Premium Black-and-White Cat Commercial VIDEO Breakdown (Prompts Included)
Recreating this premium black-and-white cat commercial works best when the identity reference is treated as the highest-priority source for the featured cat. Follow every shot boundary exactly, keep each typography line inside its assigned shot, and maintain the fixed left-to-right outfit order in the five-cat presentation. The original source included conflicting shot-heading times, so this tutorial normalizes the final prompt to the mandatory 15.069-second timeline.
Step 1
Open pollo.ai, select Image Generation, paste the image prompt below and click Generate. Set GPT Image 2.5 as the default image model. Adjust the aspect ratio according to your video needs; multiple sizes including 16:9 and 9:16 are supported.
Image Prompt
British short haired black and white cat, with a relatively large head, soft and cute, 8-month-old kitten, fluffy fur, white background, front sitting posture, smartphone shooting texture
Step 2
Once your image is ready, go to Video Generation. Upload your prepared image or pick assets from your Creations library. Select reference-to-video mode and paste your video prompt. You can also upload a video for motion reference.
Note: Add @your-image for image reference and @your-video for video reference inside the prompt. Pick any of these models: Seedance 2.5, Seedance 2.0, MiniMax H3 or Wan 3.0. Click Generate after confirming all settings.
Video Prompt: Premium Black-and-White Cat Studio Commercial
PROMPT HEADER:
Create a 15.069-second, 16:9 horizontal live-action premium pet commercial.
REFERENCE AND IDENTITY:
Use [@Image 1] as the only identity reference.
The subject is a black-and-white shorthair cat with a round face, large amber-brown eyes, pink nose, white muzzle and chest, black ears and crown, symmetrical dark facial patches, compact body, sturdy white front legs, rounded paws, and a thick dark tail.
The cat should feel like a soft, cute 8-month-old British Shorthair-style kitten with a relatively large head, plush fur, a white background reference, a frontal seated pose, and a realistic smartphone-photo texture.
Preserve the same face, markings, eye color, fur texture, body proportions, compact build, chest shape, paw shape, and tail throughout. Do not reference any video or music. Follow the exact timing below so the finished video can later be aligned to an external soundtrack. Never shift cut points, merge shots, or reorder actions.
GLOBAL STYLE:
Use real high-end pet advertising photographed in a physical white studio. Create a seamless warm-white cyclorama, clean satin floor, faint reflections, soft contact shadows, bright diffused softboxes, realistic short fur, individual whiskers, moist eyes, natural catchlights, believable depth of field, and accurate motion blur.
Keep true feline anatomy and realistic body weight. Do not use cartoon styling, illustration, plastic CGI, human-like limbs, or upright human standing. Use clean hard cuts.
Only English may appear. Do not include Chinese, logos, or watermarks.
TYPOGRAPHY:
Use clean modern medium-bold sans-serif typography in muted teal or slate blue. Use only the following text:
- “Big on Cute.”
- “Cute. Refined.”
- “Take Joy With You.”
- “Find Your Favorite.”
Do not add any other readable text.
SHOT 1 — 0.000–1.100 SECONDS:
Use an extreme macro shot showing only the top of the cat’s head and both ears. The eyes stay completely below the frame.
Warm rear-side light creates a delicate rim on the black ear edges and crown fur while the front remains cooler. Preserve the black crown pattern visible in [@Image 1].
Show one tiny ear twitch and an almost imperceptible head shift. Keep the camera nearly locked with a slow micro push-in. No text.
Hard cut exactly at 1.100 seconds.
SHOT 2 — 1.100–2.567 SECONDS:
Use a frontal close-up. The cat looks directly toward the camera with both white front paws raised toward the lens, one paw slightly closer.
From 1.100–1.450 seconds, let the face and paws dominate the frame.
From 1.450–1.850 seconds, perform a fast smooth dolly backward revealing the white chest and upper body.
From 1.850–2.050 seconds, reveal the full cat seated upright on its haunches, hind paws grounded, chest forward, front paws lifted loosely near the chest, and dark tail lying toward screen left or naturally beside the body.
From 2.050–2.567 seconds, stop and hold the centered full-body hero pose.
Preserve the round amber eyes, pink nose, and distinctive black-and-white facial pattern from [@Image 1]. Display “Big on Cute.” at the upper center.
Hard cut exactly at 2.567 seconds.
SHOT 3 — 2.567–3.367 SECONDS:
Use a tight side-profile action shot. The cat performs one natural horizontal feline leap from screen left to screen right.
The head faces right, front legs extend forward, hind legs trail, and the thick tail follows behind. Use subtle slow motion.
The camera makes only a small parallel rightward tracking move. Keep real body weight, launch trajectory, paw placement, and natural short-fur motion. No text.
Hard cut exactly at 3.367 seconds.
SHOT 4 — 3.367–5.067 SECONDS:
Use a mostly empty white frame with the camera nearly fixed. The cat begins outside the far right edge and slowly peeks in: first the black ear, then one amber eye and part of the cheek, then progressively more until the full round face occupies the right half.
Preserve the exact black crown, white blaze, white muzzle, amber eyes, and pink nose from [@Image 1]. The cat moves slightly closer and gives one tiny curious head tilt.
Keep the left half open. Display “Cute. Refined.” at left-center.
Hard cut exactly at 5.067 seconds.
SHOT 5 — 5.067–5.833 SECONDS:
Use a very low close-up of the white chest, front legs, and white paws. Keep the head mostly outside the frame.
The cat takes one deliberate forward step: one front paw lifts, moves forward, lowers, contacts the floor, compresses slightly, and accepts weight while the other paw supports.
Show toe fur, shifting contact shadow, faint reflection, and subtle body-weight transfer. Keep “Cute. Refined.” at left-center and fade it before the cut.
Hard cut exactly at 5.833 seconds.
SHOT 6 — 5.833–7.033 SECONDS:
Use a medium fixed shot. On screen right, show only the torso and hands of an adult in a tan cotton trench coat. Never show the face.
The coat has realistic texture, seams, buttons, folds, and a roomy side pocket. The black-and-white cat is partially nestled in or beside the pocket area with head, white chest, and front paws visible.
A hand supports the body from underneath and gently lifts it upward and slightly outward. Keep realistic scale and weight. Hindquarters remain supported and legs hang naturally. Leave large white negative space on the left.
Display “Take Joy With You.” at left-center.
Hard cut exactly at 7.033 seconds.
SHOT 7 — 7.033–8.200 SECONDS:
Use a closer frontal portrait of the supported cat on the right half. One hand remains beneath the body.
A second hand enters from the upper right and slowly strokes from the forehead backward over the black crown. Fingers softly compress the short fur.
The cat starts with eyes open, briefly narrows or closes them during the stroke, then opens them and looks calmly toward the camera. Add a tiny ear response and whisker shift.
Keep “Take Joy With You.” stable on the left. The camera remains fixed.
Hard cut exactly at 8.200 seconds.
SHOT 8 — 8.200–10.067 SECONDS:
Use a fixed, balanced two-cat profile composition. Show two matching black-and-white cats from the same visual family as [@Image 1], with comparable mask patterns and amber eyes.
The left cat wears a pale blue-and-white striped fitted pet shirt, small dark bow tie, and short black cape with dark red lining.
The right cat wears a dark navy formal pet outfit, crisp white collar, burgundy neck detail, and short black cape with rich red lining and a slightly raised collar.
Garments look physical, with realistic thickness, seams, folds, and fur compression.
At 8.200 seconds, the cats are separated on opposite sides.
From 8.200–8.900 seconds, they move toward center.
From 8.900–9.300 seconds, their noses approach.
From 9.300–9.700 seconds, they gently touch pink noses and hold.
From 9.700–10.067 seconds, they ease apart slightly while staying close.
Keep natural feline posture and separate whiskers. Supporting hands may barely appear at the lower edge. No text.
Hard cut exactly at 10.067 seconds.
SHOT 9 — 10.067–13.633 SECONDS:
Use a wide frontal group shot with exactly five black-and-white cats sharing the same facial family, coat pattern, amber eyes, and compact proportions as [@Image 1].
Keep this fixed left-to-right outfit order:
- Pale blue striped shirt, dark bow tie, short black cape with red lining.
- Bright yellow duck-inspired hooded jacket with a small soft orange bill.
- Center cat in a dark navy formal outfit, white collar, burgundy neck detail, and black cape with rich red lining.
- Dark green varsity-style jacket with pale trim and a playful dinosaur-inspired hood with small soft rounded spikes.
- Transparent clear raincoat with matching translucent hood, visible seams and fasteners, with fur visible through it.
Use no branding. Display “Find Your Favorite.” at the upper center. Keep the camera fixed.
From 10.067–10.900 seconds, the five cats appear in elevated presentation poses, with the center cat slightly forward. Front paws lift, hind legs partly tuck at different angles, tails balance naturally, and capes or hoods react to movement. Do not clone identical poses. Keep the scene like live-action animal photography.
From 10.900–11.800 seconds, all five descend, paws visibly reconnect with the floor, and the group begins moving forward. Contact shadows strengthen. Maintain exact outfit order.
From 11.800–12.700 seconds, all five advance toward the camera with one or two small coordinated feline steps. They become slightly larger because they physically approach; do not zoom. Tails rise naturally and clothing reacts with believable secondary motion. Preserve realistic short cat legs and compact bodies.
From 12.700–13.200 seconds, the five cats settle into a clean frontal row in the same order, slow to a stop, and prepare to sit. Keep every outfit readable.
From 13.200–13.633 seconds, all five sit on their haunches in a compact synchronized motion and hold a front-facing presentation pose. Front paws may lift slightly near chest height, but they remain anatomically feline and seated. Let capes, hoods, and raincoat settle naturally. Keep “Find Your Favorite.” visible.
Hard cut exactly at 13.633 seconds.
SHOT 10 — 13.633–15.069 SECONDS:
Hard cut to the original unclothed black-and-white cat matching [@Image 1], alone in the white studio. Show the full body in a frontal seated pose near the lower center.
Preserve the round face, amber eyes, pink nose, black crown and ears, white chest, sturdy white forelegs, rounded white paws, and dark tail.
The cat remains almost completely still with only one tiny head adjustment, blink, or eye movement. The camera is fully locked.
No text, logo, additional animal, or human. End exactly at 15.069 seconds.
ABSOLUTE TIMELINE:
0.000–1.100 / 1.100–2.567 / 2.567–3.367 / 3.367–5.067 / 5.067–5.833 / 5.833–7.033 / 7.033–8.200 / 8.200–10.067 / 10.067–13.633 / 13.633–15.069.
Every boundary is mandatory. Do not shift, merge, shorten, or extend any shot.
FINAL PRIORITY:
Prioritize exact timing, exact shot order, consistent black-and-white cat identity, believable live-action fur and feline anatomy, restrained camera movement, white-studio advertising style, stable costume continuity, and English-only typography.
NEGATIVE PROMPT:
timing drift, shifted cut points, merged shots, missing shots, extra shots, changed shot order, changed black-and-white cat identity, changed mask pattern, changed amber eyes, changed pink nose, changed crown marking, long fur, plastic fur, cartoon cat, illustration, human-like limbs, upright human standing, extra paws, duplicated cats, missing outfit, wrong outfit order, duplicated outfit, extra animals, visible human face, extra hands, distorted hands, broken anatomy, floating paws, unrealistic leap, unstable white studio, dirty background, harsh shadows, changing text, Chinese text, misspelled text, extra text, logos, watermarks, subtitles outside the specified copy, music reference, background music, added SFX, camera shake, random zoom, low resolution, CGI render