Two performers in one pink studio
The opening places one performer beside the drum kit and the other behind it. Use separate photos to choose both people and keep the roles clear as the scene moves through close-ups and wider views.
APT AI Video Generator
Turn two photos into a pink-studio duet. The sample shows the full performance; Economy and Standard use the opening 15 seconds.
0:00 / —:—
What is APT AI Video?
APT AI Video is a two-person music-video-style scene set in a pink studio. The performance moves from the drum kit to dancing and close-ups together. Choose one photo for each performer and bring your own looks to the sequence.
How to make an APT AI Video
Choose your photos, review the settings and create the prepared scene.
STEP 1
Choose two separate photos
Two separate, clear photos help distinguish the singer and the drummer. A wider photo can give the model more information about each person’s outfit.
STEP 2
Choose a generation mode
Review the available mode, duration and credit estimate in the workspace.
STEP 3
Generate and download
Create the video, then open My creations to play and download it.
APT AI Video in motion
Turn two photos into a playful pink-studio duet, with singing, drums and a shared dance.
From drums to a shared dance
The sequence includes drumming, playful gestures and a dance together. The reference supplies the movement and changing camera views, so you can focus on choosing the people and their looks.
What you choose for APT AI Video
Choose the two performers; the prepared scene provides the pink studio, drums and dance.
Two distinct roles
Assign Photo 1 to the opening singer beside the drums and Photo 2 to the opening drummer. Their positions change during the performance.
A complete look
Face, hair and outfit all come from each photograph. Photos with the shoulders and clothing visible provide more detail than a tightly cropped face.
A studio performance
The prepared clip supplies the camera cuts, pink backdrop, instruments and timing. The exact appearance of these details can vary in the result.
APT AI Video questions
Photos, timing and the prepared performance.
How many photos do I need?
Two separate photos are required: Photo 1 is the opening singer and Photo 2 is the opening drummer.
Can I use a photo of both people together?
Use a separate photo for each performer. That makes it clearer which appearance belongs to each role, including when they share the frame.
What part of the scene changes?
Your photos guide the two performers and their clothing. The studio, drums and performance follow the prepared reference.
How long is the video?
The full reference is about 25 seconds. Shorter modes use a selection from that performance; see the workspace for the current setting.
Can I provide my own singing voice?
The prepared scene uses the reference soundtrack. Uploading a photo does not create a personalized singing voice.
Will the two people look identical to the photos?
Clear images help, but faces, outfits and fine details may vary during close-ups, turns and other movement.
What does it cost?
Choose a mode and review the credit estimate shown in the workspace before creating.
Create your APT AI Video
Turn two photos into a playful pink-studio duet, with singing, drums and a shared dance.