Detailed NYC Superhero Parkour Drone Shot
An exceptionally detailed cinematic prompt for a 15-second continuous drone sequence following a female character performing parkour through New York City streets and rooftops.
Prompt
Character Reference—Required: Face—Reference Image 3. Outfit—shoulder-length black short hair, black fitted short jacket, ripped dark cargo shorts, grey hoodie tied around the waist, turquoise satin ballet point shoes, pink tights, black headphones, white gloves.\n\nKey—Character Anatomy. Non-negotiable: 165cm, 47kg. Athletic, lean, controlled. Never ragdoll. Never weak. Never loose. Core always tight. Every movement has muscular intent. She moves like a highly trained gymnast/dancer who happens to have superpowers—precise, casual, effortless. Minimum spin. Body follows the physics logic of each movement.\n\nKey—Physical Contact with Environment. Non-negotiable: She is not just flying in the air. She has physical interaction with the city—feet pushing off walls, hands grabbing ledges, body in contact with building surfaces. Every contact point: knees absorb impact, muscles tighten, body reacts to the surface. This is parkour + swing flight, not levitation.\n\nKey—Body Position for Each Movement Type:\nWeb Swing: Both arms extended forward holding the web, legs together trailing behind, core tight, back straight, chin up—clean rope swing athlete position.\nWall Push-off: Both feet flat on the wall, knees deep bend for absorption, then legs fully extended on launch, arms swinging forward for momentum.\nWall Running: Body leaning 45 degrees towards the wall, feet hitting the surface in a running gait, arms swinging, hair and hoodie pulled sideways by momentum.\nFree Flight Peak: Arms naturally open to the sides, body slightly arched back, relaxed—not posing, just body release.\nStreet Level Running: Full sprint, arms driving, head forward, turquoise point shoes hitting the sidewalk, body leaning in direction of travel.\n\nKey—Realism. Non-negotiable: True Hollywood movie. RED Monstro 8K, Anamorphic lens. Real motion blur, real fabric physics, real NYC haze. Real.\n\nKey—Camera. Non-negotiable: One continuous drone track. Zero cuts. Zero teleports. Tilt, dive, roll physically plausible. Wide enough to always show her and the environment.\n\n15-second continuous drone tracking shot. Starts directly from black.\n0–1s: Black. Then—Close-up—white gloved hand. Fingers open. Wrist flick. Web fires. Camera immediately pulls back.\n1–4s: Wide angle—NYC residential street. Brownstones, fire escapes, grocery stores. She swings low—3m from the street. Body: arms forward holding web, legs trailing, core tight. At the bottom of the swing arc, her foot skims the roof of a parked car—brief physical contact, foot light bounce, she uses it to redirect. Camera tilts 40 degrees.\n4–7s: She releases web at peak—body opens, arms out, legs extended. Then doesn't fire new web immediately—she runs along the side of a brownstone wall. Feet hit brick in real running gait—body leans 45 degrees, arms swing, 4–5 steps along vertical surface—then she pushes off hard with both feet, knees fully extended, fires new web in mid-air toward the building across the wide intersection. The swing pulls her violently to one side—camera rolls 60 degrees.\n7–10s: She flies low down a narrow street crowded with yellow taxis. 2m above ground, body streamlined—arms forward, legs trailing like an arrow. Web released. Her feet hit the ground—full sprint, body leaning forward, arms driving—she runs 3–4 steps between taxis, using momentum, feet hitting wet sidewalk. Taxis honk. She smiles. Then one foot on taxi side, explosive one-step push off the roof, fires web upward toward a high-rise, soaring up fast.\n\"Woo-hoo!\"\n10–15s: Wide angle—rooftop level, not too high. She hangs at peak—arms slightly open, body naturally arched, perfectly still for a breath-holding moment. Golden hour sky—warm orange and pink light illuminates the horizon. Huge dramatic clouds lit from below with gold. She is a small figure dead center against the massive glowing sky. City rooftops, water towers, streets below. Shot holds. She begins to fall downward.\n[End]\n\nKey—Emotion and Sound. Non-negotiable: She is alive in every frame. Not blank. Not neutral. Not offline.\nHer face and body always express real real-time emotion:\nDuring first swing—eyes wide, slight smile, pure focus.\nWhen foot skims car—quick surprised laugh, instinctive.\nWall running—jaw set, determined, intense focus.\nLow fly between taxis—teeth showing, adrenaline smile, leaning in.\nTaxi honk—she laughs out loud, head back slightly.\n\"Woo-hoo!\"—completely uncontrollable, mouth open, scream of real joy.\nFinal wide shot at peak—arms open, head back, eyes closed, face of pure freedom—not blank, not posing, just what a person looks like in the best moment of their life.\nAudio: SFX only. No music. Wind whistling. Web zip-chord sounds. Feet hit car roof. Feet hit sidewalk—real impact sound. Taxi horns. Her real laughter. \"Woo-hoo!\" echoing between buildings. Wind cutting as she rises. Then—silence at the peak.\n\nRED Monstro 8K, Anamorphic, 165cm 47kg controlled athletic body throughout, physical contact with walls/cars/surfaces at every opportunity, detailed body mechanics for every move type—swing/run/push-off/sprint, no ragdoll no levitation, heavy Dutch angle during swings, golden hour sunset sky warm orange pink, dramatic volumetric clouds, subject at rooftop level not high altitude, subject tiny in center of wide final frame, NYC residential brownstones, continuous single drone track, no cuts, photo-realistic.
How to use this prompt
- 1
Copy the full prompt above.
- 2
Open a platform that supports Seedance 2.5, such as YouMind, and paste the prompt in.
- 3
Swap the subject, style, or details to fit your idea, then generate.
This is a free AI prompt from YouMind's prompt library. Explore thousands more video prompts, all free to copy and adapt.
Explore more video prompts
All Video Categories
01
Use Cases
More Prompt Features
AI Library
AI prompt search
Let AI search through tens of thousands of prompts. Filter by model, time range, keywords, and sort by engagement — views, bookmarks, reposts and more.
Vision Tools
Image to Prompt
Turn any photo into a detailed AI image prompt. The free image to prompt converter analyzes composition, style, and lighting so you can recreate any look in seconds.
Other Prompt Features
Built for creators. Free forever.
YouMind is the AI creative copilot trusted by millions of creators worldwide. Every prompt here is curated to help you create better, faster.