Three Animal Night Drive Meme VIDEO Breakdown (Prompts Included)
Tutorial：
Open pollo.ai, head to Video Generation. Upload the referencce 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.
Sticker 1
Sticker 2
Sticker 3
Video Prompt
PROMPT HEADER:
Generate an 18-second horizontal 16:9 1080p photorealistic live-action animal-comedy video at 30 fps. Use @sticker1 as the fixed identity reference for PENGUIN, use @sticker2 as the fixed identity reference for CAT, use @sticker3 as the fixed identity reference for DOG, and use @Reference Video only as a broad camera, nighttime-lighting, edit-rhythm, and performance reference. Create a cinematic but absurd nighttime car scene with realistic animal fur and feathers, a dark glossy interior, colorful out-of-focus city lights beyond the windows, shallow depth of field, restrained camera movement, and deadpan reaction comedy.
Keep exactly three animals in one ordinary modern car throughout the video. In the opening wide windshield view, CAT is at screen-left, PENGUIN is centered, and DOG is at screen-right in the driver-side position. The car is moving smoothly at night, but the road itself remains secondary and no dangerous driving is shown. DOG may sit behind the steering wheel, but the steering wheel and dashboard remain partially visible and the vehicle stays stable. The animals are expressive but remain recognizable animals, not humans in costumes or masks.
CAT is the pale cream-and-brown cat from @sticker2, with large upright ears, brown facial patches, dark eyes, pink inner ears, and a compact upright body. PENGUIN is the gray-and-white penguin chick from @sticker1, with a fluffy gray body, black-and-white face, round dark eyes, tiny black beak, and short flipper-like wings. DOG is the brown short-haired dog from @sticker3, with a broad brown muzzle, floppy ears, expressive eyes, pink collar, large head and shoulders, and one natural front paw available for the final gesture. Never exchange these identities or screen positions.
The comedy should feel like a silent absurd reaction meme. CAT begins with an exaggerated wide-open-mouth reaction as though loudly yelling or singing. PENGUIN stays almost perfectly calm and blinks slowly. DOG looks between the other two animals with growing confusion, then ends by looking directly toward the camera and touching one paw to its temple as if asking whether the situation is ridiculous. Use no recognizable song, no quoted dialogue, no subtitles, and no readable text.
CAR, LIGHTING, AND CAMERA CONTINUITY:
Use one believable modern car at night with a dark charcoal dashboard, black or dark-gray front seats, a curved windshield frame, a small rear-view mirror near the top center, and a partial steering wheel in front of DOG. Keep the same cabin geometry in every angle. Outside the windshield and side windows, show colorful city lights as soft circular bokeh in blue, white, amber, and red. The road remains dark and abstract; no readable signs, license plates, logos, or recognizable locations.
The opening camera is low and centered outside or just beyond the front windshield, looking inward at all three animals over the glossy hood and dashboard edge. The middle shot is a shallow-focus interior close-up on PENGUIN with DOG blurred behind at screen-right. The final shot is a tight three-quarter close-up on DOG from the passenger-side/front interior, with the same bokeh lights and car frame behind it. Use clean editorial cuts between these views. Do not morph, teleport, or change the car between shots.
CONTINUOUS PERFORMANCE AND EDIT PLAN:
0.0-4.6 seconds - Three-animal opening windshield wide:
Open immediately on a centered low front view through the windshield. Frame the glossy hood or dashboard edge across the lower foreground, the curved roof and rear-view mirror above, and the three animals lined up behind the windshield: CAT at screen-left, PENGUIN in the middle, and DOG at screen-right behind the driver-side area. All three are visible at once.
CAT performs the loudest visual reaction: it tilts its head slightly upward and holds an exaggerated very wide open mouth, with the pink mouth interior clearly visible. Its ears and face remain stable. PENGUIN sits upright and almost motionless in the center, looking forward with a blank, innocent expression and only tiny natural head movement. DOG looks ahead, then turns its eyes and muzzle slightly toward CAT as if trying to understand the noise. Add small natural cabin vibration and gentle parallax in the city lights, but keep the composition readable and steady.
4.6-5.0 seconds - Cut into PENGUIN close-up:
Cut cleanly to a tight interior close-up of PENGUIN from the chest up. PENGUIN fills the left and center of frame, with a soft blurred portion of DOG's brown head and shoulder in the background at screen-right. Preserve the penguin's small round eyes, black-and-white face markings, tiny beak, and fluffy gray feathers from @sticker1. PENGUIN looks directly toward the camera with a calm, mildly puzzled expression.
5.0-7.8 seconds - Calm PENGUIN reaction:
Hold the PENGUIN close-up for a quiet contrast to CAT's exaggerated opening. PENGUIN makes one slow blink, then opens its eyes again without changing posture. Its small head shifts only slightly toward DOG, as though silently checking whether DOG has an explanation. DOG remains a soft, out-of-focus background presence and may move its muzzle a little, but must not take focus or turn into a second penguin. Keep the background dark and the city bokeh soft.
7.8-8.2 seconds - Cut to DOG close-up:
Cut to a tight front three-quarter close-up of DOG in the driver-side area. Frame the brown head and upper chest clearly, with the pink collar visible at the base of the neck, a sliver of the steering wheel or dashboard at the lower edge, and dark windshield glass with colorful bokeh behind. DOG matches @sticker3 exactly: warm brown short coat, broad muzzle, floppy ears, expressive eyes, and natural dog proportions.
8.2-11.0 seconds - DOG processes the absurdity:
DOG first looks slightly off to one side toward the other animals, mouth relaxed and slightly open as if panting or reacting. It then turns its eyes and muzzle toward the camera. Let the expression evolve from neutral curiosity to visible disbelief. Use a very small head movement and one natural blink; keep the eyes, muzzle, ears, collar, and fur stable. The camera may make a subtle controlled push-in, but do not shake or zoom dramatically.
11.0-13.8 seconds - DOG's deadpan direct look:
Hold the same close-up. DOG faces the lens more directly and pauses, creating the deadpan meme beat. Its eyes widen slightly, then settle into a skeptical look. The mouth remains naturally parted, with no human speech and no lip-sync. One front paw begins to rise from below frame on the dog's right side, moving slowly and clearly toward the side of its head. Keep the paw anatomically correct and attached to the dog's body.
13.8-18.1 seconds - Final temple-pointing payoff:
DOG raises one front paw beside its head and touches or points toward its temple/side of the head, holding the gesture for the final beat as if saying, "What is going on?" The gesture must read as a single natural animal-comedy action, not a human hand replacement. DOG looks directly at the camera while holding the pose. Keep the pink collar, broad muzzle, brown fur, and bokeh lights consistent. End on the held skeptical expression and raised paw, with no title card, text, or additional reaction shot.
VISUAL AND MOTION RULES:
Photorealistic live-action animal comedy with cinematic nighttime exposure, practical reflections on the windshield and dashboard, shallow depth of field, colorful defocused city lights, stable identities, and natural fur and feather detail. Preserve exactly one CAT based on @sticker2, one PENGUIN based on @sticker1, one DOG based on @sticker3, and one consistent car interior. The humor comes from the contrast between CAT's exaggerated open-mouth reaction, PENGUIN's calm blink, and DOG's increasingly skeptical response.
Keep the opening spatial relationship exact: CAT left, PENGUIN center, DOG right. Keep PENGUIN centered in its close-up and DOG in the background at screen-right. Keep DOG in the same driver-side position in every DOG shot, with the same collar and car geometry. Use realistic animal anatomy, restrained motion blur, stable exposure, and clean cuts. No one leaves the vehicle, no window opens, and no dangerous driving occurs.
AUDIO:
Create an original short absurdist-comedy audio bed with a low nighttime car hum, subtle tire and cabin noise, a restrained rhythmic pulse, and three clear reaction accents matching the edit: a comic open-mouth vocal or yelp from CAT, a tiny soft blink or movement accent for PENGUIN, and a dry understated reaction sting as DOG touches its temple. The final DOG gesture may have a short comedic hit or click, but do not use a recognizable song, quoted dialogue, spoken narration, copyrighted lyrics, subtitles, or on-screen words. Keep the audio synchronized with the cuts and end cleanly on the held DOG pose.
NEGATIVE PROMPT:
Extra cat, extra penguin, extra dog, duplicate animals, missing animal, animal identity swap, CAT in the center, CAT on the right, PENGUIN on the left, DOG on the left, changed cat face, changed cat markings, changed cat ears, wrong penguin species, penguin with a long beak, changed penguin feathers, changed dog breed, changed dog coat color, missing dog collar, changed dog muzzle, human face, human hands, human body, animal costumes, animal masks, clothing, hats, accessories, floating paw, detached paw, extra paws, extra limbs, extra digits, broken anatomy, dog hand instead of paw, dog standing, dog leaving the car, animal outside the vehicle, dangerous driving, crash, swerving, open window, changing car interior, duplicate steering wheel, missing windshield, broken windshield, daylight, bright studio lighting, horror lighting, warping bokeh, readable signs, readable license plates, logos, vehicle branding, captions, subtitles, title card, watermark, text, recognizable song, copyrighted lyrics, spoken dialogue, narration, excessive camera shake, dramatic zoom, morphing, teleportation, incoherent cuts, identity drift, face drift, feather drift, fur drift, low resolution, blurry faces, heavy motion blur, frozen expressions, repeated final gesture, audio mismatch.
Final Summary
Create one complete 18-second horizontal 16:9 1080p photorealistic nighttime animal-comedy video at 30 fps. Use sticker1 as the fixed identity source for exactly one gray-and-white PENGUIN in the center, use sticker2 as the fixed identity source for exactly one pale cream-and-brown CAT on the left, use sticker3 as the fixed identity source for exactly one brown DOG on the right, and use Reference Video only for broad low windshield framing, cinematic bokeh, close-up rhythm, expressive reactions, and the final comic gesture.
The finished video begins with all three animals visible through the windshield: CAT holds an exaggerated wide-open-mouth reaction, PENGUIN remains calm and blinks once, and DOG gradually becomes confused. The edit then cuts to a quiet PENGUIN close-up and finally a DOG close-up that ends with DOG looking directly at the camera and touching one paw to its temple. Preserve the three sticker identities, fixed opening positions, consistent dark car interior, nighttime city bokeh, restrained live-action realism, clean reaction timing, no readable text, no extra characters, no recognizable song, and no watermark.