[STYLE] Live-action footage + hand-drawn 2D anime sticker composite, comedic short video. First-person POV cooking vlog. Strong contrast between a photorealistic kitchen and a warm, hand-drawn watercolor cartoon sticker character. The real kitchen, cast-iron wok, food, salt grains, and human hands stay photographic and lifelike at all times; the chibi sticker character stays a purely flat, hand-drawn 2D sticker throughout. 8K ultra-sharp, vertical 9:16, handheld micro-shake, fast comedic pacing, real physics mixed with exaggerated cartoon FX. [SCENE] A real home kitchen, first-person top-down view. A black cast-iron wok sits on the stove, beef and leafy greens stir-frying inside with a realistic oily sheen, sizzling continuously, steam rising naturally. Background: white tiled wall with a visible wall outlet; a soy sauce bottle and cooking oil bottle lined up against the wall. A stainless-steel sink on the right edge of frame, natural daylight from a side window. [CHARACTER] The reference image is a photo of a real man — render him as a chibi, two-heads-tall hand-drawn anime sticker version of himself, keeping his identity clearly recognizable: light stubble and a short salt-and-pepper goatee, bright blue-gray cartoon eyes, thick expressive eyebrows, shaved head fully covered by a black baseball cap worn backwards with the snapback strap visible across his forehead. Black ribbed tank top. Both arms covered shoulder-to-forearm in dark gray geometric mandala and snowflake-pattern sleeve tattoos, drawn simplified in the same soft watercolor sticker style; chest tattoo edges peek from the tank top neckline. Warm watercolor storybook texture: colored-pencil and watercolor-wash brushwork, paper grain, soft dark-brown cartoon outline, clean white sticker edge. Smug, mischievous troublemaker expression. He remains a purely flat 2D sticker the entire video — real kitchen lighting must not re-render him with volume; he never becomes 3D, a real person, clay, or realistic anime. He sits on a small wooden stool beside the stove, about half the wok's diameter tall. The real human hands enter from the right of frame — skin, pores, lighting fully realistic. [00:00-00:03 | SHOT 1: THE SALT DUMP] First-person top-down POV. The real right hand stir-fries the beef and greens with a spatula. The chibi guy sneakily narrows his eyes, smug grin spreading, one eyebrow arched. With both tiny hands he hoists a realistic glass salt jar bigger than his own head and, mid-stir, dumps the entire jar of white salt into the wok. A continuous waterfall of realistic salt grains pours onto the food, piling into a small white mountain in the wok's center. His backwards black cap jiggles with the motion but never falls off. SFX: food sizzling, dense rushing hiss of pouring salt. [00:03-00:05 | SHOT 2: JAR SNATCH, SPATULA BONK] The real hand swiftly snatches the glass salt jar out of his arms; the other hand raises the spatula, flat side down, and gives the top of his backwards cap one light bonk — an exaggerated but harmless cartoon tap. With a "Duang" effect, a red cartoon lump pops up beside the cap. His whole 2D paper body springs up and down once, both little tattooed hands clutching the cap. Eyes go wide, smug grin wiped off, cap slightly tilted but still on backwards. SFX: metallic spatula "Duang", cartoon spring boing. [00:05-00:08 | SHOT 3: WAILING MOUTH OPEN, SALT SHOVELED IN] He holds the red lump with both hands, eyes turning into spinning swirl eyes, mouth wide open in an exaggerated bawling wail — the tough tattooed sticker guy crying like a toddler. Blue cartoon tears spray out to both sides of his stubbled cheeks like twin fountains; the backwards cap droops but the snapback strap stays visible. The real hand shovels a heaping spatula-load of salt-covered beef and greens off the salt mountain and, while his mouth is wide open mid-wail, delivers the food precisely into his mouth. The food stuffs in with exaggerated cartoon physics; his cheeks puff into two round hemispheres. No real injury, choking, or suffering — absurd cartoon comedy only. SFX: over-the-top cartoon crying, spatula scraping salt, a "pop" as the food stuffs in. [00:08-00:10 | SHOT 4: TOO SALTY, KEELS OVER] His cheeks puff into two bright-red spheres as he struggles to swallow one gulp. Eyes shrink into two tiny black dots, the whole 2D sticker fades to a pale washed-out tone — tattoos included — body stiff, vibrating rapidly for half a beat. Then his eyes turn into two cartoon "X"s, the cap tips to one side, and he tips straight backward off the stool. Limbs up in the air, tattooed arms giving one feeble paddle, he flops flat beside the stove like a thin sheet of paper. Cap stays near his head; tattoo sleeves fully visible on both splayed arms. A ring of spinning dizzy stars appears beside the red lump; a wisp of translucent white cartoon smoke drifts up from his nose. Freeze frame on the final 0.3 seconds. SFX: a stiff "clunk", a paper-flat "thud", a short comical cartoon "soul ascending" jingle. [HARD RULES] One and the same chibi character throughout, identity from the reference photo. Backwards black cap always present with visible snapback strap, never forwards, never gone. Goatee and stubble consistent. Always the black ribbed tank top. Both full geometric tattoo sleeves always visible, pattern consistent. Always a flat 2D watercolor sticker — never 3D, live-action, clay, plush, or realistic anime. Real kitchen, food, spatula, salt, and hands stay photorealistic. Stable edges between cartoon and real scene — no clipping, melting, or duplication. No subtitles, watermarks, logos, or off-screen characters. Native vertical 9:16.
Street Fashion Brand Commercial
A photorealistic cinematic video showcases street fashion models in various urban settings. The video features dynamic camera work and authentic movement to highlight contemporary clothing and accessories.
Prompt
Create a 15-second, 16:9 photorealistic editorial street-fashion film that feels captured by a real small crew on a full-frame cinema camera. Two young adult female models; keep faces, body proportions and wardrobes consistent across every cut. Model A: oversized off-white/cream streetwear, chunky white shoes, layered necklaces, small brown leather shoulder bag. Model B: dark sunglasses, loose black top, electric-blue layered/baggy streetwear, chunky black shoes, silver jewelry; one brief look adds a burnt-orange jacket over the same blue outfit. 0.0–2.2s — Modern metro/lobby interior. Floor-level 14–16mm ultra-wide/fisheye, tilted slightly upward. Model A walks calmly toward lens beneath a huge circular white LED ceiling fixture forming a halo. Metallic escalators recede behind her; glossy charcoal stone floor shows accurate reflections; dark concrete walls and a small orange panel add contrast. Camera dollies backward with subtle handheld micro-jitter and natural footstep bounce. 2.2–4.3s — Low-angle push-in. She grips the front of her oversized shirt, leans close and gives a relaxed, confident direct gaze. One hand passes near lens, creating real perspective distortion and soft edge blur. Hair and loose fabric react naturally. 4.3–5.1s — Extreme close-up of a human eye with detailed iris, moist catchlight and the circular ceiling light reflected in the cornea. Match-cut the round highlight into bright daylight; keep it photographic, not fantasy VFX. 5.1–7.9s — Exterior urban promenade beside water in warm late-afternoon sun. Model B stands on pale concrete with palms and modern towers in the distance. Camera stays below waist height on a 16–20mm lens, gently orbiting and drifting forward. She poses, then steps toward lens; wind moves hair and fabric. Cyan sky, warm skin, crisp believable sunlight and ground shadows. 7.9–10.4s — Fast beat-synced montage: indoors Model A leans into the fisheye smiling, jewelry and brown bag near lens; outdoors Model B appears from an extreme low angle against blue sky as hair sweeps through frame; indoors again, a ringed hand reaches close to lens. Use hard cuts and motivated match cuts only—no face or wardrobe morphing. 10.4–12.0s — Indoors, Model A lifts one chunky shoe playfully toward the floor camera so the sole briefly fills foreground. Hard cut outdoors to Model B centered in the burnt-orange jacket over the same blue outfit. Body balance and cloth physics must remain natural. 12.0–14.0s — Model B walks across a quiet city crosswalk in profile, relaxed stride, sunglasses on. Track parallel at hip height on a 24mm lens; high-rise, palms, railings and street geometry remain stable. 14.0–15.0s — Slightly overhead fisheye close-up outdoors. Model B looks up smiling, both hands and jewelry entering foreground. Add two very fast beat-matched flashes of Model A indoors perfectly centered inside the glowing ceiling ring, then finish on Model B. Visual finish: 24fps, 180° shutter, authentic motion blur, mild barrel distortion, subtle lens breathing, tiny handheld imperfections, realistic autofocus settling, skin pores, flyaway hairs, fabric creases, physically correct shadows/reflections. Punchy editorial grade: deep neutral blacks, cool teal/cyan shadows, warm amber highlights, controlled saturation. No plastic skin, warped architecture, extra fingers/limbs, floating accessories, impossible bokeh, camera crew, BTS labels, subtitles, logos or on-screen text. Audio: energetic instrumental fashion-electro/club beat around 144 BPM with punchy kick, tight bass, crisp syncopated percussion and subtle risers, no vocals. Land cuts, shoe movement and hand-to-lens gestures on beat; keep faint footsteps and room/city ambience underneath.
How to Use This Prompt
Copy the prompt
Grab the cleaned-up prompt in your language, or send it straight to the editor with one click.
Pick your model
We pre-select the model that produced this result, but you can swap it for any model Vorla supports.
Generate and refine
Run it as-is to reproduce the look, then edit the wording to make the result your own.
All Video Categories
Grok Imagine
Wukong Versus Golden-Horned King
Find Your Next AI Prompt
One search covers every model and both mediums, and copying what you find costs nothing.