Fly over Tokyo | A Broomstick Night FlightHolyCrab Studio
Source promptFly over Tokyo | A Broomstick Night Flight
[Character, prop and reference roles]
@Image 1 is the sole identity and wardrobe reference. Keep the same 22-year-old adult Japanese woman, face and adult proportions throughout: silver-white high ponytail with loose facial strands, narrow dark-green headscarf, dark-green short one-piece dress with matching safety shorts, white low-top canvas shoes and one natural wooden broom with a straw brush. Do not inherit the studio background, studio lighting, standing pose or still composition. No bow, backpack, handbag, shoulder bag, waist bag or straps.
@Image 2 defines the seated riding contact during 0–18 seconds and the opening gesture during 0–1 second. Her pelvis sits on the same support point on the shaft. The shaft passes between her thighs; each thigh stays on its own side and grips it. Knees bend and lower legs tuck naturally backward; the brush trails behind her hips. Only during 0–0.7 seconds use the playful expression and right-hand YEAH/V sign beside her face. At about 0.7 seconds that hand returns to the shaft; from 1 second onward both hands grip it. Omit studio lighting, grey background and a static floating appearance. This reference does not set the climbing angle at 18–25 seconds or pull the steep climbing pose back to horizontal.
@Image 3 defines Tokyo's Shibuya Scramble Crossing: broad multidirectional zebra crossings, dense night-time pedestrians, modern buildings, wet pavement, streetlights, shop windows, screens, headlights and mixed city light. Use only environment type, materials, light-source positions and color temperatures, crowd density and scale. Do not copy specific pedestrians or make any of them a featured character. Shop signs need not be legible.
@Image 4 is the sole spatial route reference. Follow the single connected cyan line from green start to red finish: straight; right at an ordinary junction; straight; left into an alley; straight through the alley; right onto a main street; straight; left at busy Shibuya Crossing; straight to the takeoff point at 18 seconds; then climb through one nearly straight vertical corridor to about 1,000 meters. No ground-level S curves, weaving, slaloms, loops or U-turns. No ascending spiral, circuits, lateral orbit, reversal or fork. The line defines topology, not speed; follow the timeline for speed. Never show navigation lines, arrows, spheres, miniature figures or map graphics in the film. Map buildings are scale placeholders, not architecture, lighting or identity references.
@Image 5 is the highest-priority riding geometry reference during the fast climb at 18.7–25 seconds. The broom points about 75–82 degrees above horizontal, the shaft's front points up along the flight direction, and the brush sits below and slightly behind the pelvis. Her seated weight remains on the same shaft contact above the straw binding. The shaft continuously passes between her legs, thighs grip it, knees bend inward, and feet stay suspended without standing on the broom. From the hips, pelvis, abdomen, ribcage, shoulders, neck and head lean backward as one stable whole. The torso is about 35–45 degrees above horizontal and about 35–50 degrees from the near-vertical shaft. Shoulders and head remain behind the pelvis. Keep a natural, nearly straight spine and engaged abdomen, without arching the lower back or bending the neck backward on its own. Chin lifts slightly and gaze follows the shaft's front toward the sky and flight direction, never the lens. Both hands firmly hold the same shaft at separated heights with visible wood between them. Each hand has five normal fingers; thumbs oppose the remaining fingers around the cylinder. No fused, missing, repeated or penetrating fingers, and no broken or reversed wrists. The reference view explains the pose; she does not spin to match it while the FPV camera orbits. Omit its background, speed lines, bright figure lighting and still composition.
@Image 6 defines only the city extent, dense lights, atmospheric perspective, distant horizon and extreme aerial scale at about 1,000 meters. It is not a new scene to cut to, nor a pose or character-lighting reference. Arrive by continuously shrinking and revealing the same Tokyo district. Show only one real orange-red lattice Tokyo Tower, without copies, mirror images, ghosting or a second tower on screens, glass or the skyline.
[Highest priority: riding contact and one continuous take]
Rider and broom remain one inseparable riding assembly. Her pelvis stays pressed to the same shaft contact, the shaft remains between her legs, and her thighs keep their grip. They translate, turn, bank, pitch, climb, decelerate and level together. Contact points never slide, detach or swap; the shaft does not slide inside her body. Use @Image 2's near-horizontal riding pose during 0–18 seconds. During 18–18.7 seconds rider and broom pitch together into @Image 5's steep climbing pose. Lock that relative geometry during 18.7–25 seconds. During 25–26 seconds level the whole assembly together, then hold a stable horizontal seated pose during 26–28 seconds.
One high-speed FPV camera tracks continuously around the combined center of rider and broom. Its orbit never makes her spin, turn her head or track the lens. Use one unbroken take: no cuts, inserted close-ups, axis jumps, time jumps or teleportation; no whip pans, occlusions, flashes, blackouts, heavy defocus or excessive blur to hide transitions. The camera never passes through the woman, broom, hair, walls, pedestrians, vehicles, signs or buildings. Show no drone, propellers, drone shadow or second drone.
[Lighting and exposure: fixed world-space sources]
No camera lights, drone lights, studio key, ring light, invisible moving fill, unmotivated rim light or AI relighting. Sources remain in Tokyo world space: practical streetlights, shop windows, screens, traffic signals, headlights, wet-ground reflections, very weak night-sky ambience and city bounce from below. When the FPV changes viewpoint, lights do not rotate with it. Backlit or occluded surfaces naturally darken, with correct self-shadow on body, hair, dress and broom.
During 0–18 seconds, passing each practical source continuously changes light color, direction, intensity, highlights and shadows on white hair, face, arms, dress, legs and broom according to real distance. Turns change which body surfaces receive light. Buildings, door frames, signs and her own body cast moving occlusion and shadows. Exposure and white balance adapt slowly, without flicker, pumping or sudden face brightening.
During 18–20 seconds nearby streetlights and screens briefly retain directional influence, then their illumination visibly falls as she gains height. Colored neon does not freeze onto her skin. During 20–23 seconds, while she clears rooftops at peak speed, ground sources reduce to very weak broad bounce from below. She grows darker with altitude; white hair never emits light. During 23–26 seconds expose for city lights and sky, leaving her roughly 1.5–2 stops below the city light grid as a readable riding silhouette. The dress becomes almost black-green; upward surfaces receive only faint cool-blue sky ambience and downward surfaces even weaker warm city bounce. During 26–28 seconds no nearby fixture, building or aircraft illuminates her. Her back faces camera and is about two stops below the city lights, with only weak cool values on hair, scarf and shoulders; back and dress stay deeply dark, and legs, shoes, hands and broom are mostly shadowed.
No subject-following or face-priority exposure, HDR shadow lifting, local tone mapping, subject masks, recovered shadows, glowing skin or hair, white halos, holy light, false moonlight or darkening the whole city to reveal clothing. Tokyo Tower is never her key, fill or rim light.
[0–1 seconds: close-up and YEAH]
Start on an ordinary Tokyo night street. She is already seated correctly as in @Image 2, broom nearly horizontal, about 1.2 meters above wet pavement and facing down the road. The FPV is 0.7–1 meter away at a front three-quarter angle, making a small continuous arc around face and right hand. She smiles playfully, looks into the lens for about half a second and shows a clear right-hand YEAH/V sign beside her face. Her left hand holds the shaft in front. At about 0.7 seconds the right returns to the shaft without changing pelvis or thigh contact; the broom stays 0–5 degrees above horizontal and accelerates gently forward. By 1 second both hands grip the shaft and the camera is physically retreating, without a cut.
[1–2 seconds: first straight]
The camera retreats smoothly to a wide full-body tracking view. She flies low and straight down the street center. Clearly show seated weight, thighs around the shaft, bent knees, tucked lower legs and brush behind. End at the first ordinary junction entrance, ready to turn right.
[2–4 seconds: right turn]
The complete rider-and-broom assembly makes one clear continuous 90-degree right turn with a natural radius, never cutting diagonally across it. The FPV follows the turn while continuing its orbit. End aligned with the second street.
[4–6 seconds: second straight]
Fly straight along the street center at about 1.5 meters, with only tiny stabilization corrections. No weaving or curves. End with the narrow alley entrance clearly visible on the left.
[6–8 seconds: left into the alley]
Make a clear 90-degree left turn and align with the alley. Tighten the camera's lateral offset to a physically passable side or upper-side elliptical arc. No passing through walls or signs. End centered in the alley.
[8–10 seconds: alley straight]
Fly straight along the alley center without slaloms or S curves. Warm shop-light pools alternate with dark gaps and create changing practical illumination. End with the main-street exit clearly visible to the right.
[10–12 seconds: right out of the alley]
Make a continuous 90-degree right onto the broad main street. Smoothly widen the FPV orbit, without using shadows or door frames to cut. End facing along the main road toward Shibuya.
[12–14 seconds: main-street straight]
Fly straight along the main-street center, rising smoothly from about 1.5 to 4 meters to clear obstacles, without starting the high-altitude climb. Shibuya's crossings and dense crowds approach. End at the Scramble Crossing entrance with vehicles safely behind signal lines.
[14–16 seconds: left at Shibuya]
Make one clear 90-degree left about 4 meters above the busy crossing. Pedestrians naturally look up but stay orderly; no collisions, falls or trampling. The open intersection permits the widest ground-stage camera orbit, without an inserted aerial shot. End aligned with the new street leaving the junction.
[16–18 seconds: final straight to takeoff]
Accelerate straight along that street, broom about 0–5 degrees, torso upright and height about 4 meters. Do not start the climb or any circuit early. The orbiting FPV keeps her whole body, broom and sky ahead visible. At 18 seconds reach the @Image 4 takeoff point, seated and gripping as in @Image 2, with strong forward momentum ready to curve into the vertical corridor.
[18–20 seconds: enter the steep climb and accelerate]
At 18 seconds the inseparable assembly smoothly redirects its forward velocity into a nearly vertical ascent along a short rounded path. Begin upward acceleration immediately, from the second frame after 18 seconds. During 18–18.7 seconds pitch rider and broom together, reaching @Image 5 and a 75–82-degree shaft by 18.7 seconds. She does not backflip and the broom does not rotate through her body. Thereafter preserve the exact contact, thigh grip, bent knees, suspended feet, straight backward-leaning torso, head and shoulders behind pelvis, upward-forward gaze and separated five-finger hand grips. Continue smooth acceleration until the single peak speed at 20 seconds. Height rises continuously from about 4 to 180 meters. End above most roofs, stable in the same ascending corridor.
[20–23 seconds: hold peak ascent speed for three seconds]
Hold the highest upward speed for the full three seconds along @Image 4's same straight vertical corridor. No further acceleration, early braking, circling or sideways movement. Preserve @Image 5's relative geometry frame by frame: seated support, thigh grip, torso lean, gaze and grips. Only hair, scarf tails, skirt and bristles respond to strong relative airflow downward. Buildings and thin clouds stream downward with the strongest parallax and background blur. The camera alone traces a narrow helical tracking path around her; rider and broom do not spin. Rise continuously from about 180 to 730 meters. End still climbing fast, with the rider markedly darker and the city lights clear.
[23–26 seconds: decelerate smoothly and level at 1,000 meters]
Begin braking only at 23 seconds. During 23–25 seconds reduce upward speed smoothly in the same straight corridor, keeping the 75–82-degree shaft and @Image 5 pose. No jolts, reacceleration or sideways drift. During 25–26 seconds complete the deceleration while rider and broom pitch forward together: shaft levels to about 0–5 degrees and torso returns upright without changing contact points. Upward speed continuously reaches zero. The camera reduces angular speed and moves naturally to a slightly elevated position directly behind her. Rise from about 730 to 1,000 meters. At 26 seconds she is level and stationary, back toward camera.
[26–28 seconds: two-second rear-view aerial hold]
Hold the entire rider-and-broom assembly steady for the final two seconds at about 1,000 meters, without climbing, descending, moving forward or rotating. Broom stays 0–5 degrees, pelvis on the same support, thighs gripping and both hands in front. See only the back of her head, silver ponytail, scarf knot, shoulders, dress back, legs, white shoes and brush. No face, looking back, profile, lens contact or gestures. She looks toward Tokyo's horizon. The FPV stays slightly above and directly behind her, allowing only slight stabilizing drift and a slow pullback, never orbiting to her side or front. Reveal @Image 6's expansive Tokyo night scale with tiny buildings and crossing below and at most one small orange-red Tokyo Tower. End naturally without freeze, fade or cut to black.
[Speed, camera and sound continuity]
One speed curve: low street flight during 0–18 seconds; smooth acceleration during 18–20; three full seconds at peak upward speed during 20–23; smooth deceleration to zero during 23–26; stable hover during 26–28. Parallax, motion blur, airflow in hair and clothes and wind sound follow this same curve. Wind grows during 18–20, stays at its strongest during 20–23 and fades with deceleration during 23–26. Street sounds recede with altitude, leaving steady high-air wind and very distant city low frequencies in the hold. No drone motor, speech, narration or background music.
[Exclusions]
No old wide spiral, two-circle orbit, S-shaped route, rider spin, rotation around the shaft, axial broom roll, barrel roll, somersault, teleportation or jump cut. No standing on or aligning the body upright along the broom, pole hugging, climbing, hanging, lying prone, pelvis detachment or sliding, released thigh grip, feet on the shaft, brush between the thighs, shaft through flesh, arched lumbar spine, backbend, bridge, backflip preparation or isolated backward neck bend. No malformed fingers, floating grips, extra limbs, doubled riders or brooms, black cat, wings, cape, hat, wand, jets, visible magic trail, bags, bows, subtitles, logos or watermarks.
Into the Wild | HolyCrab Outdoor Shoe AdHolyCrab Studio
Source promptInto the Wild · Part 01
[Cast]
@Image 1 is the sole identity reference for the adult Asian male lead: the same face, short platinum hair and hairline, silver earring, skin tone, gray-purple T-shirt, dark gray shorts, black hydration vest with two bottles, black watch and plain white mid-calf socks.
@Image 2 is the sole identity reference for the adult Black male friend: the same face and skin tone, short curls, oval black sunglasses, dark gray sleeveless top, navy shorts, black hydration vest with two bottles and plain white mid-calf socks.
@Image 3 is the sole identity reference for adult EVE: the same face and skin tone, dark roots and brown high ponytail, berry-red T-shirt and shorts, black hydration vest with two bottles and plain white mid-calf socks.
Lock each person's eye shape and spacing, eyelids, brows, nose bridge and tip, lips, cheekbones, jaw, ears and hairline independently across angles and expressions. Do not replace them with similar models or blend faces. Multiple views in each sheet depict one person. Only show the characters specified for each shot. Clothes, socks and vests have no lettering.
[Product and brand]
@Image 4 defines the one shoe design worn by all three: white fine square-woven uppers and white laces, light gray rubber wrap and midsole, and turquoise rounded-lug outsole. Preserve its shape, proportions, material and colors across locations. Worn shoes connect naturally to feet and legs.
@Image 5 defines the exact bold geometric HolyCrab lettering, capitalization, spacing and proportions. Follow @Image 4 for printing: one small light gray (#B0B4B9) wordmark on the OUTER toe-side rubber wall of each shoe, never at the front-center toe. The front toe, inner side, heel, tongue, textile side panels, midsole and outsole have no additional markings. When the printed outer surface turns out of view, the logo disappears naturally; do not relocate or duplicate it.
[Reference roles]
Reference images define identities, the product and empty environments only. Describe composition, poses, action and camera movement through the shot plan. Produce a single full-frame image, not a collage or split screen.
@Image 6 defines only the empty forest trail, trees, vegetation and spatial layout. It supplies no people, poses or product.
@Image 7 defines only the shallow forest creek, flat stones, moss, water and banks. Generate the other walking terrains from the descriptions below while retaining the same outdoor look.
[Music and rhythm]
@Audio 1 is the original song's consecutive 0–12-second excerpt. Play this file from its beginning at original speed throughout the scene, preserving melody, instrumentation, beats, accents and order. Do not loop, recompose or replace it. Let the actual beats and phrases guide cuts, footfalls, the splash, FPV acceleration and settling. The time ranges allocate the shots; fine cuts may shift within them to follow the music, with varied pacing and natural body movement.
[Shots]
0–1s — Departure. Low frontal camera on the forest trail. The lead kneels centrally on his left knee with his right foot planted forward. He leans slightly down and tightens the right shoe's laces with both hands, never looking at camera. Include his face, hands, grounded left knee and right shoe. Finish with the laces tightened.
1–5s — Continuous walking, eight terrains. Show only the lead's lower legs, white socks and worn shoes. The right shoe is the main product subject; the other foot alternates naturally. Track toward screen right from a low outer three-quarter angle at normal walking speed. Show heel contact, loading, weight transfer, forefoot push-off and forward swing. No running, high knees, marching in place, floating or sliding.
Across these four seconds, cut through eight backgrounds once each, about half a second per setting: 1–1.5s reed wetland edge; 1.5–2s sunlit grass; 2–2.5s gravel mountain trail with distant peaks; 2.5–3s flat stones in a shallow creek; 3–3.5s pine-needle forest path; 3.5–4s mossy stone path; 4–4.5s fine sand; 4.5–5s outdoor wooden boardwalk. Ground and distant environment change together, keeping shoe colors consistent. Align the cuts near musical beats while fitting all eight inside this four-second passage.
Continue the same gait across every cut: preserve direction, speed, leg positions, supporting foot, gait phase and weight transfer. Do not reset the stride or demand a fresh footfall at each cut. The shoes move with the feet, never as a frozen product overlay. Keep scale and camera position continuous. Do not cut to faces or full bodies. End while still walking.
5–5.5s — Vest adjustment. Side medium shot of the lead standing upright, casually tightening a chest buckle or strap. Open shoulders, grounded feet, relaxed confident posture, gaze toward the route. Hands make proper contact with the strap. Finish with his gaze lifted forward.
5.5–6s — Profile. Cut along the same eyeline to a close side view facing screen right. Preserve his reference face and platinum hair. Subtle breathing, eye movement and hair motion only. Calm, focused expression; no speech or look into camera.
6–6.6s — Friend joins. The Black friend steps over a low fallen log onto the same trail, raising his foot only enough to clear it. Keep his curls, oval sunglasses, sleeveless outfit and hydration vest. A blurred gray-purple shoulder may edge the frame. Finish after he clears the log.
6.6–7.2s — EVE follows. EVE gently brushes aside fern leaves in front-left with her right hand while taking a natural step. The contacted leaves bend and spring back slightly; her high ponytail follows with inertia. Keep face, hand and shoes clear, eyes along the route. No running or exaggerated leg lift.
7.2–8.7s — FPV shoe tracking. Skim rapidly through a real gap between two trees, then decelerate into matched tracking near the lead's right shoe from the outer front side, about ten centimeters above the ground. Nearby leaves sweep past while the shoe remains clear and walks naturally. Acceleration and settling respond to musical accents. Do not pass through trees or bodies or show a drone or its reflection. Finish in steady low tracking.
8.7–9.7s — Root crossing. Cut low to a real low tree root. The right shoe presses onto it, weight transfers forward, then it lifts over and the rear foot follows. Raise the leg only enough to clear the obstacle. Natural arm balance. Tilt slightly upward to reveal the focused face. Keep real spatial contact and the fixed shoe design. Finish past the root.
9.7–10.4s — Creek pause. Three people pause by the shallow creek: Black friend left, lead center, EVE right. The lead checks a flat stepping stone; the others follow his gaze and subtly adjust stance. Exactly three distinct identities and six shoes. Finish ready to step into the water.
10.4–12s — One splash, bullet-time orbit. The shoe steps into the creek only once, onto one flat stone, displacing water near a musical accent. As the splash opens, droplets almost freeze while the camera continuously circles about halfway around the fixed foot and splash, from the outside past the heel toward the rear/inner side. Then the droplets resume falling. No repeated stomp, disconnected leg, jumping stone or discontinuous water. Let the outer logo disappear when hidden; heel and inner side stay blank. Finish after the orbit with flowing water and a clean cut point for the next part.
[Continuity and sound]
Keep faces, clothing, equipment, shoe design and physical contact consistent. Do not add people or shots. Fine square weave belongs to the shoe fabric only, never skin, clothing or background. Avoid etched skin, harsh texture and sharpening halos. Use relaxed low steps and natural arm swing on level paths. No dialogue, subtitles or text beyond the specified wordmark. Keep the original music; optional synchronized footfalls, fabric, forest air and water remain below it.
Retro American Pool Challenge: The Growing Pink BalloonHolyCrab Studio
Source prompt15 seconds, 16:9, live-action cinematic imagery with the style of a late-1980s American beach comedy. Bright sunny weather, warm natural daylight, a turquoise pool, warm brown wooden decking, cream-white seaside buildings, vivid candy colors and colorful party cups, subtle 35mm film grain and soft highlights. Brisk action and exaggerated comic acting.
The contestant must match @Image1 exactly. The two views in @Image1 show the same person. There is only one lead contestant throughout.
@Image2 controls the scene layout, long runway, starting balloon, finish ramp and spectators on both sides, plus the retro American light and colors.
@Video1 is the 15-second cylinder blockout. Use it for character positions, running path, in-place balloon inflation, spectators launched outward after contact, the sequence of contact and trapping on the ramp, camera angles and editing rhythm. The sole pink cylinder represents the lead contestant; grey cylinders represent spectators. Close-ups of the cylinder's upper end mark the position of the human face close-up. Replace cylinders with real people, the balloon with a pink balloon, and the environment with the scene in @Image2. Do not copy cylinder bodies, pink human skin or blockout materials. Identity comes from @Image1; complete the human running, hand and foot support and facial reactions as described below.
The setting is a pale peach-orange water runway, approximately 25 meters long and 2 meters wide, crossing a large swimming pool. A substantial flat middle section allows continuous running. Fixed supports, distance marks and spectators on both sides establish a clear sense of distance. The far end connects directly to a sturdy solid upward ramp, approximately 45 degrees, 2.2 meters wide and 4 meters high, with a pale peach-orange padded nonslip surface. Its foot meets the runway smoothly and its top connects to an elevated exit platform. The contestant runs from the start to the far end, then up the ramp; only reaching the top counts as completing the challenge.
There is only one pink balloon. At the start signal, the lead begins running and the small pink balloon at the start begins continuously inflating. Its center remains fixed at the same starting location. It expands outward and upward around that fixed center. Extremely exaggerated inflation speed and enormous size are allowed; eventually the pink curved surface fills the pool background. As the surface grows it reaches the far end of the runway and contacts the lead on the ramp. The balloon never translates along the runway, rolls, bounces or actively chases her. Scene markers remain fixed; the camera and contestant move.
The balloon is an intact, soft, elastic sphere. Where it contacts the runway, pool edge, supports or ramp, its surface flattens or indents and bulges outside those solids. Continuous visible deformation also occurs where it touches the contestant. Each solid occupies its own space: the balloon never penetrates the runway, ramp or body, and the contestant never penetrates the balloon or ramp. The balloon's lower edge displaces the water, sending waves toward both sides.
0–1.2 seconds: A close-up of the lead's face. She looks toward the finish confidently; the small pink starting balloon appears in the blurred background. The starting tone sounds and she immediately begins running. The camera briefly follows her face and upper body as the background starts receding and the small balloon starts inflating.
1.2–7.1 seconds: Cut to a tracking shot from the front side at human height, retaining her whole body and the runway under her feet. She quickly passes several fixed supports and distance marks, with continuous footwork, arm swing and weight transfer, visibly covering a substantial distance. The same balloon behind her grows in place at the start and has not touched her. Spectators on both sides shift from cheering to looking upward in surprise. From approximately 4.3 seconds, those near the start are physically pushed by the expanding surface, then launched diagonally upward and away from its center in succession. Spectators farther along the runway are pushed afterward, following the blockout timing. These launches happen in the background while the lead keeps running. Running direction and scene positions remain consistent across cuts.
7.1–9.2 seconds: Cut to a slightly wider tracking view from beside the ramp, still centered on the lead. She reaches its foot and naturally steps onto the slope, beginning to run upward. Her stride shortens, her body leans forward and her feet alternate in firm contact with the ramp. In the background the giant surface continues expanding sideways, successively contacting spectators near the finish and launching them diagonally upward, away from the center toward the outside pool deck. Colorful cups and drinks fly with them. People follow continuous parabolic trajectories out of frame. All launches remain in the background while the lead keeps climbing.
9.2–12.4 seconds: Cut to a medium-close side view of the ramp that clearly retains her whole body, the balloon surface behind her back and the ramp in front. She has climbed the lower half and is still far from the top. The balloon keeps inflating at its fixed starting center; its extended surface first touches her back, then gradually closes the gap between her and the ramp. She braces both hands on the ramp, bends her elbows and leans forward until her front touches the slope. Her feet are staggered on the ramp with bent knees supporting her. The soft surface flattens against her back and behind her hips, trapping her between balloon and ramp and preventing another uphill step. Show the continuous order: climb first, back touches balloon, hands brace, front contacts ramp, then stop while trapped. She briefly tries another step but remains held in place. Inflation slows markedly and does not push her onward to the top.
12.4–15 seconds: Cut to her face from a side angle slightly toward the front, preserving the established trapped position. Her face and breathing remain clear. The frame edges still include the ramp in front and pink surface behind. Her body stays trapped; cutting closer does not change contact. A failure buzzer sounds. She turns her head slightly, first surprised, then comically defiant and resigned, and exhales softly. Hold that failure reaction to the end; add no new spectator launches.
Cinematography: Edit in the specified order: opening face close-up, whole-body running track, slightly wider ramp view, medium-close contact view and final face close-up. Use natural perspective and human-height side camera positions rather than a global overhead view. The camera stays on the same side of the runway with continuous screen direction. Observe the gap between balloon and ramp from beside the slope, keeping back contact, front-to-ramp contact and hand and foot support clearly visible. Only then cut to the face; the balloon never obscures it.
Sound: starting tone, fast footsteps, increasingly exaggerated inflation sound, cheers turning to startled cries, light sounds of cups and drinks scattering, water waves, then a brief failure buzzer and the contestant's comic reaction sound.
There is only one lead contestant and one intact pink balloon. It grows in place without chasing her, splitting or bursting. At the end she is trapped between the balloon and the broad ramp: she does not straddle, ride, get launched, slide down, get swallowed by the balloon or succeed by reaching the top first. The ramp stays fixed and contact between body, balloon and slope remains continuous. Spectators are pushed before launching outward, never levitating without contact. Human limbs remain complete. Comic compression and launches, no gore. No subtitles, logos or watermarks.
26s Hong Kong Property Tour: Floor Plan + BlockoutHolyCrab Studio
Source prompt26 seconds | 16:9 landscape | Hong Kong Cantonese | Live-action female property agent tour
[Reference mapping]
@Image 1 "01-floor-plan.webp": the real layout, entrance, corridor, and furniture positions.
@Image 2 "02-living-room.webp": the window-side living room, raised storage platform, mountain view, and interior finishes.
@Image 3 "03-kitchen-dining.webp": the open kitchen, dining table, and walking space.
@Image 4 "04-main-bedroom.webp": the main bedroom bed, storage cabinetry, and perceived room scale.
@Image 5 "05-second-bedroom.webp": the second bedroom doorway view, window-side desk, bed, and wardrobe. Keep its layout subordinate to @Image 1.
@Image 6 "06-presenter.webp": the only female property agent's face, side-parted long brown waves, earrings, beige suit, and white inner to
…
Open the detail page for the complete English production prompt with romanized Cantonese dialogue.
Hong Kong Grandpa vs. Gangsters: GTA-Style Five-Star ChaseHolyCrab Studio
Source prompt[Generation goal]
Use Seedance 2.5 Ultra Long Video mode to create an approximately 123-second, 16:9, 720p, 24-fps live-action Hong Kong action comedy. Use third-person open-world game cinematography throughout: a circular minimap at lower left, a white heart, green health bar and five wanted stars at upper right, plus an original weapon wheel when needed. Borrow only the game grammar; do not reproduce official characters, missions, maps or trademarked screen art.
[Lead identity]
The only lead is the same Hong Kong grandpa in his seventies: cropped white hair, lean muscular build, full black-grey tattoo across his left arm and shoulder, white vest with HolyCrab on the back, bright red retro running shorts with white piping, and black flip-flops. Face, age, height, tattoo side, clothes and
…
Open the detail page to view the complete prompt.
Red Hood & the Wolves | STORM IIHolyCrab Studio
Source prompt[Reference bindings]
@Video 1 controls only the matching blockout's positions, paths, occlusion, action timing and camera. Bind the only blue figure to @Image 1 (01-red-hood.jpg): preserve the original Red Hood's delicate face, blonde hair, raised bright-red hood, long red coat, grey dress, gloves and boots; no aging or basket. Bind every grey-white figure to @Image 2 (02-wolves.jpg): complete realistic wolf head, long muzzle, pointed ears, thick furred neck, wolf paws and loose collegiate suit; upright with two arms and two legs. @Image 3 (03-forest.jpg) supplies only the dusk forest, pink sunset and wide layered earth-and-rock terraces, without changing foot placements. Do not inherit studio backgrounds, lineup compositions, blockout colors, featureless heads or plastic material. The blu
…
Open the detail page to view the complete prompts.
Speed vs. PowerHolyCrab Studio
Source prompt[Reference roles and identity lock]
Use @Image 1 only to lock Rin: an adult woman with the exact live-action face, neck-length silver-white hair, grey knitted mini dress, a slim agile 1.68 m build, and a compact silver-blue high-speed mechanical fist on her left arm. Use @Image 2 only to lock Mara: an adult woman with the exact live-action face, deep warm-brown skin, a long burgundy braid, the original black outfit, a tall powerful but not excessively muscular 1.92 m build, and a heavy red-black hydraulic fist on her right arm. Use @Image 3 only for the live-action cyberpunk district, central fight space, HolyCrab screen, night neon, wet pavement, barriers, and spectator layout; do not inherit any identity from the location reference.
There are exactly two lead fighters throughout: Rin a
…
Open the detail page to view the complete prompt.
Crab Squat: Water Wall ChallengeHolyCrab Studio
Source prompt[Generation Goal]
Create a 15-second live-action water-game-show challenge. The only contestant, Xia Yan, must copy the crab-squat opening before a moving wall reaches her. Her pose is correct, but the opening is slightly tight at the elbows and hips, so the rigid wall keeps moving and pushes her into the pool. Use the look of a real Japanese outdoor variety show at bright summer noon: saturated broadcast color, natural skin texture, light physical comedy, realistic gravity, inertia, body contact, and water physics. Cuts occur only at the stage boundaries below; no slow motion.
[Reference Roles]
Xia Yan corresponds to @Image 1. The close-up, front full-body view, and side full-body view all depict the same adult woman. Use only her single facial identity, black high ponytail, features, ma
…
Open the detail page to view the complete prompt.
Red Hood: The Seventh Girl
1950s American Diner Frozen Time Rewind@TechHalla
Source promptPhotorealistic cinematic 1950s American diner, chrome stools, red vinyl, neon glow and checkerboard floor, shot with modern lived-in realism and soft natural window light. Subtle handheld texture, warm practicals, rich period detail, heavy film grain.
0-4s: [Medium Wide] A striking young woman in her early 20s sits alone at the counter, calm and slightly amused, slowly sipping a tall thick milkshake through a straw. Behind her a young waitress in classic uniform approaches with a tray of eggs and bacon in one hand and a full glass coffee pot in the other. An older lady starts rising from a nearby booth.
4-8s: [Dynamic Tracking] The older lady collides hard into the waitress. Tray, plate, eggs, bacon and coffee pot explode upward in chaotic slow motion. Coffee erupts into long liquid ribbons and perfect suspended droplets. Camera immediately begins a smooth continuous orbit around the impact. Time locks completely at the peak of the spill. Every face freezes in pure shock. Only the girl at the counter keeps moving, completely unfazed.
8-17s: [Slow 360° Orbital] Camera glides in a full elegant orbit through the frozen diner. Coffee hangs in mid-air as glassy ribbons and spheres with perfect volume and surface tension. Bacon strips, eggs and the spinning tray float weightlessly. Patrons and waitress remain locked in startled expressions. The girl at the counter takes one slow, deliberate sip, eyes half-lidded, almost bored, while the entire frozen world (except her) begins an elegant reverse: every droplet, every piece of food and every person rewinds smoothly back to the exact starting positions.
17-24s: [Medium Shot] Rewind lands perfectly. Waitress stands balanced again with tray and coffee pot. The girl lifts her eyes, raises two fingers in a small casual gesture and softly calls the waitress by name. The waitress turns toward her just before the older lady begins to stand, completely avoiding the collision. A tiny private smile crosses the girl’s face.
24-30s: [Extreme Close-Up] Hard cut to her face as she takes one last slow sip. Soft knowing smile, eyes almost closed in quiet satisfaction, like she has done this a hundred times. Shallow depth of field, creamy bokeh of the neon diner behind her.
Photorealistic, ultra-detailed fluid physics, perfect motion blur only on moving elements, stable characters, cinematic lighting, heavy natural film grain, no artifacts, movie-level temporal coherence, high rewatch value.
Choreographed Dance with Anime Style Overlays@Sairah
Source promptSetting: A cozy indoor room with warm, ambient lighting, featuring posters on the wall, a hanging lamp, and modern furniture.
Subject: A young woman with long dark hair, wearing a gray hooded jacket, performing a rhythmic, choreographed hand and body motion dance in front of the camera.
Key Visual Effects:
Animated Framing & Transitions: As she moves her hands to form frames and geometric shapes (triangles, rectangles) in front of her face and upper body, colorful animated overlays appear inside the framed spaces.
Anime & Superhero Styles:
The initial overlays display an anime-style digital avatar matching her expressions.
Midway through, the overlay switches to a Spider-Gwen / Spider-Verse comic style, complete with a hooded mask and neon cityscape backgrounds.
The animation dynamically shifts and transforms along with her hand movements, smoothly blending back into real life by the end of the clip.
Ultra-Realistic K-pop Music Video@Sharon Riley
Source prompt30-second ultra-realistic K-pop MV featuring two young East Asian women with flawless synchronization, cinematic lighting, glossy skin, realistic hair and fabric physics, natural body motion, and 4K live-action quality. Vibrant hot pink, electric blue, and silver color palette. 0–2s: Wide shot in a bright circular pink studio with reflective floor. Pink-haired woman (left) and black-haired woman (right) perform energetic opening pose and synchronized dance. 2–4s: Medium close-up of the black-haired woman on a blue spotlight stage, confidently pointing at the camera. 4–6s: Pink-haired woman dances before shimmering blue-silver tinsel curtains, dramatic hair flip and fluid arm movements. 6–8s: Back to the pink studio. Both perform synchronized choreography with sharp arm waves, hip sways, and strong formations. 8–10s: Extreme close-up of both faces against a blue background, glossy makeup, subtle smiles, and direct eye contact. 10–14s: Solo shots at the tinsel backdrop. Pink-haired woman mouths lyrics and gestures confidently, followed by the black-haired woman with relaxed jacket styling. 14–18s: Pink studio. Coordinated jacket choreography, hair flips, powerful synchronized dance, ending hands-on-hips. 18–22s: Glamour close-ups. Black-haired woman under glittering bokeh lights, then pink-haired woman with wind-blown hair against a soft pink background. 22–24s: Blue spotlight stage. Mirrored black-haired performer effect with synchronized spins and flowing hair. 24–26s: Both walk confidently toward the camera in front of shimmering tinsel curtains, reflections visible on the floor. 26–29s: Final synchronized dance and ending pose in the pink circular studio, standing together and looking into the camera. Style: Hyper-realistic live action, Seedance 2.5-quality motion realism, perfect lip sync, natural weight shifts, flowing hair, realistic fabric simulation, polished K-pop music video cinematography.