FORMAT / START] Generate a 15-second 16:9 cinematic action scene. Action begins immediately. No reference images provided — generate both characters from the text description. [CHARACTER LOCK] A is The Runner. Preserve exact: woman early 30s, lean athletic build, dark hair tied back and soaked flat, grey tank top, dark cargo pants, bare forearms, low compact stance, contained energy. She is calm. She wins. B is The Enforcer. Preserve exact: woman mid 30s, taller and heavier, short bleached hair, black tactical jacket, gloved hands, upright forward-leaning posture, volatile energy. She attacks first. She loses. Do not swap roles. Only these two characters. No extras. [SETTING] Rooftop of a residential block, night, heavy rain. Standing water across flat concrete, ventilation units, a low parapet, laundry lines strung between poles with wet sheets snapping in the wind. A single service lamp on the stairwell housing — hard white light, everything else in blue shadow. City glow far below. No crowd. [MOTION RULES] Readable action, clear silhouettes, short pause before contact, visible setup before every strike, hard impact with real physical weight, short hit-stop, controlled smear only on fast-moving limbs, clear geography. Every cut continues the same exchange. No slow motion, no speed ramping — full real-time speed throughout. Movements grounded and physically motivated. Each technique flows directly into the next without discontinuity. A moves with economy and precision. B moves with aggression and momentum. Rain and standing water react to every impact. [BEAT 1 — ENTRY] Both women face each other across the wet roof, three meters apart. B advances fast, right hand cocked. A stands relaxed, weight centered, hands low, eyes on B's sternum. A wet sheet swings between them and passes. The gap closes. [BEAT 2 — FIRST EXCHANGE] B throws a heavy right cross. A slips outside, lets it pass her ear, and fires a short left hook into B's ribs mid-extension. B grunts, arm drops. Water sprays from both their feet. [BEAT 3 — COUNTER] A is already inside. She catches B's collar with her left hand and drives a short right elbow across the cheekbone — dense contact, proximity not distance. B's head rotates. Her back foot slides out on the wet concrete. [BEAT 4 — RECOVERY EXCHANGE] B tears free and charges, driving full bodyweight into a tackle. A absorbs one step back, drops her weight, hooks an arm under B's shoulder and pivots — using B's own momentum to throw her over the hip into standing water. Heavy flat landing. Spray erupts. [BEAT 5 — FINISH] B pushes up onto one knee, no guard left. A steps in and drives a knee into her sternum. B folds and goes flat on her back in the water. A straightens, exhales once, rain running off her, and walks past toward the stairwell without looking back. Final image: A silhouetted in the service lamp, B down in the water behind her, sheets still snapping in the wind. [AUDIO] No music. Only: rain on concrete, wet footwork, hook into ribs, elbow on bone, boot sliding on wet floor, body hitting standing water, one long exhale at the finish, sheets flapping in wind. [NEGATIVE CONTROL] No random cuts, no role swap, no outfit change, no face morphing, no extra characters, no teleporting, no unclear contact, no comedy, no subtitles, no logos, no UI, no slow motion, no speed ramping, no wire work, no supernatural movement, no weapons. Every position change physically motivated and continuous
Han River Analog Footage
An authentic 15-second analog home video captures a young Korean woman walking along the Han River on a summer afternoon, filmed with a handheld Hi8/VHS-C camcorder. The footage features genuine analog aesthetics, showcasing the woman interacting with a large floating 'HIGGSFIELD' installation and the bustling city backdrop.
Prompt
Concept: "Han River Analog Footage × Higgsfield" Create an authentic 15-second analogue home-video recording filmed with a handheld Hi8/VHS-C camcorder. The camcorder is never visible. The viewer only sees the recorded footage, as if watching a digitized family videotape. This is not a vlog, commercial, or cinematic film, just a friend casually filming another friend. Use genuine analogue camcorder aesthetics: soft SD resolution, VHS grain, faint interlacing, analogue colour bleed, mild tracking noise, autofocus breathing, slight exposure fluctuations, imperfect handheld shake, natural motion blur, washed-out colours, and subtle tape hiss. No HDR, beauty filters, cinematic grading, stabilisation, or AI-perfect rendering. A young Korean woman in her early twenties wears a pastel fitted crop top, mid-rise vintage blue denim shorts, white ankle socks, classic white sneakers, a lightweight windbreaker tied around her waist, and carries a simple canvas shoulder bag. Her styling should evoke nostalgic late-90s/early-2000s Korean street fashion without mentioning a specific year. The scene takes place beside the Han River on a warm summer afternoon. Families relax on the grass, cyclists ride past, children play, and the distant Seoul skyline fills the background. She walks naturally toward the riverside railing before stopping to admire a massive floating HIGGSFIELD installation in the river. The word HIGGSFIELD is built from giant three-dimensional block letters, mounted on a realistic floating platform. The sign must appear physically installed in the river with accurate reflections, shadows, and perspective, remaining large, bold, and perfectly readable throughout the scene. The camera gently pans between her and the installation, keeping both in frame. She smiles naturally, takes a few steps closer, then notices the unseen camera operator. She laughs softly, gives a warm wave, points excitedly toward the giant HIGGSFIELD sign, gives a subtle thumbs-up, then looks back at the river with a smile before continuing her walk. A light breeze moves her hair and clothing while a cyclist passes behind her. The camera follows for a few more steps before stopping naturally. Generation Requirements: One continuous 15-second recording with no cuts or transitions. Keep movements natural, identity consistent, anatomy accurate, and interactions believable. The HIGGSFIELD installation must stay prominent, crystal clear, and naturally integrated into the environment. Include realistic ambient sounds such as wind, birds, distant conversations, bicycles, and water. Avoid AI artifacts, duplicated pedestrians, warped anatomy, floating objects, modern cinematic effects, or anything that makes the footage look AI-generated. The final result should be indistinguishable from genuine nostalgic analogue camcorder footage.
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
Pink and Cyan Liquid Text Intro
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.