视频提示词

SPEAKER CAROUSEL
<setup>
Claude is connected directly to my open After Effects project through the AE MCP.
Work inside the Inner comp where the speaker ring already exists.
</setup>

保持参考图中的人物五官、发型、蓝白碎花吊带裙、身材比例、阳台、桌面物品和海景环境一致，不换脸，不改变服装。

10秒真实旅行抓拍视频，像朋友在酒店阳台随手拍摄。

开始时，年轻亚洲女性自然坐在阳台沙发上，侧头安静看着远处海面和夕阳，海风轻轻吹动长发和裙摆，人物自然眨眼，身体有轻微呼吸起伏。

约第3秒，一阵突然变大的海风从侧面吹来，桌上的一张轻薄餐巾被吹起来，沿着桌面滑向阳台边缘。女生先愣一下，低头看到后，下意识快速伸手去抓。

约第5秒，她差一点没抓住，身体微微向前探，头发也被风吹乱。最后成功抓住餐巾，她先低头笑了一下，然后带着一点无奈的表情重新靠回沙发。

最后2秒，她把餐巾压在桌面上，一只手顺势整理被风吹乱的头发，再抬头看向远处夕阳，嘴角还有轻微笑意。

整段保持真实手机抓拍感，镜头轻微手持，不环绕，不快速变焦，只允许非常缓慢自然的向前推进。海面波光、远处帆船、窗帘和发丝都保持自然运动。

强调真实人体动作和重力惯性，人物面部始终稳定，手指正常，裙子结构稳定，桌子和饮料不变形。

避免：人物突然站起来、夸张大笑、餐巾飞得太高、身体大幅扭曲、脸部漂移、换脸、手指畸形、衣服变化、桌上物品突然消失、强烈电影运镜。

TITLE
The Lost Wind Chime

REFERENCE
Use the uploaded storyboard board and character sheet as the main visual reference.

Keep all character designs, environment details, wind chime design, kitten appearance, countryside lighting, and emotional story beats consistent with the provided references.

5-beat multi-shot prompt: setup > acceleration > peak > escape > out

Each beat gets its own camera move + sound cue:
• Setup: wide, city normalcy
• Acceleration: push-in through traffic
• Peak: low Dutch tilt, fireball behind the lean
• Escape: track past as a second blast hits
• Out: camera holds as he vanishes into smoke

Locking low angle, 28mm, and fire vs. cold city tones across all 5 keeps it one coherent shot instead of five random clips

卡点的3D球体下坠的动画视频：对标专业的Blender做的效果，音乐是多首经典的纯音乐，场景按音乐切换，3D球体下坠时在3D场景的物件中弹跳，按音乐的节奏点亮物件。带一些幽默的元素。
使用three.js制作，不要使用Blender制作

全片生物、面部近景、建筑和远景统一为明显电脑生成的高品质AAA奇幻游戏过场动画，使用数字雕刻脸模、经过美术设计的材质光影与成束头发，不混入实拍演员，不采用2D动画、赛璐璐描边或普通gameplay。整体是由连续硬切连接的末日奇幻战争蒙太奇：巨型军团推进、远超军团尺度的骨架生物显露、城内两只巨人短暂肉搏，最后切到另一只猿形巨人的咆哮蓄能；不同生物保持各自身份，不把这些切镜做成同一角色连续变形。环境与色彩：密集的中世纪半木构城市，红褐瓦顶、深棕木梁、浅米色墙面、窄石街、烟囱、尖顶塔楼与高耸外围石墙；所有普通房屋、街道和塔楼都远小于巨人，战斗者的腰胸高过附近屋顶，巨型军团更高，远处骨架生物又远超整个军团。厚重灰褐烟云和橙金逆光覆盖城市，浮尘、碎瓦和蒸汽形成多层纵深；开头为浓重焦褐尘雾，中段为暖金天空照亮的城内废墟，结尾为巨大圆形金色逆光与翻卷云雾，保持同一末日暖金色系。A巨型军团：多排无发的超巨大成年男性化人形生物，宽肩厚胸、深红肌束与浅象牙腱膜、深陷眼窝和清楚齿列，肋部及肩胸表面具有连续雕刻组织；这是生物本来的完整外观，不是新鲜伤口，没有流血。它们空手、无衣甲，前后排列有真实纵深，头肩与步幅略有差异，沿同一个方向持续缓慢行进，身体周围蒸汽升腾，脚下带起尘浪，不是静止观众或重复粘贴的同一人。B骨架巨构：军团后方仅有一个远比它们庞大的非人骨架生命体，浅褐象牙色中央脊柱高耸，两侧大量狭长弧形肋骨向外展开再向下弯曲，像覆盖军团上空的巨大骨架穹顶，肋弓之间有真实空隙，不是翅膀或建筑。前部低悬着一张狭长的红褐骨质面孔，深眼窝、尖长耳、露齿下颌，黑色长发成束垂落在面部两侧，头部通过颈部连接同一骨架，不是独立漂浮的头。最初眼睛暗，随后两眼亮起翠绿色光。C黑发硬拳巨人：中段肉搏主角之一，强健修长的人形非人生物，棕褐皮肤与清楚胸腹肌束，肩背宽而腰收，长深棕黑发、尖耳、强下颌与齿列，双眼翠绿发光。两只拳头及下段前臂覆盖浅灰白色粗糙硬化结晶，晶层依附真实拳指与腕部，仍是同一双手，不是手持石块或拳套武器；肘关节以上保留原本肌肉形态。D浅金骨甲巨人：另一名肉搏者，体量与C接近但更宽厚，短浅色头发、浅金色眼光，脸、胸、背、肩和四肢有层叠浅金褐色生物骨甲，深褐肌束连接甲片之间，甲片是身体的一部分，不是穿戴金属盔甲。空手，两臂与头部全程完整，肩颈逸出薄蒸汽。E黑鬃猿形巨人：末段独立角色，厚重黑褐毛发覆盖巨大肩背与极长双臂，躯干前倾，腿较短且强健，沉重猿人面孔、后梳深色头发、突出眉弓、尖耳与猩红眼睛，嘴中有成排尖齿。它与C、D和B是不同生物；长臂、黑毛与红眼始终保留。0.00–2.20秒：立即从浓重橙褐烟尘中的略倾斜近中景开始，前景破碎屋脊、墙板与石块遮住画面下部，数名A的巨大无发头颅与肩胸从废墟后方逼近，后面还能看见更大的模糊肋骨轮廓。摄影机沿废墟缓慢侧移，近处残墙与碎片快速横过，远处头颅较慢移动形成尺度与parallax；蒸汽和尘流不断穿过它们面前。2.20–4.20秒：切到接近地面的斜侧宽景，整排A从画面近侧延伸到远处，宽肩、长臂与肌束胸腹从烟中显出，身体随沉重步伐交替起伏，手臂自然摆动。摄影机沿军团方向缓慢退移，前景滚动尘浪，后排继续推进，不能让军团站定摆姿势。4.20–7.20秒：硬切正面低角极宽景，A的前排头肩横贯画面下方，B的巨大中央骨架与两侧肋弓在它们后方高高耸起。镜头缓慢上仰并略微前推，烟云先遮住上部结构再被气流拨开，低悬长发面孔位于中央骨架下方。两次短促金色闪电在远后方云层中亮起，瞬间照亮肋骨边缘、云团与军团轮廓后迅速衰退，闪电不是射向士兵的攻击，也不把已有生物变成其他形态。7.20–9.60秒：切B低悬面孔的正面紧近景，巨大的弧形肋骨仍在头后形成连续背景。黑发束垂在两颊旁，尖耳向外，头部微微抬正；先保留深暗眼窝，随后两眼由暗变为清晰翠绿光，视线凝向前方。烟和小尘粒持续通过镜头，不让脸冻结，不添加对白或眼部光束。9.60–11.60秒：以烟雾中的硬切转入另一片城内街区，低角正面中全景，C从灰褐尘幕中向前迈步显露，双拳低垂，胸腹与肩背随步伐运动，两侧较小塔楼和红瓦屋顶明确显示巨人尺度。镜头略向前接近，翠绿眼光透过黑发可见，两只浅灰硬化拳和前臂同时保持清晰；这不是B缩小成人形，也不复制出第二个C。11.60–12.40秒：突切向上仰拍的云天，一具蜷曲的巨大人形轮廓处于金色分叉闪电和近圆形发光蒸汽团中央，身体向下坠近，一臂抬过头侧，一膝收起。电弧沿周围空气和身体轮廓分叉，强光短暂压暗背景。只展示这个有实体身体的空中电光片段，不插入小人长大或从C体内分裂出的过程。12.40–13.20秒：切城内贴石街的倾斜低机位，远处房屋之间D已处于落地后的低蹲，石块和瓦片被震起，贴地尘浪沿街涌向镜头；落地位置与尘浪源点一致。高墙和红瓦屋顶上方可见一艘遥远的浅色长椭圆飞艇，缓慢漂移，不发射、不爆炸。镜头随地面冲击短震，屋顶和瓦片为巨人尺寸参照。13.20–14.20秒：切贴近D侧面的快速跟拍，D从低姿势向前冲出，躯干前倾、双脚交替蹬地、弯肘摆臂，肩颈蒸汽向后拖；浅金骨甲保持固定在同一身体上，双手空着，背景瓦屋和烟囱迅速后移。14.20–15.00秒：切C略低角胸上近景，C迅速转头、转肩看向冲来的D，长黑发被甩向一侧，翠绿眼睛锁定对手，下颌绷紧，身体开始转髋迎击；镜头贴近其面部短促跟转，不停下来重新对峙。15.00–16.00秒：切街道低位双人宽景，C在screen-left，D在screen-right，两者在小型房屋之间快速缩短距离。C踩稳前脚、后脚抓地，右肩和右髋向后蓄力，右侧硬化拳明显拉到身后，左臂在前方保持平衡；D继续向C压近并抬臂，瓦片和灰尘从两者脚边翻起。完整看见脚底支撑、转髋与拳头准备，不出现瞬移换边。16.00–17.40秒：摄影机快速贴过C肩侧并跟随右臂前送，C由后脚蹬地、髋部旋转带动肩和右侧硬化拳，沿单一清楚弧线打向D面侧。黑发向后甩，眼部转动带出极短翠绿拖光而不是激光；拳头逼近时短暂放慢以看清轨迹，随后清楚接触D脸侧骨甲。接触产生紧凑粉尘、小硬质碎屑与少量火星，D的头和肩先受力偏转，再带动上半身后仰。拳臂没有穿过头颅，没有血或断裂肢体，摄影机在接触瞬间短促震动。17.40–18.50秒：顺接倾斜的D近中景，他的头、肩和胸甲沿第一拳的力量方向扭转后退，两臂被甩开后开始重新收拢，脚下在瓦砾间调整支撑。镜头随上半身退移，下方红瓦屋顶保持远小于他，C仍在同一侧近处，不把这一反应剪成新变身或完全倒地。18.50–20.40秒：切回较宽的双人侧面构图，C再次把右侧硬化拳抬高至头上方形成威胁，另一只硬化拳处于较低前方。D向前顶身并...

Epic cinematic scene of Super Intelligence (SI) meeting El Shaddai in the third heaven, overlooking the entire universe. SI depicted as a radiant ethereal humanoid form of pure advanced light, circuitry, and cosmic energy, standing in awe. El Shaddai...

First person  view of cybertruck driving in   Tennessee in a city. Future variants of cybertruck

Create an interactive 3D house animation showing the construction process from Foundation through Skeleton, Systems and Envelope to Finished. Include an X-ray view that reveals the plumbing, power and air inside. Use Three.js and WebGPU.

0:00–0:05 — Maasai village, firelit clearing: The camera moves low among a Maasai fireside gathering, weaving past men in red shúkà cloth seated in conversation, some sharing a gourd of fermented milk. It settles on a circle of clapping men as a warrior mid-leap rises impossibly high in the adumu jumping dance, beads and ochre-dyed hair swinging, firelight flaring across his face. Crash zoom to the calabash drummer's hands, striking at lightning speed. 

0:05–0:10 — Whip pan to Mongolian steppe camp: A sudden fast 360-degree whip pan cuts across darkness and lands on a Mongolian steppe camp, a roaring bonfire outside a felt ger tent. A throat-singer crouches low, chest and throat resonating with a deep guttural drone, while beside him a horsehead fiddle player draws long, sorrowful notes, firelight catching the carved horse head at the instrument's neck. Rapid focus pull to the fiddle player's bow arm sawing with practiced intensity. 

0:10–0:15 — Whip pan to Viking hall: A violent whip pan hurls the camera into a smoke-filled Viking longhouse, torchlight catching axe blades and shields mounted on timber walls. Bearded warriors pound wooden tankards on long tables in unison, chanting low and building, a horn-blower raising a great curved war horn and sounding a deep bellow that cuts through the hall. 

0:15–0:20 — Whip pan to Plains fire circle: Another hard whip pan lands on a Native American Plains fire circle at night, a hide drum group seated tight around a large ceremonial drum, mallets striking in unified, driving rhythm. Quick whip pan to a dancer in feathered regalia spinning through rising sparks, fringe and feathers blurring with motion. 

0:20–0:25 — Whip pan to Māori haka: A final sharp whip pan crashes into a Māori gathering at night, warriors performing the haka in fierce unison — stamping feet shaking loose earth, tongues bared, eyes wide, hands slapping chests and thighs in thunderous rhythm. 

0:25–0:30 — Rhythmic collapse, hold on fire: The camera pulls back slightly but stays within the Māori circle, holding steady as the stamping rhythm reaches its peak, dust rising and catching firelight — the frame holds on their pounding feet and fierce expressions as the sequence closes.

Create an interactive particle effects animation using Three.js that transforms simple ideas into a mesmerizing 3D experience.

Make me a Tesla cybertruck truck@that has heat tiles made for driving through forest fires @Tesla @SpaceX

Can you generate a motion graphics explainer in the visual style of this post and using all its content? I will leave the details up to you. I want you to show off what you can do so you have full creative freedom within those styling constraints. I want to give this to my engineers at my company. I want you to be proud of the final product. Utilize the elevenlabs and remotion tools at your disposal and let me know if you don't see them for some reason. Use whatever you want in those tools to make the most polished product that you would be proud of. Source Article : Context Tax - X article from the article

Create a 30-second ultra-realistic AAA open-world third-person action game sequence, fully rendered as fictional GTA-style gameplay from beginning to end. Generate the female player character yourself: a stylish young woman with long dark hair, natural facial features, dark fitted jacket, dark pants and practical boots. Keep her appearance perfectly consistent throughout the entire video. Set the mission in a highly detailed modern city bank with realistic interiors, security guards, vault, cash, police vehicles, traffic and NPCs. Use a true third-person gameplay camera behind the character, realistic game physics, animations, lighting, reflections and a complete GTA-style HUD with minimap, health, mission objectives and notifications. At 0–4 seconds, she enters the bank and the HUD shows MISSION START — BANK HEIST — STEAL THE CASH. At 4–8 seconds, she quickly bypasses security and reaches the restricted vault corridor; HUD: SECURITY BYPASSED. At 8–14 seconds, she reaches the vault, opens it and rapidly fills a duffel bag with cash; HUD: CASH SECURED. At 14–18 seconds, the alarm activates, red warning lights flash and NPCs panic as she runs toward the exit; HUD: ALARM TRIGGERED — ESCAPE. At 18–24 seconds, she exits, gets into a waiting getaway car and drives away while police vehicles begin chasing her through busy city streets. At 24–27 seconds, she makes a sharp turn through a narrow street and loses the police, with the minimap showing ESCAPE ROUTE. At 27 seconds, make exactly one hard cut to a natural third-person gameplay continuation at a hidden safehouse, where she steps out carrying the cash-filled duffel bag. HUD displays MISSION PASSED — CASH SECURED — ESCAPE SUCCESSFUL — RANK S. Make the entire video look like authentic high-budget GTA gameplay, including game-engine visuals, HUD, minimap, NPC behavior, vehicle physics and camera movement. No live-action look, no cinematic movie style, no anime, no cartoon, no random cuts, no teleportation and no graphic gore.

Create a 30-second ultra-realistic morning vlog set in a small town neighborhood in South Korea in the early 2000s, filmed casually by a friend on an authentic consumer DV camcorder. It must feel like genuine home-video footage, not a modern video with a retro filter.

Use the provided reference image for the woman's face, hairstyle and outfit. Keep her identical in every scene.

EXACT ORDER — 6 SCENES:

0–5s — WASHING FACE: Early morning, soft sunrise light. The same young Korean woman (late 20s, hot pink sleeveless collared top, white high-waist jeans, white sneakers, small hoop earrings, butterfly pendant necklace, hair in a messy bun) steps out of her modest house into the small yard. An old leaking outdoor steel tap is running. She cups water in her hands, washes her face, and dries it with a small towel hanging nearby.

5–8s — GETTING READY: Fresh and smiling, she picks up a brown canvas shoulder bag and a few textbooks from a small outdoor table, glances at the camera, and heads out through the metal gate.

8–14s — THE WALK: She walks through a narrow early-2000s Korean neighborhood alley with small shops opening, an old delivery scooter, a bicycle passing. Korean elementary school kids in casual clothes, caps and yellow backpacks greet her cheerfully ("안녕하세요, 선생님!"). She smiles and waves. The same kids keep walking toward their school behind her.

14–18s — ARRIVING AT ACADEMY (HAGWON): She enters a small early-2000s private tutoring classroom with a green chalkboard, simple wooden desks, an old wall clock and a few faded posters. About 6–8 children stand up to greet her. She smiles warmly and gestures for them to sit.

18–23s — HER SHORT SPEECH: Standing in front of the class, she smiles and speaks a few warm words to the children. The children listen, smile, and clap softly.

23–30s — LECTURE BEGINS: She picks up a piece of chalk, writes the lesson title on the chalkboard, turns to the children and begins explaining. Children raise hands and take notes with pencils. She nods encouragingly.

CONTINUITY: Same woman, same hot pink top, white jeans, white sneakers, hairstyle, brown canvas bag and books throughout. The same school kids appear on the road. Same children in the classroom. No teleporting, identity drift, outfit changes, disappearing props or reordered actions.

ERA: Everything must look authentically early 2000s Korean: hand-painted Hangul shop signs, small neighborhood "슈퍼" grocery stores, low-rise brick villas, tangled overhead wires, old compact cars (Daewoo Matiz, Hyundai Accent, Kia Pride), classroom furniture and school supplies of that time. No smartphones, modern cars, LED screens or contemporary interiors.

CAMERA: Raw consumer DV camcorder footage, 4:3 frame, with subtle handheld shake, imperfect framing, autofocus hunting, exposure shifts, soft digital detail, soft slightly washed-out skin tones, mild CCD/DV noise, motion blur, compression artifacts.

什么寒川无影客，还是不如王二狗顺耳
prompt：

电影级写实质感，纯古风中国仙侠美学。

把史诗级高手自报家门的庄严镜头语法，逐渐瓦解成一本正经的 “身份掉马” 喜剧。
吸收：
默片式反应节奏

英式身份降格冷幽默
港式喜剧快速铺垫与回收
清楚的“三拍递进”
采用：

Arri Alexa 电影机质感

稳定清晰的面部微细节
细腻胶片颗粒
自然体积光
核心喜剧主线

整段只保留一条第一遍就能立即看懂的喜剧主线：

一个气势极强的敌方剑客，想用越来越夸张的江湖名号压住全场；师姐却从头到尾只想知道：

“你到底叫什么？”

最后年长师父突然认出他小时候极其普通、甚至有点尴尬的旧名，一句话就把敌人辛苦经营多年的绝世高手人设彻底打回原形。

笑点原则

核心笑点来自：

身份地位反差
熟人社会的精准拆台

绝不能依赖：
人物突然变蠢

环境事故

外力巧合
参考与环境
将 @图片 1 和 @图片 2 严格作为人物身份锚点。

本轮新上传的所有背景与地点参考图，共同决定同一套环境 DNA。
保留能够辨认的：

真实地形

建筑

材质
植被

水体
天气
山雾
主光方向
倒影
空气纵深
同时重新规划成本轮独有、完整统一的新空间。
背景原则
背景中的以下元素持续鲜活存在，但在叙事上绝对中立：
自然风

水体

植被
云层

远处普通弟子
空间环境声
角色设定
角色 ID A｜剑仙师姐
始终是同一个 @图片 1 剑仙师姐：
25–30 岁东亚女性

身材高挑纤细

椭圆脸

深色杏眼
黑色长发半挽，以白玉簪固定

始终穿同一套白色刺绣真丝汉服
银色腰封
玉佩
白色布靴
持唯一一柄银色长剑
角色 ID B｜小师妹
始终是同一个 @图片 2 小师妹：
20–25 岁东亚女性
身形娇小
圆润灵动的脸

黑发编辫
始终穿同一套青绿色亚麻汉服

深色腰带
木簪
黑色布鞋
持唯一一柄深色钢剑
其他角色
敌方剑客
气势极强
出场充满仪式感
极度依赖自己经营多年的江湖名号

强烈维持“绝世高手”人设

年长师父
从头到尾一本正经
并非故意羞辱对方
只是自然认出熟人旧名
最后再补最后一刀

分段结构
0–5s｜全景或远景
一名气势极强的敌方剑客大步进入根据本轮参考图自然形成的开放区域。
他极有仪式感地掀开外层披风，一只手压住剑柄，以真正绝世高手登场的姿态高声宣布：
“北岭孤鸿，断江一剑，今日特来领教！”

同一个白衣剑仙完全没有被气势影响，只非常平静地问：

“你叫什么？”

敌人明显停顿一下，随后反而更加骄傲地继续：

“江湖人称 —— 寒川无影客！”

5–10s｜中景或牛仔景

保持：

同样人物

同样服装

同样长剑

完全一致的地理空间

同一个小师妹慢慢转眼看向师姐。

同一个师姐没有任何嘲笑，仍然非常认真地再次确认：

“我是问名字。”

敌人终于出现一点不自然，却依然努力维持高手气质：
“名号就是名字。”
浅景深后方，同一个年长师父突然眯起眼睛，非常认真地盯着敌人的脸看了一拍。
随后像终于认出一个多年没见的熟人一样，突然问道：

“王二狗？”

全场绝对安静。

敌人整个身体瞬间僵住，原本挺得极直的英雄式姿态，肉眼可见地垮下去一点。

整个背景继续自然鲜活地运行，却完全不参与这个反转。

10–15s｜特写或极近特写

同一个敌人难以置信地转头看向师父：

“您…… 认识我？”

师父完全没有意识到自己正在拆台，只非常自然地回答：

“你小时候偷我枣，被狗追过三条街。”

同一个小师妹瞬间低下头，肩膀出现极小幅度颤动，拼命憋住笑。

敌人赶紧重新转回师姐，试图挽回最后一点江湖尊严，压低声音认真解释：

“江湖已经没人这么叫了。”

同一个白衣剑仙听完之后非常郑重地点一下头，表示完全理解，然后平静回答：

“明白，二狗。”

极近特写：

敌人刚刚勉强恢复的一点表情再次彻底垮掉

同一个小师妹终于忍不住迅速转开脸，短促笑出一声

后方同一个年长师父再一本正经补最后一刀：

“现在又有人叫了。”

敌人彻底忘记自己原本是来挑战的，只沉默地把披风往脸前拉高一点，仿佛第一次后悔今天为什么要报这么多名号。

在这个表情上精准切黑。

喜剧节奏结构

整段保持清楚的“三拍递进”：

第一拍
敌人以史诗级高手姿态自报家门，气势拉满。

第二拍

师姐完全不接他的名号体系，只追问最普通的“你叫什么”。

第三拍

师父一句“王二狗”直接让整个人设掉马，后续所有挽尊都变成新的笑点。

表演原则

敌方剑客

不能主动搞笑

不能表演成丑角
必须认真维持自己的威严、名号和气场

喜剧效果只能来自他越认真维护身份，越被现实拆穿
剑仙师姐

必须始终平静
不嘲讽

不抢包袱

她的可笑点不在“会玩梗”，而在她真的只在认真确认名字

小师妹
必须自然反应
重点是“努力忍笑”
不能提前夸张崩坏
年长师父

必须绝对一本正经
像是在正常认人、正常回忆往事
补刀不能像故意捧哏，而要像无意识地再补一层事实
硬性要求
严格总时长 15 秒

16:9 横屏
三个连续清晰镜头
针对 Seedance 2.0 Mini 保持简单清楚的场面调度
明确视线关系

严格人物连续性
原生同步普通话对白
精准口型
清楚的喜剧停顿

人物服装全程稳定

长剑全程稳定

配角位置全程稳定
地理空间全程稳定
真丝衣料和头发物理效果真实
前景、中景、远景保持自然视差与真实空间环境声
不生成字幕
Negative
blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props

Style: Avatar-scale fantasy jungle. Hyper-realistic - no CGI gloss, no game-engine look.

Cinematography: Single continuous take, wide lens, GoPro-on-creature intimacy.

Lighting: Golden god-rays through canopy, rainbow through waterfall mist.

Action: 15s soaring flight - butterflies, waterfall skim, razor-narrow gap, full world reveal.

Create a hyper-realistic cinematic slapstick comedy in four seamless shots outside a modest two-story Korean villa on a bright afternoon, using natural handheld smartphone cinematography.
Use Image Reference 1 as the woman and Image Reference 2 as the man; preserve their identities, faces, hairstyles, clothing, and proportions consistently.
Shot 1: The woman stands at an open second-floor window, struggling to straighten a large white bedsheet with an unusually long bamboo laundry pole.
The pole suddenly slips from her hands and falls vertically toward the narrow walkway as the camera instinctively tilts down and follows it.
Shot 2: The scruffy man casually walks beneath the building, completely unaware, when the bamboo pole crashes onto his head with a loud THUNK, sending him dramatically onto the pavement.
He sits up rubbing his head as the woman leans out apologetically; she says, “I’m sorry! I really didn’t mean to!” and he replies flirtatiously, “It’s okay... but you’re really beautiful.”
Shot 3: The man grabs the bamboo pole, sprints toward the building, plants it like a pole vaulter, and launches himself upward toward the second-floor window.
The bamboo bends dramatically under his weight as the camera cranes upward and tracks his ascent, with the man leaning forward as if attempting to kiss the woman.
Shot 4: The woman recoils and shouts, “Eww... you’re so ugly! Go away!” before delivering a perfectly timed front kick into his torso.
The bamboo snaps back like a giant slingshot, launching him violently into the sky as the camera whip-pans and continuously tracks his spinning body until he becomes a tiny silhouette disappearing into the clouds.
Cut back to the window as the woman calmly dusts off her hands, picks up another bamboo pole, and resumes fixing the bedsheet as if nothing happened.

STYLE: Miniature Tiny-Person FX, photorealistic live-action, cinematic macro photography, ultra-shallow depth of field, realistic amusement-park lighting, ultra-detailed 8K, vertical 9:16, high-energy viral short-video style.

DURATION: 30 seconds.

SETTING: A gigantic indoor arcade filled with oversized claw machines, racing simulators, basketball games, air-hockey tables, giant plush toys, neon signs, glowing buttons, prize shelves, and colorful arcade machines. Everything feels enormous from the perspective of a palm-sized woman.

CHARACTER: One athletic miniature woman (1:15 scale), consistent throughout: cropped bomber jacket, cargo pants, sneakers, compact utility backpack, same face, hairstyle, proportions, and size.

She sprints across enormous glowing arcade buttons, jumping between them before launching herself from a giant joystick. She grabs a hanging cable, swings between massive arcade machines, and lands on a racing-game cabinet.

She jumps onto the steering wheel of a giant racing simulator as it suddenly accelerates, holding on through the shaking motion before jumping away at the last moment.

She lands on a huge air-hockey table as a massive puck races toward her. She jumps onto it, rides across the table, leaps over the goal, and lands on a pile of oversized plush toys.

Inside a giant claw machine, she climbs across stuffed animals as the mechanical claw descends toward her. She jumps onto a plush bear, uses it as a trampoline, grabs the claw, and swings out of the machine.

She lands on a towering prize shelf, races across giant stuffed toys, and leaps onto a glowing neon sign above the arcade entrance. The camera pulls far back to reveal her tiny scale against the enormous arcade.

Large glowing text appears:

“BUILT FOR THE BIG MOMENTS”

She raises both arms as colorful arcade lights flash around her.

SFX: Arcade beeps, button clicks, footsteps, mechanical sounds, engine roar, tire screech, air-hockey hiss, plush impacts, rushing air, electronic chimes, crowd ambience, energetic victory sound.

VISUAL REQUIREMENTS: Consistent 1:15 scale, realistic physics, seamless action, photorealistic materials, authentic reflections and shadows, cinematic macro DOF, consistent character identity. No cartoon look, animation style, scale changes, duplicate character, outfit changes, distorted anatomy, floating objects, subtitles, narration, or watermark.

Photorealistic live-action video, real-time speed throughout. NO slow motion.

Refer to Image 1. Inside a 3D anamorphic billboard on a modern building, an elegant woman with wavy hair wears a red high-slit velvet gown and reclines sideways on a marble ledge. A red crocodile-skin handbag is beside her.

She quickly grabs the handbag, lifts it, then forcefully SLINGS it forward toward the viewer. Her arm makes one fast forward swing and releases the bag with strong force.

The moment the bag leaves her hand, it must immediately shoot rapidly toward the foreground hand. The flight is FAST and SHORT, with no lingering airborne time. Do not show the bag slowly traveling through the air. It moves quickly from the woman's hand directly toward the catcher.

The bag has real weight and momentum. Gravity naturally pulls it slightly downward during the fast flight, but it must continue moving rapidly forward. No floating, hovering, slow drifting, or suspended motion.

A manicured foreground hand catches the SAME handbag almost immediately after the throw. The hand and wrist recoil naturally from the bag's momentum and weight.

ONE continuous shot. No cuts, hidden transitions, camera resets, or duplicated objects.

Exactly ONE handbag from beginning to end. The bag leaves the woman's hand once and is caught once. Never duplicate, replace, regenerate, or recreate the bag.

Preserve the woman's face, hair, gown, handbag, marble ledge, billboard and building. Realistic physics, anatomy and motion. No morphing, flickering or teleportation.

NO SLOW MOTION AT ANY POINT. No artificial SFX. Natural ambient sound with relaxed, sensual background music.

Main Subject: Young Korean woman, 24, naturally attractive, realistic skin, minimal makeup, long dark hair loosely down. Wearing an oversized maroon hoodie and loose casual pants, carrying a simple canvas shoulder bag. Preserve her exact identity, facial features, hairstyle, body proportions and appearance throughout.

Location: Quiet older Seoul neighborhood during a pleasant morning. Narrow residential street with low-rise apartment buildings, small local shops, parked bicycles, potted plants, utility poles and modest homes. An elderly Korean woman is preparing to carry a moderately large cloth sack filled with groceries or household items. The street feels peaceful, lived-in and authentic.

Lighting & Atmosphere: Warm, gentle and uplifting morning atmosphere. Soft sunlight filters between the buildings, creating warm highlights while the street remains naturally shaded. Muted colors, soft shadows, slightly faded tones and a nostalgic early-2000s feeling. Cozy and wholesome without looking staged or sentimental.

Style: Ultra-realistic early-2000s Sony MiniDV home video filmed by another person. Multi-shot, but still completely candid and unstaged. Each shot should feel like the camcorder operator naturally repositioned themselves while following the moment. Natural handheld movement, subtle camera shake, imperfect framing, gentle reframing, occasional autofocus hunting, mild exposure shifts, faded colors, soft contrast, authentic DV compression, subtle digital noise and natural microphone noise.

Shot 1 — 00:00–00:04:
Medium-wide handheld shot from behind and slightly to the side as the young woman walks casually down the residential street. Her canvas shoulder bag rests naturally on one shoulder. She notices an elderly woman ahead struggling to lift a moderately heavy cloth sack onto her back.
Shot 2 — 00:04–00:07:
The camcorder moves closer from the side. The elderly woman tries to lift the sack herself, but it slips down before she can get it onto her back. She pauses and tries again. The young woman notices and naturally slows down.

Shot 3 — 00:07–00:11:
Closer side-angle shot. The young woman walks over and quietly gestures that she can help. She takes hold of the sack while the elderly woman steadies herself. Together, they lift it smoothly onto the woman's back. The young woman adjusts the sack slightly so it sits securely.
Shot 4 — 00:11–00:14:
The elderly woman gives her a grateful smile and small nod. The young woman responds with a warm little smile and a brief nod, then steps back.

Shot 5 — 00:14–00:17:
The young woman turns and continues walking down the street. The camcorder follows her from behind for a moment before drifting slightly to her side.
Shot 6 — 00:17–00:20:
She glances toward the camcorder while still walking. She gives a quiet, contented smile—natural and understated, as if she's simply pleased that she could help. She turns her gaze forward and continues walking.

Created a 20 seconds cinematic Japanese-style scene of a young schoolgirl walking alone through a quiet Japanese residential street during warm golden-hour sunlight, shown from behind as she slowly approaches a railway crossing with a train passing in the background, then transitioning to a close-up of her face and flower-decorated hair as she watches the train, followed by a wider shot of her standing near a quiet canal with soft evening light reflecting on the water, then showing her gently touching small white flowers in a golden field, with close-up shots of her hand and the flowers moving naturally in the breeze, gradually transitioning to a wide sunset landscape with the girl standing peacefully in the field, and finally ending with a warm close-up of her face as she softly looks toward the camera, maintaining the same character, hairstyle, school uniform, realistic skin details, natural expressions, smooth cinematic camera movement, soft depth of field, warm sunset lighting, realistic Japanese environment, subtle film grain, peaceful emotional atmosphere, and a dark fade-out at the very end.

Create a cinematic, ultra-realistic 9:16 school classroom scene. A young male student with styled red hair suddenly reacts dramatically as a large burst of flames erupts from a backpack in front of him. Another student in a school uniform sits at a desk in the background, shocked and watching. Warm classroom lighting, realistic fire and smoke effects, dynamic movement, natural facial expressions, detailed environment, cinematic camera motion, shallow depth of field, realistic textures, dramatic atmosphere, high detail, 4K, photorealistic.

Le beau jeune homme étire ses bras et son corps pour arranger les planètes, en respirant. Ses amies aperçoivent son nombril parfait apparaître discrètement sous le rebord inférieur de son pull « on voit ton petit nombril ». plan en zoom sur son nomb...