Pet fridge tiramisu heist — English R1

Video reference

Draft title: Pet fridge tiramisu heist — English R1

Watch external video ↗ · Playback is available at the source.

Reconstructed prompt

Reconstructed from the video, not the author's prompt. This draft has not been generation-tested. Results vary by model and photo.

FORMAT: 9:16 vertical, 10s single-shot video.

REFERENCE ROLES: @Image1 is the sole primary character (cat matching the reference coat and markings inside refrigerator).

SOUNDTRACK SPECIFICATION:
Target 105 BPM, 4/4 comedic lo-fi bounce. Soft kick, chilled keys, light munching foley. Vocal: Playful comedic English rap monologue with slight pitch shift.

SCENE AND CAMERA:
Interior refrigerator shot looking in, cool white overhead fridge lighting, slight wide lens. Steady low-angle facing @Image1 sitting upright behind a metal baking pan.

ORIGINAL LYRICS:
0.0 - 2.5: Cold fridge light, sweet delight.
2.5 - 5.0: Mom said wait, took a bite.
5.0 - 7.5: Cream so soft, spoon so deep.
7.5 - 10.0: Empty pan, back to sleep.

PERFORMANCE TARGETS:
0.0 - 2.5: @Image1 holds a metal spoon over the tiramisu, eyes wide, mouth articulates intro line.
2.5 - 5.0: Scoops a chunk from the tray, brings spoon to mouth, jaw chews to beat.
5.0 - 7.5: Rapidly scrapes the bottom corners, delivering lyrics with rhythmic head bobs.
7.5 - 10.0: Displays the empty pan, takes final lick off the spoon, blinks innocently.

PRIORITY:
Preserve @Image1 facial markings and fur texture; ensure feline jaw movement is stylized without human teeth.

EXCLUSIONS:
No human hands visible, no identity morphing, no extra limbs, no on-screen text or logos.

INPUT AND AUDIO BOUNDARY: @Image1 is the sole uploaded photo; no other image, audio or video reference. Preserve the uploaded person/pet identity, hair or fur markings and body proportions, or the reference object’s geometry and materials; do not copy another performer’s identifying appearance. Generic supporting figures are distinct. All BPM, instrumentation and lyrics are newly authored targets, not measurements or quotations of the source. Generate original audio, never clone source music, melody or a named voice. Lips match the generated vocal exactly, never precede it; during instrumental sections the mouth stays relaxed. If the input is a pet use stylized jaw articulation only, never human lips or human teeth. No recognizable copyrighted character appearance, text, logos or watermarks. Do not change the input subject’s gender or age. No generation has been tested.

Copy prompt