!!"

A Papercraft Battle in a Fantasy Valley

15s · 含音訊

【核心创意】 12 秒，16:9 横屏视频。手工纸艺立体拼贴与奇幻故事书风格的二维动画。画面由多层纸片、裁切边缘、纸张纤维、柔和层叠阴影和轻微定格动画质感构成，色彩鲜明，具有微缩舞台空间感。 故事发生在一片绿色山谷战场。左侧是英雄阵营：一名棕色长发的女弓箭手，穿黑色轻甲；一名白色长胡须的老法师，穿深蓝长袍，手持燃烧法杖；一名穿银灰色盔甲的年轻骑士，手持长剑和盾牌；远处有一匹白色独角兽和一面带白色独角兽图案的蓝色旗帜。右侧是敌方阵营：骷髅士兵、绿色哥布林和一名骑乘棕红色飞龙的黑甲骑士，旁边竖立一面黑色骷髅旗帜。远处山脉、松树林和一座冒着黑烟的黑色尖塔城堡。 【画面过程说明】 0–2 秒｜大全景： 镜头从山谷战场大全景缓慢向前 Push In。蓝色独角兽旗帜和黑色骷髅旗帜在风中摆动，城堡上方的黑烟缓慢升起，草地和火焰轻微运动。英雄阵营与敌方阵营隔着战场对峙。 2–4 秒｜中景切换： 镜头切到左侧女弓箭手。她迅速拉满弓弦，瞄准右侧骷髅士兵并射出一支箭。箭矢沿清晰轨迹飞过战场，骷髅士兵举盾挡住箭矢，产生少量纸片火花，不出现受伤或死亡。 4–6 秒｜仰拍跟随： 镜头快速 Tilt Up 跟随棕红色飞龙。飞龙扇动翅膀俯冲，向英雄阵营喷出一股短暂的橙色火焰。老法师举起燃烧法杖，形成一面半透明金色魔法护盾。火焰撞上护盾后向两侧散开，不发生爆炸。 6–9 秒｜低机位中景： 年轻骑士举起长剑向前冲锋，与一名骷髅战士发生一次清晰的剑盾碰撞。绿色哥布林从侧面冲来，骑士侧身闪避。镜头进行短距离 Tracking Shot，跟随骑士向右移动，动作快速但保持人物比例、盔甲和武器稳定。 9–11 秒｜动作高潮： 镜头切到战场中央。骑士与骷髅战士再次交锋，女弓箭手继续射箭，老法师维持金色护盾，飞龙在上方喷出短暂火焰，哥布林举盾冲向前方。加入少量尘土、火星和纸片碎屑，表现激烈战斗，但不出现血腥画面。 11–12 秒｜大全景定格： 镜头快速 Pull Out，重新展示完整山谷战场。飞龙在空中盘旋，弓箭手保持射击姿势，法师举杖维持护盾，骑士与骷髅战士停留在交锋姿态，双方仍未分出胜负。火焰、烟雾和旗帜继续运动，最后定格在战斗高潮画面。 声音：风吹旗帜声、弓弦拉动声、箭矢破空声、飞龙翅膀声、火焰喷射声、魔法护盾低沉嗡鸣、剑盾碰撞声、哥布林脚步声和紧张的奇幻战斗配乐。无对白、无旁白。 不想要：写实摄影、普通3D游戏CG、塑料材质、角色换装、脸部变化、人物数量明显增加、武器消失、箭矢倒飞、火焰爆炸、血腥画面、断肢、角色死亡、骷髅或哥布林变形、字幕、Logo、乱码文字、镜头剧烈抖动、黑屏转场。 必须保持：全片为手工纸艺立体拼贴与二维定格动画风格；女弓箭手、老法师、年轻骑士、飞龙骑士、骷髅士兵和绿色哥布林的外观全程一致；英雄阵营位于左侧，敌方阵营位于右侧；结尾双方仍在交战，不出现明确胜负。

The Orange Cat Lets It Out

15s · 含音訊

Cinematic comedy sequence, 15 seconds. [SCENE 1: 0-4s] Extreme close-up: A morbidly obese, orange tabby cat is fast asleep on a tiny, expensive velvet pillow in a pristine living room. The cat’s stomach rumbles ominously, emitting a deep, bass-heavy vibration that violently shakes the coffee table. [CUT TO] [SCENE 2: 4-7s] Low angle macro shot: The cat lifts one hind leg slightly. A tiny, glowing neon-green puff of gas escapes in ultra slow-motion, accompanied by a rippling shockwave that visually warps the air around it. [CUT TO] [SCENE 3: 7-11s] Wide tracking shot: The shockwave expands violently, blowing the living room furniture, the TV, and the doors out of the house in a fiery blast of glowing green energy and flying cat hair. [CUT TO] [SCENE 4: 11-15s] Orbiting space shot: Looking down at Earth from orbit. A colossal, glowing green mushroom cloud erupts from the continent, rapidly expanding into the exact shape of a giant, glowing cat paw. Epic cinematic lighting, hyper-realistic, deep shadows.

A Cinematic Journey in One Flowing Take

10s · 含音訊

Whip pan from a screaming crowd to a massive kraken-like creature rising from flooded city streets. Tentacles crush traffic lights and wrap around buildings. The camera sways violently with each impact. Water rushes at lens level, debris floats by. VFX water simulation, dynamic lighting, and lens flare through broken signs.

Automatic Lip-Sync for a High-Speed Rap Performance

30s · ref2va · 含音訊

モード1：Omni Reference プロンプト：添付のキャラクター参照（ 📷Image1 ）とオーディオトラックをタイミングガイドとして使用してください。オーディオにある「音声」に完全に会うようにキャラクターの口とアクションを入れてリップシンクしてダイナミックなカメラアングルでラップを披露してください。カメラはマルチカットでキャラの部位をクローズアップしてください。全て超ハイスピードで激しく行ってください。 モード2：Omni Reference プロンプト：添付のキャラクター参照（ 📷Image1 ）とオーディオトラックをタイミングガイドとして使用してください。オーディオにある「音声」に完全に会うようにキャラクターの口とアクションを入れてリップシンクしてダイナミックなカメラアングルでラップを披露してください。カメラはマルチカットで超ローアングル・超ハイアングルを小刻みに切り替えたUS東海岸のラップビデオのようなスタイルに仕上げる。全て超ハイスピードで激しく行ってください。

A Reasoning Challenge Built from Traffic Rules

14s · 含音訊

A single continuous fixed wide shot in a plain, brightly lit test room, filmed like an unedited behavioral experiment. At the start, a red cube is on a table, a drawer is closed, a lamp is off, a chair sits precisely inside a taped floor outline, a hat hangs on a wall hook beside a bare mannequin, and a door is open. One person quickly performs six clearly separated actions in this exact order: places the red cube on a shelf, opens the drawer, turns on the lamp, moves the chair away from its taped outline, takes the hat from the hook and puts it on the mannequin, then closes the door. An off-screen instructor clearly says, "Undo only the last three actions." The person pauses briefly, understands the instruction, and carries it out exactly. No cuts, no time jumps, no extra actions, no additional dialogue, realistic synchronized room sounds.

A Blue-Haired Hero Escapes with a Spirit Fox

15s · ref2va · 含音訊

Use the reference @ image for the exact character design, clothing, proportions, blue hair, pointed ears and glowing cyan spirit fox. Preserve the cinematic stylized 3D look, saturated teal jungle palette, soft volumetric light and detailed natural textures. No dialogue; environmental sound only. 0–4 seconds: Begin close to the reference composition on the ancient stone bridge. The girl kneels beside the small glowing spirit fox as ripples begin moving backward across the stream below. She notices the unnatural movement and looks over her shoulder. A massive moss-covered stone serpent suddenly erupts from beneath the bridge, lifting one side of the platform. The stone tilts physically under her weight. She loses balance, catches herself with one hand and quickly pulls the spirit fox against her chest as cracks spread beneath her knees. 4–10 seconds: The bridge collapses progressively behind her. She rises naturally from the crouch and sprints barefoot across the tilting stone slabs, carrying the fox securely with one arm. Each footfall dislodges moss and small fragments; broken slabs fall with believable weight and strike the water below, producing delayed splashes. The camera tracks closely beside her at waist height. The serpent sweeps its heavy stone tail across her path. She drops into a fast knee slide beneath it; her torn cloak and blue hair trail behind with clear inertia. Still moving forward, she catches a hanging vine with her free hand. Her momentum pulls the vine taut and swings her outward across the widening gap while the camera arcs alongside her. 10–15 seconds: At the highest point of the swing, the vine begins tearing from the temple ceiling. She releases before it snaps, travels forward in a natural gravity-driven arc and lands hard on the opposite platform. She absorbs the impact through her feet and one hand, then rolls once across her shoulder while protecting the fox against her chest. The camera drops and rolls partially with her, then stabilizes behind her as she rises into a defensive crouch. The spirit fox leaps from her arms and lands in front of her, its cyan light intensifying as the serpent crashes into the broken bridge behind them, sending water, dust and stone fragments through the backlight. Maintain one continuous route and clear cause-and-effect motion. No teleporting, floating, sudden directional changes, extra characters, costume changes or transformation of the girl. Keep the fox small throughout; only its light becomes brighter in the final moment.

A Cat Shelters an Abandoned Puppy

Popo, a cat, finds a puppy abandoned in a cardboard box under the eaves. At first, Popo acts cold and indifferent, but when heavy rain begins, the cat bravely shields the puppy from the storm and spends the night keeping it warm beneath its belly. By the next morning, a bond has formed between them. They begin facing the harsh life of stray animals together—Popo suppressing its own hunger to give the puppy its prey, even sneaking into a supermarket in search of food. Eventually, with the kindness and help of people around them, the two manage to get something to eat. As they cuddle together beneath the setting sun, they develop a deep and genuine bond that transcends species.

Bauhaus Letterforms Recompose on Beat

12s · t2va · 含音訊

Create an 8-cut kinetic-typography spot in 16:9, 24fps, exactly 12s. Style: Bauhaus / Swiss International — flat primary colors (red, yellow, blue, black, off-white), strict grid, geometric sans-serif type. This film is 90% typography and geometric shapes in motion, 10% texture accents. CUT 01 | 0.0-1.5s - Off-white void. The word "FORM" drops letter by letter onto a baseline grid, each landing with a small bounce. CUT 02 | 1.5-3.0s - A red circle rolls in from the left and knocks the "M" out of frame; "FOR—" holds one beat. CUT 03 | 3.0-4.5s - Hard cut: full yellow frame, "FOLLOWS" stacked vertically, letters sliding in alternating directions. CUT 04 | 4.5-6.0s - A blue diagonal wipes the frame; "FUNCTION" sits on the diagonal; the camera rotates until it reads horizontal. CUT 05 | 6.0-7.5s - The three words swap positions on a strict 3-column grid, snapping on beat. CUT 06 | 7.5-9.0s - All type shrinks into an 8pt grid texture; one black square scales up through center. CUT 07 | 9.0-10.5s - The square splits into a Mondrian composition; one word per color field. CUT 08 | 10.5-12.0s - End card: "FORM FOLLOWS FUNCTION — 1919" aligned bottom-left, the red circle as the full stop, hold. Typography is fully readable before any shape overlaps it. Letters never distort or melt; kerning stays optically even. Editing: hard cuts and snap moves locked to 120bpm. Audio: minimal electronic clicks + bass pulse on every cut. DO NOT: gradients, drop shadows, 3D extrusion, serif fonts, melted letters, added words.

Anime Movie Night Jump Scare

2D anime | romantic comedy | cel-shaded, clean line art, dark blue night palette. Multishot, 6 shots. Cuts only at the specified points. CHARACTERS HANA: wavy shoulder-length dark red hair, oversized gray cardigan with one button missing, a bandage on her index finger. 160 cm. YUTO: neat black hair with a small bed-head tuft at the back, navy hoodie with a pilled sleeve, glasses pushed up on his forehead. 178 cm. LOCATION Dark living room at night. They share one sofa under a single fleece blanket. A TV off-frame in front of them is the only light source, flickering blue on their faces. A bowl of popcorn between them. SUBTITLES Spoken dialogue is in Japanese. English subtitles are burned into the image as on-screen text only — they are never spoken aloud. Style: white sans-serif, thin black outline, one single line, bottom center of frame, 8% from the bottom edge. Each subtitle appears with its line and disappears at the cut. Subtitle text is shown inside 【】 brackets below; the brackets themselves are not displayed. Shot 1 (0–2.5s) — Medium front shot of both, FOV 47, static. Hana sits upright, arms crossed, smug smile, chin raised. Yuto beside her grips a cushion with both hands, already tense. Hana (spoken, Japanese): 「全然怖くないし。」 On-screen subtitle: 【I'm not scared at all.】 HARD CUT Shot 2 (2.5–5s) — Close-up on Yuto, FOV 29, slow push-in ending on his eyes. His pupils shrink to tiny dots, a vertical column of blue shade lines drops over his upper face, sweat drop on his temple. He swallows, the cushion squeezed flat. No subtitle in this shot. HARD CUT Shot 3 (5–8s) — Medium front shot, FOV 47, static. A violent white flash from the TV and a loud sting. Both jump. Clear gag faces: mouths huge and wavy, eyes white, hair standing in spikes. The popcorn bowl flips and popcorn bursts upward like confetti. Two small white ghost-shaped souls slip out of their open mouths. Hana and Yuto (spoken, Japanese): 「ぎゃああああっ！」 On-screen subtitle: 【AAAAAAH!】 HARD CUT Shot 4 (8–10.5s) — Wide shot, FOV 63, static. They are clutching each other tightly, trembling, their outlines drawn with shaky wobbling lines. Popcorn rains down on them. The souls drift back into their mouths. No subtitle in this shot. HARD CUT Shot 5 (10.5–13s) — Two-shot close-up, profile, FOV 29, static. Silence. They slowly realize how close they are, faces a hand apart. Both blush deep red at the same time. A tiny comic sparkle pops between them. They let go and shuffle apart in short jerky movements. No subtitle in this shot. HARD CUT Shot 6 (13–15s) — Close-up on Hana, three-quarter front, FOV 29, static. Normal detailed anime face: cheeks red, eyes sliding sideways, lips pouting. One popcorn kernel stuck in her hair. Hana (spoken, Japanese): 「…今のはノーカン。」 On-screen subtitle: 【...That one doesn't count.】 She pulls the blanket up over her nose. End on her eyes peeking above the blanket. LIGHTING Only light source is the off-frame TV: flickering cool blue 8500K, with a single white flash in shot 3. Deep shadows in the room. Sound: No score. Production audio only — faint TV dialogue murmur, a sharp horror sting, popcorn scattering, fabric rustle, double scream, then near silence and a soft blanket rustle. All voices in Japanese only. Characters keep the same face, hair and wardrobe in every shot. Gag faces are clear, exaggerated super-deformed expressions, then return to the normal detailed anime face. Clean consistent line art, consistent lighting between shots. Subtitles stay in the same position, size and style in every shot, spelled exactly as written. The room contains only the sofa, the blanket and the popcorn bowl.

Turning an Educational Vision into an Experience

15s · 含音訊

A Lacquer-Thread Vase from Clay Rolling to Display

15s · 含音訊

【参考图规则】 @图片1 是最终漆线雕作品的唯一权威参考。 必须严格保持图片1中的作品造型、主体比例、漆面颜色、金色漆线纹样、纹样走向、器型和整体气质。 不得随意增加龙、凤、佛像、文字或不存在的装饰。 @图片2 是包装盒、包装纸、品牌标识以及产品标签的唯一权威参考。 所有包装结构、颜色和标识均按照图片2执行。 @图片3 是厦门传统漆线雕工作室的环境与工匠服装参考。 保持真实闽南手工作坊质感，不做古装影视化处理，不制造虚假的“古代作坊”。 【目标】 制作一支15秒、9:16竖版的厦门漆线雕非遗工艺短片。 主题： “一根线，走完三百年的手艺。” 影片完整呈现： 备料 → 舂打漆线土 → 搓线 → 盘线成纹 → 安金 → 贴金 → 清理完成 → 包装 → 上架 快速剪辑， 字幕驱动， 即使完全静音观看也能理解整个制作过程。 视觉采用真实高端人文纪录广告摄影： 35毫米胶片电影质感， 细腻颗粒， 浅景深， 大量微距， 自然手持， 运动非常克制， 不做旅游宣传片， 不做华丽国潮特效， 不做博物馆宣传片。 重点永远是： 手， 线， 漆， 金箔， 纹样， 时间。 【金色就是时间】 整支影片必须存在一条不可逆的视觉变化： 画面中的“金色”从无到有，并越来越多。 影片开始： 只有黑、 深褐、 砖灰、 暗红， 几乎看不到金色。 漆线开始盘绕以后， 画面出现第一点暖金。 贴金以后， 金色迅速扩大。 作品完成时， 精细金色纹样覆盖主体。 最后上架时， 整个作品被温暖自然光照亮。 每一个镜头都必须比前一个镜头拥有更多的金色。 这个变化不能倒退。 金色就是这支影片的时间。 【固定字幕牌】 整个影片始终只有一个字幕牌。 位置： 画面下方三分之一， 水平居中， 所有镜头完全相同的位置。 造型： 非常克制的小型圆角矩形， 深朱砂红底， 暖米白文字。 两行文字： 第一行： 较细字体， 显示“工序”。 第二行： 粗体， 显示一句极短的动作描述。 字幕牌： 不移动， 不放大， 不缩小， 不淡入淡出， 不跳动。 只在指定剪辑点瞬间更换文字。 字体必须清楚、正确。 【镜头序列】 0—1.7秒 主镜头。 深夜般昏暗的传统工作台。 一盏暖色工作灯只照亮双手。 桌面上可以看到： 陈年砖粉质感的细粉、 深色大漆材料、 正在被反复捶打揉合的深褐色漆线土。 工匠双手将材料反复捶、压、揉， 逐渐形成柔软、富有韧性的泥团。 周围环境全部沉入黑暗。 没有金色。 字幕： “第一道” “捶土成线” 1.7—3.3秒 极端微距。 一小块漆线土放在传统搓线板之间。 工匠双手稳定向前推动搓板。 原本粗厚的泥条逐渐被搓成长而均匀的细线。 摄影机贴得非常近。 能够清楚看到： 漆线轻微湿润的表面， 细小纹理， 手指压力， 线条被不断拉细。 背景完全虚化。 字幕保持： “第一道” “捶土成线” 3.3—5.0秒 主镜头。 朱红漆面的器物坯体第一次出现。 工匠用极细工具， 将刚刚搓好的柔软漆线轻轻落在器物表面。 第一根漆线贴上去。 只有一根。 然后第二根。 线条开始形成第一个小小的卷云纹。 画面第一次出现非常微弱的暖色高光。 字幕： “第二道” “一线起纹” 5.0—6.8秒 微距插入镜头。 镜头几乎贴着器物表面横向观察。 工匠用竹制细工具推动漆线： 盘， 绕， 结， 堆。 几根不足毫米级视觉尺度的柔软漆线， 逐渐形成具有明显高度差的浮凸纹样。 线条之间非常紧密。 卷云、缠枝、如意形态逐渐出现。 重点展示： 线并不是画上去的， 而是真正一根一根盘出来的。 字幕保持： “第二道” “一线起纹” 6.8—8.6秒 主镜头。 器物已经完成大部分漆线纹样。 摄影机非常缓慢地向前推近。 工匠旋转器物。 光线擦过密集漆线表面。 能够看到： 高低起伏， 盘绕结构， 层层叠叠的线性浮雕。 这时依然没有真正的金箔。 只有漆线自身的暖棕色。 字幕： “第三道” “盘线成雕” 8.6—10.2秒 全片最重要的声音与视觉高潮。 极端微距。 一张极薄金箔悬在空气里轻微颤动。 几乎没有重量。 工匠屏住动作， 用传统工具将金箔缓缓落向已经完成的漆线纹样。 金箔接触表面的瞬间， 贴住。 镜头保持。 不要快速切走。 细小金箔自然贴合漆线的高低起伏， 金色第一次大面积出现。 字幕： “第四道” “一片金落下” 10.2—11.7秒 微距。 柔软毛刷轻轻扫过作品表面。 多余金箔碎屑被一点点扫开。 随着刷毛经过， 清晰、 锐利、 细密的金色漆线纹样从杂乱金箔中显现。 这是第二个视觉高潮。 镜头必须清楚表现： 杂乱金箔 变成 精确金色纹样。 字幕： “第五道” “金纹醒来” 11.7—12.8秒 主镜头。 完成后的作品放在深色木质工作台上。 工匠用双手缓慢旋转检查。 没有任何戏剧表演。 只检查： 纹样， 漆面， 金箔， 边缘， 细节。 自然光已经明显进入工作室。 金色纹样被晨光照亮。 字幕： “第六道” “最后一眼” 12.8—13.8秒 插入镜头。 作品被轻轻放入定制包装盒。 暖米色软布包裹器物。 盒盖缓慢合上。 手将包装盒推向画面前方。 纸张、 布料、 木盒均保持真实触感。 不要奢侈品浮夸包装。 字幕： “第七道” “入盒” 13.8—15秒 最终镜头。 切到极简现代非遗精品店。 温暖自然晨光。 深色木制陈列架。 一只手将完成的漆线雕作品从画面侧面轻轻放到展示台中央。 手退出画面。 作品保持完全静止。 金色漆线在自然光中形成极精细的浮雕反光。 背景虚化。 最后0.6秒不再运动。 字幕： “第八道” “上架” 画面中央仅允许出现一句极小的中文： “厦门漆线雕” 下面更小： “一线成雕” 最终画面必须像高端工艺品牌的静态产品摄影。 绝对不要继续运动。 【色彩】 整支影片限制在以下颜色： 陈年砖粉灰， 生漆深褐， 木质黑褐， 朱砂红， 暖米白， 金箔金。 影片前半段： 黑褐色占主导。 中段： 朱红逐渐出现。 后半段： 金色逐渐占据视觉中心。 禁止： 青蓝科技色， 霓虹， 紫色， 赛博朋克， 高饱和国潮配色。 金色必须来自真实金箔和真实光线。 不能使用发光特效制造金色。 【摄影】 全片使用真实人文纪录摄影语言。 大量： 100毫米微距镜头， 近距离手部特写， 极浅景深， 35毫米胶片颗粒。 摄影机运动非常少。 允许： 轻微呼吸感手持， 一次非常缓慢的轴向推进， 极细微的跟随动作。 禁止： 无人机， 环绕运镜， 快速推拉， 旋转镜头， 甩镜， 变焦冲击， 慢动作， 速度渐变， 镜头炫技。 镜头永远尊重手艺本身。 【声音】 全片没有任何音乐。 没有旁白。 没有人物对白。 没有广告配音。 只使用现场真实声音。 0—3.3秒： 凌晨安静工作室。 远处非常轻的环境底噪。 漆线土落在木板上的闷响。 手掌揉压材料的湿润摩擦声。 搓板来回运动产生细密摩擦声。 3.3—8.6秒： 整体声音进一步降低。 细工具轻碰器物表面的声音。 手指移动。 漆线被放下时极轻微的黏连声音。 器物缓慢旋转时木架产生细小摩擦声。 8.6—10.2秒： 这是整支影片最重要的声音时刻。 其他环境声音全部压低。 只留下： 金箔极薄的纸张颤动声， 轻微呼吸， 工具触碰金箔的细小声音。 金箔落到漆线表面的瞬间， 接近安静。 让观众感觉自己离这张金箔只有几厘米。 10.2—12.8秒： 软毛刷扫过金箔。 细碎金箔摩擦。 器物在木架上轻轻旋转。 12.8—15秒： 包装纸折叠。 布料摩擦。 盒盖轻轻合上。 随后进入店铺： 作品底座接触木质展台， “嗒”。 最后接近完全安静。 只保留非常微弱的室内环境声。 【核心视觉原则】 不要把它拍成： “传统文化宣传片”。 要把它拍成： “世界顶级手工艺品牌新品诞生纪录”。 传统来自材料和工艺， 高级感来自摄影、节奏和克制。 【禁止项】 不得出现任何与产品无关的文字。 不得出现旅游宣传标语。 不得出现： “匠心传承” “非遗之美” “千年文化” “东方美学” 等泛化宣传口号。 不得出现不存在的历史年代。 不得出现虚假的皇宫或寺庙场景。 不得增加和尚、古装人物、舞狮、灯笼等所谓中国元素。 不得把漆线雕表现成木雕、石雕或刀刻。 重点必须明确表现： 搓线， 放线， 盘线， 绕线， 堆线， 贴金。 不得用三维特效让纹样自动生长。 不得让漆线自行移动。 所有纹样必须由人的手完成。 不得使用魔法粒子。 不得让金箔发光。 不得使用人工光晕。 不得使用慢动作。 不得加入速度渐变。 不得加入转场音效。 不得使用呼啸声。 不得出现手机界面。 不得出现电商界面。 不得出现价格。 不得出现二维码。 不得出现网站。 不得出现社交媒体账号。 不得出现水印。 不得增加第十个镜头。 最终画面完全静止。

A Woven Handbag on the Riviera

15s · ref2va · 含音訊

A Rushed Morning After Oversleeping

15s · t2va · 含音訊

A cinematic realistic morning scene of a young adult woman suddenly waking up in a hurry. She quickly checks the time on her phone and realizes she is late. Looking stressed but determined, she immediately gets out of bed, quickly fixes the bedsheets, rushes to the bathroom and brushes her teeth. She then hurries into the kitchen, prepares a quick breakfast, packs the food into her bag, grabs her belongings, puts on her shoes, and rushes out of the apartment. Fast-paced natural movements, realistic expressions, smooth cinematic camera transitions, morning sunlight, detailed modern apartment, photorealistic, dynamic pacing, cinematic commercial quality, 4K.

A Product Reveal with Animated Callouts

15s · 含音訊

Create a 15-second luxury cinematic product showcase for a premium compact fragrance diffuser with a sculpted ceramic body and brushed-metal top. The product has no visible branding, labels, logos or printed text. 0–4s: Begin with an extreme macro tracking shot gliding across the fine matte ceramic texture, seamless curved body, precision-machined metal rim and recessed control surface. A narrow band of warm light travels across the materials against a deep black studio background, revealing delicate surface detail and controlled highlights. 4–8s: Pull back into a three-quarter hero view. The diffuser rotates slowly above a glossy dark-stone pedestal. A subtle ambient light ring gradually illuminates beneath the metal top. A fine stream of mist rises naturally and disperses softly into the air. Maintain stable geometry, consistent proportions and elegant symmetry. 8–12s: Transition into an exploded-view reveal. The ceramic shell, fragrance reservoir, ultrasonic plate, airflow chamber and brushed-metal top separate smoothly in perfect vertical alignment. Delicate illuminated mist particles flow upward through the internal airflow channel while the camera performs a restrained side orbit. At 9.2s, display a clean, partially transparent callout beside the ultrasonic plate. Connect it to the component with a fine pointer line. Use a thin champagne-gold border and minimal glass-like transparency. The callout title reads: “Silent Ultrasonic Diffusion”. Beneath it, in smaller text, display: “A refined mist without heat”. Keep the overlay sharp, readable, modern and premium without obscuring the internal construction. 12–15s: Every component reconnects seamlessly. The diffuser settles into a centered front-facing hero composition as warm rim lighting defines its silhouette. The callout fades away before the final lockup. Complete a gentle dolly-in while a controlled plume of mist rises from the top and the ambient light ring softly pulses once. Premium wellness-commercial finish, photorealistic ceramic and metal, realistic mist simulation, controlled reflections, soft shadows, shallow depth of field, crisp surface detail, stable product shape, no liquid spills, no people, no hands, no logos, no writing on the product, no distortion, no duplicated components and no illegible overlay text. 2/2

Another World Inside a Capsule Machine

15s · 含音訊

Subject: Person from Image1. Face and hairstyle must match Image1 completely; do not transform into a different person. Outfit: same casual everyday streetwear as Part 1. Ignore the outfit, background, pose, and bottom text from Image. Even if image quality is rough, facial features must remain clearly defined. 16:9 horizontal. Entire video has an old iPhone low-quality everyday-video look. Constant heavy noise and compression artifacts throughout. Setting: Same convenience store or arcade corner immediately after leaving the purikura booth. Sticker printer beside the booth, capsule toy machines, snack shelves, and bright fluorescent store lighting mixed with colorful purikura lights. Booth curtain still visible in the background. Any visible signs, packaging, and screen text remain completely illegible. Timeline: 0–3s: Holds up the phone with the newly attached sticker, smiling proudly. Notices a tiny bonus sticker still attached to the backing sheet and laughs softly. "Wait... there's another one?" 3–6s: Peels off the tiny sticker and sticks it onto a reusable drink bottle or wallet. While pressing it down, a nearby capsule toy machine suddenly dispenses a capsule by itself with a loud clunk, making them jump in surprise. 6–9s: Picks up the unexpected capsule, shakes it curiously, opens it, and finds a tiny cute keychain inside. Holds it next to the purikura sticker, laughing. "No way... perfect timing!" 9–12s: Hooks the keychain onto their bag or phone strap, admires both the sticker and keychain together, then catches their reflection in the booth window and gives themselves an amused grin. 12–15s: Looks directly at the camera, holds up the phone and the new keychain together, gives a playful wink and thumbs-up while saying, "Best random stop ever." Freeze on the final frame. Camera: Loose 1–1.5s cuts. Old iPhone, vertical, standard 1x lens (no distortion, standard field of view), handheld with slight natural shake while walking and reacting, steadier during close-up sticker and capsule moments. Slight autofocus hunting during close-ups. Mixed fluorescent and colorful booth lighting creates inconsistent white balance with a subtle magenta/pink cast. Natural exposure fluctuations throughout. Sound: No BGM. Ambient convenience store and arcade background noise (faint chatter, vending machines, capsule toy machine sounds, footsteps), sticker peeling sound, plastic capsule opening, small keychain clink, natural laughter, close slightly muffled voice, subtle booth echo, phone handling sounds. Style: Unedited low-quality phone video look. No color grading, no film look, no cinematic look, no beauty filter, no CG texture. No fisheye/ultra-wide (0.5x)/action-cam look, no barrel distortion, no vignette, no black lens-round at frame edges—flat standard field of view, frame filled edge to edge. Real skin texture maintained (pores, flyaway hairs, natural oil sheen). No cut consolidation, no scene skipping. No on-screen text (all store signs, product labels, booth screens, capsule contents, and sticker graphics/text remain illegible).

A Futuristic Ad Made for Itself

15s · ref2va · 含音訊

A Colorful Montage of Blooming Flowers

15s · ref2va · 含音訊

A Product Image Becomes a Premium Storefront

15s · 含音訊

Create a 16:9 premium ecommerce landing page UI/UX demo built around the product in Image 1. Use a luxurious, futuristic sports-performance aesthetic with oversized bold italic sans-serif typography, dark glossy backgrounds, carbon fiber and performance-mesh textures, metallic highlights, and speed-driven light streaks. Show a smooth high-speed page scroll, premium product sections, sleek feature cards, gallery modules, tech-spec areas, and strong CTA zones. Include high-impact hover interactions like scale-up, color inversion, glow effects, card expansion, and animated typography. Make the motion cinematic, expensive, and ultra-polished, like a world-class product launch website demo. 💰 Generation cost: under $3 🖼 Input: one product image 🧩 Output: a polished website concept video Try MiniMax H3 → https://bit.ly/4fES5pl #MiniMaxH3 #EcommerceDesign #UIDesign #ProductMarketing #ImaStudio

A High-Fashion Commercial in One Shot

15s · 含音訊

Prompts: [Core Concept] 15s, 160 BPM, 4/4, 40 beats. Industrial Hyperpop × Deconstructed Club: hard kicks, metallic snares, glitch hi-hats, distorted bass, sliced vocals. A timeline-based reality where rhythm controls space and motion. [Character Identity] Single androgynous dancer with short black hair, silver eyebrow mark, asymmetric black jacket, wide pants, red stitching. Maintain identical face, body, hairstyle and outfit. Multiple figures are only past-frame projections. [World Logic] Each kick compresses the timeline toward the dancer. Each snare duplicates previous movements into adjacent frames. Moving against the timeline transforms the 2D interface into a foldable 3D structure. The dancer escapes the repetition loop. [Visual Language] Black, cold white, warning red. Glass timelines, metal rails, glowing frame lines, scanning grids. Extreme wide-angle, low angles, top-down shots, Dutch angles, dolly moves, impossible perspective. 3D words COPY, SAME, TREND, OUTSIDE exist as physical architecture, not subtitles. [Motion Rules] Use anticipation → attack → overshoot → settle. Kick drives spatial compression, snare breaks frames, hi-hats animate cursors and fragments, bass bends time. Build with glitch cuts, then explode into an impossible continuous long take during the drop. [Restrictions] No character changes, extra people, random text, subtitles, logos, outfit changes, bad anatomy, flat camera angles, or meaningless flashes.

A Low-Angle Fashion Tracking Film

15s · 含音訊

Ultra realistic cinematic video, shot on ARRI Alexa 35 with spherical lens, natural daylight, photorealistic, looks like real footage filmed on location, high-end fashion film aesthetic, extreme detail, realistic skin texture, real fabric physics, subtle film grain. Continuous low angle tracking shot, camera smoothly moving backward as a beautiful young woman with long dark wind-blown hair walks and performs down a narrow sun-drenched urban alley between old textured stone buildings under deep blue sky. She wears a flowing milky white asymmetrical off-shoulder top and high-waist wide-leg technical cotton culottes with a thin rope belt. The wide pants and fabric move naturally and dramatically with the wind and her body. She sings with genuine joy, smiling and softly laughing, maintaining strong eye contact with the camera, while performing free, light dance elements — fluid arm gestures, body swaying, and elegant full turns around herself as she continues walking forward. Her movement is energetic yet effortless, full of lightness and positive energy. Cinematic natural lighting with strong sunlight and deep shadows, realistic motion blur, high dynamic range, masterpiece, best quality, no artificial look.

An Eight-Shot Luxury Skincare Commercial

15s · ref2va · 含音訊

Use the uploaded storyboard as the camera guide. Follow all 8 frames in order with smooth cinematic continuity. The same woman, outfit, hairstyle, makeup, room and product must remain perfectly consistent throughout the entire 15-second commercial. Every shot must begin where the previous shot ends with seamless match cuts and natural camera movement. Shot 1 (0-1.8s) A slow push in as morning sunlight enters through the window. The woman looks outside and gently turns toward the mirror. The camera continues moving without stopping. Transition: The camera keeps pushing forward until her face fills the frame. Shot 2 (1.8-3.6s) Without cutting, the shot becomes a close-up of her face in the mirror. She notices dull skin and lightly touches her cheek. The camera slowly circles around her as she reaches toward the vanity. Transition: Follow her hand naturally to the serum bottle. Shot 3 (3.6-5.4s) Macro shot as she picks up the serum bottle. The bottle rotates slightly in her hand while natural sunlight reflects across the glass. The camera smoothly follows the bottle upward. Transition: Continue tracking into an extreme macro of the dropper. Shot 4 (5.4-7.2s) Extreme macro of the dropper lifting from the bottle. A single drop forms and falls in slow motion. The camera follows the drop as it lands on her fingertips. Transition: The camera continues following her fingertips toward her face. Shot 5 (7.2-9.0s) Close-up as she gently applies the serum across her cheeks using smooth circular motions. Skin catches soft natural highlights. Hair moves slightly in the breeze. Transition: The camera slowly rotates around her face while maintaining eye level. Shot 6 (9.0-11.1s) The lighting naturally becomes warmer as her skin appears healthier and more radiant. The transformation happens gradually, not instantly. She smiles softly while looking into the mirror. Transition: She turns away from the mirror and walks toward the window as the camera follows. Shot 7 (11.1-13.2s) Medium shot as she confidently walks into warm sunlight. She smiles naturally at the camera while the background softly blurs. The camera slowly arcs around her. Transition: She lowers the product toward the camera until it fills the frame. Shot 8 (13.2-15.0s) Hero product shot. The serum bottle stands on a clean surface with warm natural daylight. Soft reflections move across the glass. Premium end card with elegant typography and subtle camera push in. End on the product with "Shop Now." Overall style: Ultra photorealistic luxury skincare commercial, Apple-style cinematography, ARRI Alexa 65, 50mm and 85mm lenses, soft natural daylight, realistic skin texture, premium color grading, physically accurate lighting, smooth cinematic camera movement, seamless match cuts, invisible transitions, no jump cuts, no frame skipping, no character changes, no outfit changes, no background changes, premium beauty ad quality. #MiniMaxH3 @Hailuo_AI

Kinetic Typography Inside a Coffee Commercial

15s · 含音訊

15-second premium luxury coffee commercial for the coffee brand "INSOMNIA". Create a cinematic editorial film, not a traditional advertisement. The visual language blends high-end fashion campaigns, premium product films, and modern graphic design. Every shot feels intentionally art-directed and professionally edited. Deep matte black, espresso brown, warm amber highlights, soft volumetric lighting, glossy reflections, subtle film grain, rich contrast, and an expensive cinematic color grade. Fast editorial rhythm using only crisp hard cuts synchronized with the soundtrack. No dissolves or soft transitions. Integrate bold typography naturally into the scene instead of placing it like subtitles. Massive words such as "INSOMNIA", "NO SLEEP", "STAY AWAKE", and "STAY INSPIRED" appear as architectural elements, illuminated walls, floating design layers, reflections on glass, or oversized background graphics while the camera moves around the product. Typography should remain clean, sharp, readable, and premium. Mix typography styles including giant bold headlines, thin technical labels, vertical text, rotated captions, editorial annotations, product specifications, registration marks, minimal grid lines, and stylish barcode-inspired graphic elements used only as design features, not functional barcodes. Use smooth masking reveals, frame drawing animations, split layouts, sliding typography, geometric wipes, and magazine-style collage compositions while maintaining realistic live-action footage. Show premium roasted coffee beans, aromatic steam, rich espresso pouring in macro detail, a matte black luxury coffee cup, dramatic close-ups, elegant camera movement, and refined product beauty shots. The entire film should feel like an international luxury fashion campaign directed by a top creative agency, combining cinematic realism with sophisticated editorial motion graphics. Finish with the INSOMNIA logo centered on a black background with the tagline "Stay Awake. Stay Inspired." in elegant minimal typography. Created using MiniMax H3 on @openart_ai

Surreal Fashion Inside a Blue Studio

15s · 含音訊

[Upload reference ] + Use la ragazza in reference as a strict identity reference for the model and her yellow sunglasses. Preserve face, hair, and the exact frame shape and colour throughout. 15 seconds, 16:9. Premium fashion commercial, photoreal live action. Infinite black void, polished black floor. She is the only lit element: hard key from one side, second hard light from the other, deep shadow between, strong speculars on the yellow frame and lenses. She walks slowly toward the camera in a black high-neck top and long black coat, chin level, eyes on the lens. Camera tracks backward at her pace, holding her size in frame. All type is heavy condensed uppercase sans-serif in vivid yellow, rendered as physical objects in 3D perspective with real thickness, catching the same light as she does and casting faint shadows on the floor. [0-4s] LOOK rises out of the floor ahead of her in deep perspective, grows as she approaches, and sweeps past on both sides out of frame. [4-7s] SEE enters from the right at high speed, streaks behind her with heavy motion blur, exits left. [7-10s] FOCUS appears large and fully out of focus, resolves into razor sharpness over half a second, holds, breaks apart. [10-12s] Four thin yellow lines draw a rectangle around her and FRAME assembles along its lower edge. Throughout, passing type reflects across the glossy lenses as it moves near her. [12-15s] She stops. All type collapses inward and vanishes into black. The camera continues into a tight close-up on her face and the yellow sunglasses. She holds completely still, eyes on the lens. On the black beneath her the title composes in the same yellow type: "SHIOBA LENS", and below it, smaller: "MADE TO BE SEEN". Hold. All text clean, legible, correctly spelled English capitals, each word once only. No garbled or duplicated letters, misspellings, subtitles, watermarks, or other text or logos. Audio: low sustained bass, Composition: model centered, all type within the central third of the frame

Strawberry Drink Transformation Commercial

7s · t2va · 含音訊

{ "shots": [ { "shot_id": "1", "start_time": "00:00", "end_time": "00:02", "camera_angle": "Close-up", "subject": "Strawberry", "action": "A single, dull strawberry transforms into a vibrant, ripe strawberry, floating against a pink background.", "visual_details": "Initial strawberry is muted, then becomes intensely red with visible seeds; pink background; subtle glow effect.", "audio_cues": "Light, subtle, almost magical sound effect." }, { "shot_id": "2", "start_time": "00:02", "end_time": "00:05", "camera_angle": "Medium shot", "subject": "Strawberry and beverage can", "action": "The vibrant strawberry transforms into a white and pink beverage can with 'STRAWBERRY CREAM' text. Liquid pours into the can from above, and strawberries/water droplets float around it.", "visual_details": "Can is sleek, covered in condensation; red liquid splashing into the can; numerous floating strawberries (whole and sliced) and water droplets; pink background.", "audio_cues": "Sound of liquid pouring, bubbling, and light splashes; upbeat, commercial-style music." }, { "shot_id": "3", "start_time": "00:06", "end_time": "00:10", "camera_angle": "Close-up", "subject": "Top of the beverage can", "action": "Focus on the top of the can as the liquid continues to pour and splash, with droplets and strawberries in motion.", "visual_details": "Intricate details of the can's opening and condensation; dynamic splashes of liquid; close-up of floating strawberry pieces.", "audio_cues": "Enhanced sounds of liquid splashing and bubbling; continued music." }, ] }

Golf Course Refreshment Commercial

0–2s — THE SIP Fast close-up of the ginger-haired golfer on a sunny golf course. She grabs the Sprite can, cracks it open — PSHHHT! — condensation and tiny droplets flying in slow motion. She takes a refreshing sip and gives a confident little smirk. 2–4s — GAME ON Hard cut. She tosses the Sprite can slightly upward, catches it, grabs her golf club, and steps into position. Quick whip-pan around her as sunlight flashes across the frame. 4–7s — THE SWING Rapid montage: close-up of her gripping the club → golf ball on the tee → her eyes locking onto the ball → skirt and ponytail moving as she swings. She hits the ball with a powerful, perfectly timed CRACK! 7–10s — FOLLOW THE BALL Ultra-fast camera follows the golf ball flying across the bright green course. Speed ramp as it passes trees and sunlight, then lands perfectly near the hole. 10–12s — HOLE IN ONE She watches it drop into the hole. Quick reaction shot: she smiles, spins the club casually, and walks toward the camera like she absolutely knew that was happening. 12–15s — HERO SHOT She grabs the cold Sprite can again and takes another sip. Camera pushes in as she lowers the can, smiling confidently. Condensation sparkles in the sunlight. End on a clean product close-up of the Sprite can beside the golf ball. On-screen text: “REFRESH. RELOAD. PLAY.” SPRITE — THIRSTY FOR MORE. Fast cuts, energetic commercial pacing, whip transitions, speed ramps, crisp summer lighting, realistic golf physics, dynamic camera movement, refreshing splash effects, premium sports-ad aesthetic.

An Architecture Board Assembles from Wireframes

15s · fl2va · 含音訊

A Dawn Bakery Delivery Launch

15s · ref2va · 含音訊

A Product Spectacle on a Minimal Set

10s · 含音訊

cinematic commercial Begin with peat smoke, rain droplets, and oak wood dust floating deliberately in mid-air. These materials compact into amber liquid and glass, forming the iconic Macallan bottle. Mist drifts as the label embosses and the liquid settles with slow viscosity. End with the completed Macallan bottle centered, logo present, and the 3-word slogan: “Time Finds Depth” Dark smoke-to-amber lighting, warm cinematic reflections, premium heritage tone.

Backseat Raccoon and Flying Chips

A cinematic video inside the back seat of a moving car with beige leather interior On the right a young woman with medium-length brown hair, wearing a yellow knitted sweater and blue jeans is holding a blue bag of potato chips Sitting on the left is a fluffy raccoon and a small capuchin monkey is resting close to the raccoon The woman offers a chip to the animals but as the raccoon reaches into the bag chips accidentally burst into the air and scatter all over the backseat including one landing on the raccoon's head The woman reacts with surprise and then bursts into laughter while the monkey looks around curious and playful Photorealistic soft natural lighting, vibrant colors.

The Giant Crab Escapes

Create an ultra-realistic 15-second video during a lively summer afternoon at a small Japanese fishing harbor. Use the provided reference image only to preserve the main woman's identity and appearance. The video must feel like a real spontaneous travel vlog, recorded by her friend. Natural handheld smartphone footage, fast reactions, continuous movement, realistic expressions, authentic Japanese harbor details, and clear close-ups. The story must contain multiple connected actions, audible dialogue, distinctive environmental sounds, and a genuinely surprising ending. 0–3 seconds: The woman stands beside a seafood stall, filming an enormous live Japanese spider crab displayed in a shallow tank. Suddenly, the crab stretches one long leg over the tank's edge and knocks her phone out of her hand. The phone lands safely on a nearby pile of fishing nets. She gasps, shouting, "Oh my God! Did you see that?!" The friend filming immediately exclaims, "Yo! It stole your shot!" 3–6 seconds: The crab crawls sideways toward the nets while the woman quickly retrieves her phone. A fisherman rushes over, calling out in Japanese, "Abunai! Abunai!" A metal bucket clatters onto the ground, startling a flock of seagulls into flight. The camera swings rapidly between the escaping crab, the startled woman, and the fisherman. 6–9 seconds: The crab unexpectedly grabs the loose end of a bright red fishing rope with one claw. As it moves, the rope pulls a small stack of empty plastic baskets across the wet pavement. The woman jumps aside and shouts, "Wait, wait! It's taking everything!" The fisherman laughs in disbelief and calls for someone to help. 9–12 seconds: A sudden tug pulls a lightweight fishing net off a wooden crate. The net drops over the crab like a messy tent. Everyone freezes for a moment. The fisherman carefully lifts one corner, revealing the crab sitting beside a tiny hidden kitten that had been sheltering behind the crate. The kitten meows loudly and climbs onto the fisherman's rubber boot. 12–15 seconds: Just as the woman bends down to film the kitten, the giant crab raises both claws behind her. The fisherman suddenly shouts, "Look out!" She spins around in shock, but the crab is simply holding her bright red phone strap between its claws. The woman stares at the camera in disbelief and says, "It actually wanted my phone!" End with the fisherman laughing and the crab releasing the strap. Audio must be carefully designed and clearly audible: lively harbor ambience, waves against the dock, seagulls squawking, water splashing, metal bucket clattering, plastic baskets scraping across wet pavement, the crab tapping against the tank, realistic footsteps, a loud surprised gasp, spontaneous English dialogue, the fisherman's Japanese warning, a clear kitten meow, and natural overlapping reactions. Use distinct sound events synchronized exactly with the visible actions. Keep dialogue crisp and intelligible, with the environmental sounds slightly quieter whenever someone speaks. The woman's voice should sound surprised and expressive, not continuously laughing. Include moments of silence and suspense before the final reveal. Visual style: realistic smartphone exposure, natural summer sunlight, authentic Japanese fishing harbor, believable animal movement, consistent character appearance, clear medium shots and close-ups, natural camera shake, and realistic physical interactions. Avoid constant laughter, silent characters, generic background noise, music overpowering dialogue, robotic voices, random sound effects, cinematic transitions, slow motion, cartoon behavior, impossible animal actions, distorted hands, duplicated animals, and blurry faces.

Sword Formations Above a Moonlit Immortal City

15s · fl2va · 含音訊

5秒，4:3，顶级东方仙侠3A游戏CG，电影级高端宣传片，严格参考图1的月下仙城场景与美术气质：巨大明月、云海天宫、环形仙城、悬浮仙山、瀑布、白玉仙桥、金顶楼阁、冷蓝月光。整体画面必须唯美、恢弘、神圣、危险、酷炫，像大厂正式游戏开场CG，不像普通AI视频。 双主角设定：男剑仙，黑色长发，白蓝战袍，冰蓝雷光长剑，英俊冷峻，强大沉稳；女剑仙，黑色长发，白青仙裙，月白灵剑与月华法术，清冷绝美，高贵飘逸。反派为黑金重甲魔修，手持黑色巨剑，周身暗红黑色魔气，压迫感极强。人物脸和服装全程稳定统一，保持高级游戏角色建模质感。 开场镜头从巨大明月前高速穿越云海与浮空仙山，俯冲进入宏伟仙城，来到白玉高台，男女主背对镜头立于高台边缘，衣袍长发飞扬，英雄感极强。远处天空突然裂开暗红色空间裂缝，魔修高速坠落，轰然落地，引发碎石、冲击波和魔气爆发。 男剑仙瞬间拔剑冲出，与魔修在仙桥中央高速对撞，剑刃碰撞爆发蓝红双色能量冲击、空间波纹、火星与剑气。近战动作凌厉、清晰、有重量感，包含高速斩击、格挡、反击、短暂慢动作碰撞特写，镜头低机位跟拍与高速环绕，极具电影感。 随后女剑仙御剑升空，展开巨大蓝白仙阵，发动“万剑齐发”，数百柄发光飞剑如流星暴雨般射向魔修，夜空被剑光点亮。魔修爆发黑红魔气，凝聚巨大的魔龙反击，空中连续爆炸。男剑仙御剑穿梭爆炸火光与云海，一剑斩裂魔龙，空战场面华丽震撼。 最后魔修释放百米高的黑红魔神法相，遮蔽天空。男女主并肩悬空，男剑仙开启覆盖半个天空的金蓝剑阵，女剑仙召唤巨大的白蓝月华莲华法相，二人联手凝聚数百米长的金蓝神剑，与魔神巨剑正面碰撞。碰撞瞬间进入超级慢动作，蓝色雷电、金色符文、白色月华、红色魔焰与空间裂痕同时凝固，随后爆发毁天灭地的大爆炸，形成巨大的环形云洞与能量冲击波。 结尾爆炸光芒散去，巨大明月重现，男女主并肩立于悬空巨剑之上俯瞰整座仙城，周围灵剑环绕，远处天宫亮起金蓝光柱，镜头缓慢拉远，形成极强的高级游戏主视觉结尾，并预留后期添加Logo空间。 镜头要求：超广角航拍、俯冲推进、低机位英雄视角、高速跟拍、环绕镜头、御剑追踪、短暂升格慢动作、终极碰撞震动、史诗级拉远收尾。镜头必须流畅稳定，不乱晃，不跳轴。 视觉要求：特效炫丽但高级干净，不能廉价光污染。强调冰蓝雷电剑气、金色仙纹、月华粒子、飞剑阵、空间裂缝、黑红魔焰、魔龙、巨大法相、神剑、冲击波、体积云、瀑布水雾、发光碎片。人物主体始终清晰，画面精致通透，PBR材质，真实布料与长发动效，电影级光影与空间层次。 音效：原生立体声。包含高空风声、远处钟鸣、低沉鼓点、剑刃碰撞、破风声、雷电炸裂、万剑掠空、魔龙低吼、终极爆炸低频冲击。无对白，无字幕，无水印，无乱码。

Ramen Dinner — Rack Focus to Family

8s · 768p · fl2va（仅首帧，未提供尾帧） · 含音訊

首影格

Neon Mountain Hover-Bike Race

15s · fl2va · 含音訊

Cinematic Anime Video Scene Generate a 15-second horizontal 16:9 original high-speed hover-bike racing anime video from the provided first frame. CRITICAL ENTITY LOCK: There must be exactly 2 racers and 2 bikes in the entire video: RENJI on VALKYRIE-01 (cyan/black drift bike) and ELENA on AERO-X (crimson/white draft bike). Do not add extra racers, drone support vehicles, spectators, or traffic. Maintain total visual consistency for both bikes, helmet visors, suit patterns, repulsor spark colors, and bike liveries throughout the sequence. Entity identity: VALKYRIE-01: Matte-black and cyan angular hover-bike, exposed repulsor pads, lateral drift brakes, blue plasma exhaust trails, ridden by Renji (cyan trim suit). AERO-X: Pearl-white and neon-crimson aerodynamic hover-bike, enclosed canopy, crimson energy draft aura, white-hot central booster, ridden by Elena (crimson/gold visor suit). Video style: High-budget modern sports anime, sakuga-level velocity animation, crisp line art, vibrant neon lighting contrast, high-speed camera tracking, hyper-realistic friction and energy particle effects. Set on a wet downhill mountain pass at dawn. Camera and pacing: Continuous forward velocity, zero slow-motion interruptions: 0.0s - 3.0s: High-speed rear-tracking shot diving into the first downhill hairpin curve; instant drift initiation. 3.0s - 7.5s: Tight side-parallel tracking shot as bikes navigate rock debris and trade positions through S-curves. 7.5s - 11.5s: Close camera lock on the draft-slingshot maneuver; high-energy particle displacement as booster ignition occurs. 11.5s - 15.0s: Low-angle front-facing camera lock on the final sprint to the finish line bridge, ending on a hyper-speed photo-finish freeze. Action timing: 0.0s - 1.5s: Sequence begins at speed. VALKYRIE-01 leads downhill; AERO-X locks onto its rear bumper. Anti-gravity repulsors spray road water and blue sparks into the frame. 1.5s - 4.0s: First sharp hairpin. VALKYRIE-01 deploys lateral drift airbrakes with a burst of blue thruster fire, sliding sideways at 300 km/h. AERO-X stays glued inside its slipstream aura. 4.0s - 7.0s: Mountain debris hazard. VALKYRIE-01 hops over a boulder using a repulsor burst. AERO-X ducks under it, scraping the neon magenta guardrail in a cloud of friction sparks. 7.0s - 10.0s: S-Curve exchange. Bikes lean side-by-side; their repulsor fields collide, creating a bright electrical shockwave. ELENA pulls the overdrive lever; AERO-X's rear fins extend. 10.0s - 13.0s: Slingshot maneuver. AERO-X bursts out of VALKYRIE-01's draft, igniting its central white plasma booster. Both bikes roar down the final straightaway side-by-side. 13.0s - 15.0s: Final sprint toward the finish light gate. Water sprays violently behind them. Both nose cones cross the finish line simultaneously in a flash of light. Final freeze frame. Motion quality: Fluid 2D animation, extreme speed-line integration, stable bike geometry, flawless vehicle reflection rendering, zero limb or body clipping, high-frame-rate kinetic realism. Environment: Wet mountain pass asphalt, sheer cliff walls, neon cyan and magenta guardrail lights, early dawn sky with pink/purple clouds, water spray, floating spark particles. Final output: 15 seconds, horizontal 16:9, original high-budget sports racing anime, exactly 2 racers, relentless kinetic pacing, dynamic cinematography, no subtitles, no watermarks, no logos.

A Drunken-Master Poster Comes Alive

23s · fl2va · 含音訊

Animate the uploaded CHUNG LEE movie poster as a 10-second cinematic martial-arts motion poster while preserving the original artwork, characters, typography, composition and layout. Bring the static poster to life with rich cinematic colors — crimson red, golden yellow, fiery orange, electric blue, emerald green and magenta. Animate the lanterns, drifting smoke, flying dust, sparks, debris and the surrounding crowd. Give CHUNG LEE subtle drunken-master movement: shifting shoulders, flowing hair, a confident expression and a casual lift of the gourd with liquid splashing in slow motion. Then make “CHUNG LEE” the ultimate visual flex — dramatic brush-stroke reveals, golden particles, energy trails and a powerful 3D pop-out effect that makes the title feel like it is breaking out of the poster. Add glowing red energy around the Chinese characters, dynamic martial-arts impacts, moving background fighters, cinematic camera movement and bursts of colorful light. Finish with a dramatic push toward the CHUNG LEE title, then pull back to reveal the complete poster before locking into the final frame. No redesign. No new text. No distorted typography. Preserve the original poster — just make it move. Animation made with Minimax H3

Haru in a High-Contrast Anime Opening

15s · fl2va · 含音訊

[CHARACTER LOCK — use attached reference sheet] Haru: teen boy, short messy dark-brown hair with warm amber rim-light on the edges, tired amber eyes, single silver earring on left ear, thin dark cord choker, oversized grey-blue windbreaker open over a longline blue hoodie, black joggers with dangling straps, scuffed black high-top sneakers. Face, hair silhouette, and outfit identical in every shot. [FORMAT] Anime television opening, 2D cel-shaded, crisp linework, 16:9, high contrast, film grain. Total runtime 15 seconds, 12 shots, beat-synced hard cuts. [SHOT LIST — 15s] 00.0–01.2 Black. Hard white flash. Haru's silhouette snaps in, back to camera, jacket billowing. Background floods CYAN. 01.2–02.4 Whip-pan to profile close-up. Downcast eyes flick up, sharp. Flash. Background MAGENTA. 02.4–03.2 Low-angle wide: he sprints along a rooftop ledge, coat trailing, paper and leaves scattering. ORANGE-RED, speed lines. 03.2–03.9 Freeze-frame mid-leap between rooftops. Pure black silhouette against strobing YELLOW-to-LIME. 03.9–04.7 Top-down spin: lands, one hand on concrete, dust ring bursts out. Snap to DEEP PURPLE. 04.7–05.3 Extreme close-up: silver earring swings, catches a lens flare. White flash frame. 05.3–06.2 Split-screen triptych — three duotone copies of his face (blue / red / green) rotating, one per beat. 06.2–07.4 Back view, walking into wind, hood snapping, hair whipping. Background ELECTRIC BLUE with horizontal scan lines. 07.4–08.2 Hands-in-pockets front shot, camera orbits fast around him. Colors cycle GREEN → PINK → WHITE across the orbit. 08.2–09.4 Seated on the ledge, knees up, head down, city lights blooming behind. Muted TEAL. Brief calm — no flash on this cut. 09.4–10.6 He stands, turns to camera, hair lifting, single amber rim-light igniting along his edge. Background goes pure WHITE. 10.6–15.0 Pull-back wide: Haru walks away toward the sunset skyline, hands in pockets, clothes drifting. Color settles into the warm painted palette of the reference sheet. Camera dollies out, holds on centered title-card space. [MOTION] Simple punchy character animation on twos. Hair and fabric always drifting. Camera: whip pans, snap zooms, one fast orbit, one final dolly-out. [COLOR & FX] Full-frame color swaps on every cut, synced to an implied beat. White flash-frames between shots 1–9. Chromatic aberration on impacts, halftone dot bursts, quick duotone inversions, floating leaf and paper debris throughout. Warm amber rim-light preserved on the character in every shot. [NEGATIVE] photorealistic, 3D render, live action, extra characters, text or logos, changing outfit, changing hair color, distorted face, extra fingers, watermark

A Shy Rain Cloud in the Greenhouse

15s · fl2va · 含音訊

Balancing Photorealism and Synthetic Texture

15s · fl2va · 含音訊

---------------- integrated_multimodal_description: [Shot 1] Live-action, cinematic, photorealistic with true fine pores and real skin texture, no beauty filter. A full-body side-on wide shot of a 25-year-old woman with cool fair skin, dark almond eyes and long straight black hair, walking steadily from left to right along a colonnade of stone columns on a city street. Her face is identical in every era of the film; only her clothing, her hair styling and the world behind her change. Her stride never changes speed and she never looks at the camera until the final moment. The camera trucks right with large amplitude at slow speed, travelling alongside her for the entire film with no other camera movement and no change of direction. Foreground columns sweep across the lens as the camera moves, and each time a column wipes the frame the world behind her changes to the next era. The film opens in the 1920s: low-saturation sepia light, gas lamps, a horse-drawn carriage, a beaded drop-waist dress and a cloche hat. At 00:03.000 a column wipes past and the world becomes the 1950s: warm amber light, a pastel car at the kerb, a chrome diner sign, a full-skirted dress and red lipstick. At 00:06.000 the next column wipes past and the world becomes the 1980s: dense pink and cyan neon reflecting off wet asphalt, a padded-shoulder jacket, heavy dark night air. At 00:09.000 the next column wipes past and the world becomes the present day: cool white daylight, glass office towers, passers-by lit by phone screens, an oversized wool coat. At 00:12.000 the last column wipes past and the world becomes the near future: pale blue light, floating holographic advertisements drifting between the columns, a sleek structured coat with a faint luminous seam. At 00:14.000 she stops walking. The camera comes to rest with her. She turns her head and looks straight into the lens for the final beat, holding still until the end. No on-screen text or subtitles at any point. overall_soundscape: Her footsteps strike the stone at exactly the same steady pace from the first frame to the last, the one sound that never changes. Behind her the street swaps out at each era: horse hooves and a distant bell, then car horns and chattering pedestrians, then heavy rain on asphalt and a low traffic drone, then a modern city hum, then an almost silent electric whirr. Each column wipe is marked by a short dry rush of air across the lens. non_diegetic_music: A steady four-beat pulse at a constant tempo runs from the first frame to the last, gaining one new instrument at every era change: a lone bass drum, then upright bass, then analogue synth, then layered electronic percussion, then a wide sustained synth chord. It reaches full volume as she stops and cuts off on her final look.

Kaze’s Player Stats Screen Powers Up

15s · fl2va · 含音訊

@[ref img] is the sole visual authority for Kaze, the football, the complete player-stats interface, typography, numbers, icons, colors, lighting, layout, and vertical composition. Animate this exact screen without redesigning it. Preserve all existing labels and final stat values. [Goal] Create a polished 15-second anime sports-game player stats screen opening. Use one continuous, locked, straight-on full-screen composition with no camera movement, cuts, cropping, or perspective distortion. [Sequence] 0–2.2 seconds: Begin from near-black teal. A faint horizontal scanner passes downward, revealing Kaze’s silhouette and the outer edges of the interface. Fine particles and dim mint circuitry flicker awake. 2.2–5.5 seconds: The header, KAZE nameplate, role badge, level panel, and overall panel resolve through clean line-draw animations. Kaze emerges fully from shadow, takes a controlled breath, subtly shifts her shoulders and raised arm into the referenced pose, then fixes an intense gaze toward the viewer. Her hair, ribbons, and loose clothing react naturally to a growing current of wind. The football begins a slow, stable rotation beside her hand. 5.5–10.8 seconds: The large overall score counts rapidly upward and lands precisely on 92. The level settles on 46. Each attribute bar fills smoothly from left to right in sequence—Speed 93, Power 91, Control 88, Stamina 90, Agility 94, Technique 89—each landing with a restrained mint pulse. The radar chart draws outward from its center and locks into the exact final polygon. Skill cards activate from top to bottom; their icons flare briefly while the ACTIVE and ULTIMATE states illuminate. 10.8–13.3 seconds: The player ID strip and bottom navigation fade and slide into their exact final positions. The wind energy around Kaze accelerates clockwise, wrapping around the rotating ball and sweeping behind her body with layered luminous trails. Kaze tightens her hand, leans slightly into the current, and gives one natural blink; preserve her identity, anatomy, costume, and right-side placement. 13.3–15 seconds: The energy arc reaches a bright controlled crest, then settles into a living idle pulse. Hold the fully assembled screen matching @[ref img] exactly. Kaze continues subtle breathing; hair and ribbons drift, the football rotates slowly, particles shimmer, and all stats remain stable and readable. Use crisp premium game-UI motion, clean 2D anime character animation, subtle depth between Kaze and the interface, and stable legible typography. Keep every panel, icon, label, number, and geometric boundary fixed once revealed. Do not introduce new text, extra characters, additional objects, logos, captions, or UI elements. Audio: low electronic boot hum, delicate scanning ticks, short confirmation tones as values lock, rising airy wind around the ball, soft cloth movement, and one refined completion chime. No dialogue and no music.

Sagrada Família FPV flight

15s · fl2va · 含音訊

Create a cinematic realistic high-speed drone video over Barcelona, Spain at golden hour, using the reference image as the exact location and flight-path guide. The drone starts very low above the Barcelona cityscape, almost skimming above the foreground rooftops and streets, facing La Sagrada Família. It accelerates quickly forward over the urban landscape, following the drawn path from the foreground toward the cathedral while maintaining a very low altitude. The drone then performs a dramatic climbing curve as La Sagrada Família fills the frame, executes a close cinematic orbit around the cathedral’s iconic spires, and after the orbit, pulls back while gaining altitude before tilting and opening toward the Barcelona skyline, Mediterranean Sea, Eixample grid, surrounding historic rooftops, golden-hour reflections, distant coastline, and glowing Barcelona atmosphere. The red drawn line must not appear in the video; it is only a hidden flight-path reference. Add powerful emotional cinematic music: deep cello melody, dramatic percussion rhythm, orchestral strings, subtle choir texture, epic rising percussion, and a grand heroic crescendo as the drone completes its orbit around La Sagrada Família and reaches the final panoramic reveal. No text, no subtitles, no logos, no graphic overlays.@Image1

A Five-Second Greeting from an Anime Idol

5s · ref2va · 含音訊

プロンプト置いときます✋ Japanese anime style, high-end TV anime production quality, soft pastel lighting, clean line art, subtle cel shading, bright and cheerful idol stage atmosphere, glowing lens flare, gentle bokeh in background, smooth vibrant 60fps animation feel. Scene overview: An adorable anime idol girl stands center stage, looking directly at the camera with a brilliant smile. She holds a colorful microphone, energetic and joyful, giving a cute greeting to her fans. A short, charming 5-second anime idol greeting scene. Storyboard: [0s-1.5s] Shot 1: Medium close-up: The idol girl steps forward with a big smile, bringing the microphone to her mouth, blinking playfully as stage lights twinkle behind her. [1.5s-3.5s] Shot 2: Close-up on her face: She speaks clearly into the microphone with precise lip-sync: "みんな、こんにちは！今日も一緒に楽しもうね！" (Minna, konnichiwa! Kyou mo issho ni tanoshimou ne!). She winks on "tanoshimou ne!". [3.5s-5s] Shot 3: Slightly pulled-back medium shot: She strikes a cute victory-pose/heart-pose with her free hand, tilting her head with a beaming smile as sparkle particles drift around her. Camera: Smooth pan-in at the start, staying centered and static during the lip-sync for maximum clarity, subtle handheld bounce on the final pose at 3.5s. Audio: Crisp female anime idol voice clearly pronouncing "みんな、こんにちは！今日も一緒に楽しもうね！" in Japanese. Underneath, an upbeat synth-pop idol BGM playing, accompanied by a soft microphone "pop" sound at 0.5s and a sparkling magic SFX hit at 3.5s during the pose. No real-life live action rendering, no realistic skin texture, no 3D CG look, no English subtitles or on-screen text clutter, keep the pure 2D anime aesthetic.

Lip-Synced Redub — Editing an Existing Clip

5s · 768p · ref2va（视频编辑 + 语音音色参考） · 含音訊

輸入影片

subject_definitions: <Subject 1> is the young man with short wavy blonde hair, wearing a bright pink suit jacket, matching pink trousers, an unbuttoned white shirt, and silver rings, holding a small black lamb in his arms in <Video 1>. <Video 1> is the source video for the editing task. <Audio 1> is the synchronized audio track of <Video 1>, providing the background music. <Audio 2> is the voice timbre reference for <Subject 1>'s voice, containing a spoken male voiceover. summary: [video editing + audio reference + audio reuse] The target video is an edited version of <Video 1>. <Subject 1>, wearing a bright pink suit and holding a black lamb, stands in a grassy field with other white lambs in the background. The edit animates <Subject 1>'s face to speak the user-provided dialogue. <Audio 1> is partially reused as the continuous background music, while the target references the calm male voice timbre of <Audio 2> for <Subject 1>'s spoken lines. retention_analysis: <Subject 1> (appears in [Shot 1]): fully_preserved - the man retains his identity, wavy blonde hair, pink suit, white shirt, accessories, and the black lamb he holds, with his mouth newly animated to speak. <Video 1> (source video editing): fully_preserved - the original camera framing, warm golden hour lighting, grassy hill setting, and background white lambs are maintained while the central character is edited. <Audio 1>: partially_copy - the atmospheric background music from <Audio 1> is reused in the target video, mixed beneath the newly added spoken dialogue. <Audio 2>: reference - the target audio references the male voice timbre from <Audio 2> to generate <Subject 1>'s spoken dialogue. detailed_description: The target video is in realistic photographic style. [Shot 1] The shot begins from the source <Video 1>, showing <Subject 1>, a young man with short wavy blonde hair, wearing a bright pink suit jacket, matching pink trousers, and a casually unbuttoned white shirt. He stands confidently in a sunlit green pasture, gently holding a small black lamb securely in his arms. The warm, golden hour lighting casts soft shadows across his face and the bright pink fabric of his suit. Behind him, several white lambs stand and graze on the rolling grassy hill against a clear, pale blue sky. The atmospheric background music from <Audio 1> plays continuously throughout the scene. <Subject 1> physically speaks, his mouth movements naturally syncing to the new dialogue, with his voice timbre referencing the calm male delivery from <Audio 2>. Looking thoughtfully forward, <Subject 1> (S1) speaks softly, <d>[English] Follow the wind, live free.</d> As he delivers the line, he subtly shifts his weight, cradling the resting black lamb while the camera slowly pushes in. <Subject 1> (S1) continues his thought, <d>[English] Leave worries behind, enjoy the moment.</d> Exactly as his voice stops, his lips meet in a relaxed, peaceful smile, and his jaw ceases speaking motion. He then turns his gaze slightly away toward the horizon, gently stroking the black lamb's fleece with his fingers as the camera holds on this tranquil, sunlit state through the end of the video. overall_soundscape: The soundscape consists of the continuous, atmospheric background music from <Audio 1>, overlaid with the clear, calm male dialogue spoken by the main character, referencing the voice timbre of <Audio 2>. non_diegetic_music: The atmospheric, sustained background music from <Audio 1> is reused as the continuous score, playing quietly beneath the spoken dialogue.

Adding Japanese Type to a Coastal Cycling Video

ref2va · 含音訊

Video editing, add texts into the <Video 1> while keep the layout, expressions, movement, color in <Video 1>. The bold white sans-serif word "この世界は" and "アシンメトリック" snaps upward individually behind the girl driving bicycle and in front of background in sync with the timing of the <Audio 1> audio track titled <d>[Japanese] この世界はアシンメトリック</d>.

A Ginger Cat Strolls Through Miyajima at Dusk

8s · t2va · 含音訊

Style & Visual Direction:Classic 90s Japanese anime aesthetic, Hand-drawn anime style, Studio Ghibli-inspired warm tone, cel-shaded texturing, vibrant golden hour twilight lighting, soft painted backgrounds, natural fluid animation, high quality, masterpiece. Scene Overview:A calm, peaceful afternoon on Miyajima Island. A ginger tabby cat wanders past the iconic floating Great Torii Gate standing in the serene water, enjoying a quiet stroll along the coastal stone path as deer rest nearby. Storyboard (8-Second Sequence): [0s-2s] Shot 1: Medium wide shot. The ginger tabby cat walks gracefully along the ancient stone lantern pathway near the shore, tail gently swaying. In the background, a friendly Miyajima deer rests peacefully under a maple tree. [2s-4.5s] Shot 2: Tracking shot. Low-angle side camera following the cat as it steps smoothly along the stone path. The iconic red Torii Gate is visible across the calm, shimmering water under a soft orange and pink sky. [4.5s-6.5s] Shot 3: Close-up shot. The cat pauses, turns its head toward the sea, and blinks slowly with curious amber eyes as the soft evening breeze rustles its fur. [6.5s-8s] Shot 4: Wide cinematic shot. The cat sits next to a classic stone lantern, gazing out at the floating Torii Gate reflected in the gently rippling tide. Camera:Smooth cinematic tracking, gentle pan and low-angle follow, clean cuts between shots on the natural beats. Audio:Gentle ocean waves lapping against the shore, quiet rustling leaves, soft ambient wind chimes, peaceful low piano melody carrying through to the end. Negative Prompts:No live-action photo style, no 3D CGI rendering, no text, no subtitles, no logos, no watermarks, no distorted anatomy, no abrupt jittery motion.

A Night in a 1990s American Diner

15s · ref2va · 含音訊

Photorealistic cinematic 1990s American diner — red vinyl booths, neon signs, chrome details, checkerboard floor, soft window light mixed with warm practicals, subtle handheld texture, heavy film grain. Modern realism with precise temporal control. Use the provided reference image as the exact character lock for the bald bearded man in black sunglasses and dark hoodie. Maintain identical facial structure, beard, head shape, skin texture and clothing at all times. 0-3s: [Medium Wide] The bald man rises from a red vinyl booth, turns, and collides hard into a waitress carrying a full breakfast tray (eggs, bacon, toast, coffee pot). Sudden, physical impact. 3-8s: [Dynamic Orbit into Super Slow-Motion] The collision detonates. Tray, plates, eggs, bacon and coffee pot explode upward; coffee erupts into long liquid ribbons and suspended droplets. Camera orbits the impact as time locks completely at the peak of the spill. Every face freezes in shock. Only the bald man still moves — one beat of a clear "I messed up" expression, then he calmly plucks two bacon strips and a fried egg out of the floating debris. 8-12s: [Tracking Shot] Still inside the frozen diner, he walks toward the exit taking deliberate bites of bacon, then egg. Patrons, waitress and flying food stay perfectly suspended mid-air. 12-15s: [Medium Shot into Medium Close-Up] His hand touches the door — time snaps back to full speed and everything crashes down at once: plates, eggs, tray and coffee slam to the floor in loud chaos as the patrons jolt into real-time shock. He pauses, glances back over his shoulder, raises his eyebrows and gives a small "it is what it is" shrug with a quiet half-smile, still holding the food. Photorealistic, ultra-detailed fluid and object physics, correct volume and surface tension on liquids, motion blur only on moving elements, stable character identity, cinematic lighting, heavy natural film grain, no artifacts, movie-level temporal coherence.

Cloud-Head Subway Transformation

8s · ref2va · 含音訊

integrated_multimodal_description: [Shot 1] Surreal live-action cinematic imagery in a symmetrical square deep-focus wide shot inside the same modern subway carriage established by <Picture 1>. At the beginning, the same seated passengers occupy the exact same seats with the same bodies, clothing, poses, hands, phones, bags, spacing, and calm commuter behavior, but every passenger has a distinct, anatomically normal human head and natural human face; the ceiling above them is ordinary dim stormy condensation without the giant eye. The camera holds a completely static shot for the entire video. From 00:01.600 to 00:02.700, a thin horizontal digital phase glitch sweeps across the carriage with brief RGB channel separation and blocky temporal displacement restricted to the passengers' heads; their normal human heads transform into compact volumetric storm clouds while their necks, bodies, clothing, hands, and positions remain perfectly unchanged. From 00:02.700 to 00:03.450, the interference reverses and restores the same normal, stable human faces. From 00:03.450 to 00:05.550, two faster synchronized glitch pulses alternate every head between the same normal human face and its cloud form, with no body movement, no face melting, and no change to the carriage geometry. From 00:05.550 onward, a final sustained digital stutter locks the passengers into their distinct cloud-headed states: lightning flickers inside the left foreground cloud, warm light glows inside the left midground cloud, rain falls beneath the small dark cloud, a faint rainbow forms in the right-center cloud, and a small sun glows inside the right foreground cloud. Fine luminous mist rises from the central cloud and resolves into the huge pale cloud face and single open eye overhead. The glitches settle, all motion becomes nearly still, and at exactly 8.00 seconds the passenger count, cloud shapes, body poses, wardrobe, seats, poles, windows, lighting, colors, crop, ceiling apparition, and full composition converge precisely to <Picture 1>. No cuts, no camera movement, no zoom, no pan, no tilt, no roll, no shake, no body morphing, no extra people, no missing passengers, no fused limbs, no wardrobe changes, no seat changes, no floating bodies, no text, no subtitles, no logos, and no drift from the final reference image. overall_soundscape: A steady low subway rumble, muted wheel rhythm, and soft ventilation hum continue throughout. Each transformation is marked by a brief dry digital stutter and electrical crackle, while the final cloud state adds faint rain, distant thunder, and a soft airy hiss without overpowering the train ambience. non_diegetic_music: N/A

A Miniature Highway Hidden Inside the Fridge

10s · t2va · 含音訊

integrated_multimodal_description Shot 1 A realistic suburban kitchen at night. A man casually walks to the refrigerator and opens the door. The camera starts just behind his shoulder and slowly pushes closer as bright refrigerator light illuminates his confused face. Inside the refrigerator is an incredibly detailed miniature highway network integrated naturally between the food. Several lanes of tiny moving cars weave between milk cartons, jars, leftovers, vegetables, and drink bottles. Tiny headlights and brake lights glow realistically. The camera moves closer into the refrigerator interior as if entering this tiny world. A miniature traffic jam forms beside a tipped container leaking orange juice across one lane like a flooded roadway. Tiny construction vehicles arrive. Small workers in reflective clothing place cones and redirect traffic around the spill. A tiny tow truck pulls a stalled car away. Another vehicle honks impatiently. Cars merge aggressively around a yogurt container. The man slowly reaches one hand toward the highway. Several tiny cars immediately slam on their brakes. A miniature police officer begins angrily waving at his enormous finger to move away. The man freezes, completely baffled. The camera finishes extremely close to the refrigerator highway as traffic starts moving again around his stationary finger. overall_soundscape Quiet kitchen ambience, refrigerator hum, refrigerator door opening, tiny engines, miniature car horns, distant tiny sirens, construction equipment, subtle liquid splashing from the orange juice spill. non_diegetic_music None.

An 8-Bit Girl Walks a Sunny Path

5s · 含音訊

"A cute little girl walks through a sunny forest when a small, friendly dinosaur steps out, waves, and says hi. Suddenly, the dinosaur sneezes—and a shower of colorful butterflies bursts from its nose. They both laugh. Cute, colorful animated style." - time: 15min ish - 768x768

Orange-and-Black Street Dance Commercial

15s · t2va · 含音訊

Multiplication Tables with Fish Pairs

15s · t2va · 含音訊

Silver Earbuds in the City at Night

15s · t2va · 含音訊

Create a premium 15-second cinematic ad for Audionic Trance Airbud 850. Start with a close-up of the silver earbuds and case, then show a stylish Korean girl wearing them and walking through a luxurious Korean shopping street while enjoying a modern Korean K-pop song. Use beautiful city lights, soft bokeh, elegant fashion, natural expressions and smooth cinematic camera movement. End with one clean hero shot of the silver earbuds and case only. No phone screen, Bluetooth connection, discount text, logo end card or extra ending scene.

Three Outfit Changes in a Bedroom

16s · ref2va · 含音訊

Format: 15 seconds | 16:9 | 4K HDR | 24fps | photorealistic cinematic vlog Character: Use the girl from the uploaded reference image as the exact character reference. Preserve her facial identity, eye color, skin tone, hairstyle, body proportions, and overall appearance consistently throughout every shot. No face changes or identity drift. Scene & Story: 0–3 sec — The Mystery Package The video opens with a handheld creator-vlog shot in her cozy bedroom during late afternoon. She walks into frame holding a stylish garment bag, looking genuinely curious. She places it on the bed and looks directly into the camera with a playful expression. She says naturally: “Okay… I found something for tonight, but I have absolutely no clue if I can pull it off.” She unzips the garment bag, revealing only a glimpse of the outfit. 3–6 sec — First Reveal She quickly steps behind a nearby room divider. The camera follows with a fast handheld whip-pan. She emerges wearing a chic fitted top, tailored trousers, and elegant heels. She looks at herself in the mirror, slightly surprised by how good it looks. She turns toward the camera and says: “Wait… this might actually work.” She gives a small confident pose. 6–9 sec — The Unexpected Switch Instead of snapping her fingers, she grabs a jacket hanging beside her and dramatically throws it toward the camera. As the jacket briefly covers the lens, the outfit seamlessly transforms underneath it. When she pulls the jacket away, she is wearing a completely different fashion-forward look: a stylish mini dress with statement shoes and subtle accessories. She looks down, raises one eyebrow, then laughs. 9–12 sec — The Wild Card She walks toward the mirror while the camera circles around her. She notices a third outfit hanging on the wardrobe door. Suddenly, she steps backward and spins. During the spin, her outfit naturally morphs into a glamorous evening look with a sophisticated silhouette, elegant heels, and refined accessories. The transformation happens continuously during the movement with realistic fabric motion — no jump cut. 12–15 sec — Final Decision She walks toward the camera with confident energy, then stops very close to the lens. She looks at the camera, points toward herself, then gestures toward the three outfits visible behind her. With a playful smile, she says: “Okay… you’re choosing. Which one?” The camera quickly pushes in toward her face as she laughs, ending on a natural freeze-like moment. Visual Direction: Ultra-realistic fashion creator vlog, authentic handheld camera movement, natural body language, expressive facial reactions, realistic fabric physics, seamless outfit transitions, natural hair movement, subtle mirror reflections, cinematic depth of field, realistic skin texture, soft late-afternoon daylight mixed with warm practical bedroom lighting, detailed wardrobe and bedroom environment, premium fashion-film aesthetic while maintaining casual YouTube-vlog energy. Camera: Handheld selfie framing, medium shots, quick whip-pans, subtle camera shake, smooth tracking movements, one controlled orbit around the character, final slow push-in. Audio: Natural bedroom ambience, fabric and wardrobe sounds, footsteps, garment movement, subtle mirror-room reverb, upbeat modern fashion-vlog background music, natural spoken dialogue, soft whoosh effects during the outfit transitions. No subtitles, no logos, no watermark. Consistency & Quality: No jump cuts during transformations. No duplicated character. No distorted hands or fingers. No warped clothing. No inconsistent room layout. No facial identity changes. No unnatural skin smoothing. Keep the same character, bedroom, lighting logic, and visual realism throughout.

NEON the Hacker Steps Into the Megacity

15s · ref2va · 含音訊

@[face ref] をNEONの顔、ピンクのボブヘア、黒い丸眼鏡の厳密な参照として使用します。 @[body ref] をNEONの体格、黒と赤のサイバーパンク衣装、装備、ブーツの厳密な参照として使用します。 @[audio ref] は映像のリズム、カットの強弱、主要な音楽アクセントの参照として使用します。 15秒のハイエンドなサイバーパンク・キャラクター紹介映像。 主役はNEONただ一人。 クールで知的、危険な雰囲気。動作は自信に満ち、抑制されている。 構成： 0–3秒：IDENTITY REVEAL 暗いネオン照明の空間。 ブーツ、赤いジャケットのディテール、眼鏡越しの目元を短いバーストカットで見せる。 最後に顔のクローズアップ。 カットを@[audio ref] の最初の強いアクセントに合わせる。 3–6秒：NEON ALLEY 雨に濡れた未来都市の路地。 NEONがゆっくりカメラ方向へ歩く。 ローアングル、横方向のトラッキング、濡れた路面に映る赤いネオン。 人物の動きよりもカメラワークを強調。 6–9秒：TECH UNDERGROUND 赤い警告灯が点滅する地下施設。 肩越しのショット、手袋と装備のクローズアップ、短いオービットショット。 NEONは静かに周囲を観察する。 9–12秒：MEGACITY ROOFTOP 巨大な未来都市を見下ろす夜の屋上。 風でピンクの髪とジャケットがわずかに揺れる。 ワイドショットからローアングルのヒーローフレームへ切り替える。 12–15秒：FINAL HERO REVEAL 赤とマゼンタの逆光。 カメラがNEONの周囲を短く回り込み、正面のミディアムクローズアップで止まる。 NEONが眼鏡越しにカメラを見る。 最後の音楽アクセントで力強い静止ヒーローフレーム。 編集： 合計12〜15ショット。 主要カットを@[audio ref] の強拍に合わせる。 環境変更は音楽フレーズの変化に合わせる。 細かい半拍すべてにカットを入れず、強いアクセントを優先する。 一貫性： 同じ顔、同じ髪型、同じ眼鏡、同じ体格、同じ衣装を全編で維持。 衣装の黒・赤・ゴールドの配色と装備位置を維持。 キャラクターは常に一人だけ。 禁止： 複数のNEON、分身、衣装変更、髪型変更、眼鏡の消失、 顔や身体のモーフィング、過剰なアクション、文字、ロゴ、字幕、UI、 キャラクターシート風レイアウト、分割画面、白背景。 -------------------------------------------------------

The Camera Breaks into an Arcade Game

14s · 含音訊

A handheld found-footage shot from behind a person playing an authentic Street Fighter II arcade cabinet in a dim 1990s arcade. Ryu and Ken begin a normal match as the announcer shouts, “Fight!” The camera suddenly rushes toward the curved CRT screen in one continuous motion; reflections and scanlines expand into giant glowing red, green, and blue phosphor dots, then the camera passes through them and the image resolves into a clean full-screen 4:3 Street Fighter II game view with crisp 16-bit pixel art and subtle CRT scanlines. Chun-Li unexpectedly jumps into the match, followed by Blanka dropping from above, Dhalsim teleporting into the center, Zangief charging in, and several more fighters entering from both sides. The stage widens as the match becomes a chaotic but readable eight-player free-for-all: Sonic Booms cross the screen, Blanka’s electricity shocks multiple fighters, Zangief spins through a crowd, characters collide in midair, and health bars rapidly drain. Everyone unleashes a special move at once, filling the screen with pixel explosions and impact flashes. When the smoke clears, every fighter is knocked out except Dhalsim, calmly floating above the pile. The announcer declares, “Dhalsim wins. Perfect!” Authentic arcade sound effects, energetic chiptune music, no modern 3D graphics, no camera shake after entering the game.

Dancing Across the Magical Islands of Malta

15s · ref2va · 含音訊

A Quiet Morning in the Backyard Herb Garden

15s · 含音訊

Main Subject: Young Korean woman, early 20s, loose linen shirt over shorts, hair tied back with a cloth, dirt-smudged fingers, gentle focused expression. Location: Small backyard herb garden beside the house, late morning. Wooden planter boxes, scattered gardening tools, soft natural sunlight, a low fence. No modern structures. Visual Style: Ultra-realistic documentary realism, candid hands-on feeling, bright natural daylight. Camera Style: Early 2000s DV camcorder, handheld close framing, autofocus adjusting between her hands and the plants, warm faded tones, soft grain. No stabilization. Timeline (15 sec, each slot = 2 compressed beats): 00:00–00:03 → She kneels by the planter box, then snips a few basil leaves carefully. 00:03–00:06 → She smells the leaves, then says to camera "향 진짜 좋다" ("The smell is really nice"), smiling. 00:06–00:09 → She moves to another box, then pulls a small weed from the soil. 00:09–00:12 → She wipes her hands on her shirt, then gathers the herbs into a small basket. 00:12–00:15 → She looks at camera saying "오늘 저녁에 쓸 거야" ("I'll use these for dinner tonight"), standing up as it fades. Audio: Leaves rustling, soil shifting, faint birds, distant wind. Her dialogue as noted above. No music. Goal: A small, grounded gardening moment warm, patient, authentic.

Rhythm, Performance, and Kinetic Type

15s · 含音訊

Style: Premium music commercial, ultra-realistic, cinematic, 8K HDR, natural lighting, luxury fashion aesthetic, smooth professional camera work, vibrant neon accents, realistic skin textures, high-end choreography, dynamic typography synced to the beat, music-video quality, no watermark. Scene 1 (0–3s) A stylish young female artist walks confidently through a modern city street at night, flanked by two equally fashionable dancers. They wear coordinated luxury streetwear with premium sneakers and jewelry. The beat drops as the camera circles them in slow motion. Giant animated typography appears behind them, displaying the lyrics in bold kinetic text synchronized perfectly with every word. Scene 2 (3–8s) The trio performs energetic hip-hop choreography in a neon-lit urban plaza. The camera switches between cinematic gimbal shots, low-angle tracking, drone passes, and close-ups of expressive faces. Every lyric appears on screen with premium motion graphics, glowing typography, smooth transitions, and rhythmic animations that pulse with the music. Scene 3 (8–12s) Fast-paced performance featuring synchronized dance moves, stylish hand gestures, confident attitude, realistic hair movement, natural fabric physics, and dynamic lighting. The lyrics continue appearing in large, eye-catching typography that interacts with the environment, wrapping around buildings and moving with the beat. Scene 4 (12–15s) The music reaches its climax. All three performers strike a powerful final pose as the camera cranes upward. Massive cinematic typography fills the background with the final lyric while city lights sparkle behind them. Premium commercial color grading, flawless visual effects, realistic crowd energy, luxury music-video finish. Hip-Hop Lyrics (On-Screen Typography): We rise, no limits, we own the night, Dreams in motion, shining so bright. Move with the rhythm, feel the fire, We came to win—taking it higher! Visual Style: Premium commercial production, Billboard music video aesthetic, luxury fashion campaign, realistic camera movement, cinematic lens flares, authentic facial expressions, smooth choreography, vibrant urban atmosphere, perfectly synchronized kinetic lyric typography.

He Wins the Strength Contest with Timing

15s · 含音訊

Create a 15 second cinematic sports video in 16:9 inside a real indoor strength competition arena packed with spectators. The story contrasts repeated failure with one calm, unexpected success. It must feel like authentic live event footage captured by a professional broadcast crew, with natural human motion, believable weight, consistent anatomy, coherent crowd behavior, and physically accurate object movement. 0.00 to 2.70 seconds. Show three rapid failed keg toss attempts by three different heavyweight athletes. Use low sideline wide shots that include the athlete, tall steel throwing rig, red crossbar, and full keg arc. Each attempt lasts less than one second. One keg clips the bar and spins backward, one falls short, and one drifts sideways. The athletes show brief frustration while the crowd gives disappointed gasps. Use clean match cuts based on the circular keg shape. 2.70 to 4.40 seconds. Let the music soften. Cut to a medium wide shot of an unassuming compact middle aged competitor entering from the arena tunnel. He wears a plain black competition shirt, dark blue shorts, knee sleeves, lifting shoes, and a worn leather belt. He walks calmly toward the keg while larger athletes watch from the edge of frame. 4.40 to 7.20 seconds. Use three tactile close shots. Chalk pressing into his palms. Fingers locking around a cold dented steel rim. Shoes gripping the gray rubber floor as his knees bend. Show subtle breathing, sweat, fabric tension, skin compression, and a slight forearm tremor. Keep the same face, body, wardrobe, keg, and arena geography in every shot. 7.20 to 11.80 seconds. Continue in one unbroken low angle tracking shot with a natural 35 mm lens look. He swings the keg between his legs, drives through the hips, extends the knees, pulls upward, and releases at the correct moment. The camera makes a controlled upward tilt. The keg rotates with realistic inertia and follows a clean parabolic arc. Use natural motion blur at 30 frames per second with a 1 over 60 shutter feel. Hold a brief near silence before release. 11.80 to 13.40 seconds. The keg clears the red crossbar by only a few centimeters and lands heavily on the padded platform behind the rig without an unrealistic bounce. The crowd erupts on impact. A judge instinctively raises both arms to confirm success. 13.40 to 15.00 seconds. Cut to a medium close shot as the competitor raises one fist and gives a restrained relieved smile. Larger athletes behind him stare in disbelief, then applaud. Finish on a natural crowd reaction, not a freeze frame. Use cool white overhead arena lighting, subtle blue haze, realistic warm skin tones, gentle lens bloom around practical lights, deep readable shadows, neutral cinematic color, controlled contrast, fine film grain, realistic sweat highlights, and no excessive sharpness. Sound and music. Use an original 82 BPM cinematic percussion track with deep toms, restrained bass pulses, and a steady tension build. Layer authentic arena room tone, crowd murmur, chalk rubbing, metal scraping, shoe friction, breathing, a sharp air movement sound during release, a solid steel landing impact, and a powerful crowd swell after clearance. No dialogue. Do not include text, captions, logos, watermarks, brand names, duplicated spectators, warped faces, extra fingers, changing clothing, inconsistent body size, floating objects, rubbery metal, impossible physics, sudden camera teleportation, or artificial slow motion. The final result must look photographic, grounded, spontaneous, and genuinely filmed at a live competition.

A Gentle Slice of Korean Daily Life

15s · 含音訊

Main Subject: Young Korean woman, early 20s, natural everyday appearance, oversized soft t-shirt over shorts, hair in a loose bun, minimal makeup, realistic skin texture, calm content personality. Location: Small bedroom with a pile of clean laundry on the bed, mid-morning. Soft light through curtains, a wicker basket nearby, potted plant on the windowsill. No modern clutter. Visual Style: Ultra-realistic documentary realism, unscripted domestic feeling, soft natural morning light. Camera Style: Early 2000s consumer DV camcorder aesthetic, handheld shake, autofocus hunting between her and the fabric, faded soft contrast, mild sensor noise. No stabilization. Timeline (15 sec, each slot = 2 compressed beats): 00:00–00:03 → She picks up a shirt, then folds it neatly into a small square. 00:03–00:06 → She glances at camera saying "이거 진짜 지루한 일이야" ("This is such a boring task"), laughing softly. 00:06–00:09 → She stacks the folded clothes, then reaches for a pair of socks. 00:09–00:12 → She struggles to match the socks, then finally finds the pair, smiling. 00:12–00:15 → She looks at camera saying "거의 다 했다" ("Almost done"), placing the last item in the basket as it fades. Audio: Fabric rustling, faint birds, distant street sounds, soft breathing. Her dialogue as noted above. No music. Goal: A quiet, ordinary household moment grounded, warm, believable.

A Sleepy Morning in an Oversized Cardigan

15s · 含音訊

Main Subject: Young Korean woman, early 20s, oversized cardigan over pajamas, hair down and slightly messy, sleepy relaxed expression. Location: Small kitchen counter, early morning. Sliced bread, a jar of jam, a butter knife, soft morning light through a window. No modern clutter. Visual Style: Ultra-realistic documentary realism, quiet intimate feeling, soft warm morning light. Camera Style: Early 2000s DV camcorder, handheld close framing, autofocus slow adjusting to morning light, warm faded tones, soft grain. No stabilization. Timeline (15 sec, each slot = 2 compressed beats): 00:00–00:03 → She spreads jam onto a slice of bread, then places another slice on top. 00:03–00:06 → She cuts it diagonally, then says to camera "아침엔 이게 제일 편해" ("This is easiest in the morning"). 00:06–00:09 → She takes a bite, then chews slowly, looking out the window. 00:09–00:12 → She wipes a crumb from her lip, then smiles at the taste. 00:12–00:15 → She looks at camera saying "맛있다, 진짜" ("It's really good"), taking another bite as it fades. Audio: Knife scraping softly, faint chewing, distant birds, quiet kitchen ambience. Her dialogue as noted above. No music. Goal: A quiet, cozy breakfast moment calm, warm, deeply relatable.

A Product in Psychedelic Hand-Drawn Motion

15s · 含音訊

--------------- integrated_multimodal_description: [Shot 1] 2D hand-drawn animation in a psychedelic Japanese illustration style: heavy colored-pencil and crayon grain visible on every surface, thin uneven black ink outlines that wobble slightly, flat matte fills with no gradients, and a limited palette of cream off-white, muted rust-brown, deep forest green and pale peach. One single continuous unbroken take from start to finish, no cuts and no transitions. A frontal close-up at eye level frames a teenage girl drawn in this style: loose rust-brown wavy hair falling just past her shoulders, very large eyes whose irises are drawn as tight concentric pencil rings, a plain white round collar with a deep forest-green scarf knotted at her throat, cream-white skin with a faint peach shading on her cheeks. She is centered against a flat cream off-white background with no scenery, motionless and expressionless, looking straight into the lens without blinking. The camera pushes in with small amplitude at slow speed toward her face. The concentric rings inside her irises begin to rotate clockwise, slowly widening until each iris resolves into a spiral. At 00:04.000, still within the same continuous take, individual strands of her hair detach from her head and flow sideways like poured ink, stretching into long smooth curling ribbons that sweep across the frame while her face stays still. As the hair unspools, the cream background inverts to saturated fluorescent magenta and the black outlines invert to pale cyan, the colored-pencil grain remaining visible through the inverted colors. At 00:08.000, her facial contours dissolve: the hair ribbons, the green scarf and the peach cheek shading stretch and fold into one another until the entire frame is a slow marbled swirl of rust-brown, forest green and cream, still rendered with the same hand-drawn pencil texture. The swirl rotates clockwise at slow speed and fills the whole frame. At 00:12.000, the marbled swirl contracts inward toward the center, tightening steadily until it becomes a single small round black pupil ringed by a thin gold circle, resting on the flat cream off-white background that matches the opening frame so the video loops seamlessly. No human characters other than this single girl. No text, no captions, no subtitles, no lyrics, no logos and no watermark anywhere in the frame at any time. overall_soundscape: A dry pencil-on-paper scratching runs quietly underneath the whole shot. As the hair unspools, a soft paper rustle spreads outward and drifts across the stereo field. When the frame dissolves, a low liquid whoosh rises and slowly rotates from left to right. The shot ends with one short inward suction sound as everything contracts to a point. non_diegetic_music: A slow detuned analog synthesizer drone at roughly 70 BPM that bends gradually in pitch. A muted electric-piano figure repeats every two bars over a tape-delayed hi-hat keeping a half-time pulse. The drone swells across the final three seconds and cuts off abruptly on the last beat.

Two-Part Bedroom Dance

12s · fl2va · 含音訊

動画（MiniMax H3）1本目 The young anime woman with light blue hair and a white summer sailor uniform shown in <Picture 1> is dancing in place in her bedroom on a bright morning. She sways her hips from side to side and bounces lightly on her feet in rhythm, keeping both feet in the same spot on the wooden floor. Her long light blue hair and her navy pleated skirt swing with the motion, and she keeps looking back over her shoulder with a happy smile. She stays in the same position and does not walk anywhere. Static camera, fixed framing, full body visible, morning sunlight through the curtains. Quiet room ambience, no music. 動画（MiniMax H3）2本目 The young anime woman with light blue hair and a white summer sailor uniform shown in <Picture 1> keeps dancing in place in her bedroom. She slowly raises both arms above her head and then lowers them again, twisting her upper body gently from side to side as she does. Her long light blue hair sways with the motion and her navy pleated skirt turns a little with her hips. She keeps both feet in the same spot on the wooden floor and glances back over her shoulder with a happy smile. Static camera, fixed framing, full body visible, morning sunlight through the curtains. Quiet room ambience, no music.

Tasting a Burger from a First-Person View

15s · 含音訊

Duration: 15 seconds | Aspect Ratio: 16:9 | Style: Authentic UGC / iPhone selfie-vlog, handheld, natural light, TikTok/Reels aesthetic. Product Reference: Use the uploaded gourmet burger image as the only product reference. Preserve the bun shape, patty thickness, cheese melt, lettuce, tomato, sauces, and proportions exactly in every shot. Character Description Name: Hana A young Japanese woman in her early 20s with natural beauty, long dark hair in a loose ponytail, oversized cream sweatshirt, minimal makeup, bright smile, friendly lifestyle-vlogger personality. Shot Breakdown SHOT 1 (0–2s) — Selfie showing the burger box. Dialogue: "Burger night!" SHOT 2 (2–4s) — Opens the box. SHOT 3 (4–6s) — Quick zoom on the burger. SHOT 4 (6–8s) — Hands lifting the burger with cheese stretching naturally. SHOT 5 (8–10s) — Bite reaction. Dialogue: "Okay... that's incredible." SHOT 6 (10–12s) — Casual close-up b-roll while reaching for fries. SHOT 7 (12–14s) — Toasting the burger toward the camera. Dialogue: "You need this." SHOT 8 (14–15s) — Freeze frame with overlay: "burger cravings = solved 🍔" Look & Feel Warm apartment lighting, genuine phone footage, slight grain, natural autofocus breathing, handheld imperfections, fast jump cuts. Negative Prompt cinematic grading, commercial production, CGI burger, fake cheese, distorted hands, warped food, perfect stabilization, studio lighting, text glitches, logo distortion.

Punchline Timing in an AI Stand-up Special

15s · t2va · 含音訊

Style: Live stand-up comedy special, intimate comedy club, professional multi-camera production, warm stage lighting, packed audience around small tables, sharp HD broadcast look, natural facial expressions, authentic comedic timing, clean microphone audio, realistic audience reactions, subtle handheld audience camera, 15-second video, 5 cinematic cuts 0–3s: [Wide Establishing → Medium Push-In] A comedian stands center stage holding a microphone as the audience settles. The comedian smiles and says: Comedian: “I asked AI to organize my life yesterday” Brief beat 3–6s: [Medium Close-Up] The comedian maintains a completely serious expression Comedian: “It looked at my schedule and said, ‘Actually... I’m just a language model.’” Audience immediately laughs 6–9s: [Side Angle + Audience Reaction] The comedian waits for the laughter, then slowly nods Comedian: “Even artificial intelligence has boundaries” Quick cut to the front row laughing and clapping 9–12s: [Tight Close-Up] The comedian leans toward the microphone Comedian: “My mom thinks AI is listening to everything we say” Beat Comedian: “Mom... nobody wants that podcast” Audience erupts into louder laughter 12–15s: [Medium → Wide Ending] The comedian waits for silence, then delivers the final line: Comedian: “AI isn't replacing us. It saw our search history and declined the position” Big audience laugh. The comedian smiles and lowers the microphone as the camera pulls out to reveal the applauding club Production details: Keep the same comedian, outfit, microphone, stage and audience throughout. Prioritize precise comedic timing, short pauses before punchlines, believable facial expressions and natural audience reactions. Never cut during a punchline. Audience laughter starts only after the punchline lands. No canned laughter, no overlapping dialogue, coherent eyelines, realistic club acoustics, professional live comedy special editing

A High-Stakes Acquisition in the Boardroom

15s · t2va · 含音訊

cinematic 15-second ultra-realistic sequence inside a luxurious modern boardroom during daytime. Soft natural light enters through large glass windows. Four powerful industrialists in expensive tailored suits sit around a long polished dark wooden table. The atmosphere is tense and high-stakes. The senior industrialist at the head of the table leans forward slightly and says firmly: “This acquisition will change the entire market. Either we move now, or someone else will.” Another industrialist across the table adjusts his cufflinks and replies calmly: “Moving now is risky. The numbers still don’t support a full takeover.”A third industrialist places both hands on the table and speaks with intensity: “Risk is the price of control. The investors are already waiting for our decision.”The camera slowly pushes in as the most powerful industrialist leans back, looks at everyone, and delivers the final line with quiet authority: “Then we take it. No more delays.” Cinematic lighting, sharp details on suits and the wooden table, subtle tension in their faces, realistic skin textures, high-end corporate atmosphere, shallow depth of field, filmic look.

Handheld Space-Cruise POV at a Black Hole

10s · t2va · 含音訊

amateur handheld pov footage of a tourist in their plush and comfortable room of a space cruise, carpeted floor and comfy bed, large window shows a view of Gargantua blackhole, you can see their reflection in the window, they turn off the light half way through so we can see outside better and say: "Wow look at that!", then they show back the room

A Street Photographer Meets an Old Man and His Dog

15s · t2va · 含音訊

A young Western female street photographer walks through a lively downtown street and notices an elderly man sitting outside a café with his small dog. She carefully composes the candid moment through her camera, captures the photo, then turns the camera toward the viewer to proudly show the shot she just took. She smiles, says “Look at that,” then continues walking through the city. Ultra-photorealistic visuals, natural handheld documentary movement, realistic camera interaction, authentic facial expressions, accurate hand movements, realistic dog behavior, natural daylight, cinematic depth of field, continuous character consistency, immersive city ambience, premium documentary realism.

Dolphins Appear Beside a Sightseeing Boat

15s · t2va · 含音訊

A young Western female traveler in her mid-20s walks naturally along a wooden marina dock toward a small white sightseeing boat. She wears a light blue windbreaker, white shirt, dark trousers, comfortable sneakers, sunglasses, a properly fitted life jacket, and a small crossbody bag. She carefully steps from the dock onto the gently rocking boat while holding the handrail, naturally shifting her weight as the boat responds to her movement. She walks toward the rear passenger bench, sits down, adjusts her position, and looks toward the open water. The boat engine starts with a realistic low rumble and gradually leaves the marina, creating a small bow wave and narrow wake. As the boat moves into open water, she notices movement nearby, looks surprised, and naturally says, "Wait... are those dolphins?" Two dolphins surface several meters beside the moving boat, swimming parallel at a safe distance with realistic tail propulsion, surfacing, diving, breathing, and water displacement. She picks up her phone with both hands and records them while smiling with genuine excitement. One dolphin briefly surfaces near the rear side of the boat, exhales through its blowhole, creates a small burst of mist and droplets, then dives beneath the water and leaves expanding ripples behind. She lowers her phone and says, "That is incredible." Ultra-photorealistic marine wildlife travel documentary, cinematic realism, natural human behavior, realistic walking and sitting biomechanics, physically accurate boat buoyancy and acceleration, authentic ocean waves and wake, realistic dolphin anatomy and swimming behavior, natural water reflections and refraction, accurate English lip synchronization, bright neutral daytime lighting, realistic coastal wind, immersive marina and ocean ambience, smooth documentary camera movement, continuous visual consistency, seamless storytelling from walking to boarding, departure, dolphin encounter, recording, and final reaction, no narration, no CGI appearance, no plastic skin, no robotic movement, no exaggerated dolphin jumps, no impossible water behavior, no sudden camera transitions, no text overlays, logos, or watermarks.

Setting Up Camp beside a Mountain Stream

15s · t2va · 含音訊

Main Subject : Young Korean woman, early 20s, oversized flannel over a tank top, cargo shorts, hair in a practical braid, focused cheerful energy. Location: Quiet forest campsite near a mountain stream, late afternoon. A half-set-up tent, camping gear scattered on a mat, tall pine trees, dappled sunlight. No other campers nearby. Visual Style: Ultra-realistic documentary realism, adventurous candid feeling, warm natural forest light. Camera Style: Early 2000s DV camcorder, handheld with natural outdoor shake, autofocus hunting in dappled light, soft grain, faded tones. No stabilization. Timeline (15 sec, each slot = 2 compressed beats): 00:00–00:03 → She hammers a tent stake into the ground, then checks the tension of the rope. 00:03–00:06 → She struggles with a stubborn pole, then says to camera "이거 왜 이렇게 안 들어가" ("Why won't this go in"). 00:06–00:09 → She finally gets it to click into place, laughing in relief. 00:09–00:12 → She steps back to admire the standing tent, hands on her hips. 00:12–00:15 → She looks at camera saying "다 됐다, 오늘 여기서 자자!" ("Done, let's sleep here tonight!"), smiling as it fades. Audio: Wind through trees, distant stream flowing, birds, fabric rustling. Her dialogue as noted above. No music. Goal: An adventurous, cheerful camping setup moment grounded, warm, authentic.

A Taste of Bangkok Street Food

15s · 含音訊

A cinematic 15-second ultra-realistic travel vlog following a young female creator exploring Bangkok's vibrant street food scene. She walks through a lively daytime market, introduces the legendary Pad Thai, watches a skilled street chef prepare the dish with fresh ingredients, and captures detailed close-ups of sizzling noodles, colorful toppings, and authentic cooking moments. She tastes the freshly made Pad Thai and shares her genuine reaction while surrounded by the energy of local vendors and travelers. Handheld vlog realism, natural lip-sync, expressive emotions, cinematic food close-ups, realistic market atmosphere, bright tropical daylight, ARRI Alexa 35 aesthetic, HDR, immersive street sounds, premium travel documentary style, 4K photorealistic quality, seamless character consistency, no text, no logos.

Japanese Dialogue During a Schoolyard Run

8s · 含音訊

A scene showing a male student wearing a green tracksuit and a female student in a sailor uniform running together on the school path along s small river. A shot of the two people viewed from directly the side. They are running from the right side of the frame toward the left. The frame captures their upper bodies. Several classmates on the way, walking to school. Refer to <Picture 1> for the characters. Voice 1(male):またワイら遅刻ちゃうか Voice 2(female):あと30秒！あたしらの勝ちやな！

A Seven-Second Scene on an RTX 4090

7s · ref2va · 含音訊

7-second video. The Office (US) mockumentary style, inside the Dunder Mifflin conference room in Scranton. Harsh fluorescent office lighting, beige walls, cheap chairs, whiteboard, muted colors, slightly soft consumer-documentary camera quality. Michael Scott stands at the head of the table while Jim, Pam, Dwight, and Stanley sit around him. Handheld single-camera cinematography with subtle shake, sudden reframing, and fast reaction zooms. Michael raises one hand with complete sincerity, defending an absurd opinion. MICHAEL: “Everybody says Donald Trump’s fart smelled terrible. I was there. Honestly? Not that bad.” Instant snap zoom to Dwight, who nods gravely. DWIGHT: “Strong. Presidential.” Jim slowly turns toward the documentary camera with a silent, deeply uncomfortable stare. Pam presses her lips together, trying not to laugh. Stanley keeps reading his crossword without looking up. Natural English dialogue, precise lip synchronization, realistic overlapping office ambience, awkward silence after the punchline, no laugh track, no subtitles, no on-screen text, dry deadpan comedy, authentic mockumentary performances.

Tasting Ramen in Authentic UGC Style

15s · 含音訊

Duration: 15 seconds | Aspect Ratio: 16:9 | Style: Authentic UGC / iPhone selfie-vlog, handheld, natural light, slight motion blur, TikTok/Reels energy — NOT cinematic. Product Reference: Use the uploaded ramen bowl image as the only product reference. Keep the broth color, noodle thickness, toppings, egg placement, chashu slices, and bowl appearance identical throughout every shot. Camera: iPhone 15 Pro handheld with front/back camera switching, realistic autofocus hunting, natural handheld movement, slight exposure shifts, warm apartment lighting. Character Description Name: Yuna A young Japanese woman in her early 20s with soft natural beauty, shoulder-length dark hair tied loosely, subtle makeup, oversized gray hoodie, cheerful personality, filming casually inside a cozy apartment kitchen. Shot Breakdown SHOT 1 (0–2s) — Selfie holding the ramen bowl. Dialogue: "Late-night ramen again." SHOT 2 (2–4s) — Overhead reveal with steam rising. SHOT 3 (4–6s) — Close-up autofocus on noodles and broth. SHOT 4 (6–8s) — Chopsticks lifting noodles with a natural noodle stretch. SHOT 5 (8–10s) — Selfie bite reaction. Dialogue: "That's insanely good." SHOT 6 (10–12s) — Casual b-roll of the bowl while she reaches for another bite. SHOT 7 (12–14s) — Selfie holding noodles toward camera. Dialogue: "Worth every bite." SHOT 8 (14–15s) — Freeze frame with handwritten overlay: "ramen fix 🍜" Look & Feel Warm lighting, natural phone quality, authentic UGC pacing, jump cuts, realistic handheld movement. Negative Prompt cinematic look, luxury commercial, perfect framing, CGI noodles, unrealistic steam, plastic food, distorted chopsticks, extra fingers, warped hands, overprocessed HDR, text artifacts.

Post-workout gym vlog

15s · t2va · 含音訊

CAMERA: DV 16mm tape camcorder POV. CHASE films herself, occasionally propping the camera on a wall or gym bag. Natural handheld shake, imperfect framing, delayed focus, clumsy zooms, face occasionally cut off. Camcorder never visible. LOOK: Soft blurry tape aesthetic, faint tape noise, bloomed gym lights, flickering auto-exposure, muted contrast, realistic skin. STYLE: Calm post-workout gym vlog. Relaxed, reflective, slightly tired but happy. Slow pacing, natural laughs. CHARACTER: CHASE, Korean idol (20s). Long black hair loosely tied, light post-workout glow, slim athletic build. Modest long-sleeve athletic top, loose joggers/leggings, socks or shoes off, towel around neck, no jewelry. SETTING: Quiet evening gym. Stretching mat, mirror wall, gym bag, protein shake, soft lighting, mostly empty. 15s | 6 Cuts Propped medium: sits on mat, exhales. "Okay, cool-down time." Handheld stretch: hamstring stretch, laughs. "Yeah, that was a lot today." Macro: picks up protein shake, condensation visible. Ambient sound only. Medium: drinks shake, smiles. "Okay, that's actually really good." Close: overhead stretch, rates workout. "I'd give today like an eight out of ten." Selfie: grabs bag and shake, waves. "Alright, I'm heading out—see you guys."

A Ceasefire from the Banquet-Hall Screen

添付された人物リファレンスの顔立ち、髪色、髪型、体格、衣装を正確に維持する。 劇場公開用超大作実写映画、Netflix最上位オリジナル映画級、制作費50億円規模。 GAME 05専用の巨大高級宴会場。 乱闘によって椅子が倒れ、テーブルがずれ、料理、皿、ナプキンが床へ散乱している。 15秒のシネマティックシークエンス。 前シーンの直後。 焦茶色センター分け、ブラウン系カーディガン、ストライプシャツ、ワイドスラックス姿のKAIがSPの動きを回避し、巨大モニターを強く見上げる。 呼吸が少し乱れている。 KAI： 「こんなのゲームじゃないだろ！」 VOICE — KAI： 20代前半男性。 柔らかく透明感のある中低音。 緊迫時には声に強い芯が出る。 明瞭な日本語。 全編で同じ声質とピッチを維持。 巨大モニターへ切り替わる。 金髪ロングウェーブ、黒スーツ、黒インナー、シルバークロスアクセサリー姿の女性ゲームマスター。 ゲームマスター： 「戦闘は必要ありません。」 VOICE — ゲームマスター： 20代後半〜30代前半女性。 低めのアルト。 冷たく滑らかで落ち着いた声。 ゆっくり明瞭。 感情の起伏が非常に小さい。 全編で同じ声質、ピッチ、話速を維持。 その言葉と同時に、宴会場の動きが一斉に止まる。 32mm相当のワイドショット。 黒髪ロングヘア、白黒ストライプ衣装のヤクザ系女性参加者とSPが近距離で停止。 MAELは低い姿勢で呼吸を整えている。 LUCAS、NERO、RION、角がありピンク系衣装姿の愉快犯も動きを止める。 空中を舞っていた白いナプキンだけがゆっくり床へ落ちる。 約1秒の静寂。 ゲームマスター： 「SPの前を通る。それだけです。」 全員の視線がSPと、その横にある広い通過スペースへ向く。 KAIへ切り替わる。 KAIは荒れ果てた宴会場を見る。 倒れた椅子。 割れた皿。 散乱した料理。 SPを見る。 もう一度荒れた会場を見る。 KAI： 「……じゃあ俺たち、何で戦ってんの？」 声は怒鳴らず、完全な脱力と素の疑問。 最後はKAIが無言で立っている表情を約1秒残す。 CAMERA: 冒頭KAIは50mm cinema prime相当のmedium close-up。 ゲームマスターは85mm相当のportrait close-up。 乱闘停止は32mm相当のwide ensemble shot。 最後は75mm相当でKAIのtight medium close-up。 アクション後からカメラの動きを急激に静かにする。 24fpsの自然な映画モーション。 LIGHTING: 暖かなシャンデリア光。 冷たい白色トップライト。 弱い赤色警告灯が徐々に消えていく。 KAIの焦茶色ヘアには暖かなブラウンの階調。 ゲームマスターは冷たいニュートラル光。 AUDIO: BGMなし。 冒頭はKAIの荒い呼吸、靴音、椅子やグラスが動く音、衣服の擦れ。 ゲームマスター： 「戦闘は必要ありません。」 その瞬間に激しい音が一斉に止まる。 その後は低い空調音。 揺れているシャンデリアの微かな金属音。 ナプキンが床へ落ちる小さな音。 ゲームマスター： 「SPの前を通る。それだけです。」 KAIの最後の台詞には宴会場の自然な残響。 「……じゃあ俺たち、何で戦ってんの？」 台詞後、約1秒の静寂と空調音だけを残して終了。 16:9 cinematic widescreen。

A Vintage 1947 Town Under Fire

15s · t2va · 含音訊

Create a 15-second ultra-photorealistic live-action war sequence set in the United States in 1947, designed to look like authentic historical footage captured on a 1940s film camera. The entire scene must feel grounded, documentary-like, raw, and physically realistic. Environment: A rural American town in 1947 with wooden houses, old brick buildings, telephone poles, dirt roads, vintage American cars from the 1940s, wooden fences, farmland, and period-accurate street details. Overcast afternoon light, light fog, drifting smoke, dust in the air, damaged buildings, scattered debris, and a tense wartime atmosphere. Characters: American soldiers wearing historically accurate late-1940s military uniforms, helmets, boots, and equipment. Civilians wear authentic 1940s American clothing. Natural faces, realistic skin texture, sweat, dirt, fatigue, and believable body movements. 0–3s — Establishing Shot: Wide handheld shot of a quiet rural American street suddenly filled with smoke and confusion. Vintage 1940s vehicles are parked along the road while soldiers move quickly between wooden buildings. Civilians rush toward safer areas. 3–6s — Tension: Camera moves through the street at shoulder height, following several soldiers as distant gunfire is heard. They immediately react and take cover behind a vintage vehicle and a brick wall. Their movements are cautious and realistic. 6–10s — Combat: Fast handheld tracking shot as the soldiers move between cover while distant gunfire impacts the environment. Small pieces of wood, dust, and debris fall naturally from nearby impacts. Weapon recoil, movement, and body weight must be physically accurate. Keep the violence realistic and restrained. 10–13s — Human Moment: Camera briefly focuses on a soldier helping an injured civilian move behind cover. Their breathing, facial expressions, body language, and movement should feel natural and unscripted. 13–15s — Final Shot: Camera pulls back into a wide shot of the American town as smoke slowly moves through the street. Soldiers remain behind cover while vintage vehicles and damaged buildings fill the background. The scene ends with an authentic, tense 1940s documentary feeling. Visual Style: Ultra-photorealistic live-action, authentic 1940s American environment, vintage 35mm film texture, subtle film grain, natural imperfections, realistic exposure, handheld documentary cinematography, muted historical color palette, realistic smoke and dust, natural shadows, accurate depth of field. Physics: Strictly obey real-world gravity, momentum, inertia, friction, recoil, weight, collision physics, and human biomechanics. No exaggerated explosions, impossible movements, superhero behavior, or choreographed-looking combat. Negative Prompt: modern buildings, modern cars, smartphones, modern clothing, modern weapons, futuristic technology, CGI appearance, video-game graphics, fantasy, superhero action, excessive explosions, excessive blood, gore, impossible physics, unrealistic recoil, slow-motion physics, distorted faces, extra limbs, floating objects, plastic skin, artificial-looking environments.

Hand-Painted Blizzard Survival

15s · t2va · 含音訊

Visual Medium & Craft: Traditional frame-by-frame hand-painted oil-on-paper animation, physical 12 fps stop-motion cadence with deliberate frame holds and natural line jitter between frames. Raw brushstroke textures, strictly zero CGI, no 3D rendering, no digital interpolation, no game engine aesthetics. Cinematography & Lighting: Masterful cinematography in the style of Emmanuel Lubezki and Roger Deakins, shot with physical cine lenses and a classic 180° shutter blur. Lit exclusively by a single overhead light source: pale, freezing moonlight cutting through dense atmospheric haze. Strong contre-jour backlighting with the camera positioned on the shadow side. Uniform cold blue moonlight washes over skin, clothing, snow, and tree trunks, casting sharp cold rim lights on shoulders and hoods while keeping faces in soft shadow. Atmosphere & Environment: A violent, blinding blizzard with near-zero visibility (3 meters maximum), dissolving the background into a solid white fog wall. Gale-force horizontal winds whip thick snow and freezing fog through the frame. Deep snow quickly accumulates on garments. Exhaled breath instantly vaporizes and tears away in the wind. Characters & Emotion: A desperate mother and her frightened young child battling for survival, lost in the storm at the absolute limit of their endurance. The mother conceals her panic to protect her child, while the child cries openly in fear. Both lean heavily into the gale, squinting against the biting wind, shielding their faces with forearms and ducking into their collars. Technical Details: Color palette dominated by 60% snow-blue, 30% deep trunk-black, and 10% cold highlight accents. Strict physical realism with grounded weight, true inertia, and accurate contact shadows on snow. Dynamic compositional balance using the rule of thirds and golden ratio. Uncompromising continuity across all character designs, garments, and environmental assets. 8K IMAX aesthetic.

INK AFTER DARK in Pulp-Noir Motion

15s · t2va · 含音訊

Morning at a Traditional Javanese Market

15s · t2va · 含音訊

Traditional Javanese market in Yogyakarta, early morning, present day, ultra-realistic handheld one-take. A bakso vendor hurries through impossibly narrow, crowded market aisles carrying a large steaming bowl of freshly prepared bakso. Shoppers and vendors step aside to let him pass. He weaves between vegetable stalls overflowing with chilies, shallots, and leafy greens, ducks beneath low-hanging tarps, squeezes past batik merchants and baskets of traditional snacks, and carefully avoids children running through the market. The market feels dense, humid, noisy, and full of life. He passes porters carrying heavy sacks on their shoulders, women bargaining in Javanese, and motorcycles slowly pushing through the narrow lane. He finally reaches a tiny food stall at the back of the market and serves the steaming bowl just as the power briefly flickers, leaving the market dim for a moment before the bustle continues. Oppressive realism, natural morning light mixed with fluorescent bulbs, worn concrete floors, damp walls, wooden stalls, hanging plastic signs, Javanese conversations, vendors calling out prices, clattering bowls, footsteps echoing through the covered market, immersive cinematic pacing. No cyberpunk, no stylization, documentary-like realism.

The Boy Who Returned the Moon · Chapter 4

15s · ref2va · 含音訊

Macaw Scream in Extreme Slow Motion

15s · t2va · 含音訊

/gen prompt: Cinematic wildlife documentary, vertical framing, subject centered, National Geographic award-winning cinematography, anamorphic lens, rich natural color, natural sunlight, natural motion blur. States: the scream never stops, the camera always rises, every touched object reacts. Characters: a blue-and-gold macaw, cobalt wings, golden chest, green crown, white face patch, black beak; a young man, short dark curly hair, olive t-shirt. Israeli white stone apartment building, living room. 0-2s macro: silence, the macaw inhales, chest swelling, throat feathers rising, the man mid-sip. 2-5s the beak opens, the world slams into extreme slow motion: a ripple of distorted air expands from the beak, rings race across his coffee, the mug shattering into countable shards, coffee hanging in ropes, his cheeks rippling back. 5-9s time snaps back; the wave blows the shutters open, the camera rides it out, straight up the facade. 9-14s rising floor by floor: laundry lines whipping, a dog howling in one window; crawl on pigeons detonating off a ledge, feathers suspended, the ripple passing them; snap back. 14-17s the roof: solar heaters trembling, tank water rippling, car alarms flashing far below; bold 3D text "105 DB" slams centered mid-frame. 17-20s hard cut to the room: the macaw fluffs, tilts its head, one tiny chirp; the man frozen with the mug handle. Audio: silence, a heartbeat on the inhale; a sub-bass shockwave, one raw macaw screech Doppler shifting as the camera climbs, glass shatter, dogs and alarms join, biggest boom on the text, ringing silence, a tiny chirp. Photorealistic, no deformation, every feather barb visible, crisp letter edges, smooth fluid motion, 8k, extreme details. , resolution:720p, duration:20s, aspect_ratio:9:16

Korean Idol VHS Beauty Vlog

15s · t2va · 含音訊

DV 16mm camcorder vlog with soft VHS tape quality, handheld POV by CHASE and mirror-mounted vanity shots. CHASE, a Korean idol in her 20s with long black hair and dewy skin, casually picks up the fictional Lumina Velvet Lip Tint (frosted pink tube, gold cap) at a mall beauty store, saying, "Okay, everyone's talking about this shade." She heads home, opens and swatches the lipstick, applies it smoothly in warm vanity lighting, admires the glossy finish, smiles at the mirror, then looks into the camera for a glowing close-up reveal and says, "Okay wow... Lumina Velvet Lip Tint, you've got a new fan."

Desert Buggy Combat Chase

21s · ref2va · 含音訊

Mechanical bull charge The Beasts Are Coming

15s · ref2va · 含音訊

Use the uploaded mechanical bull image as the primary reference for the bull, and use Rahul’s image as the character reference for the rider. Create a 15-second ultra-realistic cinematic fantasy-sci-fi sequence set in The Harvester universe. The setting is a foggy ruined industrial lane at dawn or overcast light, with drifting smoke, hanging wires, broken stone and metal structures, wet ground, ash in the air, and distant furnace glow. The giant mechanical bull is ancient, battle-scarred, and alive with furnace energy inside its cracked armor. 0–3s — Hook: Start with Rahul stumbling backward into frame, breathing hard, turning to face danger in the smoke behind him. The giant mechanical bull stands in front of him like a wall, half-silhouetted in steam, protecting him. 3–6s: Close on Rahul placing one hand on the bull’s armored side, steadying himself. He looks at it with trust, not fear. The bull turns its head slightly toward Rahul. Its eye glows brighter, and its internal furnace begins to pulse. 6–9s: A loud metallic roar echoes from somewhere in the fog ahead. The bull reacts instantly — it lowers its head, paws the ground, steam blasts from its vents, gears lock into place, and sparks spit from its chest cavity. Rahul pulls himself up and mounts the bull in one fast motion. 9–12s: The bull rears slightly, then slams down hard. Rahul leans forward, gripping tight. Through the smoke ahead, we briefly see threatening silhouettes moving toward them, just enough to imply incoming enemies. 12–15s — Payoff: The bull explodes forward into a full charge with Rahul riding it, smashing through smoke and embers. End on a powerful low-angle tracking shot as both disappear into the haze, charging straight toward the unseen threat. Sound: deep metal groans, steam bursts, furnace rumble, distant enemy roar, hoof impact, sparks, low cinematic score. Cinematography / Color Brief Use the same signature look: desaturated steel blue, charcoal grey, mist white, weathered bronze, and restrained furnace orange accents. Soft overcast light, smoky atmosphere, wet surfaces, and strong depth. Cinematography should feel premium and mythic: low angles, slow dramatic push-ins, tactile detail, subtle shake, sharp realism, and heavy scale.

A Tiny City Inside a Pocket Watch

Style: cinematic macro fantasy, warm amber workshop lamp light, brass and glass textures, extreme close-ups, shallow depth of field, film grain. 0-5s: One old watchmaker with a magnifying loupe over one eye opens a gold pocket watch on his wooden workbench at night, the dark window behind him showing a sleeping city, the viewer over his shoulder. 5-10s: The viewer pushes into the open watch and reveals a tiny city built among the brass gears, with tiny lit windows and tiny people walking across the turning cogs in darkness, the watchmaker's tweezers lowering in and tightening one small screw. 10-15s: A tiny sun rises over the gears inside the watch, the tiny city fills with morning light, and at the same moment real sunrise floods through the workshop window behind him, the watchmaker slowly looks up at the window, the viewer pulling back. Negative prompt: more than one watchmaker, digital watch, cartoon style, modern electronics, text, numbers, watermark, slow motion

黑色禮服與建築光影

Create a 15-second cinematic luxury fashion video in 9:16 vertical format. A tall American female model with long dark hair wears a dramatic black couture gown with silver details and a flowing train. 0–3 sec: Close-up of red satin fabric moving through darkness before revealing the model under dramatic spotlights. 3–6 sec: The model walks confidently toward the camera. A stylish whip-pan captures her turning as the gown flows naturally. 6–10 sec: Seamless transition to a modern architectural courtyard with towering stone walls and golden sunlight. The model walks gracefully as the wind moves her hair and gown. 10–13 sec: The camera circles around her as she strikes a powerful high-fashion pose. 13–15 sec: Symmetrical hero shot with dramatic golden rim lighting, fading into black. Style: Ultra-realistic luxury fashion campaign, cinematic lighting, natural fabric physics, elegant camera movements, deep shadows, black and gold color palette, 4K quality. Audio: Deep cinematic bass, subtle percussion, and soft fabric sounds. No dialogue or subtitles. Text at the end: “BEYOND THE ORDINARY” Maintain consistent facial features, hairstyle, outfit, and body proportions throughout. No distortion, flickering, watermarks, or random text.

停車場出口的喪屍反轉

Create a 15-second ultra-photorealistic live-action zombie horror movie sequence in 16:9 widescreen. Make it feel like a professionally shot theatrical horror film, with 5 connected shots, escalating tension, strong cinematic sound design and music. Realistic human movement, realistic environments, grounded physics, no comedy, no text, no subtitles, no dialogue. SHOT 1 — 0–3 sec: Night. A deserted underground parking garage. A frightened young woman walks quickly between parked cars, holding a small flashlight. The camera tracks backward in front of her. Suddenly, the flashlight beam catches a motionless person standing far behind her. Deep bass hit. SHOT 2 — 3–6 sec: Close-up of the woman's face as she stops breathing for a moment and looks behind her. The parking space is empty. The music drops almost completely silent. She slowly turns back toward the camera. SHOT 3 — 6–9 sec: A zombie suddenly appears extremely close behind her in the background — pale dirty skin, torn everyday clothing, blood around the mouth, unnatural posture. It moves toward her with a sudden violent burst. Hard music impact. SHOT 4 — 9–12 sec: She runs through the parking garage. Camera follows handheld from behind. Multiple distant zombie silhouettes suddenly emerge between the cars, blocking the exit. Emergency lights begin flashing red. SHOT 5 — 12–15 sec: She reaches the exit door and desperately pulls it open. Bright daylight floods into the dark garage. She looks relieved for half a second — then the camera moves slightly past her shoulder and reveals dozens of zombies already standing silently outside, completely blocking the exit. On the final bass hit, one zombie suddenly looks directly into the camera. CUT TO BLACK. VISUAL STYLE: ultra-photorealistic live-action theatrical zombie horror, cinematic 16:9 composition, realistic human anatomy, realistic zombie makeup and skin texture, physically believable movement, dark atmospheric lighting, practical-looking effects, subtle film grain, dramatic contrast, natural handheld camera movement, high-end horror cinematography. CONSISTENCY & QUALITY: keep the same woman, same clothing, same hairstyle and same underground parking garage throughout the sequence. Zombies must have consistent realistic anatomy. No extra limbs, extra fingers, duplicated people, warped faces, melting bodies, floating objects, cartoon appearance, video-game look, excessive gore, text, subtitles, logos or watermark. EDITING: each shot must have a clear visual purpose and connect naturally to the next. Fast pacing, no dead time. The first shot must immediately create curiosity. Build tension from mystery → realization → zombie reveal → chase → final shocking reveal.

海岸時裝與獨白

A cinematic fashion film set on a breathtaking coastal landscape. A stylish young woman walks naturally along a rugged seaside path, surrounded by wild greenery and delicate flowers. She wears a relaxed oversized brown knit sweater with elegant ivory trousers. Behind her, crystal-blue ocean waters stretch toward a towering lush green mountain rising from the sea. Soft golden-hour sunlight creates a warm, dreamy atmosphere. A gentle ocean breeze naturally moves her hair and sweater. Start with a wide cinematic establishing shot of the coastline, then smoothly track alongside her as she walks, transitioning into elegant close-ups of her outfit, hair, and subtle facial expressions. Spoken Voice / Dialogue: The woman speaks naturally while walking, in a soft, calm, confident female voice. Her delivery should feel spontaneous and conversational, with realistic breathing and subtle pauses. She says: “Sometimes, all you need is a quiet place, a little fresh air, and a moment to simply slow down and enjoy where you are.” Her lip movements must accurately synchronize with every spoken word. Natural facial expressions, realistic mouth movement, and subtle head gestures while speaking. No exaggerated acting. Ambient Audio: Gentle ocean waves crashing against the rocks, soft coastal wind, subtle rustling of flowers and leaves, quiet footsteps, and distant seabirds. Keep the environmental sounds natural and cinematic underneath the dialogue. No background music and no additional voices. Photorealistic, natural skin and hair, realistic fabric movement, cinematic lighting, smooth camera movement, shallow depth of field, soft bokeh, subtle film grain, premium fashion-commercial aesthetic, atmospheric color grading, 4K cinematic quality. No text, no logos, no watermark.

Ruby Queen Transforms Into a Warrior

15s · t2va · 含音訊

A cinematic fantasy transformation beginning with a majestic queen wearing an intricate ruby-embroidered corset gown, matching crown, and holding a glowing heart-topped scepter inside a gothic cathedral throne room. The camera zooms out to show her full attire as she turns and walks toward a grand staircase, where a burst of glowing red magical light erupts around her. Enveloped in the crimson energy, her gown transforms into sleek, ornate metallic warrior armor, while her scepter morphs into a longsword and an embossed shield. She turns back toward the camera in a powerful battle stance, positioned before a glowing red arcane circle on the cathedral steps.

A White Lion in the Lamplit Park

A Cinematic video of a young woman wearing a brown jacket walking in a peaceful park during dusk She walks along a path lined with glowing warm streetlamps On a wooden park bench, a giant, majestic white lion with glowing fur is calmly sitting The woman approaches the white lion and gently pets its mane and face. Close-up shot showing a warm connection between her and the gentle white lion with the lion nuzzling against her cheek lovingly Finally they are sitting together peacefully on the grass under a warm streetlamp at night Cinematic lighting, realistic, soft shadows 4k resolution, emotional and magical vibe.

A Living Portrait Among Statues

A cinematic fashion video set in a dusty sculpture studio filled with white plaster classical busts and statues: a beautiful young woman with long dark wet-look wavy hair sits on a white pedestal in a sheer teal off-shoulder draped dress with midriff cutouts, wearing a large silver pendant and chunky dark red jewelry, slowly shifting between elegant poses—looking down in profile, turning toward the camera with a soft gaze, close-ups of her face and manicured hands touching her shoulder and cheek—while Italian voiceover gently admires her beauty and presence.

宇宙藏在一隻眼睛裡

15 seconds STYLE: Ultra-photorealistic cinematic sci-fi, IMAX-scale visuals, dramatic volumetric lighting, realistic VFX, anamorphic lens, deep cosmic blacks, cyan and golden highlights. SCENE 1 (0–2s): A lone female astronaut in a graphite-white futuristic spacesuit stands on a colossal metallic platform floating in deep space. Galaxies extinguish behind her. The last blue star collapses. Extreme wide shot, slow camera push-in, overwhelming cosmic scale. SCENE 2 (2–4s): The astronaut runs toward an ancient stellar machine and presses a glowing golden activation core. Warning lights flash across her visor. Dynamic tracking shot transitioning to extreme close-up of her hand. SCENE 3 (4–7s): The dying star erupts into a magnificent golden energy spiral. A cosmic shockwave spreads across the darkness, reigniting galaxies. The astronaut braces against the blast. Spectacular photorealistic cosmic VFX, wide cinematic pullback. SCENE 4 (7–10s): WITHOUT CUTTING, the camera continues pulling back. The golden spiral transforms seamlessly into the intricate iris of a human eye. The entire universe is revealed as a tiny reflection inside a pupil. Surreal macro realism, seamless scale transformation. SCENE 5 (10–12s): The camera reveals a sleeping child in a warm bedroom at sunrise. The child's eye opens. The galaxy reflection slowly fades. Intimate cinematic close-up, warm sunlight, sudden quiet. SCENE 6 (12–15s): The child blinks, smiles, and raises an open palm. A miniature newborn galaxy materializes above the hand, spinning with billions of tiny stars. The child whispers: 'Again.' Gentle camera push-in. Cut to black. NARRATION: 'The last star was dying. One final chance to save everything. She brought the universe back. But it was never ours. We were only a dream.' Child whispers: 'Again.' SOUND: Deep cosmic rumble, escalating orchestral tension, enormous bass impact at the star ignition, reverse swell during the eye reveal, sudden silence, soft piano and ethereal chime at the ending. CONTINUITY: Same female astronaut and graphite-white suit throughout space scenes. Same golden spiral shape across star, eye reflection, and newborn galaxy. Maintain consistent photorealism and smooth cinematic transitions. No subtitles, no watermarks, no unwanted text.

The Sky Descends Like a Giant Wall over a Suburban Street

14s · 含音訊

A hyper-realistic handheld phone video of a quiet suburban backyard on a bright normal afternoon. A person casually waters plants near a fence while birds chirp, distant traffic hums, and everything feels completely ordinary and mundane. The camera drifts naturally like a real home video, capturing the lawn, patio furniture, and blue sky with soft white clouds. After several seconds of normal peaceful activity, a deep cracking sound suddenly comes from above. Without warning, the entire sky begins dropping straight downward like a gigantic solid ceiling, with the blue sky and clouds moving as one physical surface descending toward the yard. The person looks up in shock just as the sky rapidly fills the frame, swallowing the scene in a terrifying instant. The camera jerks and falls to the ground at the last moment. No cinematic buildup, no surreal visual style, it should feel like a totally normal real-life recording interrupted by one sudden impossible and visceral event.

The Diner That Rewinds

Photorealistic cinematic 1950s American diner, chrome stools, red vinyl, neon glow and checkerboard floor, shot with modern lived-in realism and soft natural window light. Subtle handheld texture, warm practicals, rich period detail, heavy film grain. 0-4s: [Medium Wide] A striking young woman in her early 20s sits alone at the counter, calm and slightly amused, slowly sipping a tall thick milkshake through a straw. Behind her a young waitress in classic uniform approaches with a tray of eggs and bacon in one hand and a full glass coffee pot in the other. An older lady starts rising from a nearby booth. 4-8s: [Dynamic Tracking] The older lady collides hard into the waitress. Tray, plate, eggs, bacon and coffee pot explode upward in chaotic slow motion. Coffee erupts into long liquid ribbons and perfect suspended droplets. Camera immediately begins a smooth continuous orbit around the impact. Time locks completely at the peak of the spill. Every face freezes in pure shock. Only the girl at the counter keeps moving, completely unfazed. 8-17s: [Slow 360° Orbital] Camera glides in a full elegant orbit through the frozen diner. Coffee hangs in mid-air as glassy ribbons and spheres with perfect volume and surface tension. Bacon strips, eggs and the spinning tray float weightlessly. Patrons and waitress remain locked in startled expressions. The girl at the counter takes one slow, deliberate sip, eyes half-lidded, almost bored, while the entire frozen world (except her) begins an elegant reverse: every droplet, every piece of food and every person rewinds smoothly back to the exact starting positions. 17-24s: [Medium Shot] Rewind lands perfectly. Waitress stands balanced again with tray and coffee pot. The girl lifts her eyes, raises two fingers in a small casual gesture and softly calls the waitress by name. The waitress turns toward her just before the older lady begins to stand, completely avoiding the collision. A tiny private smile crosses the girl’s face. 24-30s: [Extreme Close-Up] Hard cut to her face as she takes one last slow sip. Soft knowing smile, eyes almost closed in quiet satisfaction, like she has done this a hundred times. Shallow depth of field, creamy bokeh of the neon diner behind her. Photorealistic, ultra-detailed fluid physics, perfect motion blur only on moving elements, stable characters, cinematic lighting, heavy natural film grain, no artifacts, movie-level temporal coherence, high rewatch value.

A Green Locomotive Mechanically Transforms into a Robot

15s · fl2va · 含音訊

Human Cakes Collide on a Manhattan Street

15s · t2va · 含音訊

Shaky handheld smartphone footage, pure first-person view, bright clear Manhattan street under shiny midday sun.The camera jerks, sways and shakes heavily like a real phone held by someone walking backward in panic. Sharp sunlight, hard shadows, clean blue sky above brick buildings and dry asphalt. Strong natural motion blur and smartphone digital noise. Continuous 20-second sequence (new subject + vehicle every 5 seconds): [0s–5s] Operator walks backward from a white man in a black agent suit and sunglasses. The operator’s hand silently points urgently behind the man. The man turns his head, eyes widening in shock as he sees a bright red sports car drifting sideways at high speed toward him. The car slides in at an angle with screeching tires and physically slams into his body first — the impact throws him hard against the hood. Only after the physical hit does his body dissipate into a chaotic spray of tiny randomized fragments — almost pure thick cream mixed with very small irregular cake crumbs, no large pieces. The intricate cream explosion splatters in all directions, coating the red hood, windshield and street in messy streaks and droplets. The suit is ripped off by the force and either sticks to the car or drops to the ground. Cream heavily sprays across the lens. [5s–10s] Camera keeps shaking and moving back. A Black woman in a business blazer. Operator silently points hard behind her. She turns, face reacting with sudden fear as a dark blue SUV drifts sharply toward her. The SUV locks brakes mid-drift and physically smashes into her body first. Immediately after the impact her body dissipates into an intricate burst of tiny randomized particles — mostly thick chocolate cream with only minuscule dark cake crumbs. The fine cream spray coats the blue SUV surface and asphalt in dense, chaotic patterns. The blazer and skirt are torn away, parts sticking to the vehicle mixed with cream, the rest dropping naturally. Chocolate cream heavily splatters the lens. [10s–15s] Operator still walking backward, phone shaking. An Asian man in a hoodie. Operator silently points behind him. The man turns and freezes in panic seeing a white delivery van sliding into a wide drift. The van physically crashes into his body first. Right after the hit he dissipates into a highly randomized spray of tiny fragments — almost entirely cream with very small scattered sponge and fruit particles. The intricate cream explosion covers the van and pavement in messy droplets and streaks. The hoodie and jeans are stripped off, some cloth remaining on the van mixed with cream, the rest falling with natural physics. Cream hits the lens hard. [15s–20s] Camera continues with heavy smartphone shake. A Latina woman in a trench coat. Operator silently points urgently behind her. She spins around, eyes wide in terror as a black pickup truck performs a long cinematic drift straight at her. The truck physically hits her body first. Only then does her body dissipate into a fine, chaotic spray of tiny randomized particles — mostly thick caramel cream with only minute golden crumbs. The intricate cream blast coats the truck hood, grille and ground in dense, irregular patterns. The trench coat is ripped off, sections sticking to the truck with cream, the rest falling realistically. Cream and tiny fragments cascade over the vehicle and street, heavily streaking the lens. Throughout: constant heavy smartphone-style camera shake and jitter, natural motion blur, dense cream sprays and tiny randomized particles hitting the lens, realistic cloth physics, cinematic vehicle drifts, clear physical body impact first followed by dissipation into almost pure cream with only very small irregular cake crumbs (never large pieces or whole shapes), photorealistic, bright clear daylight, raw live smartphone footage look. No text, no logos, no stabilisation.

Clouds Form the Word MORNING at Sunrise

15s · t2va · 含音訊

Epic cinematic aerial shot: Endless rolling clouds flow across towering mountain peaks during sunrise. The golden light transforms the clouds into rivers of glowing vapor. Air currents gradually sculpt the cloud formations into the gigantic word "MORNING", stretching naturally across the sky. As the sun rises higher, the cloud letters slowly dissolve into the atmosphere while brilliant light floods the frame. Interstellar meets National Geographic, majestic, emotionally powerful.

A Warrior Walks Across a Mechanical Planet

15s · 含音訊

Zero post-production cuts. Pure spatial awareness and temporal coherence from the engine. Using semantic motion design to make typography emerge from the environment is the future of title sequences. 🎬🔥 Use the provided image as the final state. Audio-driven motion sync. [0s-6s] The space nomad walks forward with a heavy, confident stride. Procedural world assembly: the environment mechanically builds itself around him. Asteroid rock shifts, interlocking clockwork gears spin, and glowing amber holograms activate. [6s-10s] The character halts, looking out over the horizon as the mechanical world construction completes behind him. [10s-15s] CRITICAL SEQUENCE: The camera smoothly settles into a centered frame. Massive dark rusted metal and brass gears dynamically emerge from the foreground, interlocking and snapping into place to form the main title text. Satisfying kinetic pop-up motion, seamless structural transformation, cinematic finish.

A Dragon Sweeps Over a Northern Fleet and Breathes Fire

15s · 含音訊

Hyper-realistic cinematic fantasy action sequence, 15 seconds, aspect ratio 16:9. Daytime in a vast cold northern sea surrounded by jagged mountains and dark rocky cliffs. A fleet of large medieval wooden warships sails through rough black-blue water while armored soldiers prepare for battle on the decks. Massive sails snap violently in the wind. The ships carry burning braziers, ropes, shields, spears, banners, wooden siege weapons, and rows of armed warriors. Thick storm clouds hang low above the sea. Wind drives sea spray across the decks. The danger comes from the sky: a giant dragon approaches from behind the mountains, its enormous wings gradually emerging through the mist. Begin with a high sweeping view of the entire fleet moving through the dangerous northern sea. Several warships sail in formation while smaller boats move between them. Soldiers look toward the distant mountains as a huge shadow passes across the water. Shift to a low deck-level view among the warriors. Men raise shields and grab spears while officers shout commands. The camera moves toward the front of the ship as the wind suddenly becomes violent. Cut to a distant view of the mountains. The dragon bursts through the clouds and flies directly toward the fleet, enormous wings beating through the storm mist. Its silhouette grows rapidly larger. Return above the ships as the dragon dives toward the fleet. Sailors scramble across the decks while archers rush into position. Burning arrows are lit and giant ballistae are rotated toward the approaching creature. Near the end, the dragon suddenly opens its jaws and releases a massive stream of fire toward the lead warship. The flames illuminate the dark sea as the crew raises shields and desperately attempts to turn the vessel. End with the dragon flying directly above the fleet as the first fireball crashes into the lead ship, exploding across its wooden deck. Style: hyper-realistic, cinematic, intense, fast-paced, suspenseful, fantasy atmosphere, strong sense of scale, warships, dragon battle, ocean storm, medieval warfare, fire, smoke, dynamic varied camera movement, no text, no logos, no cartoon style, no slow motion, no famous celebrity faces, no recognizable actors, no movie-star resemblance, no public-figure likenesses, no clear facial close-ups. Keep proportions. Keep style and features. Aspect ratio 16:9.

Gothic Dracula Horror Scene

15s · t2va · 含音訊

DRACULA — CINEMATIC HORROR PROMPT A vast abandoned Victorian ballroom at midnight, completely different from a corridor. Broken chandeliers hang from the ceiling, moonlight pours through enormous cracked stained-glass windows, and thick black mist drifts across the marble floor. Torn velvet curtains move slowly despite there being no wind. The camera begins with an extreme low-angle shot of an empty throne at the far end of the ballroom. A single candle beside it suddenly extinguishes. Dracula is already standing behind the throne. He slowly steps into the moonlight — an elegant, terrifying vampire wearing a long black Victorian coat with a high collar, dark waistcoat, polished boots, and subtle antique jewelry. Pale skin, long black hair, intense eyes, and unmistakable sharp fangs. His presence feels ancient and powerful rather than exaggerated. The camera slowly circles him as the ballroom begins behaving unnaturally. The chandelier swings violently. Hundreds of bats suddenly erupt from the darkness above, filling the room. Dracula doesn't move. He simply watches them pass. One bat lands on his shoulder. Dracula raises his hand. Every candle in the ballroom ignites simultaneously. The camera rapidly pushes toward his face. His eyes subtly change as he looks directly into the lens. He gives a restrained, sinister smile, revealing his fangs. Suddenly, the reflection of Dracula in the polished marble floor moves independently from him. The reflection turns its head toward the camera while Dracula remains perfectly still. The camera pulls backward rapidly as the reflection rises out of the marble like living smoke. Dracula finally spreads his arms, and a massive swarm of bats explodes outward behind him, transforming his silhouette into an enormous winged shadow across the ballroom walls. The chandelier crashes down in the background. CUT TO BLACK.

Amber Perfume and a Model Amid Golden Smoke

15s · 含音訊

A Luxury perfume bottle on glossy black surface, warm amber lighting, golden smoke, dark elegant background, soft reflections, cinematic close-up, slow push-in, photorealistic 4K. Confident woman in a burnt-orange satin dress, long dark hair, luxurious dark interior with golden lights, subtle smoke, cinematic medium shot, photorealistic 4K. Close-up of the same woman spraying perfume on her neck. Visible fragrance mist, warm golden light, natural hair movement, shallow depth of field, cinematic beauty ad. Same woman walking confidently toward camera in the luxury interior. Smooth tracking shot, reflective floor, warm golden lighting, subtle smoke, elegant cinematic look. Same perfume bottle centered on glossy black surface with amber crystals and golden smoke. Dramatic spotlight, dark luxury background, slow push-in, photorealistic 4K. Consistency: Keep the same woman, face, hair, skin tone, outfit, and perfume bottle across all scenes. Warm amber lighting, realistic skin and movement. No extra people, distorted hands, duplicate objects, text, or logos. Style: Luxury fragrance commercial, cinematic, photorealistic, 4K.

A Sword-Wielding Girl Faces a T. Rex

15s · 含音訊

Create a 14-second ultra-realistic Hollywood-style action fantasy film scene featuring a brave young female warrior battling a massive realistic Tyrannosaurus Rex inside an ancient jungle filled with ruined temples, giant trees, mist, mud, rain, smoke, and dramatic sunlight. Visual Style: Premium Hollywood blockbuster, photorealistic, cinematic, epic scale, realistic human anatomy, realistic dinosaur skin and movement, dramatic lighting, detailed environment, natural physics, intense facial expressions, high-end VFX, ARRI Alexa 35 look, anamorphic lens, shallow depth of field, HDR, subtle film grain, 4K cinematic quality, dynamic camera movement, realistic motion blur. 0–2 seconds — Establishing Shot: Wide cinematic shot of an ancient jungle temple in the middle of a mysterious rainforest. The female warrior stands alone in the ruins, holding a large sword in one hand. Her clothes are rugged fantasy-warrior clothing, slightly wet from the rain. Mist moves through the trees while birds fly in the distant sky. Slow camera push-in toward her. 2–3 seconds — Hero Close-Up: Cut to a dramatic close-up of the girl's face. Her hair is slightly wet and moving in the wind. She looks determined and fearless. Small scratches and dirt are visible on her face. She slowly raises her sword and prepares for battle. 3–4 seconds — Dinosaur Reveal: Suddenly, a massive realistic T-Rex emerges from behind the jungle trees and roars aggressively. Its enormous jaws open, sharp teeth visible, water and mud splashing around its feet. Low-angle camera makes the dinosaur look huge and terrifying. 4–6 seconds — First Attack: The dinosaur charges toward the girl at full speed. She runs toward the side and performs a fast dodge at the last second. The dinosaur crashes through trees and debris behind her. Use handheld camera movement, fast tracking, realistic impact and flying dust. 6–8 seconds — Sword Counterattack: The girl quickly turns around and attacks with her sword. Show a dramatic slow-motion moment as she swings the sword toward the dinosaur. The dinosaur moves its head aggressively while roaring. Strong cinematic camera movement follows the sword. 8–10 seconds — Epic Jump: The dinosaur attacks again. The girl jumps onto a large fallen tree and then leaps into the air above the dinosaur. Her hair and clothing move naturally in slow motion. Camera rotates around her as she raises the sword for the final strike. 10–12 seconds — Final Strike: She lands a powerful cinematic sword strike against the dinosaur's armored hide. Create a dramatic impact with dust, rainwater, debris and strong camera shake. Keep the action non-gory and suitable for a blockbuster fantasy film. 12–13.5 seconds — Dinosaur Falls Back: The dinosaur loses balance and falls backward into the muddy ground with a huge impact. Water, dust and leaves fly into the air. The girl lands safely and stands ready, breathing heavily. 13.5–14 seconds — Hero Ending: Slow cinematic push-in toward the girl. She lowers the sword slightly and looks directly toward the camera with a powerful, fearless expression. Behind her, the defeated dinosaur lies in the misty jungle. Golden sunlight breaks through the clouds, creating an epic silhouette and emotional Hollywood-style ending. Camera & Cinematography: Wide establishing shots, low-angle dinosaur shots, close-up facial shots, handheld action camera, tracking shots, 360-degree movement during the jump, dramatic slow motion during key action moments, shallow depth of field for close-ups, realistic motion blur, cinematic composition. Lighting & Atmosphere: Dark stormy jungle atmosphere mixed with warm golden sunlight, volumetric light rays, wet surfaces, realistic rain, mist, smoke, flying leaves, dust and water particles.

A Good-Morning Title Rises from the Lake

15s · 含音訊

Ultra cinematic macro shot: A calm mountain lake at dawn reflects the first golden rays of sunlight. Tiny ripples spread across the mirror-like surface as morning mist drifts gracefully above the water. Billions of sparkling droplets slowly rise into the air, suspended as if gravity has stopped. They spiral together with incredible fluid realism, naturally sculpting the word "MORNING" entirely from crystal-clear water. The liquid letters shimmer with golden reflections before gently collapsing into a spectacular explosion of droplets illuminated by the sunrise. Hollywood title sequence, ultra-realistic fluid simulation, volumetric lighting, IMAX quality. #MiniMaxH3

A Last-Second Rescue

15s · 含音訊

A cinematic 15-second ultra-realistic Hollywood action sequence featuring a skilled fighter facing his final battle inside an abandoned industrial warehouse. Surrounded by three aggressive opponents, he uses precise martial arts movements to dodge attacks, counter strikes, and overcome every challenge with determination. Dust fills the air as sunlight breaks through shattered windows, creating a dramatic battlefield atmosphere. The scene builds toward a tense final confrontation as the fighter stands alone among smoke, rainwater, and debris. Dynamic handheld camera work, low-angle tracking shots, slow-motion action moments, realistic choreography, intense facial expressions, physically accurate movement, dramatic lighting, ARRI Alexa 35 aesthetic, anamorphic lens look, HDR, subtle film grain, premium Hollywood action style, 4K cinematic quality, no text, no logos.

Bat Cookie Takes Flight

15s

the cut-out bat flaps up off the board and flies away

The Corgi Secret Agent

15s, 16:9 photorealistic cinematic action-comedy. A determined adult orange-and-white corgi secret agent exits an elevator carrying one sealed kraft-paper confidential file envelope in its mouth and runs through a modern high-rise corporate office. Low-angle tracking camera follows the same corgi throughout. Several adult male agents in black business suits notice the dog and try to intercept it. The corgi dodges between desks and legs while the office erupts into a stylized non-graphic action sequence: glass partitions crack, papers fly, chairs move and agents take cover. The corgi briefly hides beneath a desk, then emerges in an absurd but cinematic spy-movie counterattack using a dropped movie-prop weapon, with brief muzzle flashes and smoke, no blood or injury detail. It then races through the chaotic office, still protecting the exact same envelope. One final suited agent blocks the path; the corgi leaps into him, knocks him backward, lands safely and keeps running. Final shot: sudden calm. The corgi reaches a wooden executive desk and places the same confidential envelope neatly on the tabletop. Behind it, the office is chaotic with scattered papers and fallen chairs while the corgi calmly looks toward camera. Hold the final frame for 0.5s. Hollywood spy action × office comedy, realistic dog anatomy, real fur, physical object weight, cinematic daylight, subtle handheld movement, 24–35mm low-angle tracking, fast pacing, consistent office geography. Same corgi, same collar and ID badge, same envelope throughout. No second dog, no anthropomorphic standing, no human arms on dog, no gore, no cartoon look, no text, no logos, no watermark.

Black Mirror: Final Reflection

MINIMAX H3 — 15-SECOND CINEMATIC FIGHT “BLACK MIRROR: FINAL REFLECTION” 16:9 widescreen, premium dark-fantasy fashion-action. Obsidian Ronin vs Inkshade Valkyrie inside a gigantic floating liquid-black obsidian mirror surrounded by an endless white void. Preserve exact established character designs, faces, hair, armor, weapons, proportions and silhouettes. No redesigns. Constant movement. No idle poses, hard cuts, teleportation, freeze frames, blood or gore. The mirror behaves like liquid glass: every sword strike creates ripples, cracks and independent reflections that briefly attack before snapping back. 0–3s: Mirror forms from liquid black glass. Ronin emerges with a katana strike as Valkyrie attacks from the opposite reflection. Blades collide, creating a huge circular ripple. 3–6s: Ronin's heavy cut meets Valkyrie's agile twin-blade counter. Reflections attack from opposite directions. Black cracks race across the mirror. Smoke briefly forms “REAL OR REFLECTION?” 6–9s: Mirror tilts vertical. Both fighters sprint across its surface, exchanging rapid sword strikes. The glass bends around them like liquid. 9–12s: Mirror explodes into floating black fragments. Fighters leap between reflections, destroying them. Fragments align into a giant blade shape. Smoke forms “BREAK THE IMAGE”, then shatters. 12–15s: Final charge. Ronin's massive diagonal katana strike collides with Valkyrie's spinning twin-blade cross attack. The entire mirror shatters into thousands of black particles. Silence. Final smoke typography: “ONLY ONE REMAINS.” Elegant black-and-white luxury aesthetic, glossy reflections, silver highlights, charcoal smoke, cinematic motion blur, precise camera orbiting, low mirror tracking, rotating blade shots and dramatic final push. 15s | 16:9 | continuous action | premium cinematic dark fantasy | exact character consistency

車庫中覺醒的怪力

15 sec | 16:9 | One continuous generation | Korean dialogue | No BGM | No subtitles STYLE: Ultra-photorealistic live-action AAA supernatural martial arts. Real actors, real environment, grounded physical VFX. CHARACTER LOCK: SO-YEON, 160cm, messy black hair, black hoodie, sweatpants, Converse. Natural skin texture, sweat, pores, micro-expressions. Same actress throughout. One human only. LOCATION: Nighttime underground parking garage. Wet concrete, fluorescent lights, concrete pillars, scooters, shopping carts, puddles, exposed pipes. SOUND: Korean dialogue, footsteps, breathing, impacts, metal rattling, fluorescent hum. No music. COMBAT: Unarmed Sanda + Muay Thai clinch + Silat. Continuous flow: evade → redirect → knee → elbow → sweep → pivot → throw. Six attackers engage simultaneously. Two bystanders react naturally. FAULT-LINE PHYSICS: Heavy foot plants and slams create realistic cracks from the exact impact point. Visible vibration, dust, debris movement. No glow, aura, particles, energy waves, speed trails, or magic. 00:00–03:00 — CORNERED Six men surround So-Yeon beside a scooter. One grabs her hoodie. A delivery worker warns, "도망가요!" Terrified, So-Yeon whispers, "그만해..." The leader swings. She instinctively ducks. 03:00–07:00 — FIRST IMPACT She catches his wrist, pivots, and knees his stomach. Her sneaker plants hard. A thin crack shoots across the wet concrete. The leader crashes into a shopping cart and knocks into two others. Everyone freezes. A thug shouts, "뭐야, 저년!" The remaining men rush her. 07:00–11:00 — CHAOS She slips a punch and elbows one attacker into a pillar. Redirects another into a puddle. Sweeps a third to the ground. 0.2-second micro slow motion: cracks spread, water ripples, dust falls. Immediate speed return. Bystanders pull each other behind a parked car. 11:00–15:00 — THE LAST MAN The final attacker grabs her from behind. She becomes completely still. Her foot plants hard. Concrete cracks sharply. She redirects and throws him onto a parking line. Dense fractures spread. The delivery worker cautiously asks, "괜찮아요?" She nods, still frightened, and walks away across the cracked concrete. Fluorescent lights flicker from the vibration. CAMERA: Close handheld pursuit, reactive movement, occasional wider shots during group combat. Low angles for impacts and fractures, natural focus hunting, slight operator mistakes. No impossible moves or heroic posing. REALISM LOCK: Attackers hesitate, collide, and react naturally. Bystanders panic and move. So-Yeon looks confused by her strength. Every piece of damage has a visible physical cause. No supernatural visual effects.

A Crystal Civilization Builds with Sound

Photorealistic alien science fiction. A civilization of towering six-legged crystalline beings inhabits a vast desert city constructed from floating mineral particles. SHOT 1 | 0–3s | LOW WIDE ANGLE Three crystalline beings stand around an enormous plaza. Their glowing throat chambers vibrate, lifting millions of sand particles into the air to form a magnificent suspended tower. SHOT 2 | 3–6s | AERIAL ANGLE A gigantic black invading machine descends over the city, emitting a violent distortion pulse. The tower disintegrates into swirling particles. SHOT 3 | 6–9s | GROUND LEVEL The crystalline beings turn toward the intruder. Their throat chambers illuminate simultaneously. The scattered particles suddenly stop moving. SHOT 4 | 9–12s | OVERHEAD A circular shockwave erupts from the beings. Every suspended particle accelerates toward the invading machine, forming an enormous rotating mineral spear. SHOT 5 | 12–15s | EXTREME WIDE The spear strikes the machine, piercing its entire body. The machine crashes into the desert as the mineral spear instantly reshapes into a towering crystalline monument. Awe-inspiring alien architecture, realistic particle motion, massive scale, powerful resonant sound, cinematic lighting. No dialogue, no text, no logos.

The Gravity Harvest

Photorealistic epic science fiction. No dialogue. SHOT 1 | 0–3s | LOW ANGLE A colossal industrial harvesting machine crawls across a barren alien valley, its massive rotating drums pressing into the ground. Gravity distortion bends the dust around it. SHOT 2 | 3–6s | OVERHEAD One drum jams. Concentric shockwaves spread through the earth. Rocks, vehicles and debris begin rising vertically. SHOT 3 | 6–10s | EXTREME WIDE An entire mountain tears free from the landscape, slowly ascending as waterfalls of soil cascade from its underside. SHOT 4 | 10–13s | VERTICAL DROP Camera plunges toward the enormous cavity beneath the floating mountain. A gigantic ancient mechanical hand lies buried in the exposed bedrock. SHOT 5 | 13–15s | LOW WIDE The mechanical fingers suddenly close around the harvesting machine, crushing it as the mountain hangs overhead. Heavy industrial sound, deep gravitational pulses, immense scale, physically convincing debris. No text, no logos.

The Sky Is Being Replaced

Photorealistic science fiction, enormous cinematic scale. SHOT 1 | 0–3s | STREET LEVEL A busy futuristic city under a beautiful blue sky. Suddenly an enormous rectangular shadow slides across the skyscrapers. SHOT 2 | 3–6s | UPWARD POV Gigantic mechanical claws descend from above the clouds and grip an invisible rectangular section of the sky. SHOT 3 | 6–9s | WIDE ANGLE The claws pull downward. The blue sky tears away as a massive rigid panel, revealing black industrial machinery behind it. SHOT 4 | 9–12s | ROOFTOP CAMERA Multiple sky panels detach in succession. Their enormous shadows race across the city while giant maintenance arms move between the exposed sections. SHOT 5 | 12–15s | EXTREME WIDE The camera rises above the city, revealing its entire horizon enclosed inside an unimaginably large mechanical sphere. A vast central mechanism begins rotating. Grounded scale, immense machinery, realistic shadows and atmospheric perspective, thunderous metallic sound. No dialogue, no text.

The Cloaked Ranger Vanishes

f/2.8 lens, eye level, static camera in Ravenholdt courtyard. Damp stone courtyard, low mountain fog. From 0s to 2s, subject holds unblinking eye contact. At 2s, he swiftly pulls his dark wool hood over his head and turns his back to camera. At 3.5s, as his cloak sweeps, his physical body rapidly dissolves and evaporates into a brief wisp of dark shadow-mist, vanishing completely by second 5, leaving the damp stone courtyard entirely empty for the final second. TEXTURES AND VFX: Optical body dissolve, realistic dark mist evaporation, fluid wool physics, organic sensor grain. Quick cloth rustle, boot pivot, brief wind gust, fading rain ambience.

巨獸反咬等離子巨炮

Photorealistic epic science-fantasy. A colossal six-legged armored predator with a broad crocodilian head, muscular neck and black crystalline plates charges a futuristic stationary plasma cannon mounted on a massive tracked siege platform. Barren volcanic plain. SHOT 1 | 0–3s | LOW FRONTAL WIDE The enormous beast charges straight toward the cannon. The weapon fires a concentrated blue plasma blast directly into its heavily armored chest, sending sparks and broken crystalline fragments flying. SHOT 2 | 3–6s | LOW SIDE ANGLE The creature crashes into the cannon's barrel, bends the long metal structure downward and bites onto its muzzle with enormous jaws. SHOT 3 | 6–11s | THREE-QUARTER ACTION ANGLE The cannon begins charging another shot while trapped between the beast's teeth. The creature violently twists its head sideways, bending the barrel backward toward the siege platform's own armored engine compartment. SHOT 4 | 11–15s | EXTREME WIDE IMPACT The cannon fires through its bent barrel, blasting directly into its own siege platform. A huge blue-white explosion tears the machine apart, throwing metal debris across the plain. The beast recoils, shakes its head and charges through the burning wreckage. CAMERA AND PHYSICS: Single beast, single cannon, consistent positioning. Clear muzzle contact, bent weapon geometry, physically readable redirection of the blast. Heavy creature movement and realistic debris. AUDIO: Thunderous charging footsteps, cannon discharge, grinding steel, heavy jaws, explosive final blast. No dialogue. No text on screen.

Learning the Days of the Week

15s · 含音訊

Create a 15-second animated educational video that introduces young children to the first four days of the week: Monday, Tuesday, Wednesday, Thursday. Learning pattern: DAY NAME → SOUND → FUN ACTIVITY ICON → PLAYFUL ACTION → DAY NAME REPEAT Target audience: children ages 3 to 6. Visual style: Same premium-cute aesthetic — pastel tones, rounded 3D icons, soft lighting, off-white background, unique glow per day, clean bold typography, gentle calendar-page-flip style transitions. 0:00–0:01 Intro: Mascot bounces onto a soft floating calendar page, text "Let's learn the days!", tap flips to reveal Monday. ▪️0:01–0:04 | Monday — School Day: Calendar page shows "Monday" in big rounded text. Narrator: "Monday. Time for school!" A tiny backpack icon bounces onto the page and wiggles happily. Word "MONDAY" highlighted in soft blue. ▪️0:04–0:07 | Tuesday — Park Day: Page flips gently to Tuesday. Narrator: "Tuesday. Time to play!" A small swing icon appears and swings back and forth once. Word "TUESDAY" highlighted in soft orange. ▪️0:07–0:10 | Wednesday — Art Day: Page flips to Wednesday. Narrator: "Wednesday. Time to paint!" A tiny paintbrush icon appears and draws one curved rainbow line. Word "WEDNESDAY" highlighted in soft purple. ▪️0:10–0:13 | Thursday — Story Day: Page flips to Thursday. Narrator: "Thursday. Time for stories!" A small open book icon appears, pages gently flutter. Word "THURSDAY" highlighted in soft green. ▪️0:13–0:15 Recap: Backpack, swing, paintbrush, book appear in four tiles with day names above. Mascot points to each; Narrator: "Monday, Tuesday, Wednesday, Thursday. Great job!" Sparkle + chime.

An 1890s Bird Plate Draws Itself

15s · fl2va · 含音訊

Circle, Square, Triangle, and Star

15s · 含音訊

Create a 15-second animated educational video that teaches young children the shapes Circle, Square, Triangle, and Star. Learning pattern for every shape: SHAPE → NAME SOUND → OBJECT → PLAYFUL ACTION → OBJECT NAME Target audience: children ages 3 to 6 Visual style: Same premium-cute aesthetic pastel colors, rounded 3D forms, soft lighting, minimalist off-white background, unique glow color per shape, crisp bold typography, polished smooth morphing transitions. 0:00–0:01 Intro: Mascot bounces in, shapes float briefly, text "Let's learn shapes!", tap reveals first shape with a ripple. 0:01–0:04 | Circle is for Orange: A perfect circle appears. Narrator: "Circle. Round and round. Circle is for Orange." Circle gains texture and a tiny stem, becomes a smiling orange, bounces once. Word "ORANGE," highlight shape outline in orange. 0:04–0:07 | Square is for Gift Box: The orange rolls and reshapes into a square. Narrator: "Square. Four equal sides. Square is for Gift Box." Square gains a ribbon and bow, wiggles playfully. Word "GIFT BOX," highlight in purple. 0:07–0:10 | Triangle is for Mountain: The ribbon folds into a triangle. Narrator: "Triangle. Three sides. Triangle is for Mountain." Triangle grows a snowy peak and a small smiling sun beside it. Word "MOUNTAIN," highlight in brown/teal. 0:10–0:13 | Star is for Sky: The mountain peak stretches into a star. Narrator: "Star. Star is for Sky." Star twinkles softly with tiny sparkles floating around it, gentle glow pulse. Word "STAR," highlight in golden yellow. 0:13–0:15 Recap: Orange, gift box, mountain, star line up in four tiles with shape outlines above. Mascot points to each in sequence. Narrator: "Circle, Square, Triangle, Star. Great job!" Sparkle + warm chime. Requirements: Each shape fully visible before morph, uppercase-clarity level precision on shape edges, no warped or duplicated forms, gentle motion only, synced sound cues, calm and beautifully polished finish.

Japanese Captions in Motion

15s · 含音訊

Cairn Munro Arrives in Motion Type

15s · ref2va · 含音訊

A Surreal Vision Inside a Laundromat

15s · 含音訊

[1] FORMAT Create a 15-second, 16:9 surreal live-action scene inside a quiet laundromat at night. [4] BEATS [0–3s] Slow handheld push toward a running front-loading washing machine. [3–6s] Inside the drum, the water becomes a miniature stormy ocean with waves, lightning, and a tiny lighthouse. [6–11s]The lighthouse beam shines through the glass as the storm grows stronger. [11-15s]The door suddenly opens. Only ordinary wet laundry falls onto the floor. [5] CAMERA One continuous handheld push-in, ending on the falling laundry. [6] LIGHT Cold flickering fluorescent lights, wet glass reflections, deep blue storm light inside the washer, realistic phone-camera texture. [8] AUDIO Audio: washing-machine rumble, water splashes, distant thunder, one door click, and wet laundry hitting the floor. BGM: a subtle 15-second mystery drone, building from 4 seconds and stopping abruptly when the door opens. [9] NEGATIVE Keep the laundromat fully photorealistic. The miniature ocean exists only inside the washing machine. No people, text, subtitles, logos, watermarks, monsters, or cartoon styling. #minimaxh3 #hailuoai

The Last Bubble Before Closing · Part 2

15s · ref2va · 含音訊

The Last Bubble Before Closing · Part 1

15s · ref2va · 含音訊

Ari and Bruno’s Croissant Bloom · Part 1

15s · ref2va · 含音訊

The Gentleman Cat and Little Mouse Surprise · Part 2

15s · ref2va · 含音訊

The Gentleman Cat and Little Mouse Surprise · Part 1

15s · ref2va · 含音訊

The Little Strawberry Wakes the Pineapple King · Part 2

15s · ref2va · 含音訊

Hand-Drawn Ginger Pork Cooking Anime

15s · t2va · 含音訊

手描きの日本の2Dアニメ、温かみのあるセルシェーディング、居心地のいい町の定食屋の厨房。15秒、ゆっくり見せる6カット、各約2.5秒。寄りのクローズアップ中心で、食欲をそそる濃厚な演出：脂、照り、湯気、たっぷりの量。 1 まな板を真上から：包丁が厚切りの豚ロースを切る、白い脂の霜降り。 2 斜め45度：熱々の鉄のフライパンに肉を並べ入れる、油が弾け、縁が反り返る。 3 マクロ：脂が溶け出し、深い焼き色の焦げ目が広がる。 4 寄り：濃い生姜醤油ダレを回し入れる、ぐつぐつと煮立って濃厚な照りのタレになり、肉に絡みつく。 5 横から：フライパンを揺すり、すべての肉に鏡のような照りがまとわり、湯気が立ち上る。 6 ラスト：湯気の立つ白ご飯の丼に生姜焼きを山盛りにのせ、タレが米粒の間へ垂れていく。 料理と手元のみ。顔なし、食べるシーンなし、文字なし、BGMなし、ナレーションなし。実写風なし、3Dなし。

Greenhouse tea isekai anime

15s · ref2va · 含音訊

高品質アニメ映像。 作品トーンと世界観は、透明感のある夏のガラス温室から、紅茶の渦の内側に存在するオリジナルの小さな不思議の国へ連続する、上品で夢幻的な叙情ファンタジー。澄んだ白、水色、琥珀色、淡い金色を主役にし、怖さや混沌ではなく、好奇心、浮遊感、静かな高揚を描く。今回は1枚のソース参照画像image1のみを使用し、image1をキャラクター、衣装、2D手描き画風、配色、現実側のガラス温室背景の唯一の参照として扱う。 【同一人物固定】 image1と完全に同じ一人の少女を全編で維持する。小さく繊細な同じ顔立ち、大きな青緑色の宝石のような瞳、同じ目の形、多層の虹彩と白いキャッチライト、淡い頬、細いまつ毛、真珠のような白銀髪、柔らかな長いウェーブ、編み込みを含むまとめ髪、淡い金色のリボン、青い雫形の髪飾りを固定する。表情変化でも目、眉、まぶた、口、視線の順を守る。白い長袖のハイネックドレス、淡い水色の刺繍と縁取り、淡い金色の腰リボン、華奢で上品な体格、白・水色・淡い金色の人物固有配色を変えない。現実の温室と不思議の国に同時に複数の少女を存在させず、光学トランジションの前後で同じ一人の少女として連続させる。変えてよいのは表情、視線、呼吸、歩行、手の動き、髪と袖とスカート裾の自然な揺れだけ。別人化、顔の平均化、衣装変更、装飾欠落、分身、余分な人物、既存作品を想起させる有名キャラクターを出さない。 【2D hand-drawn／2D手描き画風固定】 image1の細く淡い青灰色と暖灰色の線、透明感のある二層以上の色影、柔らかなグラデーション、白・ミルキーブルー・澄んだ空色・琥珀色・淡い金色の明るい配色を全編で維持する。白銀髪の真珠質ハイライト、瞳の多層反射、肌の淡い発光感、ドレスの皺と刺繍、花、葉、ガラス、白い家具、床タイル、紅茶まで高密度の手描き筆致で描く。布は柔らかく、ガラスは透明で硬質、紅茶は澄んだ琥珀色、異世界の道と建築は半透明の白いガラス質として素材を描き分ける。太い輪郭にしない。簡略TVアニメにしない。平坦な単層セル影にしない。低密度背景にしない。滑らかなCG・3Dにしない。半写実にしない。実写にしない。くすんだ色や画風混合にしない。 【舞台と小物固定】 現実側はimage1と同じ明るいガラス温室。白い窓枠と屋根骨格、青空と白い雲、外の緑と白い花、白い丸テーブル、白い金属椅子、淡い青灰色の床タイルを維持する。開始時はimage1の少女の顔、目、髪、衣装、温室背景、白・水色・淡い金色の配色、明るさ、柔らかなコントラストを維持し、追加される小物はティーポットだけ。小物の所有者はimage1の少女一人だけ。透明なガラスのティーポット一つ、透明なティーカップ一つ、透明なソーサー一つだけを使う。開始状態ではティーカップはソーサー中央に置かれ、底に浅い琥珀色の紅茶が入っている。少女は右手でティーポットの取っ手を持ち、左手はソーサーの横へ軽く添える。ティーポット、カップ、ソーサーを増殖、交換、変形させない。不思議の国ではこれらを人物や巨大な小道具として複製しない。 少女の表情は、目→眉→まぶた→口→視線の順に変化させる。まず左右の目の中にある小さなキャッチライトがわずかに明るくなり、次に眉が少し上がり、その後まぶたが柔らかく開き、口元に小さな驚きと微笑みが生まれ、最後に視線が渦の中心へ下がる。反射線、窓枠、光点を顔中央へ重ねず、顔と両目を常に明瞭に保つ。 最初のカメラ高は白い丸テーブルと同じ低い位置。少女の斜め前から、手前にティーカップとソーサーを大きく、奥に少女の胸上と顔を明瞭に置く。背景消失軸は床タイルと右側の窓枠が温室奥へ斜めに伸びる方向へ揃える。この構図の目的は、少女、ポット先端、カップ中央の着水点を最初の一画で同時に読ませること。 少女が右手首だけをゆっくり傾けると、ティーポットの先端から一筋だけの琥珀色の紅茶がカップ中央へ落ちる。ポット先端、液体の筋、着水点を一画で読み取れるようにし、紅茶はテーブル外へこぼれない。この着水点を変化の起点とする。着水点から一つの時計回りの渦が生まれ、青空の反射と淡い金色の日差しを巻き込みながら、琥珀、青、白の三色の螺旋へ育つ。 カメラはテーブルと同じ低い位置からカップの斜め上へ滑らかに上がり、人物サイズを胸上の中景から背景の顔が読める近景へ保ったまま、紅茶面へ近づく。背景消失軸は温室奥から円形のカップ中央へ収束させる。この移動の目的は、現実の着水点を異世界への案内線へ変えること。 螺旋の半分がまだ琥珀色の紅茶、もう半分が細い光の道になっている形成中の中間状態を短く明瞭に見せる。続いて螺旋が画面全体を満たした瞬間、その同じ回転方向、曲率、色の並びを保ったまま、一本の光の道へ完成する。暗転、瞬間移動、破裂、液体の中を溺れる表現にせず、紅茶面から異世界の俯瞰へ連続する光学的な形状一致として接続する。 変化後の完成状態である不思議の国は、傾いた白いガラスの庭道、空中でゆっくり反転する白い花壇、輪のように連なる温室アーチ、上下が穏やかに入れ替わる空色の庭で構成する。文字盤、数字、看板、動物、人型住民は出さない。 カメラ高は少女の胸より少し低い位置へ移り、同じ少女の斜め前を後退しながら、胸から膝までの中景で追従する。背景消失軸は琥珀と青の光の道が円形アーチの奥へ伸びる方向へ揃える。この移動の目的は、紅茶の渦だった曲線が少女を導く冒険路へ変わったことを読ませること。 少女は光の道に沿って軽やかに三歩進み、第一歩で傾いた庭道へ乗り、第二歩で浮かぶ白い床片を渡り、第三歩で円形のガラスアーチをくぐる。各足裏を順に接地させ、髪、袖、スカート裾は歩みより少し遅れて同じ風向きへ揺れる。滑走、飛行、急回転に見せない。 少女がアーチをくぐると、周囲の白い花が外側から順に淡い水色へ染まり、頭上のガラス骨格がゆっくり四分の一回転して上下の庭をつなぐ。少女自身は直立を保ち、重力方向を急変させない。 カメラは胸より少し低い位置を保って少女の肩越しへ短く回り込み、人物サイズを胸上に寄せる。背景消失軸は前方の光の道が作る一つの円へ収束させる。この移動の目的は、少女の冒険の先に帰還路が生まれることを示すこと。光の道は再び一つの時計回りの螺旋となり、その円周が現実のティーカップの縁と同じ形、大きさ、角度へ整列する。 カメラは螺旋の中心を通り、琥珀色の紅茶面の極近景から現実の温室へ滑らかに引く。カメラ高はテーブルと同じ低い位置へ戻り、人物サイズを奥の胸上へ戻す。背景消失軸は円形のカップ中央から床タイルと窓枠が温室奥へ伸びる開始方向へ戻す。この移動の目的は、異世界の冒険を一杯の紅茶の中へ回収し、少女の感情へ報酬を返すこと。同じ少女が帰還した連続性を保つ。 終端では少女が右手のティーポットを垂直へ戻し、紅茶の筋をきれいに止め、ティーポットを胸より低い高さで保持する。左手はソーサー横に添えたまま。カップ内の最後の渦がゆっくり縮み、中心に青と淡い金の小さな反射一つだけを残して静止する。 カメラはテーブル高さの斜め前で、手前の静かな紅茶面、奥の少女の三分の四顔と穏やかな微笑みを同時に読ませる。紅茶面の反射が完全に止まり、少女の両目、ティーポット、カップ、渦の名残が一画で明瞭になった瞬間に切る。 液体を黒く濁らせない。渦を黒い穴、荒れた水面、別形状の物体へ変えない。顔を歪ませない。手指を増やさない。余分な人物や余分な食器を出さない。ストロボ、激しい明滅、強い水平フレア、白飛びなし。文字、字幕、ロゴ、透かしなし。BGMなし、音楽なし、環境音なし、フォーリーなし、音響生成なし。

港口貓咪像素格鬥

Use Image 1 as the absolute reference for Cat 1 and Image 2 for Cat 2. Keep both cats visually identical to their references throughout the entire video. Create a playful 15-second retro 8-bit arcade fighting-game battle at a pixel-art harbor. A large ship is visible in the background, with water, docks, and simple pixel-art harbor details. Fixed side-view 2D fighting-game camera, full-body character visibility, low-resolution pixel graphics, limited color palette, sprite-based animation, arcade-style UI, CRT scanlines, energetic retro animation. 0–3 sec: Both cats stand facing each other in fighting stances on the harbor dock. A large pixel-art “ROUND 1” appears prominently in the center of the screen like a classic arcade fighting-game announcement. After a brief moment, it disappears and a large “FIGHT!” appears with a dramatic arcade-style flash, then disappears as the battle begins. The UI may show simple visual health bars, but do not display any timer, countdown, clock, numbers, scores, or other numerical information anywhere on screen. The only text visible during this sequence should be “ROUND 1” and “FIGHT!” 3–5 sec: Cat 1 throws a small ball of yarn toward Cat 2. 5–7 sec: Cat 2 sees the yarn and becomes extremely excited, happily jumping toward it with its paws outstretched. Cute pixel-art musical notes pop and bounce around Cat 2 to emphasize its excitement. Cat 1 calmly watches and prepares its attack. 7–10 sec: Just as Cat 2 reaches the yarn, Cat 1 activates a powerful special move. Its eyes suddenly glow and fire two bright pixelated laser beams at Cat 2. Add dramatic pixel flashes, sparks, impact effects, and a brief arcade-style screen shake. 10–12 sec: The laser hits Cat 2, sending it flying backward in a humorous exaggerated knockback animation. Its health bar reaches zero. No blood or gore. 12–14 sec: Cat 1 performs a playful victory dance. It closes its eyes, crosses its front paws confidently, and repeatedly sways its hips from side to side while gently bouncing its body up and down in a cute, rhythmic 8-bit dance. Keep the entire body visible and make the movement exaggerated and clearly readable as a victory celebration. A large pixel-art “WIN!” appears during the victory dance while Cat 2 remains defeated in the background.

A Poster Comes Alive

15s · 含音訊

Animate the source artwork as a **10-second energetic chibi anime poster assembly**, preserving the deep indigo-purple background, neon pink, cyan and yellow palette, glossy anime illustration, characters, typography, decorative border and exact original layout. Begin on the empty purple background, then draw the outer border and corner markers with quick glowing strokes; introduce the small labels, Japanese text, numbering and interface graphics through playful pop-ins, slides and type-on animation, each paired with light arcade clicks, bubbly typing sounds and soft digital chimes. Build the central world in layers: floating islands rise into position, clouds expand outward, the moon fades in, towers and airships drift into place, and sparkles scatter across the scene. Assemble the chibi robot and flying cat with quick bouncy entrances, then launch the main hero from deep inside the poster toward the camera with strong 3D parallax, allowing his shoe, hand and hair to briefly extend beyond the inner frame before settling into the original composition. Reveal the Japanese title with a bold elastic impact, followed by the English labels, release date, IMAX line and footer icons appearing sequentially. Add subtle looping life after assembly: blinking eyes, gently moving hair and clothing, small robot antenna motion, the cat’s tail bouncing, airships floating, clouds drifting and stars twinkling. Finish with a soft camera push-in, one bright starburst behind the title and a clean hold on the completed poster, keeping every element sharp and readable. No redesign, no distorted faces, no changing text, no full scene transformation, no aggressive camera rotation. 2/2

Watercolor anime fetish montage rapid cuts

15s · t2va · 含音訊

style: visual: "日本の水彩画風フルカラーアニメ" editing: "0.5秒おきの高速カット割り" animation: "作画枚数多め、滑らかな24fps" tone: "官能的だが直接的にはせず、温度・湿度・心拍を映像化する" project: id: "fetish_montage_v3_with_broll" format: "vertical_9x16" fps: 24 shot_duration: "0.5s" total_shots: 28 total_duration: "14s" ratio: "fetish 22 : b-roll 6（約3.5:1）" broll_philosophy: role: "呼吸・象徴・感情の外部化" placement: "フェチ的なカットが連続した直後、または感情の転換点" rule: "直接的な性的表現は避け、心拍・温度・湿度・緊張を伝える" broll_categories: nature_micro: - "雨粒が窓を一筋伝う" - "蝋燭の炎が揺れる。息で消えそうな瞬間" - "氷が割れる音と共に、ひびが走る" - "花弁が一枚、テーブルへ落ちる" - "蜘蛛の巣の水滴が揺れる" - "煙草の灰が静かに落ちる" - "湯気が立ち上り、消える" - "夜の街灯の周りを虫が一匹飛ぶ" object_symbol: - "壁時計の秒針のアップ。止まりそうに見える" - "コーヒーの黒い表面に天井が映る" - "床に脱ぎ捨てられた靴。片方だけ" - "誰もいないベッドの皺" - "鳴り続ける電話。誰も出ない" - "灰皿の吸い殻が二本。片方には口紅" - "ドアの隙間から漏れる光" - "鏡に映る空の椅子" texture_landscape: - "夜の濡れた路面。ヘッドライトが滲む" - "ネオンサインのフリッカー" - "シーシャの炭が赤く脈打つ" - "金属表面に映る歪んだ顔" - "革張りソファに沈む手の跡" - "湯船の水面が揺れる" body_abstract: - "心臓の鼓動に合わせ、布団が微かに上下する" - "人物の影だけが壁を伝う" - "ガラス越しの人物の輪郭。ピントがずれる" - "水滴の中に顔が映り込む" sequence: - id: 01 type: "fetish" action: "髪を持ち上げ、うなじを晒す" scale: "macro" - id: 02 type: "fetish" action: "下唇を噛み、ゆっくり離す" scale: "extreme_macro" - id: 03 type: "b-roll" category: "object_symbol" action: "壁時計の秒針が、カチッと一秒進む" intent: "時間の伸縮を意識させる" - id: 04 type: "fetish" action: "袖口のボタンを外し、袖を一度まくる" scale: "macro" - id: 05 type: "fetish" action: "襟がわずかにずれ、鎖骨に影が落ちる" scale: "macro" - id: 06 type: "fetish" action: "グラスの縁を指先でなぞる。結露が一滴落ちる" scale: "extreme_macro" - id: 07 type: "b-roll" category: "nature_micro" action: "蝋燭の炎が、一度だけ大きく揺れる" intent: "呼吸の比喩。緊張のピーク" - id: 08 type: "fetish" action: "イヤリングを外す。直後に髪が肩へ落ちる" scale: "macro" - id: 09 type: "fetish" action: "ヒールから足が抜ける" scale: "macro" - id: 10 type: "fetish" action: "喉が小さく動く。嚥下" scale: "extreme_macro" - id: 11 type: "b-roll" category: "texture_landscape" action: "シーシャの炭が、脈打つように赤く光る" intent: "心拍の外部化" - id: 12 type: "fetish" action: "口元から煙をゆっくり吐く" scale: "macro_side" - id: 13 type: "fetish" action: "薄手の布越しに、肩甲骨が静かに動く" scale: "macro_back" - id: 14 type: "fetish" action: "ペンのキャップを歯で咥え、ゆっくり引き抜く" scale: "extreme_macro" - id: 15 type: "b-roll" category: "body_abstract" action: "布団が呼吸に合わせて微かに上下する" intent: "緊張の小休止。まだ続くという予告"

城堡高架橋上的蒸汽列車

A 3D stylized animation begins with a tight close-up on the gold-spoked wheels and connecting rods of a black steam locomotive accented with metallic hoops. As the camera smoothly zooms out and pulls back, it reveals the entire train puffing spherical gray smoke clouds from its chimney while pulling red passenger cars along a railway track. The track runs across an elevated arched bridge alongside a grand medieval stone castle complete with corner towers and battlements, all set within a low-poly environment featuring scattered evergreen trees and a quiet river.

Beat-Synced Spaghetti-Western Title Sequence

10s · ref2va · 含音訊

Use the attached character reference (Image1) and audio track as the timing guide. Create a spaghetti-western pulp anime title sequence where every cut lands precisely on the beat. Style the character as a flat black silhouette against solid desert-inspired colors (burnt orange, ochre, rust, adobe tan), using bold pop-art compositions, vintage bounty-poster framing, split panels, extreme close-ups, and wide horizon shots. Alternate fast action bursts with full-beat freeze frames (draw, stride, turn, match strike, etc.), using hard cuts only. Add worn woodblock/stencil title typography that slams into frame on the beat. Finish with the character frozen in silhouette on a burnt-orange background as the title stamps in on the final hit. Apply heavy 35mm film grain, scratches, dust, gate weave, cigarette burns, and sun-faded print wear throughout for an authentic 1960s spaghetti-western look.

Typography Flows Through the Scene

15s · 含音訊

[1] FORMAT 15-second 16:9 stylized anime action title sequence — martial-arts choreography fused with 3D kinetic typography. Painterly 2D anime illustration look with cel-shaded volumes and subtle paper grain, matching the source artwork's rendering. [2] ASSETS Use Image 1 as a strict identity reference for the female duelist KAELAN — read only the character artwork itself for her face, hair, wardrobe, weapon, and color palette. Ignore the sheet's layout, panels, printed labels, handwriting, silhouette thumbnails, and background parchment; none of them may appear in the video. [3] IDENTITY Preserve exactly: deep brown skin with warm highlights; luminous crimson-red eyes with a sharp black liner shape; jet-black hair pulled into a tight scalp-wrapped part that splits into two very long thick braids falling past the hips, moving like weighted whips; large white crescent hoop earrings on both ears; black high-neck sleeveless crop top exposing a toned midriff; a sheer white long-sleeved kimono robe worn open, translucent and lightly billowing; cream wide-leg hakama trousers with a single black diamond patch on the left thigh; black wrapped fingerless gloves with lattice cord across the back of the hand; white cloth-wrapped platform sandals; a well-worn katana with a dark blue-grey blade and a black diamond-wrapped hilt. Her expression stays calm and unblinking, never comic. [4] BEATS Shot 1 — [0–3 seconds] Kaelan stands centered in a void of warm off-white light, katana point-down, braids settling. She exhales; a slow iai draw begins. → Hard cut. Shot 2 — [3–6 seconds] Mid-draw. The blade clears the saya and a clean arc of light follows the edge. The 3D extruded word "HAILUO" flies in from screen left along the blade's arc, its letter faces catching the same light, passing BEHIND her shoulder and IN FRONT of her trailing braid before exiting right. → Whip-pan cut. Shot 3 — [6–9 seconds] Full-body kata combination: descending cut, pivot, rising horizontal sweep. Her sheer robe and both braids trail one frame behind her body. The word "MINIMAX" rotates up from the floor plane in thick extruded 3D, standing taller than her, and she cuts through the gap between its letters — the letterforms hold solid, do not shatter. → Hard cut. Shot 4 — [9–12.5 seconds] Low-angle crouch landing, sword arm extended back, dust ring pushing outward. "H3" slams in from depth as a massive chromed 3D glyph directly behind her, scaling down to lock, with her silhouette reading cleanly against it. → Flash cut on the impact frame. Shot 5 — [12.5–15 seconds] She rises into the neutral standing pose, katana returning to point-down. The full lockup "HAILUO MiniMax H3" assembles from the three pieces on a single horizontal baseline at lower third, settles, and holds perfectly still through the final frame. [5] CAMERA Anamorphic-feel 35mm for wides, 50mm for the mid shots.

Two Glaciologists Enter a Blue-Ice Cave

15s · 含音訊

EXPEDITION: Two glaciologists enter a newly formed ice cave to document its internal structure before seasonal melting changes it. EXPLORERS: Two researchers, both wearing crampons, helmets and headlamps, carrying compact measurement equipment. SHOOT WINDOW: 7:05 AM – 7:20 AM Early morning outside. Overcast sky. Cold blue daylight enters through the cave entrance. LOCATION: Glacial valley, massive blue ice formation, narrow cave entrance, translucent walls, frozen water flowing beneath the surface. RECORDING STYLE: First-person expedition footage mixed with a second camera operator. Headlamps create moving pools of light across the ice. Natural breathing and footsteps remain prominent. 15-SECOND EXPLORATION: 00:00–00:03 → Researchers squeeze through the narrow entrance. 00:03–00:06 → Camera reveals deep blue translucent ice walls surrounding them. 00:06–00:09 → One researcher notices water suddenly moving beneath a transparent ice floor. 00:09–00:12 → Both carefully step backward and examine the changing surface. 00:12–00:15 → They mark the location and begin retreating toward daylight. AUDIO: Boots scraping ice, dripping water, distant cracking, breathing, muffled voices. REALISM DIRECTIVE: Ice must behave like real compressed glacier ice, not glass. Light scatters through the walls naturally. No fantasy formations, supernatural elements or impossible cave geometry.

The Black-and-White Illusion of an Endless Staircase

15s · t2va · 含音訊

A French Bulldog Under Precise Direction

14s · 含音訊

A casual handheld smartphone video filmed by the dog's owner in an ordinary suburban backyard. A cute, stocky French bulldog excitedly runs through a small homemade agility course, awkwardly weaving between plastic poles, hopping over two low hurdles, scrambling through a short fabric tunnel, and finally bumping a little bell with its nose.

Images and Typography in Seamless Motion

15s · 含音訊

BURN Forged in Fire

Extreme Hollywood pyro title sequence: begin inside a microscopic droplet of fuel suspended in darkness as a spark suddenly ignites its surface. Fire spreads explosively outward and the camera rockets backward through a chain reaction of enormous fuel explosions. Liquid fire whips across the frame like glowing ribbons while burning debris and sparks spiral into a rapidly expanding fire tornado. The camera enters the vortex and rotates around a white-hot molten core where streams of liquid metal begin violently forging the gigantic word "BURN". Every letter emerges incandescent from the inferno before cooling into cracked black steel while magma remains visible beneath the surface. The completed title slams into frame with enormous weight as flames blast through the gaps between the letters. Pressure suddenly builds inside the typography until "BURN" violently ruptures from within, unleashing a radial explosion of molten metal, sparks and fire directly into the lens. Extreme heat distortion, realistic pyro physics, aggressive camera movement, AAA theatrical VFX.

工業渦輪鍛造 POWER 字幕

Aggressive tracking shot through a gigantic abandoned industrial facility. The camera races between steel columns while electrical transformers overload one after another, sending violent arcs of electricity across the environment. Sparks shower toward the lens. A huge turbine begins spinning at impossible speed before exploding apart. Thousands of glowing metallic fragments freeze in midair for one dramatic beat, then slam together with brutal force to construct the word “POWER” in enormous heavy steel letters. Blue-white electricity crawls across every letter as the camera performs a fast 180-degree orbit. Dark industrial blockbuster aesthetic, practical sparks, volumetric smoke, realistic physics.

5300 粉絲金色慶祝動效

高品質な祝福タイポグラフィアニメーション 表示文字：「X」「フォロワー」「5300人」「YaReYaRu」「ありがとう！」 綴りと大文字・小文字を正確に保持する 【ビジュアル】 深いミッドナイトブルーを背景に、ゴールド、ホワイト、鮮やかなエメラルドグリーンで統一 主役は大きく読みやすい文字、くす玉と花火は文字の登場や変形に連動する 極太サンセリフの数字、洗練された立体文字、薄い金属反射、奥行きのある紙吹雪 上品な授賞式の華やかさと、SNSらしい軽快で力強いモーションを組み合わせる 重要な文字は中央の安全領域に配置、画面下端や右端に寄せない 【0〜2秒｜期待をつくる】 暗い画面中央で小さな金色の火花が弾け、白い「X」が瞬発的に出現 文字が一度だけ大きく弾み、細い光のリングが外側へ広がる 「X」が上部中央へ縮小移動、その下に「フォロワー」が一文字ずつ軽快に着地 背後から金色の細いリボンが左右へ走り、中央を空ける 【2〜5秒｜くす玉登場】 画面上から豪華な金色のくす玉が中央へ降りてくる 上下に重なる金色の鱗状装飾、緑の房飾り、左右対称の球体 減速して止まり、小さく一度だけ揺れる カメラがゆっくり接近、周囲の光が絞られ、くす玉の継ぎ目から緑と金の光が漏れる 下に伸びた一本の紐がぴんと張り、開く直前に一瞬静止 【5〜8秒｜5300人を大きく見せる】 強い打音と同時にくす玉が左右へぱかっと開く 左右の半球は吊られたまま残り、内側から金と緑の紙吹雪、長いカールリボンが勢いよく放出される 中央から白い垂れ幕が下へほどけ、その表面に極太の「5300人」が現れる 「5300」の数字が垂れ幕から手前へ立体的にせり出し、画面中央を大きく占める 数字は一度だけ軽くオーバーシュートして定位置へ収まり、「人」は数字の右下へ整然と配置 同時に背景の左右上方で大輪の花火が開く 短い光の衝撃と画面の微振動で到達の喜びを強調、文字が読めなくなる全面白飛びは起こさない 【8〜11秒｜名前を主役に】 「5300人」が少し上へ移動し、その下へ「YaReYaRu」が左から右へ一文字ずつ滑り込む 文字の着地に合わせて金色の小さな火花が散り、最後の「u」が収まると名前全体を緑の光が一度だけ横切る カメラが緩やかに引き、上部の「X」、その下の「フォロワー」、中央の「5300人」、下部の「YaReYaRu」がひとつの祝福ポスターとして整う 背景に高さと大きさの異なる花火が時間差で開花 紙吹雪は文字の背後を中心に落下し、少量だけ手前を横切って奥行きを出す 【11〜13秒｜ありがとう】 「YaReYaRu」の下に「ありがとう！」が柔らかな弾みをつけて出現 左右から金色のリボンが弧を描き、文字全体を囲む祝福のフレームになる 最後に背景中央上方で最大の金色の花火が開き、その内側に緑の小さな花火が重なる 花火の明るさに合わせ、文字の縁が一瞬だけ輝く 【13〜15秒｜読ませる完成画面】 文字とカメラを静止させ、完成したレイアウトを2秒間保持 「X」 「フォロワー」 「5300人」 「YaReYaRu」 「ありがとう！」 「5300人」を最も大きく、次に「YaReYaRu」を強調 開いたくす玉を上部左右に残し、花火の残光とゆっくり落ちる紙吹雪だけが動く 最後まで文字を鮮明に読める状態で終了 【音・編集】 華やかなエレクトロポップ、文字の着地に短い打音、くす玉開放に祝砲、花火に奥行きのある炸裂音 5秒のくす玉開放で音楽が大きく展開し、最後は明るい余韻 ナレーションなし カットの切り替えよりも、文字の位置移動、拡大縮小、リボンの軌道で場面を滑らかにつなぐ 文字の誤字、重複、勝手な文言追加、数字の変化、過度な点滅、粒状ノイズ、ウォーターマークは禁止

Bureaucracy Explained in Fifteen Seconds

15s · 含音訊

{ "title": "The Void Replies", "duration": "15 seconds", "aspect_ratio": "9:16", "style": "surreal architectural etching blended with animated bureaucratic flowcharts, endless stairways, cream paper, black ink and warning-red pathways, Escher-like scale, sharp editorial illustration", "prompt": "Create a meaningful 15-second vertical animation about learned helplessness inside systems so complex that personal action appears useless. Open on a citizen standing before a small civic desk labelled START HERE. They submit a simple request marked HOUSING. The paper enters a maze of pipes branching into DEPARTMENT, REVIEW, CONSULTATION, JURISDICTION, APPEAL and PENDING. The person runs alongside it through endless stairs and corridors, but the request repeatedly returns stamped WRONG FORM. Their voice becomes a visible red waveform that travels into the maze and gradually shrinks. Floating phrases gather around them: NOTHING CHANGES, WHY TRY, TOO COMPLICATED and SOMEONE ELSE'S JOB. They sit down. Another citizen arrives carrying a different request. Instead of entering alone, the two connect their red waveforms. More people join, and the combined signal illuminates a direct path through the structure. The maze does not vanish, but doors begin opening and officials become visible. Finish with the original request reaching a real human desk as bold text appears: POWERLESSNESS GROWS IN ISOLATION. AGENCY GROWS THROUGH CONNECTION. Avoid suggesting that every civic problem has a simple solution.", "timeline": [ { "time": "0.0-3.0 seconds", "visual": "A HOUSING request enters a vast bureaucratic maze.", "text": "HOW MANY TIMES CAN A PERSON TRY?" }, { "time": "3.0-8.0 seconds", "visual": "The request cycles through REVIEW, JURISDICTION, PENDING and WRONG FORM.", "text": "" }, { "time": "8.0-12.0 seconds", "visual": "NOTHING CHANGES and WHY TRY surround the exhausted citizen.", "text": "" }, { "time": "12.0-15.0 seconds", "visual": "Connected voices illuminate a shared route through the maze.", "text": "AGENCY GROWS\\nTHROUGH CONNECTION" } ], "voiceover": { "enabled": true, "delivery": "empathetic, grounded and steadily empowering", "script": "When every path leads nowhere, people stop walking. Connection can make a route visible again." }, "audio": { "music": "repetitive ticking rhythm expanding into layered human percussion", "sound_design": "paper tubes, stamps, footsteps, fading echoes and joined vocal tones" }, "camera": { "movement": "paper-following maze chase, dizzying overhead pullback and direct final push toward the open desk", "editing": "repeating loops interrupted by connected red lines" }, "negative_prompt": [ "mocking public workers", "simple anti-government message", "photorealism", "hopeless ending", "illegible flowcharts", "magical instant solution" ] }

A Cybernetic Operative Appears on a Stat Panel

15s · 含音訊

Wake the Wonder

15s · 含音訊