In one phone take, two friends stage a street prank: a coffee cup seems to levitate until the camera circles to reveal a hidden arm

Prompt

PROMPT:
15 seconds, vertical 9:16, native iPhone camera look, one single continuous shot, filmed in one take, with no editing, jump cuts, or transitions. Use the reference video only as a reference for the rhythm and camera movement of “a front-facing floating performance in the first half, followed by moving around to the right to reveal the mechanism in the second half”; do not copy the location, ground support, top subtitles, watermark, or people from the reference video. The scene is a city sidewalk outdoors during the day, with bright but not overexposed lighting, soft natural daylight, and a genuine casual phone-shot look. Two adult women are pulling off a lighthearted little prank by the roadside like close friends. The sidewalk is flat, clean, and spacious; the main background is a non-reflective light-colored solid building wall with a small amount of natural greenery. No storefront windows facing the street, mirrored doors, or reflective metal walls. In the distance, one or two ordinary adult pedestrians may occasionally walk naturally across the frame; pedestrians remain at least 4 meters from the subjects, do not stop, watch, look at the camera, imitate the actions, or pass through the core performance area occupied by the coffee cup, boom arm, @1, and @2. The only core props visible throughout are one coffee cup, one gray horizontal boom arm, and one white paper strip. 【The only physical mechanism already assembled from the first frame】 Exactly one rigid straight gray horizontal boom arm, parallel to the floor, extends forward from @2’s waist toward the camera, with the coffee cup fixed at its front tip. The same boom already exists at frame 1 and never appears, grows, extends, changes direction, or changes shape later. The only gray boom arm is approximately 80 centimeters long and 2.5 centimeters in diameter. It remains perfectly straight and parallel to the ground at all times, positioned at @2’s waist-to-chest/abdomen height. The front end of the boom is connected only to the exact center of the back of the coffee cup, with the connection point completely hidden behind the cup; there are no short rods or connectors protruding from either side of the cup. The last approximately 10 centimeters of the rear end are completely concealed and secured by @2’s forearm and sleeve pressed tightly against her waist and abdomen. The boom arm does not touch the ground, wall, or ceiling. The entire open space between the bottom of the cup and the ground remains clearly visible. At the opening, the camera’s optical axis, the center of the coffee cup, the boom arm’s longitudinal axis, and the center of @2’s torso are strictly aligned along the same depth-of-field line. The coffee cup completely blocks the boom arm behind it when viewed from the front, so although the mechanism genuinely exists from the first frame, it is completely invisible from the front; it is revealed gradually only through parallax caused by the camera moving around to the right, and is never a new rod generated halfway through. Medium-sized blue-and-white takeaway coffee cup, royal blue cup body, white lid, with only clear white English text “JOHN” centered on the cup. No real brand and antler pattern. The cup remains fixed in the same position in space throughout, upright, unchanged in size, with no drifting, rotating, or deformation. There is only this one cup in the entire video. The white paper strip is 14 centimeters wide and 10 centimeters high, already secured from the first frame to the underside of the middle section of the boom arm with two small pieces of transparent tape. Its top edge is attached to the arm, and the vertical plane of the paper is parallel to the boom arm’s longitudinal axis: when viewed from the front at the opening, the paper strip is strictly edge-on to the camera, revealing only an extremely narrow edge; after the camera moves around to the side, its front gradually unfolds naturally through parallax. The paper contains only two lines, with the first line never broken:
您的广告位
hf_20260723_023253_17d01f18-b189-45de-be9c-f30db6d27116
@john87445528 @1
Wearing @1 reference outfit
图片_20260710063944_1206_183(1)
, always remains in the left third of the frame, with both feet staying in place. Her body and head never cross the center line of the frame, and she never moves directly in front of the coffee cup or between the coffee cup and @2. @1 only reaches both hands toward the areas above and below the cup from the left side of the frame; her palms remain approximately 10 centimeters from the cup at all times and never touch it. She is playful, lively, clever, and quick-witted, as if teasing a close friend on the street: naturally relaxed with a slight turn of her body, softly rotating her wrists, and slowly spreading all ten fingers. Her gaze naturally shifts between the cup, @2, and the camera. She occasionally raises one eyebrow slightly, wears a mischievous smile as if she can barely contain her laughter, and, after successfully demonstrating the “floating” effect, gives the camera a brief, playful wink. Not a formal commercial pose, not stiff, not vulgar, no exaggerated writhing, and no silly faces. @2
Wearing @2 reference outfit
图片_20260710063950_1209_183
, keeps both feet still and remains on the same depth-of-field axis directly behind the coffee cup. @2 hides the rear end of the boom arm with her forearm and sleeve held close to her waist and abdomen. The arm, body, and stance securing the mechanism remain completely still throughout; however, during the first 5 seconds, while her face remains clearly visible, she acts as if she is playing along with her friend’s prank: first pretending to seriously focus on the cup, then raising her eyebrows and slightly widening her eyes, knowingly pretending to be surprised. When she sees @1 blow on the cup, she briefly presses her lips together to hold back a laugh, then gives @1 and the camera an innocent, humorous look that says “I almost fell for that.” The two women have a familiar, relaxed rapport. @2 makes only facial expressions and subtle eye movements; she does not speak, open her mouth wide, shake her head, or shrug. After 5 seconds, the camera moves closer, and the faces of @1 and @2 are naturally cropped out of the frame. 【Strict continuous timeline】 0—2 seconds: front-facing medium-wide shot, with the camera not moving laterally at all. The cup is centered in the frame, @1 is fixed on the left, and @2 is directly behind the cup. The full sidewalk surface beneath the cup is clearly visible. @1 holds one hand above the cup opening and the other below the cup bottom without touching it; she first looks at the cup with feigned seriousness, then glances at @2 and the camera from the corner of her eye, slightly raises one eyebrow, and shows a mischievous expression as she tries not to laugh. @2 plays along by first staring seriously at the cup, then slowly raising her eyebrows and slightly widening her eyes, humorously pretending that “it really floated.” Neither woman moves her body or feet. One pedestrian may naturally pass in the distance, but does not look at them or enter the subjects’ axis. 2—5 seconds: the camera remains in the same front-facing position. @1’s feet and body do not move; she performs only three clear, slow hand movements: her right hand sweeps horizontally over the cup opening; her left hand sweeps horizontally beneath the cup bottom; both hands spread outward to show that they are empty. She acts as if deliberately teasing @2, with the corners of her mouth gradually lifting into an uncontrollable smile; she then leans in from the left and gently blows toward the cup opening, looks at @2 first after blowing, then looks at the camera and gives a brief, playful wink, and finally frames the cup with both hands, one above and one below, wearing a smug little smile that says “Well? Pretty impressive, huh?” @2’s body and the arm securing the boom remain absolutely still; she responds only with facial expressions: first glancing back and forth between the cup and @1, pressing her lips together to hold back a laugh when @1 blows, and finally looking at @1 with an innocent, humorous expression that says “I’ll just sit here and watch you perform.” They behave like familiar close friends naturally teasing each other, not like actors reciting lines. Throughout these 3 seconds, the cup, @2, and the camera’s optical axis remain aligned, with the boom arm completely hidden behind the cup. 5—7 seconds: the camera moves slowly forward along the optical axis only, without lateral movement or rotation, pushing in from a medium-wide shot to a close-up approximately 45 centimeters from the cup. Autofocus locks onto “JOHN”. The faces of @1 and @2 gradually leave the frame, leaving only the cup, @1’s hands, small edges of their clothing, and the open space beneath the cup. The boom arm remains invisible because it is blocked by the aligned view. 7—10 seconds: using the coffee cup as the fixed center of rotation, the camera slowly and evenly moves around to the right by approximately 70 degrees at the same height and distance, completing the movement over the full 3 seconds without whipping the camera. The cup and boom arm do not move. At 7—8 seconds, slight parallax reveals only a small section of the gray horizontal bar behind the cup; at 8—9 seconds, approximately half of it becomes visible; at 9—10 seconds, the same complete boom arm is visible, extending straight from the back of the cup toward @2’s waist and abdomen. It appears as a horizontal line in the frame, while the paper strip gradually unfolds from an extremely narrow edge. The people’s faces no longer appear in the frame. 10—12 seconds: keep the same shot as the camera slowly moves along the side of the boom arm from the front end at the cup toward its middle section. The coffee cup naturally recedes to the left edge of the frame, the only gray horizontal bar runs through the center, and the front of the paper strip gradually turns toward the camera. The focus smoothly shifts from the bar to the paper strip; the paper strip does not suddenly appear. 12—15 seconds: once the camera reaches a close-up of the paper strip, stop moving and hold steady. The paper strip occupies approximately 50% of the frame width, with the gray boom arm running horizontally behind it, and only a small portion of the coffee cup remaining at the left edge. The two lines of text are stable, upright, and clearly readable:
“您的广告位
hf_20260723_023253_17d01f18-b189-45de-be9c-f30db6d27116.”

15 秒，竖屏 9:16，iPhone 原生相机质感，单个连续镜头，一镜到底，无剪辑、无跳切、无转场。参考视频只用于参考“前半段正面悬浮表演、后半段向右绕行揭露机关”的节奏和运镜，不复制参考视频中的场地、落地支架、顶部字幕、水印和人物。 场景是白天的城市室外人行道，天气明亮但不过曝，柔和自然日光，真实手机随手拍质感。两位成年女性像关系很好的闺蜜一样，在路边临时开一个轻松的小玩笑。人行道平整、干净、空间开阔；主要背景是一面无反光的浅色建筑实墙和少量自然绿化，不出现临街玻璃橱窗、镜面门、反光金属墙。远景偶尔有一两名普通成年路人自然横向走过，路人距离主体至少 4 米，不停留、不围观、不看镜头、不模仿动作，也不穿过咖啡杯、悬臂、@1 与 @2 所在的核心表演区域。画面核心道具始终只有一个咖啡杯、一根灰色水平悬臂和一张白色纸条。 【从第一帧已经搭建好的唯一实物机关】 Exactly one rigid straight gray horizontal boom arm, parallel to the floor, extends forward from @2’s waist toward the camera, with the coffee cup fixed at its front tip. The same boom already exists at frame 1 and never appears, grows, extends, changes direction, or changes shape later. 唯一的一根灰色悬臂长约 80 厘米、直径约 2.5 厘米，始终笔直并与地面平行，保持在 @2 腰部至胸腹部高度。悬臂前端只连接咖啡杯背面正中央，连接点完全藏在杯后，杯子左右两侧没有突出的短杆或接头；后端最后约 10 厘米被 @2 紧贴腰腹的前臂和衣袖完全遮住并固定。悬臂不接触地面、墙壁或天花板。杯底到地面之间始终是清楚可见的完整空地。 开场时，镜头光轴、咖啡杯中心、灰色悬臂长轴、@2 躯干中心严格处在同一条景深直线上。咖啡杯从正面完整遮住其后方的悬臂，因此机关虽然从第一帧就真实存在，正面却完全看不见；后续只因摄影机向右绕行产生视差，才逐渐看到同一根悬臂，绝不是中途生成一根新杆。 中号蓝白外带咖啡杯，皇家蓝杯身、白色杯盖，杯身正中只有清晰白色英文“JOHN”。没有真实品牌 and 鹿角图案。杯子全程固定在同一个空间位置，保持竖直，大小不变，不漂移、不旋转、不变形。全片只有这一个杯子。 白色纸条宽 14 厘米、高 10 厘米，从第一帧起就已经用两小段透明胶带固定在悬臂中段的下侧。纸条顶边贴杆，纸面所在的竖直平面与悬臂长轴平行：开场正面看时纸条严格侧对镜头，只露出极窄纸边；镜头向右绕到侧面后，纸条正面才随视差自然展开。纸条只写两行，第一行不得拆行： 您的广告位
hf_20260723_023253_17d01f18-b189-45de-be9c-f30db6d27116
@john87445528 @1
穿 @1 参考服装
图片_20260710063944_1206_183(1)
，始终站在画面左侧三分之一处，双脚原地不动，身体 and 头部绝不越过画面中线，绝不走到咖啡杯正前方或咖啡杯与 @2 之间。@1 只从画面左侧把双手伸向杯子上下方表演；手掌与杯子始终保持约 10 厘米距离，不接触杯子。她像在街边逗闺蜜开心一样俏皮、活泼、聪明灵动：自然放松地轻微侧身，柔软翻腕，十指缓慢张开。她的眼神在杯子、@2 与镜头之间自然移动，偶尔轻挑一侧眉毛，露出忍不住想笑的顽皮笑容，并在成功展示“悬浮”时给镜头一个短促俏皮的眨眼。不是正式商业摆拍，不端着，不低俗，不夸张扭动，不做鬼脸。 @2
穿 @2 参考服装
图片_20260710063950_1209_183
，双脚不动，始终站在咖啡杯正后方的同一景深轴线上。@2 用贴近腰腹的前臂和衣袖隐藏悬臂后端，固定机关的手臂、身体 and 站位全程不动；但在脸部仍清楚可见的前 5 秒里，她像正在配合闺蜜恶作剧：先故作认真地盯着杯子，随后眉毛上扬、眼睛略微睁大，明知机关却装作吃惊；看到 @1 吹气时短暂抿嘴憋笑，再以“差点被你骗到”的无辜幽默眼神看一眼 @1 和镜头。两人之间有熟悉、放松的默契感。@2 只做面部和轻微眼神变化，不说话、不张大嘴、不摇头、不耸肩。5 秒后镜头推近，@1 与 @2 的脸自然被裁出画面。 【严格连续时间轴】 0—2 秒：正面中全景，摄影机完全不横移。杯子位于画面中心，@1 固定在左侧，@2 位于杯子正后方。杯底下方完整人行道路面清楚可见。@1 一手停在杯口上方、一手停在杯底下方，不接触；她先故作认真地看杯子，再用眼角看向 @2 和镜头，轻挑一侧眉毛并露出忍笑的顽皮表情。@2 配合闺蜜先认真盯着杯子，随后眉毛慢慢抬起、眼睛略微睁大，装出“居然真的浮起来了”的幽默反应。两人的身体 and 脚都不移动。远处可以有一名路人自然经过，但不看她们，也不进入主体轴线。 2—5 秒：摄影机仍在同一正面位置。@1 的脚 and 身体不移动，只做三组清楚、缓慢的手部动作：右手从杯口上方横向掠过；左手从杯底下方横向掠过；双手向外张开展示空手。她像在故意逗 @2，嘴角逐渐忍不住上扬；随后从左侧靠近杯口轻轻吹气，吹气后先看 @2 一眼，再看向镜头短促俏皮地眨一次眼，最后带着“怎么样，厉害吧”的得意小笑容用双手一上一下框住杯子。@2 的身体 and 固定悬臂的手臂保持绝对不动，只用表情接梗：先在杯子 and @1 之间来回看一眼，@1 吹气时抿嘴憋笑，最后用“我就静静看你演”的无辜幽默眼神看向 @1。两人表现得像熟悉的闺蜜自然打趣，不像演员背台词。整个 3 秒内杯子、@2 与摄影机光轴保持共线，悬臂完全被杯子遮住。 5—7 秒：摄影机只沿光轴缓慢向前推近，不横移、不旋转，从中全景推进到距离杯子约 45 厘米的近景。自动对焦锁定“JOHN”。@1 and @2 的脸逐渐离开画面，只保留杯子、@1 的双手、少量服装边缘以及杯底下方的空地。悬臂仍因共线遮挡而不可见。 7—10 秒：摄影机以咖啡杯为固定旋转中心，在同一高度、同一距离缓慢均匀向右绕行约 70 度，用完整 3 秒完成，不甩镜。杯子 and 悬臂都不动。7—8 秒只因轻微视差露出杯后的一小截灰色横杆；8—9 秒看到约一半；9—10 秒看到同一根完整悬臂从杯背面笔直延伸至 @2 腰腹方向。它在画面中呈水平横线，纸条也从极窄纸边逐步展开。人物面部不再入镜。 10—12 秒：保持同一个镜头，摄影机在悬臂侧面沿着悬臂从杯子前端缓慢移动到中段。咖啡杯自然退到画面左边缘，唯一的灰色横杆贯穿画面中央，纸条正面逐渐转到镜头前。焦点从横杆平滑转移到纸条，纸条不是突然出现。 12—15 秒：摄影机到达纸条近景后停止位移并稳住。纸条约占画面宽度 50%，灰色悬臂从纸条背后水平贯穿，咖啡杯只在左边缘保留少量。两行文字稳定、端正、清晰可读：“您的广告位
hf_20260723_023253_17d01f18-b189-45de-be9c-f30db6d27116
.”