南瓜踢 AI 趋势旋转、踢、定格、"万圣节"

咖啡桌上的发光南瓜灯、一个旋转高踢,画面定格成黑白慢动作并显示草书"万圣节"标题。添加一张照片,选择服装,你或你的宠物就能踢南瓜。

南瓜踢是一个 10 秒的万圣节短视频:在夜晚的游乐场,一位穿小红帽服装的女士将发光的南瓜灯放在桌上,旋转并用高踢将它踢爆。画面定格成黑白并带有雪花和"万圣节"标题。添加一张照片,你就能取代她的位置。

Also called 南瓜踢爆趋势 · 踢南瓜定格画面 · 万圣节南瓜踢

Example

南瓜踢视频的效果

这是 AI 创作者 @ai.creatorledii 的原始短视频,带有自己的声音。你的照片会替换视频中的女士,因此你的视频会遵循相同的桌子、旋转、踢和定格,并带有你的脸和你选择的服装。每次生成结果都不同。

@ai.creatorledii 原始短视频,10 秒
@ai.creatorledii 的原始短视频:小红帽在夜晚游乐场的咖啡桌上放置发光的南瓜灯,旋转并用高踢将它踢爆,画面定格成黑白并显示"万圣节"标题。Human 会让你取代她的位置。
Use this reference
Step by step

如何在 Smew AI 上制作南瓜踢视频

所有操作都在浏览器中运行。无需编辑应用、无需编写提示词、无水印。

  1. 添加你的照片

    点击"创建你的视频"并添加你的照片,脸部清晰。用相机拍摄或从相册中选择。

  2. 点击生成

    按钮会显示价格。Seedance 2.5 将你的照片放入南瓜踢趋势视频中,并逐帧复制 10 秒,带有短视频的原始音乐。你无需编写提示词。

  3. 下载或分享

    视频将在几分钟内准备好,格式为 9:16 MP4。下载它、从手机分享它,或稍后在我的视频中找到它。

哪种照片效果最好?

上传一张照片:Human 用你自己的照片,Pet 用你宠物的照片。

  • Human: 半身或全身照,脸朝向镜头,清晰且光线良好。清晰的脸部最重要。
  • 不戴墨镜、不戴遮住头发的帽子或兜帽、不用重度美颜滤镜。
  • 你的脸和头发来自照片。服装来自你选择的选项;只有自己的服装会使用照片中的衣服。
  • Pet: 一只动物,全身或头部和胸部在画面中,在日光下拍摄。它的毛色、耳朵和斑纹来自你的照片,它会获得一件小红帽斗篷。
  • 任何背景都可以:游乐场、桌子和南瓜来自短视频。
  • 使用你自己的照片、同意的朋友照片或你自己的宠物。绝不使用名人或陌生人的照片。

南瓜踢趋势从何而来?

The pumpkin kick AI trend comes from @ai.creatorledii, an AI creator who makes and sells AI video templates. On 30 October 2026, the day before Halloween, she posted the reel on Instagram with the caption "How do you like this version?" (in Russian). The same AI red riding hood character had walked with a pack of wolves in her reel of 24 October.

The reel is one continuous shot. A Ferris wheel and string lights glow behind a round cafe table by a lake. She puts down a horned jack-o'-lantern, holds it by the stem and makes a face, then turns away in a spin. The kick lands on the beat, the pumpkin bursts, and the picture freezes into black-and-white slow motion while a white handwritten "Halloween" writes itself across the frame.

The sound is a trending original audio by @elenatepl_, used in about 4,900 reels by 30 October. The reel had 43 likes and 3 comments on its first day, and two of the comments asked for the prompt. This is a brand-new Halloween kick trend: the template lets you post your own pumpkin kick video before Halloween on Saturday, 31 October 2026.

  1. @elenatepl_ posts the reel whose original audio the pumpkin kick reel uses. It has 31,000 likes by 30 October, and about 4,900 reels use the sound. Instagram

  2. @ai.creatorledii posts an AI reel of the same red riding hood character walking down a snowy forest road with grey wolves. It has 789 likes by 30 October. Instagram

  3. @ai.creatorledii 发布南瓜踢短视频:旋转高踢踢爆发光的南瓜灯,然后黑白定格并显示"万圣节"标题。首日获得 43 个赞和 3 条评论。Instagram

Copy and paste

南瓜踢提示词

你不需要这些:一键流程会为你运行它们,连同趋势视频。[Image 1] 和 [Image 2] 是你的两张照片,[Video 1] 是视频复制的趋势视频。

Human

1 photo: you, face clearSeedance 2.510 s · 480P · 9:16, like the original152 credits
Video prompt

Recreate the reference video [Video 1] shot for shot: the same night fairground by a lake, with the lit Ferris wheel, the string lights in the trees, the old street lamp, the wet ground with colored reflections and the round wooden cafe table in front; the same fixed vertical camera, timing and moves, one continuous take with no cuts. The ONLY change: the woman who kicks the pumpkin is now the person in [Image 1]. [Image 1] is the sole reference for the kicker's face and hair; [Video 1] is for the moves, the effects and the camera only. The kicker = the person in [Image 1], in EVERY frame, also in the spin, in the kick and in the black-and-white ending: copy the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles). The same real person in every frame, so their friends instantly recognize them. Never morph, never drift back to the original woman's face: not her face shape, her eyes, her nose or her full lips. NO long dark wavy hair with a red tint unless [Image 1] shows it: the hair is the hair from [Image 1]. The costume is the Halloween look and stays exactly as in the video, never the clothes from [Image 1]: the long red hooded cape tied at the neck with a red ribbon, the white ruffled off-shoulder blouse, the black laced corset and the short red skirt. For a man: the same red hooded cape over a white shirt, a black laced vest and dark trousers. The moves, second by second: 0-1 s: the empty table in front of the fairground lights. 1-2 s: the kicker steps in from the right and sets a glowing carved jack-o'-lantern with two small black horns on the table. 2-5.3 s: stands behind the table, holds the pumpkin by its stem, looks down at it, then pulls a cheeky, sassy face at the camera. 5.3-6 s: turns away in a fast spin, the cape flaring wide. 6-6.4 s: the spinning high kick hits the pumpkin: it bursts into big orange pieces that fly off the table. 6.4-10 s: the picture freezes into black-and-white slow motion: the kicker hangs in the air at the end of the kick, pumpkin pieces and snowflakes float, and a white handwritten cursive title "Halloween" writes itself across the middle of the frame, letter by letter, exactly as in the video. Only replace the kicker; the fairground, the table, the pumpkin, the kick, the freeze, the black-and-white look, the snow and the title stay completely unchanged. Keep everything else the same. Anatomy rules: one head only, on the kicker's shoulders. Two arms, two legs, five fingers on each hand. Exactly one person. The only text is the single word "Halloween" in the same white cursive script: no other text, no captions, no logos, no watermark. No dialogue throughout the entire video. No background music.

2825 characters

Pet

1 photo: your pet, whole bodySeedance 2.510 s · 480P · 9:16, like the original152 credits
Video prompt

Recreate the reference video [Video 1] shot for shot: the same night fairground by a lake, with the lit Ferris wheel, the string lights in the trees, the old street lamp, the wet ground with colored reflections and the round wooden cafe table in front with a glowing carved jack-o'-lantern with two small black horns; the same fixed vertical camera, timing and effects, one continuous take with no cuts. The ONLY change: the woman who kicks the pumpkin is now the pet in [Image 1], whole body, and the pet knocks the pumpkin off the table. [Image 1] is the sole reference for the pet; [Video 1] is for the timing, the effects and the camera only. The pet = the pet in [Image 1], whole body, in every frame: the same species and breed, head shape, muzzle, eyes, eye color, ears, fur colors, fur length, markings and body shape as in [Image 1], with the natural body volume and proportions of that animal: never flattened, squashed, stretched or merged with anything, so its owner instantly recognizes it. It wears only a small red hooded cape tied at the neck with a red ribbon. The woman from the video never appears: no human body, no human face, no human hands, no legs in a skirt. If [Image 1] shows a dog or another animal, that animal takes the same place and makes the same moves. The moves, second by second: 0-2 s: the glowing jack-o'-lantern stands on the table; the pet jumps up onto the table from the right and lands beside it. 2-5.3 s: the pet sits beside the pumpkin, sniffs it, taps it with one front paw and gives the camera a cheeky look. 5.3-6 s: it turns around on the table, the little cape flaring. 6-6.4 s: it pounces with a jump and a swipe of its paw, and the pumpkin flies off the table and bursts into big orange pieces. 6.4-10 s: the picture freezes into black-and-white slow motion: the pet hangs in the air in mid-jump, pumpkin pieces and snowflakes float, and a white handwritten cursive title "Halloween" writes itself across the middle of the frame, letter by letter, exactly as in the video. Only replace the kicker with the pet; the fairground, the table, the pumpkin, the burst, the freeze, the black-and-white look, the snow and the title stay completely unchanged. Keep everything else the same. Real animal anatomy: one head, four legs ending in round furry paws, never human hands, no fingers, one tail if the animal has one. Exactly one animal, no people. The only text is the single word "Halloween" in the same white cursive script: no other text, no captions, no logos, no watermark. No dialogue throughout the entire video. No background music.

2592 characters

需要多少积分?

You pay in credits. The Generate button shows this price before you spend anything. These are the options on this page.

OptionModelWhat you getCredits
Human: Red Riding HoodSeedance 2.510 s · 480P · 9:16, like the original152
Human: VampireSeedance 2.510 s · 480P · 9:16, like the original152
Human: WitchSeedance 2.510 s · 480P · 9:16, like the original152
Human: Own outfitSeedance 2.510 s · 480P · 9:16, like the original152
PetSeedance 2.510 s · 480P · 9:16, like the original152

One-time packs and plans are on the pricing page. A failed video gives its credits back.

南瓜踢视频每秒发生什么?

每个版本都复制原始 10 秒短视频,你的照片会取代踢击者的位置。游乐场、桌子、摄像机和效果来自短视频:

时间HumanPet
0 到 2 秒你走进来并将发光的带角南瓜灯放在咖啡桌上。你的宠物跳上桌子,在发光的南瓜旁边。
2 到 5.3 秒你握住南瓜柄,低头看它,然后对镜头做俏皮表情。它嗅南瓜,用爪子拍它并对镜头做调皮表情。
5.3 到 6 秒你旋转转身,斗篷飘扬。它在桌上转身,小斗篷飘扬。
6 到 6.4 秒旋转高踢将南瓜踢成大块橙色碎片。它扑过去并将南瓜从桌上打掉,南瓜爆裂。
6.4 到 10 秒画面定格成黑白慢动作:你悬在空中,碎片和雪花漂浮,"万圣节"在画面上书写。相同的定格,你的宠物在半空中。

你会获得一个 10 秒的竖屏 480P 视频,带有短视频自己的声音,在运行后放回,因此踢击落在节拍上。AI 使用可用的最佳 AI 视频模型,从你的照片和短视频制作。运行需要 5 到 15 分钟,创建页面会在你花费任何积分之前在生成按钮上显示确切价格。

你可以选择哪种南瓜踢服装?

Human 提供四种服装。它们都使用相同的短视频、相同的踢击和相同的定格,价格相同:

  • 小红帽(默认):原始短视频的服装,长红色连帽斗篷、白色褶边衬衫和黑色系带紧身胸衣。这是最接近小红帽南瓜踢的复制。男性会获得相同的红色斗篷,搭配白色衬衫和黑色马甲。
  • 吸血鬼:长黑色斗篷,高领和血红色内衬,苍白皮肤,深红色嘴唇和小尖牙。
  • 女巫:高尖黑色帽子,黑色蕾丝裙和短黑色斗篷。
  • 自己的服装:照片中的衣服,用于在你真实的万圣节服装中踢南瓜。

小红帽服装是最安全的选择,因为短视频已经展示了它。新服装会覆盖在短视频上,因此有时会保留一点红色斗篷:如果出现这种情况,请重新运行。

Pet 让你的狗、猫或其他宠物穿着小红帽斗篷站在桌上。宠物不能做旋转高踢,因此它会跳起来并将南瓜从桌上打掉,然后悬在相同的黑白定格中。

会出现什么问题,如何修复?

问题修复
你获得了长黑色波浪发短视频中的女士有长黑色波浪发。除非你的照片显示它,否则提示词会禁止它。使用清晰的近期照片并重新运行。
旋转中的脸看起来不太像你踢击时你的背部会暂时转向镜头。脸会在定格中回来。近距离正面照片最有帮助。
标题拼写错误或缺失标题是 AI 复制的短视频的一部分,有时会改变它。重新运行。
新服装保留了一些红色选择小红帽,或重新运行。
南瓜没有爆裂每次运行都是新的拍摄。重新运行。
模型拒绝照片有些照片会被拒绝。积分会返还;尝试另一张照片。

你应该如何发布南瓜踢视频?

你的视频带有短视频自己的声音,相同的 10 秒,因此可以直接发布。你可以在结果屏幕上关闭它。声音属于其所有者,Smew AI 不授予你任何权利。

话题标签: #pumpkinkick、#pumpkinsmash、#halloweentrend 和 #halloween。保留平台的 AI 标签。

配文建议: "你喜欢这个版本吗?"、"我 vs. 十月最后一个南瓜"、"不给糖就踢",或在每种服装中发布一次。在 2026 年 10 月 31 日星期六万圣节之前效果最好。

FAQ

南瓜踢趋势问题

什么是南瓜踢趋势?
这是一个 10 秒的万圣节短视频:一位穿小红帽服装的女士在夜晚游乐场的咖啡桌上放置发光的南瓜灯,做鬼脸,旋转并用高踢将它踢爆,画面定格成黑白慢动作并带有雪花和"万圣节"标题。AI 创作者 @ai.creatorledii 在 2026 年 10 月 30 日发布了它。
我如何用照片制作南瓜踢 AI 视频?
点击"创建你的视频",选择 Human 或 Pet,选择服装并添加一张清晰的照片。点击生成;按钮会先显示价格。你会获得一个 10 秒的竖屏南瓜踢视频,带有短视频的声音,准备好后会在我的视频中等待。你无需编写提示词。
南瓜踢 AI 和南瓜踢爆趋势是一样的吗?
是的,很多人称它为南瓜踢爆趋势。这个南瓜踢爆 AI 模板复制原始短视频:发光的南瓜灯、旋转、踢击、爆裂和黑白定格。要自己踢南瓜,添加你的照片。
我的狗或猫可以踢南瓜吗?
可以。选择 Pet 并添加一张宠物的清晰照片。它会获得一件小红帽斗篷,跳上桌子并将发光的南瓜打掉,然后悬在相同的黑白定格中并显示"万圣节"标题。宠物南瓜踢是跳跃和爪击,不是高踢。
我必须穿小红帽服装吗?
不。小红帽是默认的,因为原始短视频展示了它,但你可以选择吸血鬼、女巫或自己的服装。自己的服装会保留照片中的衣服,因此适合你已经穿着的南瓜踢服装。
有踢南瓜 GIF 吗?
踢南瓜 GIF 通常是某人踢南瓜灯的短循环。Smew AI 将你自己的南瓜踢制作成带声音的 MP4 视频,而不是 GIF:你可以将它发布为短视频或 TikTok。
结尾的定格画面是如何工作的?
踢击之后,原始短视频立即定格成黑白慢动作:踢击者悬在空中,南瓜碎片和雪花漂浮,白色手写"万圣节"在中间书写。这个踢南瓜定格画面是 AI 复制的短视频的一部分,因此你的视频也会获得它。每次拍摄都是新的,因此标题可能会略有不同。
此模板使用哪个提示词?
创作者没有分享提示词:两个人在短视频下询问但没有得到回答,其他网站也没有。此模板在原始短视频上使用自己的提示词,规则可以在每一帧中保留照片中的脸和头发,包括旋转和定格。
它对男性有效吗?
有效。你的脸、头发和性别来自你的照片。男性会获得男性剪裁的服装:对于小红帽,红色连帽斗篷搭配白色衬衫和黑色系带马甲。
视频时长和格式是什么?
10 秒,480P 竖屏 MP4,带有短视频自己的声音。它可在 TikTok、Reels 和 Shorts 上播放,没有水印。
南瓜踢需要积分吗?
是的。每个视频需要积分,创建页面会在你花费任何积分之前在生成按钮上显示确切价格。如果视频失败,积分会返还。
视频是真的吗?
不是。你或你的宠物是通过 AI 从一张静态照片放入短视频的,没有人拍摄你。也没有南瓜受伤。发布时保留 AI 标签。
这是我可以真实做的南瓜灯踢挑战吗?
你可以,但带旋转的真实南瓜灯踢很容易出错,而且带蜡烛的雕刻南瓜有火灾风险。AI 版本从一张照片为你提供旋转、踢击和定格,没有人在湿地上滑倒。
南瓜踢也是 TikTok 趋势吗?
It started on Instagram on 30 October 2026, and the halloween freeze frame trend style (a hit, then black-and-white slow motion with a title) works on TikTok, Reels and Shorts alike. Your clip is vertical, so it fits all three.
Related

More like this

Template

Bby Wow Guy AI: Insert Your Face Into the Guy Dancing at a Quince Meme

Groove toward the camera at a quinceañera, take a bite of the concha, lock eyes with the lens while chewing with stuffed cheeks, then groove back into the crowd. Upload one photo to star as the bby wow guy, complete with the song.

Read more
Template

Babydoll Dance AI: Create the Trending Jamie Miller Dance With One Photo

Energetic forward bounces, swinging arms, side steps, ball changes and a high arm flourish, all timed to the music. Upload a photo of yourself or three photos of you with two friends, and generate your Babydoll dance video with the song.

Read more
Template

End of Watch Locker Scene AI: Hold Your Gear Up to the Camera From One Photo

A locker-room gear check in black tactical clothes: sidearm, light, knife, cuffs, radio, spray, then a salute. Your face, your partner, or your pet. The outfit stays the clip's, not your street clothes.

Read more
Template

Bottle Kick Challenge: A serious wind-up for an intentionally silly bottle kick.

Create the stacked-bottle gag with your own face or your pet. The setup, practice moves and oversized reaction matter as much as the kick itself.

Read more
Template

Pumpkin Head Photoshoot AI: Halloween Trend From a Single Photo

Keep your clothes, swap your head for a glowing carved pumpkin in a field at twilight, with film texture. Skip carving and location scouting. Solo, couple, or short video.

Read more
Template

AI Red Riding Hood: Walk Out of the Snow With the Wolves

A tiny red figure far down a snowy forest road, a pack of grey wolves at her side, and then the hood comes down: it is your face. Add one photo of yourself or your pet and get the cinematic reel with its moody slowed song.

Read more

制作你自己的南瓜踢视频

添加一张照片并点击一次。无需编写提示词。152 积分。

No watermark. A failed video gives its credits back. Secure checkout by Stripe.