
Short answer: to make the First Time in a Fancy Cafe AI video, open the First Time in a Fancy Cafe AI template on ClipRemake, add a clear photo of yourself (and one of a friend or your partner, if you like) and press Remake this. You star in the viral "POV: Your first time in a fancy cafe" skit: you sit perched on a tiny round table in a bare concrete cafe, sipping your coffee, until someone walks in, sits on the bench and uses the table the right way, and you quietly climb down. Without a second photo the AI makes that person up. About five minutes later you download a 15-second, 9:16 MP4 with the clip's own sound and no watermark. One video costs $9.99 with one or two photos, and there is no free version.
What is the First Time in a Fancy Cafe trend?
On November 1, 2026 TikTok creator @leehoustonx posted "POV: Your first time in a fancy cafe". In a minimalist concrete cafe, a man sits on top of a tiny round wall table like it is a stool, feet on the bench, sipping his coffee. A woman in a black dress walks in, sits down on the bench and puts her coffee on the table. He looks, realizes, climbs down and sits the right way as if nothing happened.
It passed 6 million views by November 2, and people search for it as First Time in a Fancy Cafe AI and the "fancy cafe trend" to put themselves on the table.
Who can be in it
Two adults: you as the one on the table, and a friend or your partner as the one who walks in. Each of you keeps your own face, hair and clothes. Only your photo is required: with one photo the AI makes up the one who walks in, someone who looks like none of your photos. Our two examples below are made both ways, a man on the table and a woman on the table. It is made for people only.
How to make the First Time in a Fancy Cafe AI video, step by step
Step 1: Add your photo
Open the First Time in a Fancy Cafe AI page. Tap box 1, You, on the table, and choose a clear, front-facing photo of yourself.

- One person per photo, face to the camera, no sunglasses or heavy filters.
- Waist up or head to toe. The camera is wide, so a sharp face and your outfit both matter.
- Everyday clothes. Smart casual looks most natural in the concrete cafe.
Step 2: Add the one who walks in (optional)
Box 2, The one who walks in, is the person who shows you how it works. Add a photo or leave it empty; the price is the same. Use only photos of adults who agreed to be in the video. Want to be the one who walks in? Put a friend in box 1 and yourself in box 2.
Step 3: Choose the sound
The switch (3) has two settings:
| Setting | What you get | When to pick it |
|---|---|---|
| Trend sound (default) | Your video with the clip's own 15 seconds of audio | You want it ready to post, beat for beat with the original |
| No song | A silent video | You will add the sound inside TikTok or Reels |
Step 4: Press Remake this
Press Remake this (4). If you are not signed in, you sign in with Google first. If you have no credits yet, you pick a pack: one video is $9.99, and bigger packs and plans cost less per video. Pay by card, Apple Pay or Google Pay. If a render fails, the credits come back on their own.
Step 5: Download and post
About five minutes later the video is in My videos. Download the MP4: it is 15 seconds, vertical 9:16, with no watermark and no text. Add "POV: your first time in a fancy cafe" as a caption or a text sticker, and switch on the AI-generated label when you post.
What your video looks like, beat by beat
The cafe, the tiny tables, the static camera and every beat come from the original skit. Only the two people change:

| Time | What happens |
|---|---|
| 0:00–0:01 | You sit perched on the tiny table, sipping your coffee |
| 0:01–0:03 | The other person walks in with a coffee and puts a bag down on the bench |
| 0:03–0:05 | They sit on the bench the right way, coffee on the next little table |
| 0:05–0:10 | You both sip; you glance over and slowly get it |
| 0:10–0:12 | You climb down off the table |
| 0:12–0:15 | You sit on the bench the right way and sip as if nothing happened |
The moments can shift a little between renders, and the one who walks in may carry a different bag or drink.
Tips for a better result
- Two different looks. The skit reads best when the two of you look different, as in the original.
- Even light. Photos in daylight blend best with the soft light of the concrete cafe.
- One person per photo. A second face in the frame confuses who goes where.
Is it free?
No. Every video is a real render that costs money to make, so there is no free version, free trial or watermarked preview. One video costs $9.99 with one or two photos, the pricing page lists packs and plans that cost less per video, and failed renders are refunded in credits automatically. Unused packs bought by mistake can be refunded under the refund policy.