Photos define the subjects
Keep the face, hair, body appearance and visible outfit from each uploaded photo. Pet modes preserve the animal’s fur, ears, markings and paws.
Sweep both arms out and upward, place the hands behind and above the head, lift a knee into a forward kick, then continue the body roll and hip sways through the final pose. Keep the full 15-second sequence at original speed in one continuous vertical shot.
The LISA Tarantino dance brings broad arm sweeps, an overhead pose and a knee lift into a compact vertical clip. This template follows the reference’s complete 15-second window, keeping the body roll and hip sways in their original order.
Solo and pet modes use the single-performer reference. Duo builds a two-adult performance from two separate photos, with the same routine and soundtrack. Each uploaded image supplies the subject’s face, hair or fur, body appearance and visible clothing; the photo’s pose and background are ignored.
Sweep both arms out and upward, place the hands behind and above the head, lift a knee into a forward kick, then continue the body roll and hip sways through the final pose. Keep the full 15-second sequence at original speed in one continuous vertical shot.
The output is a vertical 9:16 video lasting 15 seconds. The source is kept at its original speed, with no artificial slow motion or stretched choreography. The soundtrack comes from this exact reference clip.
Keep the face, hair, body appearance and visible outfit from each uploaded photo. Pet modes preserve the animal’s fur, ears, markings and paws.
The video uses the indoor doorway with the plain room and doorframe. Photo backgrounds are ignored; there is no separate scene upload.
The original audio from the selected reference is restored after video generation. There is no music picker or replacement song.
Choose your cast, then add one clear photo for each required slot. In two-photo modes, photo 1 is the opening-left subject and photo 2 is the opening-right subject.
Review the choreography preview and cast order. Confirm you have permission to use the photos, then generate for 10 credits.
Check the subjects, movement and ending, then download the vertical MP4. Keep your permissions and soundtrack rights in mind when sharing.
Solo and Your pet use one photo; Duo uses two separate adult photos.
For two-photo modes, photo 1 belongs to the opening-left performer and photo 2 to the opening-right performer. The identities remain assigned to those roles as the subjects move.
No. This template uses the indoor doorway with the plain room and doorframe. Your photo background is ignored.
Yes. The uploaded photo supplies the subject’s visible clothing and appearance. Use a photo wearing the outfit you want; do not rely on the reference costume.
The clip lasts 15 seconds in a vertical 9:16 frame. It follows the selected reference window at original speed.
Yes. The original audio from the selected reference is restored to the generated video. There is no replacement music selector.
The preview shows the single-performer source. Duo is reconstructed as two adults from your separate photos, using the same routine and soundtrack.
Each generation costs 10 credits. Sign in to generate; if you need more credits, choose an available credit pack.
Choose Your pet for one animal.
Use photos you own or have permission to use, and only consenting adults for human roles. Obtain the necessary permissions for the images, likenesses and soundtrack before publishing.
Choose the photos and review the routine before generating.