Prompt

Create a photoreal vertical 9:16 smartphone POV video (about 15 seconds) filmed in a bright pet-supply store aisle. The camera is handheld with slight natural shake, positioned behind a metal shopping cart, angled slightly downward into the cart. The cart is filled with several tall colorful pet food bags (generic designs, no readable brands), forming a cozy nest. Inside the cart sits a large black-and-tan Rottweiler, calm and stoic. Standing confidently with its front paws on the Rottweiler’s head is a tiny tan chihuahua wearing a bright yellow hoodie with white drawstrings (same look as reference), giving a “tiny boss” expression. The chihuahua is clutching a small teal treat bag tightly to its chest. At ~1.5 seconds, a human hand enters from the right side and gently grabs the treat bag, tugging it upward/right. The chihuahua instantly reacts with a dramatic bark/yelp, eyes wide, mouth open, trying to hold on. As the bag is pulled, the chihuahua loses balance and flops backward into the pet food bags, paws flailing comically. The Rottweiler remains steady and patient, barely reacting except a small eye movement. From ~6–12 seconds, the chihuahua is mostly hidden behind the tall bags, occasionally peeking out. At the end (~13–15 seconds), the chihuahua pops back up between the bags (still in the yellow hoodie), climbs back to place paws on the Rottweiler’s head again, and gives one final funny bark/exclamation to finish. Style notes: real-life phone video, natural fluorescent store lighting, slight background blur, autofocus on the dogs and treat bag, one continuous shot, no captions, no watermark, no logos.

Result

Create a photoreal vertical 9:16 smartphone POV video (about 15 seconds) filmed in a bright pet-supply store aisle. T...

Settings