The APT. trend puts two new people into the pink room from ROSÉ and Bruno Mars' "APT." music video: one on the drums, one on the mic. It started on October 1, 2026, with a split-screen post on X comparing the official video to an AI remake, and within days people were swapping in their friends, partners and coworkers.
This guide shows how to make your own with the APT AI video generator: what you need, how the character swap works, which photos give the best result, and what it costs.
What you need
- Two photos, one person in each. Or one photo with both of you in it.
- A browser on your phone or computer. There is no app to install and nothing to film.
- A few minutes while the video renders
- 10 credits for a 720p video (see the cost section)
Step 1: Decide who drums and who sings
The APT. character swap has two fixed roles, like the original:
- Photo 1 is the drummer. This person sits behind the kit.
- Photo 2 is the singer. This person kneels by the drums at the start and carries the song.
If you only have one picture of the two of you, choose One photo of both. Whoever stands on the left plays the drums, and whoever stands on the right sings.
The two photos do not need to be taken together. A selfie from today and a photo of your friend from last year work fine. The AI puts both of you in the same pink room.
Step 2: Pick photos that work
Most bad results come from the photo. A few things make a real difference:
- One clear, front-facing face per photo
- Even light. Daylight from a window beats a dim room.
- Nothing covering the face: no sunglasses, masks or caps pulled low
- A visible mouth. The clip has lip close-ups, and a hidden mouth has to be guessed.
- For one photo of both: just the two of you, both facing the camera, nobody else in the frame
Each person keeps their own face, hair and outfit from their photo. If you want a particular look in the video, use a photo where you are wearing it.
Step 3: Make it
Open the APT AI video page, add your photos, keep the APT. Pink Studio effect selected and tap Make the effect. The video is ready in a few minutes.
Here is what you get:
| Length | 15 seconds |
| Shape | Landscape 16:9, like the original |
| Motion | The first 15 seconds of the official video, beat by beat |
| Sound | The matching 15 seconds of the original song, laid over the video |
| Quality | 720p (Standard) or 480p |
The 15 seconds break into four beats:
- 0–3s: the singer kneels by the drum kit and starts singing.
- 3–10s: both of you behind the kit, cheek to cheek.
- 10–13s: lip close-ups.
- 13–15s: a little dance side by side.
Step 4: Download and post
Preview the result, then download the MP4. Because the song is already in the file, you don't need to add it in an editor.
Is there a free APT AI video?
Not here, and we would rather say so up front. Here is what it costs:
- 720p Standard: 10 credits. That is the same as one song, so a $9.99 Single pack covers one APT. video.
- 480p: 7 credits.
- Failed renders are never charged. If a render fails, the credits go back to your account.
- Packs never expire. Credits you don't use today are still there next month.
See pricing for the current packs and plans.
Before you post
Get consent. Everyone whose face is in the video should be fine with it, even if it is a joke. Anyone under 18 needs a parent or guardian's consent.
No celebrities. Use your own photos and your friends' photos, not photos of ROSÉ, Bruno Mars or other famous people.
The song is the original recording. Platforms may mute, limit or remove videos with copyrighted music, and you are responsible for how you share it.
It is a fan trend. RapVideo AI is independent and not affiliated with ROSÉ, Bruno Mars or their labels.
FAQ
Can I do it alone?
The APT. effect is built for two people, a drummer and a singer. Ask a friend, or use one photo of both of you.
Can the two photos have different backgrounds?
Yes. The AI places both people in the pink room, so the original backgrounds don't matter.
Why is it 15 seconds and not the full song?
It follows the opening 15 seconds of the official video, the part with the drums, the cheek-to-cheek shot, the lip close-ups and the side-by-side dance. The matching 15 seconds of the song come with it.
Is it vertical?
No. It is landscape 16:9, the same shape as the original video.
How long does it take?
A few minutes per video.
Make yours
Pick two photos, decide who's on drums and try it on the APT AI video page. Curious where the song's name comes from? Read APT. song meaning.