A staggered opening
The dancers begin at different depths in the ornate hall, already moving to the beat. Separate portraits are enough; clothing and body proportions come from the assigned photos, rather than the original dancers.
Upload one photo to dance with yourself, or two photos for a duet. The 15-second dance and original sound are included.
Paid credits required. Check the cost before generating.
Photo 1 replaces the dancer who starts at the back. Add Photo 2 for the dancer who starts in front; with one photo, both dancers look like you.
The 15-second dance reference is included. Add an optional request such as “Keep my glasses”.
Check the credit cost, watch the full result with sound, then download your video.
One photo supplies both dancers as two separate copies of you. With two photos, photo 1 starts at the rear and photo 2 at the front. These opening roles stay assigned even as the dancers move. Both versions use the 15-second hall performance and original sound; you do not need a photo of the pair together.
The dancers begin at different depths in the ornate hall, already moving to the beat. Separate portraits are enough; clothing and body proportions come from the assigned photos, rather than the original dancers.
Pointing, claps, compact punches and arm sweeps carry the middle of the routine. Watch each face when an arm passes in front. Matching outfits can make the two roles harder to distinguish, so review their hair and facial features as well.
The hands rise near the head before the closing accents. Check both bodies remain separate, the feet stay grounded and sound continues through the ending. A new attempt can differ and uses credits; inspect the whole result before requesting another version.
It makes a 15-second duet following the included Mi Chico dance. One photo casts you in both roles; two photos give each dancer a separate identity.
No. Add one or two person photos. The movement reference and prompt are included; your optional instructions are appended.
Yes, when sound is enabled. The original first-15-second audio is attached to the generated video. It does not clone your voice.
Movement timing, facial details and lip-sync can differ. Watch the full example and review your result before sharing.