Prompt

Real life realistic smartphone video, not animation, not CGI. Vertical 9:16, cinematic lighting, shallow depth of field, photorealistic fur and textures — mimics high-end AI film (e.g., Sora v2), presented as accidental footage. Scene: Retro living room — vibrant orange shag rug, warm wood-paneled walls, amber table lamp, mustard-yellow armchair in background. Characters: One hyper-realistic domestic cat with full feline anatomy — short dense fluffy fur, calico pattern (distinct orange/black/white patches), white chest/paws, pink nose, large green eyes, no human traits. Cat is young adult (~1 year), sitting upright on hind legs, wearing a sleek black leather harness (snug but not tight). A miniature wooden accordion (brown body, red bellows, white buttons) rests on its lap, held securely by front paws (pads pressing, claws sheathed). Action: 0:00–0:01: Calico cat stares ahead, ears perked, tail curled beside body. 0:01–0:02: Gently compresses accordion bellows with both front paws — red pleats expand/contract smoothly. 0:02–0:03: Left paw presses a button; right paw stabilizes instrument. Eyes narrow in concentration. 0:03–0:04: Bellows pulse rhythmically — cat’s head bobs slightly in time (natural reflex, not dance). 0:04–0:05: Opens mouth in soft meow — tongue visible — as if singing along. 0:05–0:06: Continues playing, fur ruffling slightly from movement. 0:06–0:07: Glances at camera, blinks slowly, keeps playing. 0:07–0:08: Bellows expand fully; cat holds pose, proud expression. 0:08–0:09: Releases pressure, accordion settles. 0:09–0:10: Final frame: calico cat sitting upright, accordion in lap, eyes bright, harness gleaming — serene maestro. Visual style: Photorealistic fur (individual guard hairs), accurate eye refraction, natural leather/fabric texture, realistic accordion physics. The upright posture is brief and supported by haunch engagement (plausible for confident cats in staged shots). Audio: ONLY soft accordion bellows whoosh, calico’s gentle meow, light paw tap on button, quiet breathing

Result

Real life realistic smartphone video, not animation, not CGI. Vertical 9:16, cinematic lighting, shallow depth of fie...

Settings

Reference images