Starter
$0.17 per credit
$8.90USD
- 2 videos
- 52 credits
- Audio included
- Landscape 16:9 · Portrait 9:16
- Works with every template
- Credits never expire
Photo 1 plays the drums. Photo 2 sings. The pink studio and camera follow the reference, with newly generated reference-guided audio.
JPG, PNG or WebP · one clear, front-facing face
0 / 2 photos selectedOnly use everyday photos of yourself or friends who agreed to be featured. Photos of politicians, celebrities or other public figures, and film or MV stills, raise likeness-rights and legal issues and are rejected in review.
15s · 16:9 · 768p · Reference-guided generated audio
One-time payment · No subscription
These previews replay the same 15-second reference. The drummer and lead performer keep separate marks in the pink room.
Photo 1 takes the drum-kit role, performing independently behind the lead.
Photo 2 takes the foreground performance and solo close-ups.
The same reference shows the pink set and two independent performances.
If a pairing looks crowded, use cleaner photos with one person in each file. The template never adds a third performer.
No prompt and no keyframe list. Cast the kit and the floor, then download.
One bright, front-facing photo per person. A separate file for each role keeps faces from blending.
Photo 1 stays the drummer and photo 2 stays the singer. That fixed casting is the whole point.
Pick portrait or landscape, wait for the job, then save the MP4 with audio.
It runs in your browser. Sign in on this page and generate from the same form.
The room stays recognizable and the two people stay distinct.
Photo 1 becomes the drummer and photo 2 the singer. Separate images keep each look distinct.
The shot holds both people and the back-and-forth between them.
Walls, marks and lighting are part of the template. You only choose who stands there.
Friends, coworkers, a costume beside a plain T-shirt, or one person in two outfits.
If you want a new camera path or a different song, this is the wrong tool.
Watching the preview is free. There is no unlimited free plan. Each finished video uses 26 credits and includes audio. Packs are one-time: pay once, keep the credits, spend them when you want a video.
$0.17 per credit
$8.90USD
$0.15 per credit
$19.90USD
$0.14 per credit
$39.90USD
Unused pack within 7 days: full refund. Credits already spent on a generation are not refunded, and a failed generation returns its 26 credits as credits, not cash. Email support@aptvideo.app with your account email and transaction ID, and we confirm within 2 business days.
Card payments are processed by Waffo Pancake on behalf of apt duo ai, and that is the name you will see on your statement.
By paying you confirm that you are 18 or older and accept the Terms of Service, Privacy Policy, Refund Policy and Acceptable Use Policy. Card payments are processed by Waffo Pancake, and we never store full card numbers.
The original video, downloads, pricing and what this tool does not do.
A two-photo remake in the pink studio: photo 1 plays the drums and photo 2 sings. It is an independent fan-made tool and is not affiliated with ROSÉ, Bruno Mars or their labels.
No. The official APT video is the film by ROSÉ and Bruno Mars. This tool borrows the look of that room for your own cast.
In the song, APT is a greeting that also sounds like "apartment". That is part of why the video is set in a bare pink room.
No. This generator does not add verses on screen. For the words, watch a licensed lyric video.
No. The choreography belongs to the official video. This tool places your photos on those marks; it does not teach the steps.
The pink studio and the two roles. You can choose portrait 9:16 or landscape 16:9, and every export includes audio.
There is no unlimited free plan. Watching the preview and the examples costs nothing. Each finished MP4 uses 26 credits, and the Starter pack covers 2 videos. A failed job gives the credits back.
When a job finishes, choose Download MP4. You get one file with audio in the frame you picked. Signed-in jobs stay waiting if you leave.
It runs in your browser. Sign in, add two photos and generate from this page.
New exports include reference-guided generated native audio, not an identical copy of the original soundtrack. If you swap the track when you publish, use music you have the right to use.
People who have agreed to be featured. Never add photos of minors, and never present a generated clip of a real person as something they filmed.
Most clips are ready within a few minutes. Progress is saved with the job, so you can leave and come back for the file.
Each video uses 26 credits. Packs cost $8.90 for 2 videos, $19.90 for 5 and $39.90 for 11. Every pack is a one-time payment, with no subscription.
Yes. Add two different photos of the same person. A change of outfit or expression makes the pair easier to tell apart.
Videos you generate with paid credits are meant for posting. If any mark applies, the form tells you before you generate, and a failed job never spends your credits.
Two photos, one APT video with audio. Packs start at $8.90.
Create your video