APT is a two-person routine set in a bright pink studio. The pair face the camera, dance in step, then cut to a short drum bit, and the shots keep switching so the pace never drops. "APT AI" usually means the version where an AI video model builds that duo from two photos.
Where It Came From
We cannot confirm the source of the trend. We can't point to a first post, we can't say when it began, and we don't say who is in the original videos. The name is used here only to describe the routine.
What we can say is what the scene looks like: a candy-pink room with a drum kit and a microphone, two performers, and fast cuts between them.
How People Play It
- As a duo. Two friends, a couple or two siblings copy the routine side by side. It is easy to spot and more fun with a partner.
- In order. Face the camera, dance in step, then cut to the drum bit.
- Short and easy to post. The quick cuts suit short-video apps.
The routine spreads because it is easy to read at a glance. The pink room, the drum kit and the quick cuts tell you what you are watching in the first second, and the structure is simple enough for two people to learn in an afternoon. The AI version keeps that structure: the same studio, the same cuts and the same pace, with the people in your photos in the lead. Photo one plays the first performer and photo two plays the second.
AI Version, Filter and Face Edits
These three are different things.
- A filter changes a video you filmed. You would still need a partner, a camera and a drum kit.
- A face-in-footage edit puts a face into someone else's footage. We do not offer it.
- The AI version makes a new clip. You give two photos, and an AI video model animates the person in each through the staging, cuts and timing of the pink-studio scene. Who stands where can change from shot to shot, so the roles follow the performers, not the sides of the frame.
The trade-off is control. You don't choose the moves or the cuts. Lips move naturally but don't match any words, and hands and drumsticks can blur in close-ups.
Try It
Put Me In's APT AI video is 15 seconds, 16:9 widescreen, silent and labelled AI generated. It is not open for orders yet: the template page is live, but you can't pay for one today. Hotel Lobby is the template that is open now.
Put Me In is an independent tool. We have no connection with the people, the song or the video behind the original APT clips.
Frequently asked questions
- What is the APT AI trend?
- It is an AI-made version of a two-person routine in a bright pink studio. Two photos go in, and a new 15-second widescreen clip comes out.
- What happens in the routine?
- The pair face the camera and dance in step, then cut to a short drum bit. The shots keep switching so the energy stays up.
- Is an APT AI video a filter?
- No. A filter changes a video you filmed yourself. The AI version builds a new clip from two photos, so you film nothing.
- Do you offer face-in-footage edits for it?
- No. We do not put a face into someone else's video. We make a new clip in which the people in your photos perform the routine.
- How many photos does it take?
- Two, one for each performer. Each photo shows one adult, with the whole face visible.
- Does the video have sound?
- No. The clip is silent, and the mouths do not match any words. You add your own sound in the app you post to.
- Can I make one today?
- Not yet. The template has a page but is not open for orders. Hotel Lobby is the template that is open now.
Read more
Viral AI Video Meme Trends (2026): Every Template, With a How-To
All the AI video meme trends you can recreate with your own photos on Put Me In, with one-photo and two-photo templates, how each works and which one is open for orders.
What Is the Alors on Danse AI Trend? The Meme Explained
What the Alors on Danse AI trend is, how people play the two-person keyboard bit, and how an AI version differs from a filter. One-minute read.
What Is the Bby Wow Dance AI Trend? The Meme Explained
What the Bby Wow Dance (also Baby Wow Dance) AI trend is, how people play the banquet-hall party clip, and how an AI version differs from a filter.