Photorealistic Diner Cat Comedy VIDEO Breakdown (Prompts Included)
Recreating this photorealistic diner cat comedy video works best when the seating layout and prop count are established before the dialogue begins. Use a fixed front three-quarter camera at the orange cat’s eye level, keep the two booths visibly separated, and describe each payment attempt as a single readable action. The final joke works only when the gray tabby pays successfully and then takes the entire plate back for itself.
Text-to-Video Workflow
Open pollo.ai and select Video Generation, then choose the Text-to-Video mode. Paste your full video prompt, set your preferred video duration and aspect ratio. Select any one of these models: Seedance 2.5, Seedance 2.0, MiniMax H3 or Wan 3.0. Click generate once all settings are confirmed.
Video Generation Screen
Video Prompt: The Cat’s Declined Dinner
PROMPT HEADER:
Create a 10-second vertical 9:16 ultra-photorealistic comedic animal video in one continuous shot. Set it inside a classic American diner during daytime, with burgundy-red vinyl booths, beige laminate tables, black-and-cream checkerboard flooring, large windows on the right, warm round ceiling lamps, and a softly blurred diner counter in the distance.
Use realistic phone-camera texture, natural daylight mixed with warm practical light, detailed natural fur, and subtle handheld movement. Use a fixed front three-quarter camera at the orange cat’s seated eye level. No cuts, transitions, or sudden camera changes.
SEATING LAYOUT:
At the beginning, the two cats are seated in two completely separate diner booths. The orange cat sits alone in the nearest foreground booth at the round table closest to the camera. The gray tabby sits alone in a different booth one full row behind the orange cat.
A tall red vinyl seatback and a clearly visible strip of aisle must separate the two booths. The cats must never appear seated side by side or sharing the same seat or table. The gray tabby remains visibly farther from the camera until it gets up and walks forward.
CHARACTERS:
The main customer is exactly one realistic chubby orange-and-white British-Shorthair-like cat. It has dense orange tabby fur, a white muzzle, a white chest, two white front paws, a round face, and a slightly serious expression. It sits upright in the foreground booth like a human while remaining fully feline. Its voice is a slightly anxious young adult male voice.
The second character is exactly one realistic gray-brown tabby cat with a white muzzle, white chest, and white paws. It begins seated in the separate rear booth, one full booth row behind the orange cat. Its voice is a calm, dry adult male voice.
Maintain the same identities, fur markings, body sizes, and positions throughout. A human diner server wears a plain black long-sleeve uniform. Only the server’s torso, arms, and two hands enter from screen right. The server has a polite adult female voice. Never generate the server’s face or additional limbs.
Keep both cats fully feline and photorealistic, with real cat heads, fur, paws, and anatomy. Their upright posture and gestures can be gently anthropomorphic, but do not give them human hands, clothing, or human bodies. When speaking, use extremely subtle natural jaw and mouth movement without exaggerated human lips or cartoon facial deformation.
0.0–1.2 SECONDS:
Start with the orange cat already sitting alone in the foreground booth, with both front paws resting near the edge of its empty round table. In the background, the gray tabby is clearly visible sitting alone at a different table in the next booth row, separated by the red booth backrest and aisle. The gray cat quietly watches from a distance.
The server enters from screen right carrying exactly one white ceramic oval plate holding one whole golden-brown roasted chicken. She places it in the center of the orange cat’s table and says warmly:
SERVER: “Here’s your roast chicken.”
The orange cat stares eagerly at the crispy chicken. The plate makes a soft ceramic sound when it touches the table.
1.2–2.7 SECONDS:
The server raises exactly one small black handheld payment terminal in front of the orange cat, with the screen facing both the cat and the camera. The orange cat produces exactly one green bank card with one front paw and says confidently:
ORANGE CAT: “Put it on this.”
It taps the green card once against the terminal. After a brief pause, the terminal screen shows one large red X completely contained inside the screen and makes a sharp rejection beep.
SERVER: “Declined.”
The orange cat freezes and glances awkwardly at the terminal. The green card must not multiply, float, or change color.
2.7–4.7 SECONDS:
The orange cat lowers the green card and presents exactly one different red bank card.
ORANGE CAT: “Try this one.”
It taps the red card once. The terminal again shows one clear red X and produces a second rejection beep.
SERVER: “Declined again.”
The orange cat’s ears tilt outward. It looks embarrassed and disappointed while glancing between the server and the untouched roast chicken. Do not allow the orange cat to begin eating.
4.7–6.7 SECONDS:
The gray tabby notices the problem from its separate rear booth. It stands, steps out of its booth into the aisle, and walks forward toward the orange cat’s table. Show this short physical movement clearly. The gray tabby must not teleport from the rear booth.
The gray tabby stops beside the foreground table, presents exactly one dark charcoal-gray bank card, and says calmly:
GRAY TABBY: “I’ve got it.”
It taps the terminal once. The terminal immediately changes from the red X to one bright green check mark completely contained inside its screen. A pleasant approval chime plays.
SERVER: “Approved.”
The orange cat turns toward the gray tabby with visible relief.
ORANGE CAT: “Oh, thank you!”
6.7–9.2 SECONDS:
After a short comedic pause, the gray tabby does not give the meal to the orange cat. Instead, it places both front paws firmly on opposite sides of the white plate, slides the entire plate away from the orange cat, and carefully lifts the plate with the single roast chicken against its chest.
The gray tabby delivers the punchline in the same calm, dry voice:
GRAY TABBY: “I was buying it for me.”
The gray tabby turns toward screen right and begins carrying the entire plate back toward its own rear booth. Keep the plate horizontal and keep the roast chicken securely on the same plate. The food must not fall, disappear, or duplicate.
The orange cat freezes in disbelief, then raises one empty white paw toward the departing gray tabby and protests:
ORANGE CAT: “Hey! That’s mine!”
9.2–10.0 SECONDS:
The gray tabby continues walking toward its separate rear booth, gradually showing its back to the camera. The orange cat remains seated alone at the now-empty foreground table, with one paw extended and an offended, betrayed expression.
End immediately on the orange cat’s reaction without a fade, title card, or additional action.
AUDIO:
Use natural diner room tone, faint dishes, distant conversation, a ceramic plate sound, two different payment rejection beeps, one approval chime, soft paw movement, and plate-sliding sounds.
Add very light playful comedy music underneath, becoming slightly more noticeable during the final reveal. Dialogue must remain clear and finish before the video ends. No narrator and no subtitles.
CONTINUITY RULES:
Maintain exactly two cats, two separate booths, one server, one payment terminal, one plate, one roast chicken, one green card, one red card, and one charcoal-gray card.
Each card appears only during its designated attempt. Maintain correct eye-lines toward the food, card reader, and other cat. The terminal always stays in the server’s hand. The gray tabby must physically leave the rear booth and walk to the foreground table before paying.
STRICT NEGATIVE CONSTRAINTS:
no shared booth at the beginning, no cats sitting beside each other, no same-table opening, no gray cat already standing beside the orange cat, no teleportation, no extra cats, no duplicated cats, no extra paws, no human hands on cats, no deformed anatomy, no floating cards, no card morphing, no multiple terminals, no duplicate plates, no duplicate chicken, no eating before payment, no sliced chicken, no cartoon style, no Pixar style, no plastic CGI fur, no exaggerated talking mouths, no subtitles, no text overlays, no watermark, no logos, no cuts, no zooms, no slow motion, no chaotic camera shake.
Final Summary
Create a 10-second vertical photorealistic animal comedy video set inside a classic American diner. Keep two cats in separate booths, maintain realistic feline anatomy, and use a simple payment problem to build toward a dry comedic twist.
The scene depends on precise spatial continuity: the orange cat begins in the foreground booth, the gray tabby remains one full booth row behind, and the gray tabby must physically walk forward before paying for the meal. The prompt also locks the number and timing of every card, plate, terminal, roast chicken, cat, and server.