I Love The Smiths AI让你走进电梯场景

添加一张你的照片和一张朋友、心仪对象或宠物的照片。一人戴上大耳机,另一人说出“I love the Smiths”,再提高音量重复一次后离场,生成带对白的 15 秒视频。

I love the Smiths是电影《和莎莫的 500 天》电梯场景中的台词:一个人听到同事耳机里漏出的音乐,说出“I love the Smiths”,再提高音量重复一次后离开。这个 AI 版本会把两个你选择的角色放进电梯,分别需要倾听者和说话者的照片。

Also called Tom 和 Summer 的电梯场景 · 和莎莫的 500 天电梯 AI 趋势 · I love X / Me Too 梗 · 电梯相遇梗 · I Love The Smiths 分屏趋势 · Elevator Duet Transition

Example

I Love The Smiths 视频是什么样

示例中的人物和宠物均为 AI 生成。Full scene 使用 24 秒参考并输出 15 秒,恢复对应音轨;其他版本生成新的场景和声音。每次生成结果都可能不同。

两张 AI 生成的人像:左侧为倾听者,右侧为说话者
两张 AI 输入人像:左侧倾听,右侧说话
输入与结果
示例把两张 AI 人像与完成的电梯场景并列展示:倾听者戴耳机,说话者说出“I love the Smiths”,再提高音量重复一次后离开。
Use this reference
电梯参考片段 · 24 秒
两位 AI 人物完成从对话到电梯门开关的完整表演。Full scene 使用这段 24 秒参考,生成 15 秒版本并恢复对应音轨。
Use this reference
Step by step

如何在 Smew AI 制作 I Love The Smiths 视频

全程在浏览器完成,无需剪辑软件、提示词或水印。

  1. 添加两张照片

    点击“Create your own”,先添加戴耳机的倾听者(留在电梯),再添加说出台词的人(离场)。顺序决定角色,可以直接拍照或从相册选择。

  2. 点击 Generate

    按钮会显示价格。Seedance 2.5 根据你的照片生成 15 秒场景,无需先制作中间图片,也无需手动填写提示词。

  3. 下载或分享

    视频完成后会出现在 My Work。你可以播放带声音的 MP4、下载到设备,或稍后回到私密作品区查看。

哪张照片效果最好?

使用两张照片,每张只出现一个人或一只宠物。所有版本都遵循相同顺序。

  • 照片 1 是倾听者:戴耳机、站在左侧,没有听清第一句话,最后留在电梯里。宠物版本中,这里是你的宠物。
  • 照片 2 是说话者:站在右侧,说两遍“I love the Smiths”后离场。
  • 面部清晰、光线良好,尽量看向镜头。半身照片最适合这个近距离双人镜头。
  • 服装来自照片,两人选择不同颜色更容易区分。
  • 不需要提前戴耳机,场景会添加。
  • 每张照片只保留一张脸,合照请先裁开。

I Love The Smiths 趋势从哪里来?

这句台词来自 2009 年的《和莎莫的 500 天》。在故事第 4 天,Tom 戴着大耳机站在公司电梯里,Summer 听到漏出的歌曲后说“I love the Smiths”。他没有听清,于是她提高音量又唱了一句便离开,留下愣住的 Tom。歌曲是 The Smiths 的“There Is a Light That Never Goes Out”。

多年后,这段电梯互动成为 TikTok 梗。Searchlight Pictures 于 2024 年 2 月分享官方片段,人们引用台词、用它表达共同爱好,也与朋友重演。2022 年的粉丝二创和 2023 年 Zooey Deschanel 的参与又推动了传播。近来的 AI 版本则让观众用两张照片替换电梯里的角色。

  1. 《和莎莫的 500 天》上映,Tom 与 Summer 在电梯中讨论 The Smiths 的音乐。

  2. 一条电梯场景粉丝二创在 TikTok 传播,让重复表达逐渐变成常用的声音和反应形式。

  3. Zooey Deschanel 发布自己的短版回应,配文“I said what I said.”,把趋势与 Summer 的扮演者重新联系起来。

  4. Searchlight Pictures 在 TikTok 分享官方“I LOVE THE SMITHS”片段。页面显示的日期可能因用户所在时区而不同。

  5. @akssoxn 发布歌词二创,本次核对时 TikTok 页面显示约 220 万次播放。TikTok

  6. @michael.5456 发布电影二创,本次核对时约 160 万次播放。TikTok

  7. @hanan.selini 在公园长椅上翻拍这段对话,本次核对时约 77.6 万次播放。TikTok

  8. Summrs 发布双照片 AI 制作教程,说明这种模板已经成为一种明确的创建方式。Summrs

  9. #ilovethesmiths 和 #500daysofsummer 标签继续汇集电影二创、翻拍和 AI 版本。TikTok

Copy and paste

I Love The Smiths 提示词

无需手动复制,一键流程会按变体自动发送。[Image 1] 是倾听者,[Image 2] 是说话者;Full scene 还会把 [Video 1] 的 24 秒无声参考一并发送。

双人

2 photos: 戴耳机的倾听者(留在电梯) + 说出台词的人(离开电梯)Seedance 2.515 s · 480P · 9:16189 credits
Video prompt

The famous elevator meet-cute meme, filmed like a real film scene: a small, old office-building elevator with warm dark wood-paneled walls, brass trim, a brass handrail and brushed metal doors, under soft warm overhead light on a quiet morning. Photorealistic, natural skin and natural colors, gentle film grain, a warm cinematic grade, not CGI, not a cartoon. Vertical frame. The two stand side by side facing the doors, about an arm's length apart, framed from the waist up, so both faces stay large, sharp and well lit. The listener is the person in [Image 1], on the LEFT in every frame: 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), with the clothes from [Image 1]. They wear large over-ear headphones with no logo. The one who speaks is the person in [Image 2], on the RIGHT in every frame: copy the exact face from [Image 2] (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), with the clothes from [Image 2], holding a thin stack of folders. If an image shows an animal, that one is that animal with its own face, fur and markings, not a person. Never blend their faces, never swap their clothes. Each face stays the same from the first frame to the last, so their friends recognize them at once. The shots: 1. 0-3 s: a medium two-shot from the front. The elevator hums upward. The listener stares straight ahead and nods very slightly to the music; faint, tinny guitar music leaks from the headphones. The one who speaks glances over, hears it, and a small smile grows. 2. 3-5 s: a medium close-up of the one who speaks, turned three-quarters to the listener. Warm and a little shy, they say: "I love the Smiths." 3. 5-7 s: a medium close-up of the listener, who did not hear. They slide one headphone cup off one ear, puzzled, and say: "Sorry?" 4. 7-11 s: the one who speaks, louder, with a playful, confident smile: "I said I love the Smiths." Then, eyes half closed, they softly hum a short wordless tune and sway a little. 5. 11-13 s: a soft bell rings. The doors slide open on a bright office hallway. The one who speaks gives a small sideways smile and steps out without looking back. 6. 13-15 s: the listener alone in the elevator, from the chest up, frozen, eyes wide, mouth slightly open, as the doors slide shut in front of them. They whisper: "Wow." Audio: the elevator hum, faint tinny guitar music from the headphones (an original melody), the two voices in natural English with exact lip sync, the soft hum, the bell and the doors. No other dialogue. Only these two, nobody else in the elevator or in the hallway. No text, no subtitles, no logos, no brand names, no watermark. No other music, no famous melody, no lyrics.

2921 characters

情侣

2 photos: 你,戴耳机(留在电梯) + 你的心仪对象,说出台词(离场)Seedance 2.515 s · 480P · 9:16189 credits
Video prompt

The famous elevator meet-cute meme, filmed like a real film scene: a small, old office-building elevator with warm dark wood-paneled walls, brass trim, a brass handrail and brushed metal doors, under soft warm overhead light on a quiet morning. Photorealistic, natural skin and natural colors, gentle film grain, a warm cinematic grade, not CGI, not a cartoon. Vertical frame. The two stand side by side facing the doors, about an arm's length apart, framed from the waist up, so both faces stay large, sharp and well lit. The listener is the person in [Image 1], on the LEFT in every frame: 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), with the clothes from [Image 1]. They wear large over-ear headphones with no logo. The crush is the person in [Image 2], on the RIGHT in every frame: copy the exact face from [Image 2] (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), with the clothes from [Image 2], holding a thin stack of folders. If an image shows an animal, that one is that animal with its own face, fur and markings, not a person. Never blend their faces, never swap their clothes. Each face stays the same from the first frame to the last, so their friends recognize them at once. The shots: 1. 0-3 s: a medium two-shot from the front. The elevator hums upward. The listener stares straight ahead and nods very slightly to the music; faint, tinny guitar music leaks from the headphones. The crush glances over, hears it, and looks at the listener a beat too long. 2. 3-5 s: a medium close-up of the crush, leaning a little closer, with a soft, flirty smile: "I love the Smiths." 3. 5-7 s: a medium close-up of the listener, who did not hear. They slide one headphone cup off one ear, puzzled, and say: "Sorry?" 4. 7-11 s: the crush, louder, holding the listener's eyes with a teasing smile: "I said I love the Smiths." Then they softly hum a short wordless tune, eyes on the listener. 5. 11-13 s: a soft bell rings. The doors slide open on a bright office hallway. The crush steps out, then looks back over the shoulder with a small smile and a tiny wave. 6. 13-15 s: the listener alone in the elevator, from the chest up, frozen, then a slow, smitten grin spreads and one hand goes to the chest as the doors slide shut. They whisper: "Wow." Audio: the elevator hum, faint tinny guitar music from the headphones (an original melody), the two voices in natural English with exact lip sync, the soft hum, the bell and the doors. No other dialogue. Only these two, nobody else in the elevator or in the hallway. No text, no subtitles, no logos, no brand names, no watermark. No other music, no famous melody, no lyrics.

2908 characters

完整场景

2 photos: 戴耳机的倾听者(留在电梯) + 说出台词的人(离开电梯)Seedance 2.515 s · 480P · 16:9, like the original228 credits
Video prompt

Recreate the reference video [Video 1] shot for shot: two people in a small office elevator with warm beige wood-paneled walls, the same camera positions, framing, cuts, timing, moves and mouth moves. The ONLY change: the two people are now the people in [Image 1] and [Image 2]. STRICT SOURCE CAMERA AND ENVIRONMENT LOCK: Replace only the two actors. Preserve the elevator wall and door colors, materials, reflections, exposure and lighting of [Video 1] in EVERY shot. Keep the exact camera position, lens, framing, crop and subject screen size at every frame. No zooming, no reframing, no new camera movement. Preserve every original cut at its exact time. PERMANENT CAST: [Image 1] replaces ONLY the man on the LEFT with the headphones and the brown leather shoulder strap. [Image 2] replaces ONLY the woman on the RIGHT with the dark bangs. The person from [Image 2] walks out at the exact original moment. The final shot contains ONLY the person from [Image 1]; do not reinsert the other person. FULL REPLACEMENT: the person on the LEFT = the person in [Image 1], in EVERY shot: 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 person on the RIGHT = the person in [Image 2], in EVERY shot: copy the exact face from [Image 2], with the same details. Rebuild entire heads and bodies, not just faces: NO black side-parted hair and NO moustache on the left person, NO dark bangs on the right person, unless their photo shows them. Both change: no one from [Video 1] stays, also in the wide shot. Never morph, never drift back to the faces in [Video 1], never blend the two faces. CLOTHING: each wears the clothes from their own photo, with no navy shirt on the left person and no cream cardigan on the right person unless their photo shows them. The left person keeps the over-ear headphones and the shoulder bag from [Video 1] as props. ACTION AND LIP SYNC: the exact poses, hand gestures, gaze, head turns, timing and walking of [Video 1]. The mouths move only on their own lines, in sync with [Video 1]: Shot 1 [0-4.7s]: the two-shot from the front. The right person, smiling: "I love the Smiths." The left person slides the headphones down: "Sorry?" The right person: "I said I love the Smiths." Shot 2 [4.7-11s]: hard cut, the same two-shot. The right person says "Yeah", faces forward and softly sings a short line with a smile, then: "I love them." The left person stares, stunned. Shot 3 [11-15s]: hard cut, a wide shot into the elevator: the doors slide open, the right person walks out, the left person stays alone inside, frozen, and mutters two words. SCENE: photorealistic live action, natural skin and hair, stable outfits and identities. No extra people, no swapped faces, no merged bodies, no extra limbs. No other dialogue. No background music. No text, no captions, no logos, no watermark.

2972 characters

你 + 宠物

2 photos: 你的宠物,戴耳机(留在电梯) + 你,说出台词(离开电梯)Seedance 2.515 s · 480P · 9:16189 credits
Video prompt

The famous elevator meet-cute meme, filmed like a real film scene: a small, old office-building elevator with warm dark wood-paneled walls, brass trim, a brass handrail and brushed metal doors, under soft warm overhead light on a quiet morning. Photorealistic, natural skin and natural colors, gentle film grain, a warm cinematic grade, not CGI, not a cartoon. Vertical frame. The two are side by side facing the doors, about an arm's length apart, framed from the waist up, so both faces stay large, sharp and well lit. The listener is the pet in [Image 1], on the LEFT in every frame, sitting upright on a small wooden bench so its head is at the person's chest height: the same species and breed, face, eyes, ears, muzzle, fur colors, fur length and markings as in [Image 1], with the natural body volume and proportions of that animal, never flattened, stretched or turned into a person. It wears small over-ear headphones made for its head, with no logo. The one who speaks is the person in [Image 2], standing on the RIGHT in every frame: copy the exact face from [Image 2] (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), with the clothes from [Image 2], holding a thin stack of folders. If [Image 1] shows a person, the listener is that person standing, with the exact face from [Image 1]. Never blend the two, never swap their looks. Each face stays the same from the first frame to the last, so their friends recognize them at once. The shots: 1. 0-3 s: a medium two-shot from the front. The elevator hums upward. The pet sits still and stares straight ahead; faint, tinny guitar music leaks from its headphones. The person glances over, hears it, and a small smile grows. 2. 3-5 s: a medium close-up of the person, turned three-quarters to the pet. Warm and a little shy, they say: "I love the Smiths." 3. 5-7 s: a close-up of the pet, who did not hear. It tilts its head, one headphone cup slips off one ear, and it makes one small, puzzled sound of its own kind. 4. 7-11 s: the person, louder, with a playful, confident smile: "I said I love the Smiths." Then, eyes half closed, they softly hum a short wordless tune and sway a little. 5. 11-13 s: a soft bell rings. The doors slide open on a bright office hallway. The person gives a small sideways smile and steps out without looking back. 6. 13-15 s: the pet alone on the bench, frozen, eyes wide, ears up, staring at the doors as they slide shut in front of it. Audio: the elevator hum, faint tinny guitar music from the headphones (an original melody), the person's voice in natural English with exact lip sync, the pet's one small sound, the soft hum, the bell and the doors. The pet never talks. No other dialogue. Only this pet and this person, nobody else in the elevator or in the hallway. No text, no subtitles, no logos, no brand names, no watermark. No other music, no famous melody, no lyrics.

2993 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
双人Seedance 2.515 s · 480P · 9:16189
情侣Seedance 2.515 s · 480P · 9:16189
完整场景Seedance 2.515 s · 480P · 16:9, like the original228
你 + 宠物Seedance 2.515 s · 480P · 9:16189

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

四种版本:双人、情侣、完整场景,或你和宠物

在创建页选择版本。前三种竖屏版本都使用两张照片生成 15 秒场景;Full scene 则使用 24 秒参考并输出 16:9 的 15 秒视频。

版本内容
双人你和朋友或同事。照片 1 戴耳机;照片 2 说两遍台词、轻声哼唱后离开,照片 1 愣在电梯里。
情侣更偏相遇和暧昧的版本。照片 2 靠近并微笑,离开时回头挥手,照片 1 最后露出心动的笑容。
完整场景使用 24 秒参考,保留镜头、动作、演唱、电梯门和最后的惊讶表情,输出 15 秒、16:9 视频并恢复对应音轨。
你 + 宠物宠物戴着小耳机坐在长凳上,听到台词后歪头。你说话后离开,留下宠物盯着电梯门。

所有版本都会显示准确的积分价格,完成后可回到 My Work 查看。

这段对话如何展开

这段对白很短,视频按相同的节奏推进:

  1. 电梯上升,倾听者跟着耳机里的音乐轻轻点头,另一人听到漏出的旋律。
  2. “I love the Smiths.”
  3. 倾听者摘下一侧耳机:“Sorry?”
  4. 对方提高音量,微笑着说:“I said I love the Smiths.”随后轻声哼唱。
  5. 提示音响起,电梯门打开,说话者离开。
  6. 倾听者独自留在电梯里,愣住。

网上也会出现不同的重复和改写方式。双人、情侣和宠物版本使用原创旋律,Full scene 则恢复参考中的对话和歌曲。

声音、配文和标签

双人、情侣和宠物版本包含对白、电梯声、耳机里轻微的原创旋律、提示音和开关门声,不包含电影原声。Full scene 使用 24 秒参考,并恢复前 15 秒对应音轨。

配文可以写“I said I love the Smiths”,也可以改成“终于有人懂我的音乐品味”,或用“I love [你的爱好]”表达共同兴趣。

常见标签包括 #ilovethesmiths、#500daysofsummer 和 #thesmiths。互动数字会变化,不把某一天的播放量当成永久事实。

常见问题如何处理?

问题建议
人物不像照片换用清晰、正面、光线良好的照片再试。
两张脸混合或交换位置每张照片只放一个人,照片 1 始终是左侧倾听者。
台词含糊或被截断重新生成,每次都会产生新的表演。
宠物被压扁或显得太小使用宠物坐姿、看向镜头且头部完整的照片。
生成失败积分会退回,可以换照片重试。

电梯、服装、动作和时间可能因生成而略有不同。

FAQ

I Love The Smiths 常见问题

I love the Smiths 是什么趋势?
它源自《和莎莫的 500 天》的电梯场景:一个人听到别人耳机里漏出的音乐并说“I love the Smiths”,对方没听清后又重复一次。人们引用、重演,近来也用 AI 把自己的脸放进场景。
“I said I love the Smiths”来自哪部电影?
来自 2009 年的《和莎莫的 500 天》,发生在故事第 4 天的电梯里。相关歌曲是 The Smiths 的“There Is a Light That Never Goes Out”。
怎样制作 I love the Smiths AI 视频?
点击“Create your own”,选择双人、情侣、完整场景或宠物版本。照片 1 是倾听者,照片 2 是说话者,然后点击 Generate,完成后在 My Work 查看。
这是一个 I love the Smiths 梗图生成器吗?
它生成的是视频:两张照片替换电梯里的角色,而不是只给静态图片加文字。如果需要梗图,可以播放后截图,或从视频中截取几秒。
视频里会出现电影片段或演员吗?
双人、情侣和宠物版本会重新生成相似场景,不使用电影画面、演员或原声。Full scene 使用参考视频,并恢复参考中的对话和歌曲。
视频包含 The Smiths 的歌曲吗?
双人、情侣和宠物版本只有对白、电梯声和耳机里的原创旋律。Full scene 恢复参考中的对话和歌曲。发布时也可以按平台规则选择趋势音频。
哪张照片说台词?
照片 2。照片 1 戴耳机、问“Sorry?”并留在电梯里;照片 2 说两遍“I love the Smiths”后离场。交换照片就会交换角色。
可以和宠物一起制作吗?
可以。选择 You + your pet,照片 1 是宠物,照片 2 是你。宠物戴耳机、歪头并做出自然反应,但不会说人话。
什么是 I love X / Me Too 梗?
它用同一个场景表达共同爱好:一个人说喜欢某个乐队、节目或食物,另一个人回应“me too”或露出惊讶表情。这个模板保留原始的 Smiths 台词。
它和 500 Days of Summer AI 趋势是同一种吗?
是。两个名字通常都指把新角色放进同一个电梯场景,也有人用“I said I love the Smiths”称呼它。
elevator scene 和 lift scene 有区别吗?
没有。lift 是英式英语,两个名字指同一段电梯互动。
视频有多长、什么规格?
所有版本都是 15 秒、480P。双人、情侣和宠物为 9:16,Full scene 为 16:9。Full scene 的参考片为 24 秒,输出仍按 15 秒合同。
Full scene 和分屏视频有什么关系?
Full scene 使用上面的 24 秒电梯参考,替换两位角色并输出 15 秒、16:9 视频,恢复对话和歌曲。分屏则是发布者常用的展示方式,把两个版本上下排列。
需要支付积分吗?
需要。双人、情侣和宠物版本各 189 积分,Full scene 为 228 积分。Generate 会在提交前显示准确价格,失败会退回积分。
我的照片是私密的吗?
照片和结果只用于你的创建流程,不会作为公开示例展示给其他用户。视频进入私密 My Work,你可以在那里管理和删除。
Related

More like this

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

La Tormenta de Arena AI Trend: Te He Perdido Entre la Gente

Someone gazes down from a balcony overlooking a crowded club, the view shifts to the dance floor below, and a bright spotlight reveals another person looking upward. Upload two photos or pet images to generate your video with its soundtrack.

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

Hotel Lobby AI: Create the Hotel Lobby Trend Video

Put two people into the 2022 orange-booth performance, song included, or choose the cat reel or a 10-second booth copy for people or pets.

Read more
Template

Elevator Outfit Change AI: The Doors Close, a New Outfit Steps Out

You stand inside a steel elevator, filmed straight on. The doors slide shut, open again, and you are wearing a new outfit. Pick the women's looks (four evening gowns) or the men's looks (three outfits and a walk out), keep the reel's looks or write your own. One photo in, a vertical clip with the reel's sound out.

Read more
Template

Somebody That I Used To Know AI: Sing the Painted Wall Duet

A flat wall of pink, terracotta and beige. One singer faces the camera, the other answers in profile, shoulders painted into the shapes. Duo and Two pets are 15 seconds in wide 4:3. Solo is the patchwork costume, about 8 seconds, vertical 9:16. The song on the file is this clip’s own soundtrack.

Read more

制作你的 I Love The Smiths 视频

添加两张照片,选择双人、情侣、完整场景或宠物版本,一键生成 15 秒视频,189 积分起。

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