How to Make the POV First Time in a Fancy Cafe AI Video
What’s new on this page
- — Published: our first POV First Time in a Fancy Cafe AI video (Wan 3.0, 15 s, 480p, 300 credits, first try, about 5 minutes), the full prompt, frames, who sits where and photo tips.
A POV First Time in a Fancy Cafe AI video puts two people from two photos into the viral TikTok skit: one of you sits on a little round metal cafe table as if it were a chair, the other walks in, sits on the bench and puts a coffee on that table. We made the clip above on 4 November 2026 from two AI-generated cosplay characters (not real people), a Gryffindor first-timer and a Slytherin regular. This is exactly what we did, what it cost and how you can make the same thing with a friend.
What is the POV First Time in a Fancy Cafe trend?
The POV First Time in a Fancy Cafe trend is a silent skit about not knowing how a minimalist cafe works. TikTok user @leehoustonx posted the original on 1 November 2026, set to "Oh Yeah?" by Steve Lacy, and it passed 9.2 million views in two days, according to Know Your Meme. By 2 November the remakes had taken over: an Instagram version by @kevinwinnik gained more than 14.5 million likes in a day.
What happens in a POV First Time in a Fancy Cafe AI video?
The whole clip is one locked wide shot of a concrete cafe with the "POV: Your first time in a fancy cafe" caption on top. Nothing is said; the joke is the slow realization. In our result:
| Seconds | What happens |
|---|---|
| 0–1 | The first-timer sits on the round metal table, coffee in hand |
| 1–4 | The regular walks in with her cup and a bag |
| 4–6 | She sits on the concrete bench and sets her cup on the table |
| 6–11 | He sips and slowly looks over at her |
| 11–13 | He climbs down off the table |
| 13–15 | He sits on the bench and puts his coffee on the table, like she did |
How we made our first POV First Time in a Fancy Cafe AI video
We built it by hand first, the way you would without a template, so we know which parts matter.
1. We started from a 15-second cut of the original skit
We used a 14.9-second vertical cut with the whole beat in it: the man already on the table, the woman walking in and sitting down, and him moving. The caption is part of the frame, so it carries straight into the AI version.
2. We used two photos that look nothing alike
Photo 1 was a full-body shot of a young man with round glasses in a red Gryffindor robe, scarf and tie. Photo 2 paired a face close-up with a full-body shot of a blonde girl in a Slytherin uniform, tights and loafers. A red robe next to a green-and-black uniform made it easy to check that nobody ended up in the other person's clothes.
3. We told the model who plays whom
With two people in one frame, the model needs to know which face goes where, so photo 1 maps to the man on the table and photo 2 to the woman who walks in. We also asked it to keep each full outfit, not only the face. This is the prompt we ran on Wan 3.0, 480p, 15 seconds, sound on, with the skit as the reference video:
Replace the man in the source video with the person from IMG 1, and replace the second person with the person from IMG 2. Each person's face, hairstyle and outfit must match their own reference photo exactly. Keep the camera angle, background, lighting, pacing, body movements and facial expressions of the source video unchanged. Faces stay consistent in every frame, with natural skin texture, realistic proportions, no flicker and no extra people.
4. It rendered in about 5 minutes
We submitted at 14:23 UTC and the video was ready at 14:28: first try, 300 credits. Both faces held up across the wide shot, the robe, scarf and tie stayed on him, the Slytherin crest and tights stayed on her, and the coffee cups landed on the tables at the right moments. That run is what the template now uses, with the prompt and settings already in place.
How to make a POV First Time in a Fancy Cafe AI video in 4 steps
Step 1: Open the template
Go to the POV First Time in a Fancy Cafe AI page. The template is already loaded at the top, with the model and prompt set up.
Step 2: Add the first-timer
The First-timer sits on the table and slowly realizes the mistake, so pick the friend who always pretends to know the place. A full-body photo with a clear face works best.
Step 3: Add the regular
The Regular walks in, sits on the bench and uses the table the right way. Missing a friend? Click Use example under that slot and keep our sample photo.
Step 4: Generate and download
Press Generate. The button shows 300 credits before anything is charged. The video lands in My Videos, so you can close the tab while it renders. Download the MP4, which has no watermark, and post it.
Who sits on the table in the POV First Time in a Fancy Cafe AI video?
| Slot | Role | Best photo |
|---|---|---|
| Photo 1 | First-timer: on the table from the start, climbs down at 11–13 s | One person, full body, face clear |
| Photo 2 | Regular: walks in at 1 s, sits on the bench | One person, full body, outfit visible |
To trade roles, swap the upload order.
What photos work best for a POV First Time in a Fancy Cafe AI video?
- One person per photo. A face cut out of a group shot is too small once it becomes a full-body figure.
- Show the outfit. The camera never cuts closer than a wide shot, so clothes and shoes are half of what people see. A face close-up plus a full-body shot in one image worked well for us.
- Two different looks. Contrast makes the two roles readable at a glance.
- Keep the face clear. No phone or hands over the face. Glasses are fine: ours stayed on the whole time.
- Adults only. Use photos of yourself or adults who said yes. Photos of children, celebrities and public figures aren't allowed.
Can you make the POV First Time in a Fancy Cafe AI video alone?
Not with one photo: the template has two slots and does not split a group photo. If your friend isn't around, put yourself in photo 1 and use our sample photo as the regular. If the faces drift, our guide to keeping characters consistent in AI video explains what helps.
That's why we packaged it: the role order, the full-outfit line in the prompt and the model are already set, so you don't pay to rediscover them. Make your POV First Time in a Fancy Cafe AI video with the same settings.
Is POV First Time in a Fancy Cafe AI free?
Not completely. New accounts get 75 free credits and one video takes 300, so you need the one-time $5.99 pack (540 credits). That covers one video at about $3.33 and leaves 240 credits, with no subscription. See pricing. Failed renders are refunded automatically.
How long is the video and how much does it cost?
About $3.33 for one video: 300 credits for a 15-second, 480p vertical clip with the POV caption and sound. Ours took about 5 minutes to render.
What song is in the fancy cafe video?
The original TikTok by @leehoustonx uses "Oh Yeah?" by Steve Lacy, according to Know Your Meme. The AI video comes with sound, so you don't add music yourself.
Do we keep our own outfits?
Yes. In our test the Gryffindor robe, scarf and tie stayed on the first-timer, and the Slytherin uniform, tights and loafers on the regular.
Why don't we look like our photos?
Usually it's a small face cropped from a group shot or a mirror selfie with the phone in the way. Use a sharp single-person photo facing the camera for each slot and run the POV First Time in a Fancy Cafe AI generator again.
Is this the official video?
No. It's a fan-made template, not affiliated with @leehoustonx, TikTok or Steve Lacy.
Want another duo? Our 58th Floor AI tutorial puts two of you at one hanging mic in the COLORS studio, and our Pimp Walk Entrance AI tutorial has one holding a door while the other struts in.