Choose who solos first
Photo 2 takes the first foreground solo; Photo 1 begins the handover second.
The library duo opens together; the opening-right dancer solos first before the opening-left dancer takes over near the end of this 15-second cut.
Ba Ba Ba Dance AI casts two adults in the library routine. They begin side by side, the opening-right dancer takes the foreground first and the opening-left dancer returns to take over.
Put the person who should solo first in Photo 2. Photo 1 belongs to the adult who opens on the left and starts the second solo near the end of this selected cut. The same identities follow their performers as they move across the frame.
This version uses the first 15 seconds at the reference’s original pace. It includes the opening, first solo and handover; it does not continue through the later second solo or final reunion.
The shelves, counter and angular ceiling lights remain around the dancers. The scene keeps the source camera, pauses and changes in how close each person is to the lens.
Each photo supplies that adult’s face, hair, build and visible outfit. The cap, camouflage jacket and headphones in the example identify the original parts; they are not required costumes for your portraits.
The download includes the recording from this same 15-second window. It does not offer a song picker, longer 30-second performance or a separate video of just one dancer.
Photo 2 takes the first foreground solo; Photo 1 begins the handover second.
Separate photos supply each adult’s own appearance and clothing.
Download the 15-second vertical MP 4 with its matching reference sound.
Use one adult per image, with a clear face and the clothing you want in the video.
Assign opening-left/second to Photo 1 and opening-right/first to Photo 2, then confirm consent.
Review both faces as the foreground changes, then download the MP 4 with sound.
Photo 2 starts on the viewer’s right and takes the first solo. Photo 1 starts left and begins the second part near the end of the selected cut.
Two separate adult photos are required, one for each dancer. There is no missing-partner or one-photo twin mode in this version.
This version uses only the first 15 seconds. It includes the opening, the first solo and the beginning of the second dancer’s handover, ending before the later second solo and final reunion.
Each photo supplies that person’s visible clothes, identity, hair and body appearance. The library and choreography remain from the reference.
This version uses two adults in the fixed library scene. It has no pet, background-upload or soundtrack-selection input.
The download uses the original recording from the same selected 15-second window. It does not generate new vocals or change the sound according to the photos.
One 15-second 9:16 video at 720p uses 10 ReelTada credits. Your live balance is checked before photos are uploaded or generation starts.
Start side by side in the library, then trade the foreground. Two adult photos follow the opening groove, the right dancer’s solo and the left dancer’s handover.