Loading page…
Loading page…
Upload two photos and create the viral Smalltown Boy duo dance video.
Image 1 replaces the curly-haired dancer in the purple shirt, closest to the camera at the opening. Image 2 replaces the mustached dancer in the red-and-black plaid shirt behind them. Use one clear person or pet per JPEG, PNG or WebP photo, up to 10 MB each.
Choose the first 12 seconds, or the full 21-second performance. Select 480p or 720p, keep the original frame or choose a crop, and check the displayed credits before confirming.
Your private MP4 follows the selected source segment and receives that segment’s original audio. Check both identities as they exchange positions, lean toward the camera and overlap, then download your video.
The public preview shows an orange cat and a black-and-white cat performing the dance. The orange cat illustrates Image 1’s role; the black-and-white cat illustrates Image 2’s role. Their positions change during the sequence, so each photo follows a character rather than a fixed side of the screen.
The demonstration has its own vertical 720 × 1280 frame and soundtrack. Generation uses a separate, private 560 × 752 two-person performance lasting exactly 21 seconds. The downloaded result follows your chosen source segment and its audio. The cat demonstration is a preview of the effect, not a result generated with your uploaded photos.
Yes. You can assign a clear person or pet photo to each role. For a pet, show its face, ears, fur and distinctive markings clearly. The model is instructed to keep each character recognizable; anatomy, gestures and fine details may vary between generations.
The performers change positions in the source. Image 1 stays assigned to the character who opens in the foreground wearing purple; Image 2 stays assigned to the character who opens behind them in plaid. Review the result for identity changes during close-ups and overlaps.
The studio plays the full cat demonstration for every length. The selected duration controls your generation and credit quote: 12 seconds is the opening segment of the private dance source, while 21 seconds covers the full performance.
Original keeps the full 560 × 752 source composition. Square and 9:16 options are centered crops and may remove hands, feet or a character near the edge. The cat demonstration uses a different frame, so its edges do not show the exact crop of your result.
You can watch the demonstration for free. Generating a video uses credits; the studio shows the quote for your chosen length and resolution before you confirm. Compare video credit rates.
This template uses its prepared performance. Upload two character photos and obtain permission to use any person’s likeness. A parent or legal guardian must authorize the use of a minor’s photo.