How to Make the First Time in a Fancy Cafe AI Video with Your Dog or Cat

A bare concrete cafe. A big fluffy dog balanced on a tiny metal table fixed to the wall, coffee in its paws, looking like a regular. Then someone elegant walks in, sits on the bench and puts their cup on the identical table. That's the "POV: your first time in a fancy cafe" trend, and here's how to make it with your own pets, from one or two photos.

What is the First Time in a Fancy Cafe trend?

It's a POV joke that took off on Instagram and TikTok around 31 October 2026. Someone in a minimalist cafe sits on a little round wall-mounted table, thinking it's a stool. When another customer uses the same thing as a table, they quietly climb down and act like nothing happened. Creators rushed to remake it, and pet versions followed within days.

Our First Time in a Fancy Cafe template follows AI pet versions of that clip: the moves and the timing, not their animals.

How to make it

1. Open the First Time in a Fancy Cafe template.
2. Pick dog or cat. Dogs, rabbits and other pets use the dog version; cats have their own.
3. Add one or two pet photos. One animal per photo, face to the camera, in good light. Photo 1 sits on the table and photo 2 walks in; with one photo, the second animal is made up.
4. Pick a version and generate. Premium renders the whole ~21 seconds; Balanced renders 15 seconds with the whole gag.
5. Download the MP4. It comes with the trend's sound. To pick the sound yourself when you post, turn Include the song off or use Download without music.
6. Post it to TikTok, Reels or Shorts with the caption "POV: your first time in a fancy cafe". The video itself has no text on it.

What happens in the video

• 0–5.5 s: the perch. Your pet sits on the little wall table, knees up, sips its coffee and looks around like a regular.
• 5.5–10 s: the entrance. An elegant animal strolls in with a coffee, sits on the bench and sets its cup on the same little table.
• 10–14.5 s: the side-eye. Your pet doesn't move. It glances over, glances down at what it's sitting on, and slowly gets it.
• 14.5–17 s: the climb down. An awkward scramble onto the bench, cup placed on the table as if it was always there.
• 17–21 s: nothing happened. Both seated, both cups on their tables, your pet staring straight ahead.

Balanced renders 3.5–18.5 s of this, from just before the entrance to the moment your pet sits down, so the joke stays whole. The camera never moves, and the video is vertical (9:16).

Pet photos that work best

• Face clearly visible. Eyes, nose and ears sharp and toward the camera: the side-eye is the whole joke.
• Good light. Daylight or a bright room; a dim photo makes dark fur muddy against the concrete.
• The whole pet, if you can. Your pet is on screen head to tail, so a full-body photo gets its fur and markings right. A clear head shot still works.
• One animal per photo. No second pet, no person holding it.

Breed, face, ears and fur come from your photo, so a small dog stays that breed even though the reel's dog is a Great Pyrenees.

What does it cost?

Premium (the full ~21 seconds) is 40 credits at 480p, 80 at 720p and 145 at 1080p; Balanced (15 seconds) starts at 15 credits. Without an account, one video costs from $7.99 at checkout. No watermark, and failed renders and rejected photos are refunded automatically.

FAQ

Does my pet need to be in a cafe in the photo? No. Any clear photo works. The cafe, the table and the coffee are generated.

Can I use a photo of a person? Not with this template: it takes pet photos only.

What's the song? "Oh Yeah?" by Steve Lacy, the title track of his 2026 album.

How long does it take? Usually a few minutes. Your photo is reviewed first, then the video renders.

Make your Fancy Cafe video →