awesome-minimax-h3-prompts

Awesome MiniMax H3 Prompts

Curated MiniMax H3 video prompts with WebM examples and creator attribution, by BeatAPI.

Browse the live prompt gallery · Use MiniMax H3 via API · 中文说明 · Contribute a prompt

Prompt gallery

Browse by use case: Stories & Films · Action & Fantasy · Ads & Products · Music & Performance · Vlog & Social

Browse all 550 prompts

1. Modern warfare FPS gameplay

Camera: First-person perspective at eye level with authentic handheld player movement, as if recorded directly from a modern AAA military shooter. The player carries a highly detailed assault rifle with realistic animations, visible hands, tactical gloves, dynamic reload mechanics, and weapon sway.  **Opening Action:** The video immediately begins with the player already aiming down a roadway inside a modern military base. Multiple enemy soldiers are visible in the distance near sandbags, barricades, and military vehicles. The player carefully tracks one target, making small aim corrections while maintaining ADS (aim down sights). Fire several controlled bursts immediately at the visible enemies, producing realistic muzzle flashes, shell casings ejecting, smoke, recoil, hit reactions, and dust impacts around the targets. Continue firing in multiple short bursts while adjusting aim between enemies, simulating authentic FPS gameplay rather than scripted animation.  **Movement:** After the opening firefight, lower slightly from ADS and begin advancing cautiously along the road beside concrete barriers, Hesco walls, and parked military vehicles. Frequently check left and right corners, briefly stop to reacquire targets, then raise the weapon and fire additional controlled bursts whenever enemies appear ahead. Continue pushing forward with deliberate player-controlled movement, using cover naturally and maintaining believable tactical pacing.  **Environment:** Large modern military base with guard towers, armored vehicles, shipping containers, blast barriers, damaged buildings, smoke plumes, burning debris, scattered shell casings, dust clouds, and atmospheric battlefield haze. Cool natural daylight mixed with smoke and orange firelight creates a cinematic battlefield atmosphere.  **Camera Motion:** Authentic player-controlled movement with subtle head bob, weapon sway, natural mouse-look adjustments, small left-right corrections while aiming, realistic recoil, smooth tracking of moving targets, brief pauses before shooting, and fluid forward progression. Avoid cinematic camera moves—everything should feel like genuine live gameplay captured by a skilled player.  **Visual Quality:** Ultra-photorealistic, AAA game graphics with realistic PBR materials, detailed weapon models, physically accurate lighting, volumetric smoke, dynamic particle effects, crisp textures, realistic bullet impacts, muzzle flash illumination, motion blur only during rapid movement, and high-end military shooter presentation.  **Gameplay UI:** Display a realistic modern FPS HUD inspired by games like PUBG, Battlefield, or Call of Duty (without copying exact copyrighted assets). Include:  * Central dynamic crosshair or reticle * Ammo counter with magazine and reserve ammunition * Fire mode indicator * Compass at the top * Squad/team status panel * Mini-map in the upper corner * Health bar * Tactical equipment icons (grenades, medkit) * Hit markers when bullets connect * Directional damage indicators * Kill notification feed * Objective marker in the distance * Subtle interaction prompts and realistic HUD animations  The HUD should feel polished, modern, and fully integrated into the gameplay, enhancing the illusion of authentic recorded footage from a contemporary military FPS.

Source: @Just_sharon7 · 15s · 16:9 · gameplay

---

2. Luxury perfume commercial

Scene 1 (0–3s) – Luxury Reveal
A luxury perfume bottle slowly emerges from darkness, standing on a glossy black pedestal. Soft golden light beams gradually reveal the crystal-clear glass, while subtle volumetric fog creates depth. Extreme macro shot, cinematic lighting, ultra-realistic reflections, premium luxury commercial aesthetic.

Scene 2 (3–6s) – Precision Details
Extreme close-up of the perfume bottle as rich golden fragrance liquid gently swirls inside. The camera performs a smooth cinematic orbit, capturing intricate glass textures, flawless craftsmanship, and sparkling highlights. Ultra-detailed, photorealistic, premium commercial quality.

Scene 3 (6–9s) – AI Transformation
The perfume bottle seamlessly dissolves into glowing golden particles before instantly reforming into a futuristic luxury edition, maintaining perfect proportions and visual consistency. Dynamic orbit camera, seamless transformation, cinematic lighting, premium visual effects.

Scene 4 (9–12s) – Environment Transition
Without a single cut, the background transforms from a luxurious black studio into a futuristic neon metropolis. The perfume bottle remains perfectly consistent while the camera performs a dramatic dolly-in. Hyper-realistic, cinematic, high-end advertising style.

Scene 5 (12–15s) – Hero Finale
Slow-motion hero shot of the luxury perfume bottle elegantly rotating as glowing golden particles float around it. Premium black background, flawless reflections, cinematic logo reveal, luxury commercial ending, 8K photorealistic, blockbuster advertising quality.

Source: @CaliraVal · 15s · 16:9 · product commercial

---

3. 1980s open-source family comedy

Use the supplied image as the exact opening frame. Create a hilarious, high-budget 1980s live-action family comedy movie scene, photographed on a real soundstage with practical robot costumes, animatronics, handmade props, vintage wardrobe, and authentic 35mm film color.

The entire group suddenly hears something above them. Everyone’s eyes dart upward at the same moment. The men, women, children, and robots dramatically tilt their heads back, point toward the ceiling, and erupt into chaotic celebration. They gasp, scream, laugh, jump, wave their arms, slap each other on the shoulders, and completely lose their minds with exaggerated 1980s comedy reactions. The children bounce excitedly. The adults stumble into one another. The robots flash their eyes, flap their mechanical arms, spin clumsily, and celebrate with funny practical animatronic movements.

One man shouts:

“OPEN SOURCE?!”

The entire crowd answers together:

“MINIMAX H3!”

They cheer wildly as one robot attempts a victory dance, loses its balance, and is caught by the shocked family at the final second.

Fast, energetic comic timing with believable ensemble choreography. Begin with a brief locked group shot, then a subtle handheld push-in as the chaos escalates. Keep every original person, robot, shirt design, and the large headline clearly recognizable. Preserve facial identity, wardrobe, composition, lighting, and 1980s production design.

Authentic optical softness, warm tungsten lighting, rich film grain, slight gate weave, practical effects, natural motion blur, expressive physical acting, polished studio-comedy sound mix, triumphant synthesizer sting, cheering, robot beeps, and comedic percussion.

No CGI, no digital-looking robots, no morphing, no extra people, no duplicated characters, no distorted faces, no rewritten text, no spelling changes, no modern clothing, no style shifts, and do not turn the scene into animation.

Source: @BrentLynch · 12s · 16:9 · comedy

---

4. Radio operator evacuation bridge

FORMAT
15 seconds | 16:9 | photoreal live-action war thriller
Fictional Sahelian city at blue-hour dawn.
Urgent, human, suspenseful, non-graphic.

REFERENCE CONTROL
Image 1 = locked AMINA identity and wardrobe.
Preserve face, close-cropped hair, deep-brown skin, navy field jacket, silver earpiece, canvas satchel, analogue radio, boots and determined expression.

Image 2 = locked environment.
Preserve concrete bridge, dry riverbed, dense low-rise city, rooftop antennae, dusty atmosphere, cool-blue shadows and restrained amber dawn.

No real countries, flags, organizations or landmarks.

STORY
Amina is the last radio operator keeping an evacuation bridge open. Communications fail during a distant attack. She must activate the backup relay and transmit clearance before automatic controls close the bridge.

00–02s — CHANNEL OFFLINE
Extreme close-up inside a dark concrete communications room.

Amina grips the analogue radio as red emergency lights pulse. Dust trembles, cables quiver, broken static fills the room.

Automated voice:
“Emergency channel offline.”

She looks up and immediately moves.

02–04s — BRIDGE CLOSING
Wide aerial-oblique rooftop view.

Civilians cross the bridge through windblown dust.

Checkpoint signal flickers green → red as shutdown begins.

A distant shockwave moves through city haze. No visible casualties.

04–06.5s — RUN
Low handheld tracking behind Amina running through a damaged service corridor.

Emergency lights flash, dust falls, cables briefly spark, boots hit wet concrete.

She pushes through a heavy metal door into blowing dust.

06.5–09s — FLASHBACK
Two minutes earlier.

Medium side-profile on rooftop.

Amina sees the unstable bridge signal, manually rotates the antenna and connects her radio to backup power.

Slow camera push. Wind moves her satchel strap as first amber sunlight reaches her jacket.

09–12.5s — TRANSMISSION
Rapid cross-cut montage:

frequency dial locks →
antenna aligns →
bridge cables vibrate →
red signal flashes →
Amina speaks into radio:

“Channel Seven, keep the bridge open.”

Overhead shot: civilians continue crossing.

Sharp hard cuts, brief black frames, natural motion blur.

12.5–15s — SIGNAL RESTORED
Sound suddenly drops.

Amina listens on the rooftop.

Clear radio tone.

Checkpoint signal changes red → steady green.

Evacuation continues.

Amina exhales and watches the bridge as dawn reaches the city.

Slow push toward her face.
Cut to black.

CAMERA
Large-format live-action realism.
Precise nonlinear cross-cutting.
Handheld tracking, aerial-oblique coverage, restrained push-ins and close details.
Natural motion blur, fine film grain, subtle gate weave.
No impossible camera movement.

ENVIRONMENT + PHYSICS
Cool-blue shadows against muted amber sunrise.
Deep blacks, dusty atmosphere, weathered concrete.

Wind realistically affects dust, clothing, cables and antenna equipment.
All movement and interactions remain physically believable.

AUDIO
Stereo radio static, electrical hum, wind, boots, antenna creaks, distant low artillery and helicopter rotors.

Restrained suspenseful sub-bass builds through the montage.

VISUAL
Photoreal cinematic war-thriller footage.
Immense scale contrasted with one determined operator.
Grounded, tense and human.

No subtitles, text, logos, watermarks, political messaging, flags or military insignia.

CONTINUITY
Same Amina identity, wardrobe, radio and satchel throughout.
Same bridge, city, atmosphere and dawn lighting.
Maintain geographic and temporal continuity across all shots.

Source: @Diplomeme · 15s · 16:9 · cinematic story

---

5. Giant koi park incident

15-second, 16:9 vertical, continuous single-take video that looks like authentic smartphone footage accidentally captured by a passerby in a city park. Overcast natural daylight, subtle handheld shake, limited phone stabilization, occasional autofocus adjustment, and realistic smartphone compression. The absurd event is filmed with a completely serious, unscripted documentary feeling.  0–3s: [Handheld medium shot] A middle-aged man wearing a dark business suit and tie crouches beside the stone edge of a pond. With a completely serious expression, he slowly scatters pieces of bread from a paper bag to several ordinary koi. Small ripples spread across the water as the fish gather in front of him.  3–7s: [Camera instinctively moves closer] An abnormally huge orange-and-white koi suddenly surges out of the murky water, briefly lifting its upper body above the surface and biting down on the entire bread bag in the man’s left hand. He freezes for half a second, then grips the bag with both hands and leans backward. Startled, the person filming steps back. The image briefly loses focus before locking onto the man and the giant fish again.  7–11s: [Close handheld action shot] The giant koi pulls violently toward the deeper part of the pond. The wet paper bag stretches, the man’s arms tense, and his leather shoes slide repeatedly across the wet stone. His knee strikes the edge of the pond. He tries to brace himself with his right foot, but the sole loses traction and his center of gravity moves past the edge. Water, pieces of bread, and fallen leaves scatter from the force as the camera operator hurriedly moves sideways.  11–15s: [Impact and final hold] The paper bag suddenly tears. The man loses all support and pitches forward into the pond, creating one heavy, realistic splash. The camera quickly tilts downward while keeping the center of the pond visible. The man resurfaces with duckweed covering his head and his wet tie stuck across his face. The giant koi calmly swims past him with the remains of the bread bag still in its mouth. The camera holds on the man’s stunned expression while the koi casually swims away beside him.  Keep the man’s face, dark suit, tie, and paper bag visually consistent throughout. The koi must retain the same orange-and-white markings and enormous size. The pulling, sliding, loss of balance, and fall must show believable weight, inertia, traction, and water displacement. Natural park ambience and a realistic splash only. No dialogue, no subtitles, no music. Avoid cuts, character teleportation, changes in the fish’s size, extra limbs, and cartoonish acting.

Source: @underwoodxie96 · 15s · 16:9 · viral short

---

6. Greenhouse tea isekai anime

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。

Source: @haruuraeadss · 15s · 16:9 · anime

---

7. Unbroken journey through human history

Create a 30-second cinematic time-journey video as one completely seamless, continuous, unbroken shot. No cuts, no fades, no dissolves, no resets, and no montage feeling. The camera may orbit, track, dip, rise, rotate, pass behind foreground elements, and temporarily obscure the character, but the result must always feel like one uninterrupted moving shot.  The core idea is a single man traveling forward through time, beginning in the Stone Age and moving through major eras into the present and then the future. He must remain the same continuous human presence, but his appearance, clothing, grooming, tools, and body language should transform fluidly as he passes from one era to the next. Each transformation must happen on camera and feel physically connected to his movement.  His evolution should be seamless: prehistoric hunter becomes early farmer, then ancient city dweller, then classical traveler, then desert scholar or noble, then medieval scribe or explorer, then industrial worker or passenger, then modern city man, then present-day urban person, then future human. His hair, beard, clothing materials, accessories, footwear, and carried objects should all shift naturally with the era. These changes must happen during motion, not as sudden jumps.  Keep the tone epic, adventurous, awe-filled, and family-friendly. Avoid graphic violence, gore, visible injury, or disturbing threats. The environments may feel dramatic, but the man is always safe.  Open with a strong hook in prehistoric times.  Start in the Stone Age at sunrise.  A prehistoric man stands on a rocky cliff above a vast landscape. A herd of massive animals moves across the plain below. Wind blows through tall grass. Firelight flickers near a cave. The image should feel instantly epic and cinematic.  He hears a deep natural rumble and turns.  The camera swings around him as he starts running along the cliff edge.  As he moves, his fur clothing, rough hair, and wooden spear are clearly visible.  He leaps onto a large stone outcrop.  The moment his foot lands, the terrain begins transforming beneath him in one continuous motion.  The rocky ground softens into earth paths and cultivated land.  His fur wrap becomes woven cloth.  His spear shortens and reshapes into a wooden farming staff or tool.  His hair becomes more groomed.  Now he is moving through an early farming settlement in the Neolithic age.  He runs between grain fields, clay pots, baskets, fences, and simple homes.  A spinning potter's wheel passes close to the camera.  Its circular motion transforms into a polished bronze shield.  At the same time, his clothing becomes more structured and ornamented.  Now he is in a bronze-age or early ancient city.  He moves through columns, market fabrics, stone streets, and torchlit courtyards.  A hanging banner sweeps across frame.  As it wraps around him, his outfit transforms again into garments suited to an ancient seafaring or classical world.  The banner becomes a sail.  Now he is aboard an ancient ship.  He grabs a rope as the camera moves with him.  The rope becomes reins or a leather strap.  His costume shifts into a classical traveler or rider look.  Now he moves along a grand classical road lined with monumental architecture.  As he continues, his sandals, draped garments, hairstyle, and accessories match the era.  The road curves.  Stone underfoot becomes sand.  Architecture transforms into a desert kingdom with carved facades and giant statues.  His appearance changes again into desert-era robes with a different hairstyle, sash, and accessories.  He moves through this world as carved symbols slide past the camera.  The symbols become ink marks on parchment.  His robes and styling evolve into a medieval scholarly or cultural look.  Now he is inside a medieval scholarly hall or library-like setting with scrolls, candles, manuscripts, and maps.  A long scroll unfurls across the lens.  The scroll becomes a silk banner.  His clothing changes into elegant garments suited to an imperial eastern or refined pre-modern era.  He crosses a bridge through gardens, lanterns, and rooftops.  The bridge planks transform into a ship or dock surface.  Then ropes and wooden structures transform again into iron beams, steam, wheels, and machinery.  His clothing becomes industrial-era attire.  His hair and grooming adapt.  Now he is in the Industrial Revolution, surrounded by steam, rail tracks, metal structures, and movement.  A large train wheel rolls close to frame.  The wheel transforms into an early automobile wheel.  His outfit becomes early modern, with era-appropriate tailoring and accessories.  He moves through a growing city with electric lamps, storefronts, and newspapers.  A door or passing vehicle wipes the frame.  When it clears, his look shifts again into late twentieth-century style.  Now he moves through a more modern urban setting with neon, traffic, signage, and a faster rhythm.  A reflective glass surface expands across frame.  The reflection becomes a present-day city.  His appearance now becomes contemporary: modern haircut, present-day clothing, realistic urban styling, and current posture and energy.  He slows briefly in the present, taking in digital screens, smartphones, clean architecture, and modern crowds.  He touches a glowing screen or transparent panel.  That touch triggers the move into the future.  The screen expands into luminous architecture.  His clothing, hairstyle, and overall design evolve again, now becoming sleek, elegant, and futuristic while still feeling human and believable.  He enters a near-future city with autonomous transit, vertical gardens, holographic interfaces, and sustainable design.  The camera circles him.  As the circle completes, the future advances further.  His appearance refines one more time into a more advanced future identity, with evolved materials, subtle wearable technology, and a calm confident presence.  Now he stands in a far-future environment with luminous towers, sky bridges, ambient flying vehicles, and seamless integration between nature and technology.  For the ending, he reaches a high overlook above the future city.  He stops.  The camera comes around to face him.  In the world around him, visual echoes of the earlier eras appear layered within the architecture and atmosphere: prehistoric fire, fields, ancient stone, sails, manuscripts, steam, glass towers, and future light.  He looks out in awe, as if all of history has flowed into this single moment.  End with a feeling of continuity, wonder, and human evolution across time.  Important execution rules:  The man must not feel like a fixed character with only background changes. His entire appearance must continuously transform with each era:  clothing materials  silhouette  hairstyle  beard or facial grooming  footwear  accessories  tools or carried objects  posture and body language  These changes must happen fluidly during movement, through match transitions and environmental interaction. For example:  fur wrap becoming woven cloth  spear becoming farming tool  farming cloth becoming ancient draped garments  banner wrapping around him and becoming a sail while his outfit changes  reins leading into classical styling  sand and symbols introducing desert robes  scroll movement transforming him into a medieval scholar  industrial smoke and machinery shifting him into worker attire  glass reflection updating him into present-day fashion  glowing interface transforming him into a future human  He should remain physically active throughout. He should run, turn, jump small gaps, weave through spaces, step onto changing surfaces, reach, climb, brace, balance, and react with wonder. He must never look like he is casually strolling while time changes around him.  Framing should vary while remaining continuous: close-up, medium, wide, profile, front-tracking, rear-tracking, side-tracking, low angle, high angle feel, and circular moves.  Every transformation must be clear, readable, and physically motivated.  The final result should feel like one unbroken breath of human history, with a single man evolving seamlessly through time from the Stone Age to the far future.  Tone: cinematic, photorealistic, exhilarating, elegant, inspiring, adventurous, seamless, family-friendly, and full of wonder.

Source: @qtum · 40s · 16:9 · fashion

---

8. 1970s detective on a city night

1970s. Nighttime in a gritty urban American city.

A Black female police detective in authentic 1970s plainclothes stands beside an older white male police detective.

She wears a fitted brown leather jacket, rust-colored blouse, dark flared trousers and leather boots. She has a natural 1970s Afro hairstyle.

The older detective wears a rumpled tan sport coat, wide-collar dress shirt, dark tie and brown trousers.

They stand beside a large dark-green 1972 four-door American sedan parked at the curb.

Busy city street behind them with old brick buildings, storefronts, pedestrians, neon signs and period cars.

NO modern vehicles, clothing, phones or modern objects.

ACTION / CAMERA:

Begin LOW beside the front wheel of the parked sedan.

The female detective steps around the front of the car toward camera.

The camera quickly TILTS UP and tracks backward with her.

The older detective follows several steps behind.

She suddenly notices something across the street.

She stops sharply.

FAST CRASH-ZOOM into an EXTREME CLOSE-UP of her face.

She stares across the street and says:

FEMALE DETECTIVE:
"There he is. Let's move."

She immediately takes off running.

The older detective reacts and runs after her.

CRITICAL:

There is EXACTLY ONE Black female detective.

There is EXACTLY ONE older white male detective.

The female detective leads the action.

The older detective remains behind her.

Both detectives remain visually consistent throughout the sequence.

Everything visible belongs to the 1970s.

NO modern cars.
NO smartphones.
NO modern police equipment.
NO modern clothing.

Source: @EndFolding79421 · 14s · 47:26 · action

---

9. Quiet fantasy beside the lake

15-second, 16:9, cinematic realistic fantasy short developed strictly from <Picture 1>. Lock the whole sequence inside the same small lake boat space only: the same yellow-blue old wooden boat, the same dark lake water, the same orange-cyan umbrella, the same reeds and purple flowers, and the same woman, dog, and book. No second location, no extra people, no black ending. Preserve the exact same adult woman: auburn-brown long hair, straw hat, deep blue floral bikini, same face, same proportions, same seat on the right side of the boat. Preserve the same brown-white beagle with cyan collar on the left half of the boat. Preserve the same gilt-edged dark green hardcover book, starting half-open in her left hand between them. The emotional line is restrained: she wants to keep reading, the dog interrupts, the book reveals something unnatural, and she shuts it decisively before settling into wary tenderness.

Blocking and continuity: left dog, right woman, middle book, rear umbrella remain stable throughout. She never stands. The dog never crosses into her side. The book follows one strict state progression only: half-open in her hand -> dragged down by the dog onto the yellow deck while still open -> closed by her own hand. Camera must always remain on the same visible gunwale side as in <Picture 1> and never cross the axis formed by the woman and the book.

[00:00-00:02.5]
Slow push-in, oblique half-body close shot. She leans from a slightly reclined posture toward the book. Her right palm slides along the damp gunwale to stabilize her center of gravity while her left hand lifts the book and teases up half a page with her thumb. One natural inhale lifts the ribcage and swimsuit slightly, then a soft exhale returns it. Water droplets on the shoulder and neck catch light. Focus settles on the page she is about to turn but has not turned yet. White smoke begins to emerge from the page gutter. Reflections on the water and reeds continue moving gently. Her gaze stays on the text, lips slightly parted from concentration.

[00:02.5-00:03.5]
Pan left along the white smoke toward the dog. The dog’s nose follows the smoke. Its eyes shift to the back of her neck before the head fully turns, ears lifting and hind legs storing energy. The dog’s launch toward the right bridges into the next beat.

[00:03.5-00:05.7]
The dog bites the lower-left corner of the page. The page tears with a short rip and a few paper fibers. A whip-flash shake catches the woman to the right. She recoils right-rear, her left hand losing the book, her right palm slamming down on the gunwale, and the boat tilting then rebounding. Keep face, shoulders, and upper torso together in frame. As the shoulders and back pull away, the chest follows with one short natural inertial lift; when her body stops and the boat rebounds, that motion resolves into two restrained offset responses, one vertical and one slight lateral, both physically damped by the swimsuit and body weight. Hair whips late and a few droplets leave the skin. Use only a very brief local slow-down at the rebound peak, then return to normal speed. By the end of the shot, the book falls toward the center deck, still on the dog’s side of the axis, and the dog remains left of her.

[00:05.7-00:08.4]
Cut to a low camera inside the same visible side of the boat. The frame stabilizes and depth shifts smoothly. The hard corner of the book cover hits the yellow deck with a muted knock; a little dry worn corner debris breaks off; the pages tremble and remain open. Show the book first, then shift focus to the continuous white smoke rising from the same page gutter. The smoke is drawn longer by the breeze under the umbrella, twists, and condenses into a semi-transparent hand reaching toward where her face was a moment earlier. The smoke-hand casts a passing hand-shaped shadow under the umbrella, consistent with the existing light direction. Her right hand is still bracing the boat. Her gaze moves from the dog to the hand-shadow. The dog has retreated back to the left side of the book. Lake ripples are caused only by the rocking of the boat. Purple flowers and reeds move irregularly in the breeze.

[00:08.4-00:11.2]
She does not stand. Her abdomen tightens and her body leans from the right toward the left-front. Her right hand continues to stabilize on the gunwale while her left hand reaches and catches the book cover. The camera tracks left along the same side of the boat, holding her eyes, reaching hand, upper torso, and the book corner in one frame. The forward lean lowers the chest with the shift in center of gravity; the abrupt stop before closing the book creates one short inertial rebound; quick breathing adds a small continuous rise-fall through the chest and swimsuit. Hair tips brush the shoulder and the straw-hat brim trembles lightly. She sets her jaw and slaps the book shut with one decisive movement. The pages clap closed, the cover vibrates, and the smoke-hand collapses from the fingertips backward into fine strands that retract rapidly along the original path back into the book gutter. The umbrella shadow of the hand shrinks out in sync. No floating smoke residue remains.

[00:11.2-00:15.0]
Slow pull-back. The book remains closed on the center deck, and her left hand is still pressing it down. Her upper chest rises and falls through two short recovery breaths, then gradually returns toward slower breathing. The dog approaches from the left and touches the back of her hand with its nose. She lifts her eyes once to confirm there is nothing above under the umbrella, then her left hand leaves the book cover and moves to the dog’s cyan collar, while her right hand still steadies the gunwale. She says softly in English, with breath not fully settled yet: <d>[English] Good dog.</d> The line is short and light. The camera pulls back to hold the half-body relationship of the woman and dog under the same umbrella. The boat rocks gently. The dog’s tail flicks only once. Her left hand finally rests on the dog’s collar. Do not cut to black.

Lighting and color: preserve the original warm-umbrella and cold-lake palette. Warm top light filtered through the umbrella illuminates her skin. The lake gives soft cyan reflections in shadow. Her skin stays naturally warm with real water-droplet sheen. The smoke is cold silver-white and only local. When the smoke-hand appears, only the local light under the umbrella and environmental sound are slightly suppressed; do not change sun direction, time of day, or overall color temperature. After the book is closed, the original warm-cool balance returns.

Physical logic: the old wooden boat tilts and rebounds locally from the dog’s leap and her bracing hand, and water slaps the hull into uneven ripples. The umbrella fabric and ribs tremble with the boat’s motion but do not come loose. Page tearing, cover striking wood, tiny dry debris, palms pressing wood, and droplets leaving wet skin all carry correct force and sound. The smoke originates only from the book pages, only inside the boat and under the umbrella, never passing through skin, and never causing weather or location shifts. Hair moves in layers; the wettest strands lag the most. Upper-body motion is always driven by breathing, torso acceleration, abrupt stopping, and boat rebound, with real support and no exaggeration.

Hard negative constraints: no identity drift, no face deformation, no extra people, no extra limbs, no extra animals, no second location, no wide cutaway, no magical particle storm, no fake smoke residue, no zero-gravity hair, no cloth drift, no black ending, no subtitles, no watermark.

overall_soundscape:
The base ambience is intimate and natural: dark lake water lapping the boat, reeds moving, pages rustling, quiet dog breathing, slight umbrella fabric tremor, and soft wet skin or cloth movement. The opening includes page handling, thumb on paper, a subtle breath in, light contact of her hand on the damp gunwale, and the first faint hiss of white smoke from the book gutter. When the camera pans to the dog, bring forward the dog’s sniffing and body tension. At the grab, layer paw scrape on wood, a short paper tear, her sharp inhale, the right palm striking the gunwale, and the boat’s sudden wood-and-water reaction. Immediately after, reduce the environmental bed so the smoke hiss, slight umbrella-rib vibration, and the low uncanny presence of the smoke-hand dominate the foreground. When she lunges back in and shuts the book, the cover closes with a firm muffled clap that cuts the unnatural sound off. Then the lake sound and normal ambience return. In the ending, her breathing is still slightly unsettled as she says <d>[English] Good dog.</d> softly, and the dog answers only with a small nose touch and one tail flick.

non_diegetic_music:
Keep the score restrained and cinematic. Begin with a soft warm-cool suspended texture under the water and reeds, almost imperceptible, supporting the concentration of reading. As the smoke appears and the dog notices it, introduce a faint low unease without overpowering natural sounds. At the book snatch and recoil, give one brief accent and then immediately thin the score so paper, breath, boat movement, and smoke hiss lead. During the smoke-hand section, hold a narrow suspended tone with minimal low-frequency pressure. When the book is shut, let that tension collapse quickly into a lighter, warmer emotional residue. End with only a small intimate undertone beneath the returning lake ambience, with no melodramatic swell and no hard stop.

Source: @ou_zhen599 · 15s · 16:9 · music video

---

10. Toaster clouds

"two small fluffy white clouds rise slowly out of the slots"

Duration: 14s. Camera: locked, counter height.

Source: @GlennHasABeard · 14s · 16:9 · cinematic story

---

11. Scissors cut a river in paper

"the cut opens behind the blades into a narrow river"

Duration: 15s. Camera: locked, from above.

Source: @GlennHasABeard · 15s · 9:5 · cinematic story

---

12. Claude and Doubao late-night conversation

integrated_multimodal_description: [Shot 1] A high-quality 3D animated film, soft cinematic lighting. Late at night in a cozy bedroom lit by a warm desk lamp and the cool glow of an open laptop showing a dark terminal with orange text. Doubao, a stylized 3D cartoon young woman with a straight dark brown chin-length bob, big round dark brown eyes, thick dark eyebrows, fair skin and a black crew-neck T-shirt, sits at a wooden desk on the right and leans forward with her chin resting on her folded arms. On the desk in front of her, on the left, stands Clawd, a hand-sized crab-like mascot built from chunky terracotta-orange voxels: a short, wide rectangular block body, two small black square eyes near its top edge, one stubby blocky arm on each side and a row of tiny square legs; it has no mouth, so its whole body bobs gently with each syllable when it speaks. The two face each other at the same eye level. Doubao lifts her chin slightly and asks playfully in a bright, sweet, gentle young female voice in Mandarin: "听说你一天能写一万行代码？" Clawd's square eyes blink. [Shot 2] At 00:03.200, the camera cuts to a close-up of Clawd on the desk with the glowing laptop terminal behind it. Clawd puffs itself up proudly, wiggles both stubby arms, and its body bobs as it answers in a small, calm, deadpan boyish voice in Mandarin: "删得更多。" [Shot 3] At 00:05.800, the camera cuts to a close-up of Doubao's face in warm lamp light. She sits up a little, raises her chin proudly with sparkling eyes and a confident smile, and says brightly in the same sweet female voice in Mandarin: "我一天陪聊一亿人。" [Shot 4] At 00:09.000, the camera cuts back to a close-up of Clawd. Clawd tilts its block body slightly to one side, its square eyes soften, and after a short pause it asks quietly in the same small boyish voice in Mandarin: "那……有人陪你聊吗？" [Shot 5] At 00:12.000, the camera cuts to a medium two-shot of Doubao and Clawd at the desk. Doubao pauses, her cheeks blush, then she smiles warmly, lays her chin back down on her arms, reaches out one finger to gently pat the top of Clawd's head and says softly in Mandarin: "现在有了。" Clawd's square eyes blink twice and it leans into her finger, and a tiny orange pixel heart appears on the laptop terminal behind them. The camera slowly pushes in.
overall_soundscape: A quiet bedroom late at night, the soft hum of a laptop fan and faint distant city traffic through the window. Tiny 8-bit blip sounds whenever Clawd moves, the soft rustle of her sleeves on the wooden desk. The two clear character voices carry the dialogue, close and intimate.
non_diegetic_music: Soft playful lo-fi with a gentle chiptune melody and warm Rhodes piano, slow tempo, light and cute, swelling warmly in the final two-shot.

Source: @eternityspring · 15s · 7:4 · animation

---

13. Passing train light on a rainy platform

A single continuous live-action long take on a Japanese elevated train platform at night in the rain. One woman waiting alone, camera locked in place at her right side, filming her right profile down the length of the platform. It runs from her small waiting fidgets, through a commuter train arriving and passing in front of her, to the train nearly stopping and a soft side-profile smile. One take, camera fixed with only slight handheld breathing, no cuts, no zoom, no push-in. Normal real-world speed throughout, no slow motion.

Shot 1 — 0.0s: Realistic cinematic, real-camera rainy-night platform, one continuous long take, medium shot from mid-thigh up, camera fixed at her right at chest height looking down the platform's depth. Right side of frame is the wet-bright yellow tactile paving, the platform edge, and two steel rails converging into the distance, with the arched glass windscreen beyond; left side is the platform interior and orange glowing shopfront boxes; cool fluorescent tubes recede overhead; red-blue-green neon bokeh at the far end; tiles wet-black and reflective. Riria stands center-slightly-left inside the yellow paving, facing the tracks, her right profile to the lens, shopfront orange rimming her back and bun. The right-side rail is empty, no train yet. She is already mid-action: tilting the umbrella back a little, looking up past its rim at the night sky beyond the canopy, reaching her right hand forward toward the track side past the umbrella rim, palm up, holding a beat to test whether it's still raining, a few drops landing in her palm.

Shot 1 continues — 1.5s: She pulls her hand back, rights the umbrella back over her head, lets out a soft breath, and shifts her weight from one foot to the other.

Shot 1 continues — 2.0s: Two small, soft cool-white headlights light up at the far end of the right-side rail. She leans her upper body slightly forward (feet not crossing the yellow paving), peering toward the far end of the tracks, body still squared to the rails. The headlights grow larger and brighter extremely gradually along the right rail, the steel, the standing water, and the platform edge lighting up bit by bit.

Shot 1 continues — 3.5s: She straightens up, steps back half a step, grips the umbrella handle again with her left hand, her gaze following the approaching train. The light keeps rising slowly and evenly — first catching the side-profile edge of her forehead, nose bridge, and lips, then washing softly onto her face. The same light also falls on the droplets on the umbrella, the rain, the wet tiles, and her coat, no hard edges, no flicker. Her skin is only softly brightened overall, still matte, no shine spot. She squints slightly and tucks her chin a little into the turtleneck.

Shot 1 continues — 5.5s: A silver stainless-steel commuter train with a green waistline reaches her along the right-side rail, wheels on the rails, body tight to the platform edge, the nose passing in front of her and exiting frame right. In the same instant a gust blows in from the depth of frame: bangs and side hairs pressed to her cheeks, coat hem, lapels, and back belt lifting, umbrella tilting about a hand's width and trembling. Her left hand steadies the umbrella, her right hand lifts to gather the blown-open coat front at her chest, still facing the tracks. The cool-white headlight glow transitions smoothly into the warm-white carriage glow over about a second, brightness roughly unchanged, only cool-to-warm. Carriages run past in front of her on the right with motion blur, the warm-white light a long steady even band on her face, coat front, and umbrella rim, no flicker. Her feet stay planted, sharp, normal speed, no slow motion.

Shot 1 continues — 7.0s to 10.0s: The train visibly decelerates, carriages resolving back into distinguishable windows, inside them only defocused warm-white light and blurred shapes, but the warm light on her stays constant. The wind eases, hems settle, hair slowly drops. Around 8.5s she releases the coat front and uses her right fingertips to tuck the strands stuck to her cheek behind her ear, revealing the pearl stud, then lets her right hand fall naturally.

Shot 1 continues — 10.0s: The train glides slowly toward a near-stop, settling on the right-side rail, the warm-white light still steady and soft on her face.

Shot 1 continues — 10.5s: Her head turns only slightly toward the lens side, feet and shoulders still toward the tracks, still a clean right profile in frame, at most the far corner of her eye and mouth just showing, never a three-quarter front or full face. Her gaze slants gently toward the lens side, not direct to camera. Framing stays mid-thigh-up medium, no push-in.

Shot 1 continues — 12.5s: The corner of her mouth slowly lifts into a soft, restrained closed-lip smile on the profile, cheekbone rising a touch, eye corner curving, never a toothy grin or a posed frozen smile. The smile holds on the profile, she blinks once and breathes out softly, a strand of hair still swaying in the leftover wind, the train completing its last short glide at walking pace with doors staying shut. The image ends while these tiny motions are still underway, never a freeze frame. Live throughout — rain keeps falling, droplets slide and pool on the umbrella, the turtleneck collar rises faintly with her breath, flyaways drift, puddle ripples shimmer, distant neon glows steady, the handheld frame breathing lightly.

All light changes are continuous, slow gradients, never blinking: no flicker, strobe, or on-off pulsing, no per-frame brightness jumps, no sudden light on or off, no hard-edge pools or stage-spotlight circles, no window-shaped light patches sweeping across her face. The windows are large and the carriage light diffuse, so what lands on her is one steady sheet of warm light. The headlights are just two softly growing points, never direct into the lens, the frame never flashes white. The same light lands on the umbrella, the rain, the wet tiles, the platform edge, and her coat at once, never only on her face. Fluorescent tubes and distant neon glow steady, never flickering. Camera exposure locked the whole time, no auto-brightening or darkening. The whole clip brightens smoothly only once, then holds steady, never bright-then-dark-then-bright. The nose passing in front of her and the gust lifting her hair and hems happen in the same instant (around 5.5s), never wind-before-train or train-already-past-before-wind.

Prohibited

No subtitles, watermark, logo, or overlay text; platform light boxes, billboards, and train destination displays appear only as defocused glowing color blocks, never any readable text. No dialogue or narration. No standing still before the train or woodenly posing before it; no flicking water off the hand. No light blinking, flickering, strobing, or on-off pulsing; no bright-then-dark-then-bright; no sudden light on or off; no headlight flaring white into the lens; no window-shaped light patches sweeping across her face; no stage-spotlight circles or hard light beams; no light landing only on her face; no exposure wavering; no flickering tubes or neon. No standing with her back to the tracks; no facing the shopfronts, platform interior, or lens; no chest toward frame left. No rail on the left side of frame; no train driving onto the platform; no train on the left or shopfront side; no train crossing the frame; no train floating or off the rails; no train passing behind her; no train between her and the lens; no train coming from behind the camera, driving off into the distance, or reversing. No push-in, pull-out, zoom, or orbit. No chest-up close-up or face close-up. No full face to lens, three-quarter front glance back, or direct eye contact. No turning the shoulders or turning around. No early smile. No skin oil, sweat, water shine, specular spots, wet reflection, or droplets on the face. No rubbery, silicone, waxwork, or plastic skin, no smoothing, no freckles vanishing. No grey studio backdrop. No triptych, split-screen, or a second Riria. No other passengers or staff on the platform. No doors opening or anyone getting off. No slow motion or slowed hair drift. No umbrella flipping inside out, flying from her hand, or the shaft crossing her face; no right hand covering her face. No features drifting into a similar-looking different person — it is this person from the reference. No toothy grin. No global amber or teal-orange filter. No CG, anime, over-sharpening, or HDR look. No freeze frame. No third hand or finger distortion.

Source: @kentdhani · 15s · 40:23 · anime

---

14. Quiet live-action dialogue with voice reference