Smalltown Boy AIVideo generator
Make a Smalltown Boy AI duet from two pet photos.
Choose who goes first.
JPG, PNG or WebP · Up to 8 MB each
10 seconds · Portrait · With sound
Uses paid credits. Review credits before generating.
Two new pets.
The familiar switch.
A ginger cat and Shiba take the two roles in this Clico example.
Keep the reaction
and the switch.
Clico uses the reference for both pets’ moves and the cut.
Watch the source and example together, at normal speed.
Start with the pets
you want in the video.
The reference and role instructions are included.
You don’t need to film or describe the moves.
JPG, PNG or WebP · Up to 8 MB each
10 seconds · Portrait · With sound
Uses paid credits. Review credits before generating.
Choose each pet’s part
Photo one goes first. Photo two dances behind, then takes the next close-up.
Use two clear pet photos. Upload or change them here or at the top.
Review your draft in Clico
Open template in Clico. Both photos and the built-in scene travel together.
Sign in if needed. Review the photos and credit cost, then click Send to generate.
Watch the switch and download
Check both pets’ faces, the paw movement, the switch and the sound in your finished video.
Download the MP4 or continue with the AI video editor.
Smalltown Boy AI
questions
How many photos do I need?
Upload two separate photos, one pet in each.
Use a clear face and show the body where possible.
Which pet takes the first close-up?
The first photo replaces the pet nearest the camera at the start.
The second starts dancing behind, then takes the next close-up.
Do I need to write a prompt or film the dance?
No.
The reference, role instructions and starting settings are included.
Add your two pet photos to open the draft.
Which Smalltown Boy version does this make?
This is the ten-second red-fence cat-duet excerpt shown at the top.
It ends during the second close-up, before the longer dance finale.
Does the video include sound?
Yes.
It keeps the built-in reference excerpt’s soundtrack and timing.
It does not add new barking, meowing or dialogue.
What kind of pet photos work best?
Use a clear, unobstructed face and one pet per photo.
Avoid heavy motion blur or another animal covering the face.
Will both pets look exactly the same in every frame?
Results vary with the photos.
Paws near faces, wide-angle close-ups and the switch can affect identity, clothing and movement.
What format will I receive?
A ten-second portrait MP4 at 720 × 1280.
Download it or continue editing in Clico.
Can I generate the duet for free?
Video creation uses paid credits.
Open the template in Clico to review both photos and the credit cost.
Try another
familiar scene.
Start with a different performance and the photos it needs.
Make your
Smalltown Boy AI duet.
Start with two pet photos, one for each role.