Smalltown Boy sample: from two images to a dance video

See the fictional cat and dog input images and the 14-second 720p demonstration. The original song was added after generation.

Updated October 13, 2026.

This is the published fictional cat-and-dog demonstration, made with Wan 3.0. The video is 14 seconds, 720 × 1280 pixels and vertical 9:16. The original soundtrack was added after generation. It is a product demonstration, not a customer review or a guarantee of the result from your photos.

The input images and finished demonstration

Photo A — fictional character for the opening reaction

Photo B — fictional character for the background dancer

Published demonstration with original music added in postproduction. Customer deliveries use generated audio, which may differ. Play with sound to hear the edited sample.

What you can inspect here

Compare the two input subjects with the close-ups and the moving figures. Watch the opening reaction, the partner dancing behind and the ending. Look for changes in face shape, markings, paws, clothing and movement. This lets you judge this specific sample instead of relying on a thumbnail.

The photos supply the identities. A fixed red-fence reference supplies the movement and timing; the studio does not ask you to write a prompt or upload that reference.

Before you try your photos

This demonstration uses fictional characters and an edited soundtrack. Your photos can produce different faces, motion and AI-generated audio. We do not guarantee identical details in every frame, watermark-free output or a fixed completion time. The homepage inspiration gallery is separate from our delivery samples.

Make an informed first attempt

Read the photo preparation guide, inspect current prices, and follow the two-photo steps. Opening the studio does not start a generation; you choose and confirm your own photos and review the cost there.

Choose your own photos · All guides · Ask about the sample