Two pets
One pet with face, coat and whole body clear. A second pet photographed alone with face, coat and body visible.
The first pet dances upright by the bed while the foreground pet holds a phone, films, bounces and kicks to the beat.
The first pet dances upright by the bed while the foreground pet holds a phone, films, bounces and kicks to the beat.
The two pet photos guide the dancer and filmer identities; the bedroom, phone, choreography, framing and timing come from the reference.
The selected reference runs 15.09 seconds at original speed and keeps its complete shot window.
The first pet dances upright by the bed while the foreground pet holds a phone, films, bounces and kicks to the beat.
The two pet photos guide the dancer and filmer identities; the bedroom, phone, choreography, framing and timing come from the reference.
The output follows the actual 540 × 936 reference framing rather than stretching a different crop.
Visual generation is silent. After the media checks pass, the AAC track from the same locked reference snapshot is restored.
One pet with face, coat and whole body clear. A second pet photographed alone with face, coat and body visible.
The first pet dances upright by the bed while the foreground pet holds a phone, films, bounces and kicks to the beat.
Download the full 15.09 seconds scene with the selected reference audio.
One pet with face, coat and whole body clear. A second pet photographed alone with face, coat and body visible.
Confirm photo permission, then create the prepared scene for 10 credits.
Check identity, role order, motion, prop contact, framing and sound before saving.
Two pets: One pet with face, coat and whole body clear. A second pet photographed alone with face, coat and body visible.
The first pet dances upright by the bed while the foreground pet holds a phone, films, bounces and kicks to the beat.
No. The locked reference supplies the setting, camera, fixed props and shot order.
The two pet photos guide the dancer and filmer identities; the bedroom, phone, choreography, framing and timing come from the reference.
Yes. Audio is restored from the same selected reference snapshot after silent visual generation. There is no replacement-audio upload.
One generation uses 10 ReelTada credits and targets a 15.09 seconds vertical MP4 at 720p. Your balance is checked before upload and generation.
Two pets, the complete 15.09 seconds scene and selected reference audio.