【风格】 真人实拍质感的拟人猫咪搞笑短视频。猫咪保持真实的毛发、猫脸、胡须、耳朵和肉垫，身体能够拟人坐立、抱臂和操作麻将，但不能变成人脸、人手或卡通身体。室内柔和顶光，清晰自然的毛发细节、皮革纹理和麻将塑料反光。笑点依靠动作、停顿和两只猫的反应形成，不依靠夸张卡通特效。【时长】 10秒，9:16竖屏。全程单一连续镜头，正常速度，不切特写、不慢放。【场景】 现代居家麻将房，米白色墙面、简洁装饰画、右后方浅灰色落地窗帘，天花板有方形灯槽和嵌入式照明。前景是一张绿色绒面自动麻将桌，深色桌框，左下方露出一部分圆形控制盘。 麻将为蓝色牌背、白色牌面，牌面有红绿黑色图案。桌面中间散放少量打出的牌，近处与左右两侧排列着其他玩家的牌墙。西部牛仔猫面前有一排横向整齐排列的麻将，牌的蓝色背面朝向摄影机，看不见里面的花纹。画面下方和右侧偶尔出现其他玩家的真人手与前臂，完成摸牌、放牌和整理牌墙的小动作，不露出其他人的脸。【角色一：坐着打麻将的西部牛仔猫】 使用参考图一中的灰褐色猫形象。 它坐在麻将桌对面的深色椅子上，位于画面中央偏右，面对摄影机。桌面高度约在它腹部，两只前爪能自然伸到桌面。帽檐略微上翘，始终能看清眼睛。气质像自以为牌技高超的冷面高手，动作越花哨，表情越淡定。嘴里还夹着一根烟，非常酷拽的表情。 只借用参考图的猫咪外貌和牛仔服装，手中只操作麻将；不加入参考图中的枪械、滑板、设定卡文字或其他装备展示。 【角色二：站着围观的工牌猫】 使用参考图二中的银灰色虎斑猫：颈部佩戴挂绳，胸前悬挂透明卡套，卡套内有猫咪证件照，工牌大小适中且始终可辨认。 工牌猫直立站在牛仔猫身后偏左的位置，头部高于坐着的牛仔猫，身体露出上半身。前半段两只前爪交叉抱在胸前，工牌从交叠前臂下方露出。它始终面无表情地盯着牛仔猫的动作，眼神带审视和嫌弃，身体基本不动，形成和牛仔猫花式动作的反差。 【镜头与构图】 摄影机位于麻将桌另一侧，接近坐着的玩家视线高度，略微向下拍摄桌面。绿色麻将桌占画面下半部，两只猫占中上部。牛仔猫位于前方中央偏右，工牌猫位于后方偏左，始终保持这组前后关系。 轻微手机广角，固定位置手持微晃。两只猫的脸、牛仔猫的双爪、面前整排麻将和工牌猫的工牌都尽量留在画面内。镜头不绕行、不突然推近，结尾依靠动作制造冲击。 [00:00–00:01.40] 动作段1：开场牛仔猫已经坐在桌前，挺着胸，微微抬起下巴，眼睛半眯，摆出胸有成竹的神态。 它先用右前爪沿桌面向画面左侧轻快伸出，拨动一张麻将，再把爪子收回。随后两只前爪分别按住面前全是背面的横排麻将的左右两端，向中间轻轻归拢，将牌列理齐。动作干净利落，肩膀几乎不动，像对桌上的局面完全有把握。 工牌猫在身后抱臂站立，只用眼睛跟随它的爪子移动，没有笑容，也不帮忙。右侧一只真人手把一张麻将放入桌面中间，随即收回。音效：清脆的麻将碰撞声，轻微室内环境声。 [00:01.40–00:03.20] 动作段2：牛仔猫从面前牌列中拿起一张蓝背麻将，左前爪在胸腹前摊开，肉垫朝上，形成承接姿态；右前爪将麻将压在左爪上 亲亲抚摸，摆出一副不用看牌就知道的表情。 工牌猫抱臂不动，目光向下，盯着它搓牌的双爪。音效：几下节奏紧凑的“嗒、嗒、啪”麻将声。 [00:03.20–00:05.80] 动作段3：牛仔猫右爪再次夹持一张麻将，从桌面抬起，向摊开的左爪做一次短距离递送。麻将贴近两爪之间翻转，随后被右爪带回桌面，轻轻磕在面前牌列旁。 它略微前倾，双爪贴着绿色绒面滑回自己的牌列两侧，再将横排麻将理成一条直线。完成后停顿半拍，抬起眼睛看向摄影机方向，下巴微抬，保持故作高深非常自信的的冷静表情。 桌面右侧和下方的真人手继续正常摸牌、整理牌墙，衬托牛仔猫刻意耍帅的表现。工牌猫的头部略微低下，眼神更加严肃，但仍然抱臂不动。音效：麻将擦过绒面的轻响，零星碰牌声；停顿时减少音效，突出它装腔作势的神态。 [00:05.80–00:07.70] 动作段4：牛仔猫上身向前探，右前爪从自己面前伸向画面左下方的蓝背牌墙，爪垫压住最外侧一张麻将，把它从牌墙端部拖出，再沿桌面带回自己面前。 右爪收回时，它的身体重新坐直，头部却故意向上抬，目光看向上方偏右，仿佛不用看牌也知道下一步。左爪搭在自己的牌列旁，右爪把新摸的牌放在牌列附近。 。 音效：摸牌“咔”的一声，随后是一小段尴尬的安静。 [00:07.70–00:08.65] 动作段5：牛仔猫胸有成竹的表情，做出一副要麻将胡了的动作：转两只前爪分别伸到自己面前整排麻将的两端，向内夹住牌列，试图把整排麻将同时提起并向上翻动。 它双肘弯曲，双爪快速上抬，但中间的麻将没有得到支撑，牌列立刻从中间断开。靠近双爪的几张牌先被带起，中间多张麻将接连滑落；蓝色牌背和白色牌面在空中交替翻转，落回绿色桌面。 失手只发生在桌面上方很短的高度，麻将以不同角度撞击、弹跳、翻倒，向桌面中央和左右散开，碰乱附近打出的牌。整排麻将从有序直线变成一桌凌乱，桌子本身不翻倒。 牛仔猫双爪仍停在半空，短暂保持原本准备展示的姿势，随后发现爪中已经空了。牛仔猫冷面高手的气势瞬间消失，表情略显尴尬。音效：从一声失手的“咔”迅速变成密集的“哗啦啦、噼里啪啦”，最后几张麻将零星弹跳收尾。 [00:08.65–00:09.25] 动作段6：牛仔猫双爪尴尬地悬在胸前，先低头看散乱的麻将，再慢慢转头望向身后的工牌猫。耳朵略向两侧压低，眼睛睁圆，表情从自信变成心虚。 工牌猫低头看一眼桌面，再看牛仔猫，眼睛略微眯起。它终于松开交叉的前爪，其中一只爪子从胸前抬起，肘部弯曲，爪垫朝向牛仔猫帽顶。胸前工牌随着解除抱臂的动作轻轻摆动。 保留短暂的对视停顿，让观众先看到牛仔猫意识到自己闯祸。音效：最后一张麻将落稳的轻响。 [00:09.25–00:10.00] 动作段7 工牌猫抬起的前爪从上方向前下方快速挥出，用柔软爪垫在牛仔猫的帽顶和后脑方向狠狠拍了一下，动作短促明确，像对炫技失败的嫌弃提醒。 牛仔帽受到触碰后直接被扇飞。牛仔猫立即缩脖子、低头，身体向画面右侧躲开，双爪本能抬到脸和帽檐旁挡住，肩膀耸起。它仍坐在椅子上，不摔倒、不离开画面。 工牌猫的前爪跟随动作伸直，再开始收回，脸上始终保持无语的严肃表情；胸前工牌因挥爪轻轻晃动。桌面上留着刚才散落的麻将，其他玩家的真人手短暂停在桌边。音效：一下轻巧的“啪”，。【动作与一致性要求】 坐着打麻将的始终是西部牛仔猫，站在身后围观并在结尾抬爪的始终是工牌猫，不交换位置、服装或身份。牛仔帽、围巾、皮衣、虎斑花纹和工牌保持连续一致。 前半段突出“冷脸、稳坐、花式搓牌、抬头装高手”，后半段突出“整排提牌失手、麻将散落、空爪僵住、心虚回头、被轻拍帽顶”。必须先失手撒牌，再有工牌猫的反应和拍帽动作。 麻将是有厚度的硬质长方体，蓝背白面，接触双爪时有明确支撑，掉落时有重力、碰撞与反弹。麻将不凭空复制、不变成纸片、不长时间悬空。工牌猫前半段保持抱臂，直到失手后才松开前爪。两只猫保留真实猫爪与毛发，不出现人类手指。 整个视频是轻松喜剧，结尾只有一次轻拍，无受伤、无流血、无打斗升级。无字幕、无水印、无角色设定卡文字、无武器、无滑板、无卡通星星或夸张表情贴纸。
Tornado to Cotton Candy
A cinematic, handheld video captures a man throwing pink sugar into a looming tornado. The funnel cloud transforms into a massive, swirling column of pink cotton candy, creating a surreal and whimsical natural phenomenon.
Prompt
Create one uninterrupted 15-second vertical 9:16 handheld smartphone recording. @image1 is ONE complete 3-column by 4-row storyboard, read left to right across each row and then downward. Its twelve pictures are chronological action checkpoints within this single take, NOT twelve shots. Use the sheet as the visual authority for the people, field, weather, enormous tornado and cotton-candy transformation. Render a live full-screen scene from the phone's lens, never the sheet itself, its borders, a collage, a still-image slideshow or a pan across pictures. At the beginning, the phone operator films his friend beside the field with the enormous gray tornado looming in view. Over roughly the first five seconds, keep the friend's pink sugar visible before he throws it. Follow the airborne sugar as the wind carries it into the same funnel; only after the sugar reaches it do pink fibrous bands begin wrapping around the gray tornado. The friend naturally leaves the left edge as the operator reframes toward the funnel. He is not the person who gets lifted. Over roughly the next five seconds, the fibrous bands thicken through the pictured intermediate states until the same gigantic tornado has become a towering mass of fluffy pink spun sugar. Preserve its immense scale against the field. The operator walks closer while continuing to film: foreground grass passes below the lens, the funnel grows through real approach and parallax, and wind shakes the handheld view. Keep the action and transformation visibly continuous; this is not a zoom between still poses. Airborne grass and dust intensify as he gets too close. During roughly the final five seconds, the stronger pull jerks the operator and the phone forward and upward together. The phone stays in his hand throughout. Its view pitches downward during the lift, revealing his own two dangling legs and shoes as the field visibly drops farther beneath him. Hold that height-and-feet proof long enough to understand that the FILMER is being sucked up, then carry the same viewpoint into the deep pink cotton-candy spiral shown in the final picture. End inside that moving spiral. No outside view of the filmer, no selfie, no detached or dropped phone, no drone viewpoint, no cut or teleport into the tornado, and no extra rescue or aftermath. Maintain the spontaneous feel of an amateur phone recording: natural handheld sway and footstep bob, increasing gust-driven shake, modest autofocus and exposure response, and continuous real spatial motion. Keep the essential throw, transformation and dangling feet readable in portrait framing. No slow motion, cinematic coverage, editorial cuts, transitions, freeze frames, captions, graphics or readable text. Native location audio only: wind buffeting the phone microphone, rustling grass, spontaneous laughter at the transformation, and a startled nonverbal yell during the lift. No intelligible speech
How to Use This Prompt
Copy the prompt
Grab the cleaned-up prompt in your language, or send it straight to the editor with one click.
Pick your model
We pre-select the model that produced this result, but you can swap it for any model Vorla supports.
Generate and refine
Run it as-is to reproduce the look, then edit the wording to make the result your own.
All Video Categories
Grok Imagine
Woman Riding Off-Road Motorcycle
Find Your Next AI Prompt
One search covers every model and both mediums, and copying what you find costs nothing.