SEELE TV / Prompt archive

181 Seedance 2.5 popular video prompts.

Explore 181 receipt-validated Seedance 2.5 video prompts with more than 200 English words: 165 current-page records and 16 preserved historical-only records. Every card keeps the complete prompt, author, directly playable source video, self-hosted first-frame poster, lightweight original-post link, copy control, and SEELE Workspace handoff together.

Video generation177 text + 4 reference181 mapped cases

Exact mapped collection

All cases

24 of 181 cases
  1. 001
    MAX (@maxxmalist)post 2087289253466108215
    TEXT
    View original post on X ↗

    Prompt · 580 English words · 3,719 characters · daily-source-public-card

    CAMERA: Handheld DV 16mm daily vlog footage. The video MUST begin with Emma holding the camera at arm's length in selfie mode while stepping outside her apartment building with her dog. The entire video remains handheld selfie-style. The camera itself is never visible.
    
    Keep subtle handheld shake, drifting composition, gentle autofocus hunting, small rushed reframing, slight uneven movement, exposure breathing, occasional imperfect framing, and natural motion blur throughout. The footage should feel genuinely handheld and imperfect, like a real person's casual morning vlog.
    
    LOOK: Warm analog tape texture with gentle film grain, slightly softened sharpness, subtle halation around sunlight, realistic skin tones, low contrast, tiny exposure shifts, and natural motion blur. Authentic everyday footage rather than a polished commercial.
    
    STYLE: Relaxed morning lifestyle vlog. Quiet, cozy, spontaneous, and natural. Emma speaks casually to the camera with short, believable sentences and comfortable pauses. She occasionally looks at her dog while talking. Keep the pacing slow and realistic. Do NOT rush actions or dialogue.
    
    CHARACTER: EMMA — a beautiful white woman in her mid-20s. Long light brown hair in a messy ponytail, green eyes, minimal makeup, oversized gray hoodie, black biker shorts, white sneakers, and a small crossbody bag. She is walking a happy golden retriever.
    
    SETTING: A peaceful suburban neighborhood on a sunny morning. Tree-lined sidewalks, quiet residential streets, birds singing, a small neighborhood park with benches, green grass, and soft golden morning light. Very few people are around.
    
    SCENE — 30 SECONDS
    0–8 SECONDS:
    The vlog begins as Emma steps outside her apartment building with her golden retriever on a leash. She holds the camera in selfie mode and smiles naturally.
    She says:
    "Good morning. I swear, this guy has been waiting by the door for like ten minutes."
    She looks down at the dog and smiles.
    "He's ready to go."
    Keep her movements natural and slow. The dog stays beside her.
    8–16 SECONDS:
    Emma walks slowly down the quiet sidewalk with the dog. The dog stops to sniff a tree.
    Emma pauses and looks down at him.
    She laughs softly:
    "Of course we have to stop at every single tree."
    She waits for the dog instead of pulling him immediately.
    "Take your time."
    The dog finishes sniffing and they continue walking.
    16–23 SECONDS:
    They enter the small neighborhood park. Emma continues holding the camera in selfie mode while walking slowly.
    She briefly turns the camera slightly toward the dog, then back toward herself.
    She says:
    "It's actually so nice out this morning."
    She looks around at the trees.
    "I really should come here more often."
    Keep the camera movement smooth and natural. Do not introduce any new actions.
    23–30 SECONDS:
    Emma continues walking through the park with the dog beside her. She looks down at him and smiles.
    She says:
    "He's definitely happier than I am right now."
    She laughs quietly.
    After a short pause, she looks back into the camera:
    "Anyway, coffee time. See you later."
    She gives a small natural wave and ends the recording.
    
    IMPORTANT: The entire video is exactly 30 seconds long. Prioritize realistic pacing, continuity, and visual accuracy over fitting in more events. Do not compress actions. Do not make Emma move or speak unnaturally fast. Every action should happen sequentially and have enough time to render correctly. Keep the dog movement simple and physically realistic.
    No cuts. No editing. No montage. No time-lapse. No camera placement. No additional characters. No additional dialogue. No sudden scene changes. The entire video should feel like one continuous authentic morning vlog generated from a single prompt.
  2. 002
    Pierrick Chevallier | IA (@charaspowerai)post 2086512920725238128
    TEXT
    View original post on X ↗

    Prompt · 260 English words · 1,677 characters · historical-snapshot-public-card

    POV motocross sequence on an erupting volcano. The entire scene is from the rider’s perspective, with helmet-camera realism, natural head movement, violent suspension shake, dust on the lens, heat haze, flying ash and intense engine sound. The rider never drives on lava. He stays strictly on rocky volcanic paths, ash-covered trails, loose black gravel and narrow ridges while avoiding lava flows and glowing cracks.
    
    0-5s: POV accelerating downhill on a steep black volcanic trail. Gloved hands, handlebars and front fender visible. Lava flows are visible nearby on both sides at a distance, but the bike remains on solid rocky ground. Small rocks bounce across the trail, smoke rises in the background.
    
    5-10s: The rider weaves through falling debris and sharp turns on a narrow ash-covered path. A fresh lava stream cuts across the route ahead, so he sharply turns onto a higher rocky side trail, avoiding the lava completely.
    
    10-15s: The path narrows along a ridge. The rider jumps over a glowing crack in the ground, clearing it cleanly without touching the molten area below, lands hard on solid volcanic rock, and keeps control while larger stones tumble behind him.
    
    15-20s: A dense wave of ash rolls down the slope. The rider threads between two collapsing boulders, descends a final rocky path, and bursts onto a safer lower ridge far from the lava. He briefly looks back toward the erupting crater while still riding away at speed.
    
    Photorealistic motocross physics, realistic suspension movement, coherent volcanic terrain, practical disaster realism, no third-person shots, no fantasy look, stable bike geometry, intense POV immersion.
    #DreaminaCPP  @dreamina_ai
  3. 003
    Nexlow (@nexlowx)post 2086473834442437029
    TEXT
    View original post on X ↗

    Prompt · 507 English words · 3,247 characters · historical-snapshot-public-card

    SHOT 1: ECU, 85mm push-in / on the phone screen as it shakes on rumpled sheets / SFX: alarm, sheet rustle.
    
    SHOT 2: WS, 35mm handheld jolt / Rhythmic cut into her jolting upright through side light, throwing the blanket aside, planting her feet in one rushed motion / SFX: mattress bounce, blanket whip, sharp breath.
    
    SHOT 3: MCU, 50mm slide / Cut on action into face wash at the sink, droplets catching the top light / SFX: faucet rush, water slap.
    
    SHOT 4: Insert, 85mm lens focus / Match cut into the toothbrush, mint foam and mirror eye / SFX: bristle scrape, sink drip.
    
    SHOT 5: Interior fridge view, 24mm wide / Object pass into the camera inside the fridge looking out as the door snaps open, blue light framing a hurried grab / SFX: fridge hum, bottle clink, shelf scrape.
    
    SHOT 6: Insert, 50mm handheld / Rhythmic cut into egg and toast hitting the pan under warm practical light / SFX: butter sizzle, chop tap.
    
    SHOT 7: MCU, centered 50mm push-in / Match cut into one rushed bite, a clock glance, an immediate rise / SFX: crunch, ceramic clink, chair scrape.
    
    SHOT 8: Bird’s-eye, 35mm overhead / Match cut on action as the sleep tee disappears under a fitted top and jacket; keys, transit card, and bag scooped in one grab / SFX: fabric whip, key jingle, zipper pull.
    
    SHOT 9: MS, 35mm pan / Camera slips into the rushed outfit change / SFX: fabric whip, key jingle, bag rustle.
    
    SHOT 10: Insert, 50mm overhead / Match cut into lace-up shoes slamming on, laces yanked tight in one impatient pull / SFX: sole thump, lace tug, short breath.
    
    SHOT 11: WS, 24mm parallel / Whip pan transition into her rushing through the corridor into bright light without breaking stride / SFX: latch click, rapid footsteps, hallway air.
    
    SHOT 12: MS to CU, 35mm glide into 85mm push-in / Sound bridge into the metro as she grips the pole and slips through the closing doors, chrome streaking, city blurring / SFX: train rattle, door chime, light breath.
    
    SHOT 13: Insert to MCU, 50mm snap zoom / Smash cut to the office entrance, access card on the reader, glass door unlocking, dropping into her chair / SFX: badge beep, door click, laptop chime.
    
    SHOT 14: OTS, 35mm handheld / Rhythmic cut into fingers racing across the keyboard, blue monitor light on her face / SFX: keyboard clicks, notifications, mouse click.
    
    SHOT 15: WS, 24mm pull-out / Match cut back to the bedroom composition from the opening shot as she collapses onto the bed / SFX: body drop, fabric rustle, heavy exhale.
    
    A few things worth noticing about why it’s built this way:
    
    Every shot names its transition in. Not “then this happens” but cut on action, match cut, object pass, sound bridge. The connection is specified, so the sequence has rhythm instead of just order.
    
    Shot 15 deliberately matches Shot 2’s composition. Same bedroom, same framing, opposite energy. That bookend is what turns a montage into a day.
    
    The SFX line is separate on every shot and never repeats. Bristle scrape, shelf scrape, lace tug. Audio detail at that resolution is what makes fifteen fast cuts feel like one continuous space.
    
    And the lens changes carry meaning, not variety. 85mm for the intimate inserts, 24mm for the wides, a snap zoom for the smash cut. Focal length is doing narrative work.
  4. 004
    Glitter Gal (@glitterpixely)post 2086471938650624231
    TEXT
    View original post on X ↗

    Prompt · 945 English words · 6,343 characters · historical-snapshot-public-card

    [REF]
    
    @Image
     1 defines only the rain-soaked ancient bronze arena: giant suspended bell, flooded stone lane, furnaces, cranes, timber-and-bronze architecture, orange firelight, storm light, and deep scale. No background people.
    
    @Image
     2 defines only the hooded fighter’s face, black bob haircut, eye covering, rust-brown layered clothing, wraps, pendant, belt gear, proportions, and footwear. Exclude the white background and static pose.
    
    @Image
     3 defines only the teal-haired fighter’s face, black-and-teal bob haircut, distressed teal-and-black clothing, belt gear, gloves, boots, and single hip blade. Exclude the white background and static pose.
    [LOCK]
    Exactly two fighters and one blade. Do not swap faces, hair, clothes, dialogue, weapons, or effects. The hooded fighter begins by the furnace tower and uses rust-red spatial seals plus an original hand-seal teleportation jutsu. The teal-haired fighter begins beneath the bell and uses cyan blade energy. Preserve the axis between those landmarks. Every teleport shows departure, briefly empty space, then one arrival; the previous position fully disappears. No clones or persistent afterimages.
    [STYLE]
    High-end stylized anime action-RPG duel. Fast, tactical, forceful combat with rapid hard cuts, explosive acceleration, readable silhouettes, sharp impact endpoints, and immediate environmental damage. Both fighters attack, evade, intercept, and counter. No slow motion or prolonged power-up.
    [SEQUENCE]
    Shot 1: Extreme wide down the flooded lane; rain lashes sideways, furnaces flare, and the bell sways over both fighters. Push quickly into paired medium shots. In English, cool and challenging, the teal-haired fighter says, {Take off the blindfold.} The hooded fighter listens with mouth closed, then replies in English, calm and amused, {Make me stay long enough.} The teal-haired fighter keeps their mouth closed.
    Shot 2: Low lateral tracking. Before the reply fades, the teal-haired fighter explodes forward, the first step blasting water backward, and attacks with one cyan draw-cut. The hooded fighter collapses into a thin rust-red seal ring, fully vanishes, then reappears behind the attacker with a glowing palm strike. The teal-haired fighter spins and catches the palm on the blade flat. A white-hot bronze pressure ring, violent camera jolt, and crater throw water and tiles outward.
    Shot 3: Medium-wide on the same axis. The hooded fighter attacks with a sweeping kick, teleports above the counter-slash, then drives a heel into the lane; the teal-haired fighter rolls clear as wet stones buckle. Rain bends toward the next exit before it opens. Reading the clue, the teal-haired fighter pivots early, intercepts the reappearance with a shoulder check and spinning kick, and launches the hooded fighter through a wooden scaffold. Braces bend and wood bursts; the hooded fighter lands crouched.
    Shot 4: Clean waist-up close-up of the hooded fighter’s two unobstructed, anatomically correct hands. At fast but readable speed: palms clap; index and middle fingers interlock into a square lattice; thumbs hook as wrists rotate outward; fingertips close into a triangle. Each sign creates one concentric rust-red geometric seal. The pendant flashes, nearby raindrops halt, the bell hums, and the seals compress into a dark bronze sphere. No extra fingers, fused hands, or hidden poses. The teal-haired fighter rushes in to interrupt. Holding the final seal, the hooded fighter says in English with sudden force, {Resonance Jutsu: Ninefold Gate.} The sphere implodes with a vacuum crack; the hooded fighter vanishes before the cyan thrust lands. The bell tolls once and three gates ignite across walls, puddles, and beams.
    Shot 5: Three rapid hard cuts show the single hooded fighter teleporting sequentially through three gates, never simultaneously: above with a descending palm; beside the bell chain with a sweeping kick; at ground level with a rust-red thrust. The teal-haired fighter evades the palm, blocks the kick with the blade hilt, and parries the thrust. Each contact creates a cyan-and-rust flash, warped rain, bronze sparks, a vacuum pop, and hard recoil. Re-establish both full bodies after the exchange.
    Shot 6: Tight shot on rain curving toward the next exit. The teal-haired fighter predicts it, attacks the empty space first, and splits the forming gate with one cyan slash. The hooded fighter reappears off balance but counters by trapping the blade between two palm seals; metal screams and the ground fractures. The teal-haired fighter elbows free and cuts upward. The hooded fighter bends under the blade, teleports above it, and dives with a two-palm seal strike. The teal-haired fighter raises the blade flat to intercept. Their collision detonates a huge spherical cyan-and-rust shockwave: rain blasts outward, furnace flames flatten, scaffolds shake, stone splits across the lane, and the bell booms. Both fighters are hurled apart and skid through shallow water. Camera shakes only at impact, then stabilizes.
    Shot 7: Low wide aftermath. Both rise into guarded stances as rain crashes back into the empty sphere. Rust-red seals dissolve into bronze dust; cyan electricity drains from the blade into puddles. In English, breathing hard but composed, the teal-haired fighter says, {Every exit leaves a sound.} The hooded fighter stays silent with mouth closed. End with both standing and the swinging bell between them.
    [VFX / CAMERA / AUDIO]
    Keep faces, hands, contact points, and landings readable. Use whip-pans, short tracking bursts, directional motion blur, displaced rain, hard cuts, and brief impact shake. Hooded effects originate from the hands and pendant, form as nonverbal rust-red geometric seals, open along the travel path, snap shut after arrival, spark on collision, and dissolve into dust. Teal effects originate only from the blade, follow each slash, flare on contact, and dissipate into cyan sparks and vapor. Heavy rain, splashing boots, cloth snaps, blade rings, teleport vacuum cracks, bass-heavy impacts, cracking stone, bending metal, debris, furnace roar, and bell resonance. No BGM; only dialogue, ambience, and action sounds. No subtitles, narration, readable text, logos, gore, extra fighters, extra weapons, face swaps, wardrobe changes, body merging, extra limbs, VFX-covered faces, or constant camera shake.
  5. 005
    MagicAI (@magic_ai_skill)post 2086468227547467953
    TEXT
    View original post on X ↗

    Prompt · 1766 English words · 10,114 characters · historical-snapshot-public-card

    A thirty-second chase and fight in a rain-soaked industrial ninja city at night. 2D hand-drawn cel animation in the style of a famous ninja anime. Stage the action widely across that world: rooftops, chimneys, pipe runs, iron bridges, canals, power lines, interior passages. THE SHOT SIZE CHANGES DRASTICALLY WITH EVERY CUT — an extreme wide where she is a speck, then a close-up where an eye fills the frame. The same size never repeats back to back.
    
    THE STAGE: a vertical city stacked in black iron and rusted pipework.
    
    Dozens of thin spires, lightning rods, antennae and chimneys stab up at different heights and thicknesses — some twice the height of their neighbours, some leaning — so no pattern reads in the skyline. Identical blocks never repeat in a row — storey counts, widths and leans all differ.
    
    IN WIDER SHOTS THE FRAME LAYERS FRONT TO BACK. Something near — a pipe bundle, a railing, an iron stair — cuts across and breaks the view; beyond it wet metal roofs and a lattice-truss arch bridge; further back a forest of spires blurred to silhouette by rain and steam, fading with distance so depth reads. Never a mirror-symmetrical corridor.
    
    Wherever sky shows, black cloud hangs low and rain slashes diagonally. Chimney steam blows sideways and drifts flat; water pours in ropes from gutters. The windows are NOT a lit grid — only a scattered few burn orange. Red circular emblem signs hang here and there. A black canal runs below with the lights smearing long across its surface. Metal taking the rain head-on carries long wet highlights, while what sits under eaves or in the shadow of pipework stays dry and dark. The background is held down in a desaturated grey-blue; only the orange window light is warm.
    
    THE WOMAN: an East Asian woman of about twenty. Long straight black hair past her waist, parted in the middle. A white sleeveless wrap top with a standing collar, cut deep at the front so the black under-layer shows; a black obi at the waist with a white braided cord and tassel over it. A black wrap skirt slit long at the front, a cream underlayer patterned with cherry blossom and water beneath it. A white band and black pouch strapped to her right thigh, fishnet below it. Her whole left arm is sheathed in black plate armour running down to a fingerless glove, with a silver band on the left upper arm. Black ankle-wrapped heeled sandals. Almost no expression. She carries no sword. Instead she switches weapon every cut — punches, kicks, parries with the armoured guard, and kunai drawn from the thigh pouch. The same attack never appears in two cuts running. SHE NEVER STAYS IN ONE PLACE — in every cut she covers ground: running along pipe runs, climbing a chimney, leaping roof to roof. Her face, hair, outfit and gear stay identical from the first frame to the last.
    
    THE UNIT: white hooded cloaks marked with teal-tinged falling-drop patterns, black masks, dark indigo garb and bandaged shins beneath; only the eyes show. In wider shots several are in frame at once with more behind. Silhouettes and weapons differ by role — a chain-sickle trailing, a straight blade drawn, a short curved blade held reversed, a chain coiled in a fist. Cutting her off, they exhale white mist that swallows the view; inside it the cloaks read only as silhouettes.
    
    THE CAPTAIN IS READABLE BY SILHOUETTE ALONE. A full head taller, shoulders squared wider, cloak to the ankle with a ragged pointed hem dragging on the wet deck. His hood is deep and hollow-black inside, and above a PALE face-plate only the eyes show — every other mask in the unit is dark, so his is the one bright face in the crowd. A thick neck guard and a metal ring, a round metal disc hung at the chest, a leather harness crossing his chest at an angle holding several short blades, and a long wooden tag on the wide indigo sash at his waist. He alone walks with his long blade already drawn. When he moves, whoever is in front steps aside without a word, and around him alone the falling rain turns to white mist and settles low about his feet.
    
    THEY DO NOT LINE UP. One crouches on a railing, one hangs off a truss diagonal, one stands mid-deck, others are silhouettes back in the rain — no two at the same height. Nor do they all look one way at once: the gaze travels back from the front rank a beat at a time, one still watching the captain, another wiping rain off with a hand. Their faces are hidden, so their feeling reads through posture — one dropping his shoulders, one giving half a step back, one pulling a chain taut.
    
    AURA: a vivid PINK aura rides the outline of her body AT ALL TIMES. It is already on from the first frame to the last — she never forms a seal or strikes a pose to switch it on. The background is desaturated grey-blue, so this pink is the only colour that pops on screen. Running or leaping leaves long afterimages of it behind her. The instant a hand or foot lands, the aura bursts from that point and the water on the ground rises with it, hardening into blade shapes and scattering. The same pink sits in her eyes.
    
    CAMERA: use the devices of a current Hollywood action film. Mix in cut transitions where a foreground element — a pipe, a railing, a swinging cloak — sweeps across the lens and wipes the frame. On a change of direction the frame WHIP PANS hard and the background smears. Jumps and falls carry a hard-tilted horizon that levels on landing. The camera overshoots her, drops behind, catches up. When a weapon comes forward, focus RACKS from the weapon in front to the face behind it. Just before a finishing blow the speed ramps down, then snaps back to full speed on contact. In the cuts that follow her, the frame shakes very slightly.
    
    ACCUMULATED DAMAGE: broken pipes, bent railings, chains buried in walls and the fallen all stay where they are. Nothing is removed or redrawn between cuts — the wreckage only builds as the video goes on.
    
    ANIMATION GRAMMAR: a decisive blow cuts to a single-frame IMPACT FRAME — the image inverts to white and black with radial speed lines. Fast movement carries long smear afterimages stretched along the direction of travel. Rain is drawn as white streaks slashing diagonally across the frame.
    
    0-5s [EXTREME WIDE HIGH ANGLE PLUNGING INTO LOW-ANGLE MEDIUM] The whole city spread out below — spires and chimneys past counting, iron bridges between them, the black canal far down. She crouches on a spire top at the edge of frame as a tiny silhouette, then throws herself off. The camera dives with her between the spires, pulls up level with an iron bridge and flips to look up from beneath it. The white cloaks are scattered there at every height, their heads tipping back one rank at a time to track what is dropping toward them, and the captain steps forward as the ones in front move aside.
    
    5-8s [GROUND-LEVEL TRACKING] The camera rides almost against the wet pipework. She drops in from above and lands two-footed on the pipe run, water bursting out around her boots, then runs it toward the bridge as a chain-sickle whips in and buries itself in the pipe. She steps onto that chain and springs off it, driving an elbow into the jaw of the man in her way.
    
    8-12s [WIDE, CAMERA LOCKED OFF] The camera holds beside the bridge while the action passes in front of it. She enters frame left and runs its whole length as white cloaks close from both sides; she alternates punches and spinning kicks, pink aura and water blades bursting wherever she passes, five or six driven off over the railing. She exits frame right.
    
    12-15s [EXTREME CLOSE-UP, zoom in along the arm] At the far end of the bridge, a straight blade comes in head-on. As she knocks it up with her armoured guard, TIME DROPS INTO SLOW MOTION, the camera SLOWLY ZOOMING IN along that arm until the point of contact fills the frame. On contact it SNAPS BACK to full speed, an impact frame flashes, and the blade snaps and flies.
    
    15-18s [EXTREME LOW ANGLE, vertical climb] She vaults the bridge railing and throws herself down; the camera falls with her to the surface of the canal and turns to look up. Chain-sickles come after her but every one misses and bites into the pipework on the wall. She uses those chains as footholds and kicks upward in a zigzag with the camera rising alongside.
    
    18-22s [LONG SHOT, lateral tracking] Rooftops stream past below the frame. She leaps roof to roof as white cloaks run her down from behind and alongside. One cuts her off and exhales white mist that swallows half the frame, cloaked silhouettes shifting inside it. She throws kunai from mid-air and bursts out of the mist, three flung aside.
    
    22-26s [KNEE SHOT, orbit] A rooftop still strewn with the chains driven into it earlier and bent railings. She lands in the middle of it and spins like a top, taking two of them down with that turn. Water rises in a ring along the aura into a vivid pink hoop. She then goes on hitting the rest with punches and kicks, one after another. The camera swings a full circle around her the opposite way, pink bursting at every point of contact, six or seven going down in order.
    
    26-30s [MEDIUM INTO EXTREME CLOSE-UP] The captain, who has been on her the whole way, cuts off the roof's edge and faces her. His long cloak billows in the rain and he draws his blade without a sound. They spring at each other and meet head-on, and the camera drives straight into the point of contact. Her armoured guard and his blade lock together, that point fills the frame, and the video ends on the frame where pink light bursts out of the join.
    
    This must read as hand-drawn cel animation. Line weight stays consistent across cuts, shadows are hard-edged cel shading rather than soft gradients, character designs stay identical cut to cut, and hands always have five fingers. Rain is hand-drawn white streaks, not 3D particles, and the backgrounds are painted plates, not photographs. Reflections on wet metal are painted highlight shapes. No glossy 3D-render texture, no faces drifting subtly frame to frame, no clothing folds or ornaments multiplying on their own, hands and feet never lose their shape, no rubbery water-like motion, no artifacts.
  6. 006
    Tbros6868 (@tbros6868)post 2086467909770166740
    TEXT
    View original post on X ↗

    Prompt · 1332 English words · 8,711 characters · historical-snapshot-public-card

    [Style] Large-scale Japanese variety show water obstacle challenge special program (Japanese TV Game Show, Live-Action Broadcast), multi-camera real-time broadcast, 4K photorealistic photography, high-saturation summer colors, real-time throughout without slow motion.
    
    [Duration] 30 seconds
    
    [Scene] Sunny outdoor large leisure pool obstacle course, five stages lined up from left to right. Stage 1: 5-meter high wooden jumping platform, Tarzan rope with pulley on overhead cable. Stage 2: 3-meter diameter red and yellow circular floating disc on the water, rotating continuously at a constant speed on an underwater axis, slippery surface. Stage 3: Four square floating blocks of varying distances, bobbing up and down with the waves. Stage 4: A slanted blue slippery climbing wall with grab ropes hanging from the top. Stage 5: A huge yellow cylindrical pipe spanning the water, wet reflective vinyl surface printed with red flame patterns, rotating continuously at a constant speed by a motor, just thick enough to be hugged by arms and legs, the right end connected to a small finish platform, directly below is a clear pool with no safety mats. Background includes palm trees, large water slides, light stands, commentary booth, temporary stands full of spectators. The entire film moves from left to right.
    
    [Character] Challenger (adult Japanese female, strong and healthy athletic build, wearing clothes).
    
    [Fixed Items] The position, size, color, and connection of the five stages remain unchanged throughout the film; only one challenger is always in the frame; hair and clothes are dry at the start and only naturally soaked after falling into the water; the circular floating disc and yellow pipe must be continuously rotating in all shots where they appear.
    
    [00:00-00:03] Shot 1: Tarzan rope launch (Eye-level Medium → Wide Pull-back, ENG Camera)
    Visual: She stands on the edge of the 5-meter platform holding the rope, toes gripping the edge.
    Dialogue: "Zettai clear shimasu!" (I will definitely clear it!)
    Action: When the buzzer sounds, she kicks off forcefully, the pulley slides right along the cable, her body swings over the water in a pendulum arc, hair blown back by the wind.
    Commentary: "Mazu wa Tarzan Rope!" (First is the Tarzan Rope!)
    SFX: Start buzzer, pulley sliding, crowd cheering.
    
    [00:03-00:07] Shot 2: Landing on rotating disc (Fixed Side Shot)
    Visual: Fixed camera on the side of the floating disc, showing the person, rope, and disc.
    Scene: The red and yellow circular floating disc is rotating continuously at a constant speed on the water, the slippery surface reflecting light.
    Action: She releases the rope and lands on the disc; as soon as her feet touch, she is carried sideways and backwards by the rotation. She spreads her arms and takes small, rapid steps in the opposite direction to offset the rotation, knees bent and center of gravity low, stabilizing after a few wobbles.
    Expression: Eyebrows fly up, teeth clenched, then a quick grin.
    Commentary: "Kaitenban da! Taeta!" (It's the turntable! She held on!)
    SFX: Low-frequency hum of the turntable axis, sound of soles rubbing, a burst of cheers.
    
    [00:07-00:12] Shot 3: Floating board jumps (Dolly Track L→R)
    Camera: Dolly camera moving parallel to the direction of progress, tracking from left to right.
    Visual: Four square floating blocks bobbing up and down with the waves, unevenly spaced.
    Action: She jumps from the edge of the turntable, crossing the floating blocks with four consecutive single-foot jumps. On the second block she missteps, the block sinks sharply, her upper body lunges forward and arms circle wildly for balance. Her right foot splashes in the water before she manages to step onto the third block, and the final jump lands both feet on the fourth block.
    Dialogue: "Abuna...!" (That was close...!)
    Commentary: "Nimaime de kuzureta! Demo tsunaida!" (She faltered on the second one! But she recovered!)
    SFX: Muffled sound of blocks hitting water, splashing, intermittent gasps from the audience.
    
    [00:12-00:17] Shot 4: Slippery climbing wall (Front 3/4 Medium Shot)
    Visual: Front diagonal medium shot, showing the person, the sloped wall, and the grab ropes at the top.
    Scene: The blue slanted wall is covered in running water, reflecting light.
    Action: She runs up the wall, takes three steps, then her soles slip and she slides down a bit. She immediately drops her body to grab the wall, fingertips digging into the surface texture, and climbs again, right hand grabbing the rope hanging from the top, pulling herself up with arm strength.
    Expression: Neck muscles tensed, forehead creased, breathing heavily.
    Dialogue: "Yoisho, yoisho...!" (Heave-ho, heave-ho...!)
    Commentary: "Suberu kabe! Ude dake de nobotta!" (The slippery wall! She climbed it using only her arms!)
    SFX: Friction on the wet wall, rope tightening, applause from the crowd.
    
    [00:17-00:21] Shot 5: Hugging the rotating log (Rear Side Fixed Shot)
    Visual: Slightly rear fixed side shot, clearly showing the pipe is rotating.
    Scene: The yellow cylindrical pipe rotates continuously by a motor, a layer of water on the wet vinyl surface, red flame patterns rolling across the screen as it turns.
    Action: She jumps from the top of the slope and straddles the base of the pipe, clamping it with her chest, stomach, arms, and legs. The rotation immediately carries her to the right; she adjusts her center of gravity in the opposite direction and shuffles toward the finish by moving her arms and legs in small increments.
    Dialogue: "Ehh, mawatteru!?" (Eh, it's rotating!?)
    Commentary: "Kaiten maruta da! Kore ga sainankan!" (It's the rotating log! This is the hardest part!)
    SFX: Low-frequency motor sound, wet vinyl friction.
    
    [00:21-00:26] Shot 6: Flipped over - Limit before finish (Front Close-up → Medium Pull-back)
    Camera: Front close-up at the finish side slowly pulling back to a medium shot, camera axis remains unchanged.
    Action: The pipe continues to rotate, slowly flipping her body to the right. Her center of gravity passes the highest point of the pipe and she can't pull it back. Her right leg detaches first, flailing in the air, then her right hand releases to reach for the finish platform, her full weight hanging by her left arm and leg as the pipe continues to rotate right.
    Expression: Veins bulging at temples, arm muscles shaking, eyes wide.
    Dialogue: "Mou dame, matte...!" (I can't, wait...!)
    Commentary: "Kaiten ni maketa! Ato sukoshi!" (Beaten by the rotation! Just a little more!)
    Connection: Right fingertips are about 20cm from the finish platform, left hand still clinging to the rotating pipe.
    
    [00:26-00:28] Shot 7: Falling into water before finish (Fixed Side Shot)
    Visual: Fixed side shot of the pipe, showing the pipe, outstretched right hand, finish platform, and the water surface directly below.
    Action: As the pipe rotates further, the supporting left hand is turned to the underside and slips. Her body falls sideways into the pool under gravity, creating a large splash. The pipe continues to rotate in place after she falls.
    Dialogue: "Ahhh!"
    Commentary: "Ochita! Maruta ni mawasareta—!" (She fell! Spun off by the log!)
    SFX: Loud splash, gasps from the audience.
    
    [00:28-00:30] Shot 8: Water surface reaction ending (Water-level Close-up, Static)
    Visual: Water-level front close-up, static camera, focusing on the face.
    Action: She emerges from the water, wet hair sticking to her cheeks, wipes her face, looks toward the finish with a frown, and splashes the water with her hands.
    Dialogue: "Kuyashii!" (How frustrating!)
    Action: Turns her gaze back to the camera, frown relaxes into a shy smile, shoulders shrugging slightly. In the background, the yellow pipe is still slowly rotating.
    SFX: Huge cheers and applause peaking.
    
    [Audio] High-paced game show style BGM. Synchronized sound effects: crowd cheering, applause, laughter, start buzzer, pulley, rotating motor, splashes, friction, water drops. Clear natural Japanese dialogue, no other voices, lipsyncing. BGM lowers during dialogue.
    
    [Camera and Editing] Natural multi-camera TV broadcast, hard cuts only. Mix of ENG, wire, dolly, water-level, and telephoto shots. Maintain 180-degree rule and left-to-right progression. No high-speed camera moves, spinning, crash zooms, or drones. No slow motion, replays, freezes, or time jumps.
    
    [Prohibitions] Maintain consistency of face, hair, body, clothing, skin color, and number of limbs. Physics must be realistic (gravity, inertia, slipping, rotation). No teleporting, backwards movement, static air, body deformation, or background replacement. Healthy athletic variety show style, no clothing malfunctions. No real brand names, logos, watermarks, or gibberish text.
  7. 007
    Lad (@ladprofit)post 2086467607398617386
    TEXT
    View original post on X ↗

    Prompt · 320 English words · 1,981 characters · historical-snapshot-public-card

    CLIP 1, Getting ready (0:00–0:15)
    
    use @image 1 (damp hair, no makeup), @image 2 (blush/lipstick), @image 3 (curling hair), @image 4 (fit-check dress) as style and identity references only, not as start or end frames.
    
    0-3s: hard cut open, she stands at the bathroom vanity in a white robe, hair damp and pushed back, gently patting it dry with a small towel, no makeup yet, gaze on her own reflection in the mirror.
    
    3-6s: hard cut, she smooths on a light layer of lotion and dabs concealer under her eyes with her fingertip, focused on the mirror.
    
    6-9s: hard cut, she sweeps blush across her cheeks and applies lipstick, quick confident motions, still focused on the mirror.
    
    9-12s: hard cut, she curls a section of her hair with a curling iron, one hand holding it near her face.
    
    12-15s: hard cut, now in a fitted cocktail dress with soft curled hair, she turns side to side in a full-length mirror checking her look, small satisfied smile.
    
    voiceover (her voice, narrating over the visuals, not lip-synced, she is never shown speaking on camera): "Fresh out the shower, hair's still damp. Skin prep first, lotion, then a little concealer. A little blush, and this lipstick I've been obsessed with. Now let's get these curls going. Okay... this dress might be the one."
    
    audio: the voiceover plays over quiet bathroom ambience for the first four beats, shifting to quieter bedroom ambience for the last beat, no music, no on-screen dialogue.
    
    style: candid mobile camera quality, natural color, effortless aesthetic raw, hard cuts between every beat, no cross-dissolves, soft bathroom daylight through the first four beats, warm lamp light for the fit-check beat, deep focus, no artificial blur.
    
    constraints: preserve identity across all five beats using the reference images for face, hair, and build only, do not use any reference image as a literal start or end frame, no readable text, no logos, no extra characters, no morphing hands, no revealing or suggestive framing.
  8. 008
    simeon-sanai (@naiknelofar788)post 2086463744314683460
    TEXT
    View original post on X ↗

    Prompt · 521 English words · 3,563 characters · historical-snapshot-public-card

    Create a 30-second ultra-realistic multi-shot candid observational video of a young Korean woman relaxing naturally in her bedroom. Use multiple distinct shots and camera angles, not a single continuous take. The footage should feel like an accidentally captured real-life moment.
    
    STYLE:
    Handheld documentary realism, imperfect framing, subtle camera shake, gentle exposure breathing, autofocus settling slightly late, realistic skin texture, soft natural indoor light and shallow depth of field. Natural blinking, breathing, body movement and restrained authentic expressions. No posing, glossy commercial look or cinematic perfection.
    
    SUBJECT:
    A naturally beautiful young Korean woman in her early 20s with long dark hair. She wears a matching cotton pajama set: scoop-neck sleeveless top and loose shorts. Barefoot, minimal makeup, realistic skin texture.
    
    SETTING:
    A lived-in, slightly messy bedroom with an unmade bed, soft bedding and everyday personal belongings. She relaxes on her stomach across the bed while browsing a shopping page on a black smartphone. A house cat interacts naturally with her.
    
    SHOT 1 — 0–4s:
    She lies on her stomach, casually scrolling through a shopping page. She frowns slightly, then mutters in Korean: "아, 뭐 살랬더라..." ("Ah... what was I going to buy again?"). Natural Korean lip sync. Her bare feet gently sway behind her. A low handheld camera glides beside the mattress.
    
    SHOT 2 — 4–8s:
    A house cat jumps onto the bed, compressing the blanket and walking toward her arm. It gives one natural meow. The camera reacts with a tiny jolt, then reframes toward her face, hands and cat.
    
    SHOT 3 — 8–12s:
    She turns toward the cat and gently strokes it from forehead to shoulders. She affectionately says: "우리 애기 왔어?" ("Did my baby come?"). Accurate lip sync. The camera pushes closer through the cat's softly blurred foreground.
    
    SHOT 4 — 12–16s:
    Her friend's ringtone sounds. She looks down, checks the caller, swipes to answer and brings the phone to her ear. The camera makes a loose semicircular movement from a slightly tilted overhead angle.
    
    SHOT 5 — 16–21s:
    Her friend talks. She listens with a confused expression, then reacts: "어, 왜? 진짜 거짓말!" ("Huh? Why? No way, you're kidding."). She immediately bursts into genuine laughter. The cat kneads the blanket beside her. A close handheld side angle captures her profile and phone.
    
    SHOT 6 — 21–25s:
    A clear doorbell interrupts her laughter. She and the cat turn toward the bedroom door. She pauses, realizing her food has arrived, braces one hand on the mattress and begins getting up. The camera reacts slightly late before correcting back to her movement.
    
    SHOT 7 — 25–30s:
    Still holding the phone, she says in Korean: "어, 나 밥 왔다. 끊어." ("Oh, my food's here. I'll hang up."). She ends the call, gets off the bed and walks toward the door. The cat follows across the blankets. The camera tilts upward as she stands, ending with a natural handheld follow toward the doorway.
    
    AUDIO:
    No music. Raw realistic production sound: quiet breathing, bedding rustling, finger taps, cat movement, meow, faint purring, ringtone, call connection tone, muffled friend voice, accurate Korean dialogue and lip sync, genuine laughter, doorbell and call-ending tap.
    
    IMPORTANT:
    No subtitles, captions, logos, watermark or on-screen text. No duplicated subjects, slow motion, exaggerated acting or perfect stabilization. Keep movements spontaneous and observational. Maintain the same woman, outfit, hairstyle, bedroom and cat throughout.
    
    DURATION: 30 SECONDS
    ASPECT RATIO: 16:9
    TOTAL SHOTS: 7
  9. 009
    Ai Girllie (@inshrah_ali_)post 2086452771029647477
    TEXT
    View original post on X ↗

    Prompt · 290 English words · 2,141 characters · historical-snapshot-public-card

    Create a premium cinematic 15-second transformation story following the SAME young female protagonist continuously through three visual styles: realistic live-action → high-end anime/3D animation → Hollywood blockbuster.
    
    0–5s — REALISTIC WORLD
    A stylish young woman walks alone through a modern city at night.
    
    Rain falls lightly. Neon signs reflect across the wet street. She wears a sophisticated black streetwear outfit with subtle red accents.
    
    She hears a powerful hip-hop beat.
    
    She stops.
    
    Close-up of her eyes.
    
    She looks toward camera and begins a confident dance-inspired movement.
    
    Typography appears:
    “WHO ARE YOU?”
    
    Camera rapidly pushes toward her hand as she raises it toward the lens.
    
    5–10s — ANIMATED WORLD
    The exact hand movement triggers the transformation.
    
    The live-action city smoothly becomes a breathtaking high-end animated world.
    
    The SAME girl, SAME outfit, SAME pose and SAME movement continue without interruption.
    
    Stylized energy particles surround her. Buildings stretch upward. Neon colors pulse with the beat.
    
    She performs a powerful choreographed movement through the animated city.
    
    Typography dynamically forms around her:
    
    “WHO YOU CHOOSE TO BE.”
    
    Use fluid premium animation, detailed facial expressions, realistic cloth movement and cinematic camera choreography.
    
    10–15s — HOLLYWOOD BLOCKBUSTER
    During her final animated movement, the environment suddenly transforms into an epic Hollywood-style cinematic cityscape.
    
    The SAME girl lands on a rooftop overlooking a massive glowing metropolis.
    
    Realistic wind moves her hair and clothes. Dramatic clouds, atmospheric haze, anamorphic lens flare and powerful backlighting create blockbuster scale.
    
    Camera circles her as she turns toward the lens.
    
    Final beat.
    
    She confidently smiles.
    
    Huge cinematic typography appears:
    
    “BECOME UNSTOPPABLE.”
    
    Final hero frame with dramatic music impact and premium movie-trailer finish.
    
    VISUAL RULE: The transformation should feel like ONE continuous shot/story—not three separate clips. Preserve the girl's identity, clothing, movement, camera direction and emotional expression through every style transition.
  10. 010
    Anissa (@simplyannisa)post 2086421650967556288
    TEXT
    View original post on X ↗

    Prompt · 475 English words · 3,288 characters · historical-snapshot-public-card

    30s | 16:9 | 9 cuts
    
    Style: Authentic 16mm DV camcorder, handheld POV by CHASE. Real documentary/home-video realism: natural shake, imperfect framing, autofocus hunting, subtle tape grain, soft highlights, mild exposure flicker, muted colors and realistic motion blur. Natural lighting and location sound. Normal human pacing — not slow, not rushed. Physically believable actions and equipment. No flashy transitions or impossible camera movements.
    
    Character: CHASE, Korean woman in her 20s, long black hair, glass skin, natural makeup. Same face, hair and body throughout. Outfit: morning loungewear → modest director outfit with simple jacket and trousers → evening loungewear.
    
    Locations: Apartment → small film set → outdoor location → apartment.
    
    VOICEOVER: Natural conversational female voice, medium speed, relaxed pauses. Never rushed or unnaturally slow. Match each line to the action.
    
    1. MORNING — 0:00–0:03
       CHASE wakes up, checks the time, gets dressed, ties her hair, grabs her phone and production notebook, then leaves.
       VO: "Filming days usually start a little earlier than I want."
    
    2. BREAKFAST — 0:03–0:06
       In the kitchen, she grabs coffee and a quick breakfast while checking her shot list on her phone. She picks up her notebook and leaves.
       VO: "I check the plan, grab some coffee, and get moving."
    
    3. ARRIVE ON SET — 0:06–0:09
       CHASE arrives at a realistic small film set. A camera operator sets up a camera and tripod while another crew member adjusts a light. She checks the setup and talks briefly with the crew.
       VO: "Once I get to set, everything starts moving pretty fast."
    
    4. FINAL SETUP — 0:09–0:12
       CHASE checks the camera monitor, looks at the scene, adjusts a small prop and discusses framing with the camera operator. Crew makes practical adjustments.
       VO: "We make a few last-minute changes before rolling."
    
    5. ACTION — 0:12–0:16
       CHASE stands behind the camera and says, "Action." The actor performs the scene while the camera operator films.
       No voiceover. Natural set ambience only.
    
    6. REVIEW — 0:16–0:19
       The take ends. CHASE watches it on the camera monitor with the operator, points out one small issue and asks for another take.
       VO: "Sometimes the shot looks right... until you see it back."
    
    7. SECOND TAKE — 0:19–0:23
       The crew resets and films the scene again. CHASE watches the monitor and gives a subtle satisfied nod afterward.
       VO: "One more take usually makes the difference."
    
    8. WRAP — 0:23–0:27
       Evening. CHASE leaves the location carrying her notebook and phone while the crew packs cameras, tripods and lights into cases behind her.
       VO: "And then suddenly, the whole day is gone."
    
    9. NIGHT — 0:27–0:30
       Back home, CHASE watches a short clip from the day's footage on her laptop. She leans back tired but satisfied, closes the laptop and turns off the desk lamp.
       VO: "Long day... but we got the shot."
    
    CONTINUITY:
    One logical day: apartment → set → filming → wrap → home. Same woman and consistent clothing, props and equipment. Realistic film set with believable camera, tripod, lights and monitor. Natural human movement and expressions. No teleportation, floating equipment, duplicated people, distorted hands, random props, futuristic technology or unrealistic Hollywood production.
  11. 011
    mayv@簡単プロ級プロンプト公開中! (@haruuraeadss)post 2086411587192303988
    TEXT
    View original post on X ↗

    Prompt · 233 English words · 8,539 characters · historical-snapshot-public-card

    高品質アニメ映像。
    高密度3Dトゥーン/セルルックによる、サイバー神社型の映画的高速剣戟。劇場版クラスのキーアニメーション、上質なコンポジット、透明感のある照明、密度の高い背景美術。回避、破壊、偏向、反撃、最大衝突までを、構え直しや待機を挟まない一つの連続運動として描く。
    【参照と人物固定】
    image1 is the face reference and identity reference. image2 is the outfit reference and full-body reference, including accessories and weapon. If references conflict, face and identity have priority from image1 ; outfit, full-body design, accessories and weapon have priority from image2 .
    image1 は剣士の顔と同一人物性の参照。柔らかく繊細な小さめの顔立ち、17歳の年齢感、紫桃色の大きな瞳、宝石のような虹彩、多層の白いキャッチライト、濃い上まつ毛と柔らかい下まつ毛、目の大きさと間隔、金色の目元差し色、淡い頬の血色、小さな口元、前髪、長いピンクのツインテール、紫の花と結晶の髪飾りを最優先する。image1 の背景は使わない。
    image2 は剣士の衣装、装飾、全身、体型、武器の参照。身長160cmほどの細身のシルエット、濃紺と紫の制服調レイヤード衣装、金縁、紫の星型ブローチ、白いプリーツブラウス、紫のリボンタイ、ベルトと腰飾り、紫の重ねプリーツスカートとシアーレイヤー、背面リボン、黒タイツ、花飾り付きの紫黒ヒールブーツ、紫の刀、菱巻きの柄、星型の鍔、紫の房、左腰の鞘を最優先する。image2 の設定表レイアウト、枠線、文字、白背景、複数ポーズは映像へ入れない。
    参照が衝突した場合、顔、目、虹彩、顎、前髪、髪色は image1 、衣装、装飾、体型、全身シルエット、刀は image2 を優先する。全編で image1 と image2 が示す同じ一人、same person、same character identity を維持する。
    【人物A / Character 1:剣士固定】
    剣士は一人だけ。顔立ち、目と虹彩、髪型と髪色、衣装と装備、体型とシルエット、ピンク、紫、金の固有配色を変えない。高速動作中や引きの画でも成人化、平均顔化、無表情な能面化を起こさず、両目、虹彩、まつ毛、頬、金色の目元差し色を保つ。変化してよいのは表情、敵へ向く視線、口元、姿勢、呼吸、髪と衣装の自然な遅れだけ。髪やエフェクトで顔を隠さない。
    【人物B / Character 2:Cyber-Oni Sentinel固定】
    敵は Cyber-Oni Sentinel 一体だけ。黒金属の重量級フレーム、角付きの面、左右の前腕へ接続された二本の金属爪、シアンのプラズマ排気口、剣士のおよそ二倍の質量、大きく前傾した固有シルエットを変えない。滑らず重心移動で動き、自ら横薙ぎ、偏向、押し返し、爪突きを行う。敵本体を水晶像、結晶人形、霧、抽象物へ変えない。
    人物Aと人物Bの顔または面、目、髪または頭部、衣装または装甲、装備、体型、シルエット、固有色を混ぜない。顔の平均化、衣装交換、装備交換、クローン、余計な人物を起こさない。
    【画風固定】
    レンダリングレーンは3Dトゥーン/セルルックだけ。細く繊細な青紫系の色付き輪郭線。顔、髪、衣装、武器には明快な二段から三段のセルシェーディングと透明感のある中間影。キーライト、影色、発光は剣士固有のピンク、ラベンダー、バイオレットから取り、シアンのネオンは敵と背景の補助色だけに抑える。背景は人物より一段暗くし、人物固有色を画面の主色にする。瞳と髪は多層ハイライト、髪束、まつ毛、刺繍、金縁、リボン、宝石まで高密度。布、革、肌、磨かれた金属、濡れた瓦、ガラスを異なる反射と粗さで描き分ける。背景も瓦の目地、鳥居の金属継ぎ目、ケーブル、蒸気、支柱外装まで劇場版密度を保つ。太い黒輪郭、平坦な単層セル影、簡略TVアニメ、汎用3D美少女顔、滑らかなプラスチックCG、低密度背景、半写実、写実、くすんだ色、画風混合へ変えない。
    3D toon/cel-look only: fine blue-violet colored linework; two-to-three-step cel shading; a pink, lavender, violet and gold character color palette; layered eye and hair highlights; high-density fine detail and high-density background detail; distinct material roughness for skin, cloth, leather, polished metal, wet roof tiles and glass. No thick outlines, flat single-layer cel shading, generic 3D anime faces, smooth plastic CG, low-detail backgrounds, photorealism, semi-realism, dull colors or style mixing.
    【武器の実寸・構造・操作固定】
    剣士の刀は合計五本。右手で柄だけを握る手持ち刀一本と、念力で操作する四本の浮遊刀。鞘は左腰の一本だけ。五本すべてを image2 の刀と同じ実寸、同じ比率、同じ材質感を持つ日本刀として描く。各刀は全長およそ95〜105cm、刀身70〜75cm、柄23〜28cm。磨かれた暗紫色の金属刀身、連続した直線的な刃先、刃文、切っ先、星型の鍔、菱巻きの柄、柄頭が一本につながった完全な構造で、手持ち刀と浮遊刀の大きさを揃える。静止時も高速移動中も、切っ先から柄頭までの長い金属刀身を主役として明瞭に見せる。
    四本の浮遊刀は開始時、剣士の背後へ非対称で奥行き差のある四つの固定待機点に置く。一本は左肩より高い後方、一本は右肩よりさらに高く深い後方、一本は左腰の後方、一本は右膝より低い後方。互いに等間隔にせず、同一平面へ並べず、それぞれの長軸と切っ先を敵へ向ける。人物と刀の間、刀同士の間に常に明瞭な空間を残す。剣士は浮遊刀へ手で触れず、敵へ向けた視線、開いた指、短い手首の返しだけで出発方向を与える。
    浮遊刀の発光は金属刀身の刃先と刃文に密着する極細の紫光だけ。静止中は残光を出さない。移動中だけ、金属刀身の後方へ刀身より短い直線的な紫、バイオレット、マゼンタの残光を引く。残光は刀身を置き換えず、切っ先、刃、鍔、柄を隠さない。短剣、小型ナイフ、湾曲した発光片、三日月状の光刃、柄だけの光る玩具へ変えない。
    通常の攻防では一本ずつ発進し、動かない三本は別々の固定待機点で完全に静止し、実寸の金属刀身を見せ続ける。発進する一本には、出発点、開いた直線または浅い斜線、単一の接触点、偏向後の新しい直線、停止点を必ず持たせる。刀全体は一つの剛体として動き、切っ先だけを回転させない。剣士の周囲を周回せず、共通中心を持たず、閉じた軌道を作らない。四本が同じ角速度で回転する動き、放射状の回転盾、光輪、風車、プロペラを作らない。
    終盤の最大衝突で一度だけ四本すべてを使う。その場合も四つの固定点から別々の開いた直線または浅い斜線を通り、異なる深度とわずかな時間差で到達する。互いに重ならず、融合せず、同一平面の十字形や回転羽根に並ばない。直後はそれぞれ別の直線経路で四つの固定待機点へ戻る。刀は増殖、消失、融合、変形せず、剣士の身体を貫通しない。右手は鍔より後ろの柄だけを握り、鍔が手と刀身を明確に分離する。
    Sentinel の武器は左右前腕へ接続された二本の金属爪だけ。前腕、手首、爪先まで一体の構造で動き、接触の反力を爪全体から胴体へ返す。Sentinel に刀を持たせない。
    【舞台】
    夜の屋上寺院街。連続した濡れた瓦屋根、吊り足場、ネオンの鳥居回廊、ケーブル、鋼鉄支柱が一つの空間として接続されている。薄い蒸気と濡れた瓦の反射。瓦の目地、鳥居、鋼鉄支柱を移動距離と奥行きの基準にする。寄り、ミディアム、局所的な引きだけで構成し、剣士の顔と五本の刀の実寸が読める人物サイズを維持する。
    【戦闘運動契約】
    Body mechanics remain readable: supporting leg, center of gravity, hips, shoulder and footwork physically drive every move. Every parry or impact shows a visible pre-contact gap, one named contact point, then reaction force, recoil, hit-stop and sparks only after contact. Continuation uses the momentum and reaction force into the next attack or counter without a neutral reset.
    【連続アクション】
    開始時、剣士は中景の画面右で画面左の敵へ正対し、右脚支持。手持ち刀は右手に順手。四本の実寸浮遊刀は背後の非対称な四つの固定待機点で完全に静止し、長い金属刀身と鍔と柄を見せる。敵は前景左から剣士へ踏み込む。
    敵が右爪を横薙ぎにすると、剣士は腰を落として左脚へ荷重を圧縮し、爪の下を低く前方へ抜ける。回避姿勢を保持せず、沈んだ左脚の反発をそのまま次の前進加速へ渡す。表情は、まず両目が爪の軌道を捉え、次に眉がわずかに寄り、続いて上まぶたが持ち上がり、その後に口元が引き締まり、最後に視線が敵の中心へ固定される順で変化する。
    接触直前まで屋根の棟と瓦は無傷で、火花、破片、蒸気はまだ出ない。爪は空振りで止まらず、剣士が抜けた直後の屋根の棟へ斜めに食い込む。接触後にだけ黒い瓦片、橙金の金属火花、薄い蒸気が大きな斜め扇となってレンズ前へ噴き上がり、画面の半分以上を横切る。
    その遮蔽中、剣士は左脚を一気に伸ばし、画面右手前から左奥へ身体を押し出す。低い姿勢のまま瓦の目地を二本越えて距離を縮め、顔と両目は敵へ向けたまま、ツインテール、リボン、スカートの重ねだけが遅れて大きく流れる。
    間を置かず、右膝より低い後方で静止していた実寸浮遊刀一本だけが、切っ先を先頭にレンズ脇の開いた斜線を通って敵の防御側の爪へ飛ぶ。出発から接触まで切っ先、長い金属刀身、鍔、柄を連続して見せる。金属刀身の後方へだけ幅広く非対称な紫、バイオレット、マゼンタの色面が短く残り、刀そのものを光へ置き換えない。接触直前まで浮遊刀と爪の間には隙間があり、刀と爪の形を保つ。敵は爪全体で刀を横から叩き、単一の接触点で衝突する。その瞬間だけ小さな白熱核、太い紫の衝撃片、橙金の火花が接触点から破裂し、微小ヒットストップを一度だけ置く。
    弾かれた浮遊刀は武器全体が一体のまま新しい直線へ向きを変え、敵の背後の鋼鉄支柱外装へ切っ先から到達する。支柱外装は刀が届く直前まで無傷。明確な空間を通過した後に接触し、接触後にだけ外装が裂けて鋼芯が露出する。金属片と火花がレンズ前へ飛ぶ。偏向の反力で敵の胴がねじれ、そのねじれで開いた斜め経路へ、右肩より高い深い後方で静止していた二本目の実寸浮遊刀だけが切っ先から直進する。二本目は敵のもう一方の爪の外側へ一度だけ接触し、防御線を押し開いた後、剣士の右上後方の停止点へ直線的に抜けて静止する。最初の刀も支柱接触後に剣士の右後方の別の停止点へ直線的に戻って静止する。二本は人物の周囲を回らず、互いに異なる高さと奥行きで止まり、剣士自身は前進を止めない。
    カメラは最初、剣士の右斜め前、足首の高さの全身中景から右から左へ低く追従する。背景の消失軸は屋根の棟から敵へ向かう対角線。目的は、回避する全身、爪、屋根の接触点、静止する実寸浮遊刀を一画に残すこと。瓦片がレンズを覆った瞬間、その斜め縁を硬い前景ワイプとして、剣士の左斜め前、胸の高さの中近景へ切り替える。背景の消失軸は発進した刀、爪、奥の支柱を結ぶ斜線へ変わる。目的は、剣士の両目と金の目元差し色、刀と爪の接触、偏向後の支柱到達を一続きで見せること。
    【中盤の明確な一回攻防】
    敵は防御のねじれから即座に剣士へ向き直り、右爪を斜め下前方へ押し込みながら鳥居回廊の奥へ圧力をかける。剣士は距離を切らず、右手の手持ち刀を下から斜めに差し込み、右爪を一度だけ受け流す。同時に左足を瓦の目地一本ぶん左後方へ滑らせる。手持ち刀と爪は接触直前まで離れ、柄、鍔、刀身、爪の形が見える。反力は右手、肘、肩、腰へ順に返り、長い鍔迫り合いで静止せず、その腰のひねりを次の体外しへ渡す。
    この圧力が続いている間に動く浮遊刀は、左肩より高い後方の固定待機点に全長を見せていた一本だけ。残る三本は右上後方、右後方、左腰後方の互いに離れた固定点で完全に静止し、長い金属刀身を見せ続ける。
    左上の実寸浮遊刀は固定待機点から切っ先を先頭に発進し、剣士の左肩の外側を通る一本の開いた直線斜線で、敵の右爪と右前腕の外側金属面へ向かう。刀は自転せず、回転せず、全長およそ100cmの切っ先、刀身、鍔、柄を同じ向きのまま複数フレーム見せる。接触直前まで刀と右爪の間に明確な空間を残す。単一の接触点で当たった瞬間だけ微小ヒットストップを置き、接触後にだけ橙金の金属火花を出す。敵は受け身にならず、右爪全体で浮遊刀を外側へ能動的に叩く。その反力で右爪と右前腕が外へ回り、剣士の前に一本の明瞭な通過線が開く。
    弾かれた浮遊刀は完全な一本の剛体を保ち、接触点から新しい上外方の直線へ抜け、敵の背後かつ画面上縁近くの固定停止点で完全に止まる。この区間では剣士の周囲へ戻らず、周回もしない。
    剣士は手持ち刀で受けた反力と腰のひねりを止めず、開いた右腕の外側を斜めに一息で通過する。敵の腕の下外側へ身体を沈め、同じ連続運動のまま手持ち刀を一度だけ切り返し、すでに露出している前面装甲の継ぎ目を斜めに斬る。斬る直前まで装甲板は閉じ、接触後にだけ継ぎ目が開いて片側の外装板が瓦へ落ちる。敵の重心が支持域を越えた後にだけ片膝が瓦へ沈み、瓦が割れる。ここでは二本目の浮遊刀攻撃を加えない。
    この一回攻防の因果は、敵の右爪の圧力、手持ち刀の一度の受け流し、左上の実寸浮遊刀一本による直線迎撃、敵がそれを外へ叩いて生じる通過線、剣士の体外しと装甲継ぎ目への一太刀、接触後の片膝沈下の順だけで明瞭につなぐ。
    カメラは敵の右斜め前かつ剣士の左斜め前、腰の高さの全身寄り中景を保ち、鳥居回廊の奥行き軸に沿ってわずかに後退する。人物の周囲を旋回しない。前景の右爪、中央の剣士と手持ち刀、左肩外側を直進する一本の実寸浮遊刀、別々の深度で静止する残り三本を同じ空間へ置く。目的は、三本が静止していること、発進する一本の全長、爪との接触、開いた通過線、剣士の通過と装甲への一太刀を読み切れるようにすること。刀身や手を顔前へ重ねず、剣士の両目と敵へ固定した視線を保つ。
    【終盤の反撃と最大衝突】
    敵は片膝から立ち上がる勢いをそのまま反撃へ変え、左爪を剣士へ直進させる。剣士は短い横移動で爪の線から画面右へ外れ、両ブーツを瓦の目地へ踏み固める。爪は剣士の肩の脇の空間を通過し、敵の前進速度を残したまま伸び切る。
    剣士は体外しの沈み込みから手持ち刀を斜め上へ切り返し、開いた前面装甲の中央継ぎ目へ到達させる。接触直前まで装甲と五本の刀はそれぞれの形を保つ。手持ち刀が中央継ぎ目へ接触した直後、四本の浮遊刀が、現在の互いに離れた四つの固定点から別々の開いた直線または浅い斜線を通って発進する。各刀は異なる高さと奥行きを保ち、到達をわずかにずらす。切っ先から柄頭までの実寸金属刀を見せたまま、中央継ぎ目に隣接する四つの異なる装甲点へ一度ずつ接触する。四本は互いに交差せず、重ならず、同一平面へ放射状に並ばず、中心の周囲を回転しない。
    各接触の直前には刀と装甲の隙間があり、接触後にだけ局所的な白熱核、橙金の火花、紫、バイオレット、マゼンタの幅広く不規則な圧力面が生じる。純白は小さな接触核だけに限定する。四つの局所接触から生じた色面は、金属刀身の形を隠さず、接触後にだけ敵の背面方向へ一枚の非対称な衝撃面として合流する。最大色面は複数フレーム明瞭に保持し、その終了と同時に衝撃波を開始する。直進する刀圧、接触点から左右へ裂ける扇状圧力面、上へ巻く蒸気の乱流を統合する。濡れた瓦の反射、蒸気、瓦片、剣士の髪と衣装、敵の重量フレーム、鳥居、カメラの短い反動が同時に反応する。
    力は五つの明瞭な接触点から敵の胴体へ伝わる。黒金属の胴体が先に後方へ運ばれ、両脚が遅れて屋根から離れる。敵はネオンの鳥居枠を突き破り、露出した鋼芯へ背中から到達する。鋼芯は敵が接触する直前まで曲がらず、接触後にだけ敵の背面を挟むように座屈して動きを止める。敵の黒金属の身体、角付きの面、二本の爪、シアン排気口は結果後も同じ構造を保つ。
    終盤のカメラは剣士の左斜め前、腰の高さの中景から短く横移動する。背景の消失軸は剣士の足元から敵の前面装甲へ向かう斜線。目的は、爪を外す足運び、手持ち刀の中央接触、四本の浮遊刀が別々の固定点から異なる直線で順に入ることを一続きで見せること。紫の圧力面がレンズ端を横切った瞬間、鳥居と露出支柱の奥行き軸に沿う右斜め前、膝より低い位置の中近景へ切り替える。目的は、敵が鋼芯へ到達し、接触後だけ座屈して止まる結果を剣士の顔と同じ画面へ残すこと。
    【音響】
    BGMと劇伴なし。濡れた瓦を蹴る靴音、金属爪のサーボ音と風切り、爪が瓦へ食い込む硬い衝突音、瓦の破砕、実寸の金属刀が空気を切る短い風音、刀と爪の鋭い金属接触、支柱外装が裂ける音、装甲板が瓦へ落ちる金属音、鳥居の金属破断、鋼芯の座屈、落下する瓦と金属片を、それぞれの可視イベントへ同期する。剣士の短い呼気は最初の踏み切りと終盤の切り返しだけ。長い叫び、会話、ナレーションなし。
    【重要固定】
    人物は剣士一人と Cyber-Oni Sentinel 一体だけ。刀は手持ち一本と実寸浮遊刀四本の合計五本、敵の爪は二本で全編固定する。浮遊刀を短剣、小型ナイフ、湾曲した発光玩具、分離した柄、三日月状の光片へ変えない。人物中心の円周運動、閉じた光輪、回転盾、風車、プロペラ、共通回転軸、同速回転を作らない。追加人物、分身、装備交換、刀の増殖、消失、融合、変形、場所のリセットを起こさない。文字、字幕、ロゴ、透かし、UIなし。持続する全画面白飛びなし。都市全景へ引かず、終端でも剣士を中景以上の大きさに保つ。
    【終端】
    敵は座屈した鋼芯へ背面を挟まれ、右爪を引き抜こうと力をかけるが剣士へ届かない。剣士は前景の中景サイズを保ち、両目と金の目元差し色を見せたまま敵へ視線を固定し、右手の刀を下げきらず低い前方ガードへ保つ。四本の浮遊刀は互いに交差しない別々の直線経路で、左肩上後方、右肩上の深い後方、左腰後方、右膝下後方の非対称な四つの固定待機点へ戻りきる。四本とも実寸の金属刀身、鍔、柄を見せ、切っ先を敵へ向けて完全に静止する。剣士が呼吸を止めず前脚を次の瓦の目地へ踏み込み、足裏が接地し、身体が次の攻防へ前傾した瞬間を最終フレームとして即カットする。
    The final subject is the heroine in a medium shot. Her final action is one forward step while maintaining the low forward guard. The result state is the enemy trapped in the buckled steel core and unable to reach her. Cut when her front sole contacts the next roof-tile seam and her torso tips forward into the next exchange.
  12. 012
    NΞXUS (@nexus_to_nova)post 2086408659114901932
    TEXT
    View original post on X ↗

    Prompt · 564 English words · 3,718 characters · historical-snapshot-public-card

    SCENE TYPE / DURATION / STYLE
    
    30-second, 16:9 Muay Boran street fight. Crowded Thailand night market. Grounded Thai action-cinema energy. Wet pavement, neon signs, warm food-stall lights, steam and traffic glow. No music.
    
    TEMPO LOCK
    
    Fast real-time choreography. No slow motion, speed ramps, pauses, posing, or resets. Every defense immediately becomes an attack. Reactions stay brief. Cuts happen during movement and carry the same speed into the next angle.
    
    CONTINUITY
    
    Fighter A remains screen-left, driving right. Fighter B remains screen-right, retreating toward a pillar and closed metal shutter. Maintain close fighting distance: one metre during strikes, chest-to-chest inside the clinch. Preserve faces, bodies, outfits, lighting, injuries, and screen direction.
    
    COVERAGE AND ACTION
    
    MASTER / GEOGRAPHY
    
    Waist-high 28mm side view. Camera tracks right past a scooter and plastic tables. The fight begins immediately. A flicks a lead-hand feint. B swats it away and fires a fast right cross while retreating.
    
    MEDIUM / ATTACK AND COUNTER
    
    Match the punch at full speed. A slips outside, redirects B’s wrist, and steps directly into Sok Tad, a horizontal elbow across B’s guard. Contact turns B’s shoulders. A follows before B can recover.
    
    OTS / CLINCH PRESSURE
    
    Over B’s shoulder. A catches the neck in a tight Pam clinch, jerks B off balance, drives a short knee into the thigh, then immediately lands Khao Trong into the ribs. B folds, posts against A’s chest, and twists sideways out of the clinch.
    
    MASTER / ESCAPE AND CHASE
    
    Wide side view restores both bodies. B escapes toward the pillar and throws a desperate left hook while moving. A ducks beneath it, catches the extended arm, and pulls B past him. Neither fighter stops moving.
    
    MEDIUM-WIDE / REVERSAL
    
    A pivots under the trapped arm and whips Sok Klap, a spinning back elbow, across B’s guard. B crashes shoulder-first into the concrete pillar and metal shutter. The shutter buckles and rattles. A immediately closes the distance.
    
    MEDIUM / DESPERATE EXCHANGE
    
    B rebounds with a rapid right-left combination. A shoulder-rolls the right, traps the left forearm, and drives a short rising elbow through the center. B snaps backward, then stumbles forward beside a plastic table.
    
    INSERT / TAKEOFF
    
    Low close-up. A’s foot strikes the tabletop without hesitation. The plastic bends, water jumps from its surface, and the table leg scrapes across the pavement. A explodes upward. Cut while the foot is still pushing off.
    
    LOW WIDE / AIRBORNE FINISH
    
    Low 24mm three-quarter view. Preserve the takeoff speed. A rises across B’s path, clamps both thighs around B’s neck, and rotates sideways into a flying scissor takedown. B’s feet leave the pavement only after the neck trap redirects his momentum. During the fall, A drives one descending Sok Ti elbow across B’s upper shoulder line. One rotation only. Keep the entire stunt and contact geometry visible.
    
    END FRAME / CONSEQUENCE
    
    The camera drops with them. A releases the trap, catches himself with one hand, and lands in a low crouch facing right. B slams onto the wet pavement behind him. Water splashes, bottles roll, motorbike mirrors vibrate, and the crowd recoils several steps.
    
    PERFORMANCE
    
    A stays focused and economical: fixed eyes, loose shoulders, short nasal exhales. B becomes increasingly frantic: rapid blinking, clenched jaw, raised shoulders, and hurried counterattacks.
    
    NEGATIVE CONTROL
    
    No slow motion. No waiting between moves. No repeated strikes from different angles. No floating jumps, random flips, hidden contact, extra rotations, teleporting, crossed screen direction, weapons, blood, extra fighters, face morphing, civilian interference, comedy, subtitles, or logos.
  13. 013
    Feyber | AI Creator (@woleswoosh)post 2086405889544860044
    TEXT
    View original post on X ↗

    Prompt · 1394 English words · 9,548 characters · historical-snapshot-public-card

    Left side woman: Cold Tide barrier master, blue-white long robe, water-element mage. Uses cold water, barriers, water walls, water rings, water-flow traction, and ink-wash tidal waves in combat. She must maintain distance and must never allow the man to stably close in.
    Right side man: Crimson-black long robe red-blade swordsman, solid red large blade, black cloak, crimson fire-ink, black ink waves, golden shattered ink. Fighting style is strong assault, breaking formations, charging in, horizontal slashes, aerial heavy chops. He must constantly attempt to close the distance and break through the water walls.
    
    Generate a 15-second 16:9 landscape 720P high-definition 2D ink-wash wuxia combat video. Overall high-energy 2D ink-wash combat aesthetic: fierce, fast, explosive actions, strong ink-follow, large-area splash-ink explosions, characters high-definition and clear. No 3D, no live-action, no CG feel, no sketch style, no static illustration.
    
    Combat arena: rainy aftermath of shattered water-courtyard ruins, large areas of shallow water covering a green-stone plaza, surrounded by broken bridges, residual pillars, collapsed water pavilions, broken tiles, stone steps, distant ink clouds. The ground must have large water surfaces; character movement produces water splashes, ripples, reflections, and ink-wash ripples. During combat the water surface is split by blade energy, water walls are shattered, residual pillars are broken by water waves, green stone is cleaved by the red blade, broken tiles are swept up by water flow and shockwaves.
    
    Core combat relationship: The woman is a mid-to-long-range water mage who actively controls the field and suppresses. The man is a close-range red-blade fighter who must constantly charge to break distance. The woman always uses the water surface, barriers, water walls, and spatial displacement to keep 3–8 meters distance. The man constantly uses ground-hugging dashes, diagonal charges, aerial downward chops, and spinning horizontal slashes to forcibly close the gap. Every time the man is about to get close, the woman must use water walls, water rings, surging waves, mirror-position swaps, sliding-water retreats, or barrier rebounds to interrupt. She cannot stand still to cast; she must cast while sliding, spinning, retreating, or leaping on water.
    
    Absolute real-time high-speed combat. No slow motion, no variable frame rates, no speed ramps, no static charging, no one-move-one-stop, no idle time after collision. From the first frame to the last frame continuously. At least 3 effective offense-defense exchanges per second: water-wall blocking, red-blade breaking walls, water-wave counter-push, charge dodging, barrier rebound, pursuit avoidance happening continuously.
    
    Ink-wash special effects must be extremely strong. All of the woman’s actions carry cyan-blue ink, water splashes, cold white flying white, water-ripple barriers, transparent water walls, vortex water rings. All of the man’s actions carry crimson fire-ink, large red blade arcs, black cloak ink waves, golden shattered ink. Water and fire-ink must contrast sharply: cyan-blue tides suppress red-black blade waves; when the red blade splits a water wall, red-blue colliding splash-ink explodes. Ordinary exchanges occupy one-third of the frame with ink effects, heavy strikes occupy half the frame, final explosion is full-screen ink-wash detonation.
    
    0–3 s: Low camera close to the water surface rapid tracking. Woman slides backward on water, sleeves roll out three cyan-blue water rings, semi-transparent water wall rises from the surface. Man charges violently from the distance hugging the ground, red blade dragging and splitting the water surface, crimson fire-ink and water splashes exploding simultaneously. Man horizontal-slashes the first water wall; woman sideways slides on water to change position; second water wall rolls up from his side and deflects his slash momentum. Camera stays low on the water surface chasing, water splashes hitting the lens.
    
    3–6 s: Medium-close rapid cuts. Man consecutive three-stage strong assault: diagonal charge horizontal slash, spinning upward lift, aerial downward chop. Woman retreats while casting without pause: water sleeves flick to form an arc water shield, foot vortex shifts her body sideways three meters, both hands form seals to raise two water walls for pincer attack. Red blade shatters the water shield, shattered water turns into cyan-blue splash-ink rain; woman uses the water wave to push herself sliding to the side of the broken bridge, maintaining distance.
    
    6–9 s: Large-scale spatial displacement. Man stomps and shatters green stone, leaps across the water channel, black cloak trailing red-black ink waves, red blade chopping down from above. Woman does not hard-block; she leaps on water, water column underfoot lifts her into a side flip, circular water-ripple barrier appears behind her. Blade energy chops into the barrier, water surface explodes into a ring-shaped giant wave, man is forced half a step back by water pressure. Woman lands on top of a residual pillar on the opposite side and immediately flings three water blades from different angles to seal the man’s pursuit path.
    
    9–12 s: Pursuit and counter-suppression. Man forcibly breaks through the water blades, ground-hugging rapid charge, red blade continuously splitting the water surface forming three crimson blade scars. Woman high-speed retreats along the water surface, both sleeves trailing long cyan-blue ink tails, spins and summons a row of water walls pushing forward like a tidal wave. Man uses the large blade to continuously break the walls; his body is repeatedly shocked back, slides, then forcibly charges forward again; water surface underfoot is stomped and explodes, red-blue splash-ink continuously detonating. Camera rapidly switches between weapon close-ups, water-wall shattering close-ups, and full-body chase shots; cuts never interrupt the action.
    
    12–15 s: Final high-intensity explosion. Man finally charges into close range, aerial heavy chop, red blade carrying a crimson fire-ink giant wave pressing down. Woman instantly slides back on water and spins; large area of water underfoot rises into a ring-shaped water tornado, three layers of transparent water walls stack continuously. Man shatters the first layer with one chop, spins horizontal slash to tear open the second layer, lands dragging the blade upward to crash into the third layer. Woman pushes both hands forward; the water tornado contracts into a huge cyan-blue ink-wash shockwave. Man’s red blade hard-blocks; red-black blade wave and cyan-blue tide collide head-on, full-screen splash-ink, water flowers, flying white, shattered ink, golden shattered ink explode. After the explosion the man is blasted sliding backward several meters, blade tip plowing the water surface; woman slides back on water to a distance, water rings still rotating behind her; both remain in residual combat momentum, not a static pose.
    
    Camera requirements: Tsui Hark-style rapid camera work combined with high-energy 2D ink-wash combat. 70% medium-close and water-surface tracking shots, 20% full-body medium shots showing large displacements, a small amount of long shots showing the water-courtyard ruins and large water surface. Must include low water-surface camera, blade-splitting water-wall close-ups, water-splash explosion shots, woman’s water-sliding side-move tracking, man’s charging whip-pan, overhead water-ring barrier shots, low-angle aerial downward chop shots, final frontal explosion collision. Cuts must continue the same movement direction—no breaking of moves, no stuttering.
    
    Character force feedback must be strong. Every time the man shatters a water wall he must be counter-shocked by water pressure: shoulders lean back, feet slide, cloak explodes open. Every time the woman is forced close by blade energy she must use water-surface sliding, side flips, or spinning retreats to evade; her robes and long hair are blown by the impact. Both cannot float lightly; every attack has weight, inertia, and reaction force.
    
    Anti-misunderstanding requirements: The woman is a water mage but cannot stand still reading bars or cast statically; she must cast while moving. The man cannot swing empty air from far away; he must continuously break water walls, barriers, and distance. Water walls are transparent cyan-blue water curtains, not glass walls; the red blade is a solid large blade, not a lightsaber. The picture cannot be ordinary 2D action only; there must be continuous ink-follow and large-area splash-ink.
    
    Sound: Keep only combat Foley and water-courtyard environmental physical sounds: water surface footsteps, water wave roaring, water wall breaking, blade cutting wind, large blade splitting water, metal resonance, cloak cutting wind, flying broken tiles, residual pillar breaking, ink-wave explosions, body being shocked back by water pressure, ruins echo. No soundtrack, no drum beats, no human voices, no animal sounds.
    
    Negative requirements: No slow motion, no variable frame rates, no speed ramps, no freeze frames, no static charging, no standing still to cast, no one-move-one-stop, no idle time after collision, no man easily closing in, no woman standing still taking hits, no small-space mutual beating, no too little water surface, no blank background, no sparse special effects, no ordinary light effects, no 3D, no live-action, no CG feel, no sketch style, no static illustration, no subtitles, no text, no logos, no watermarks.
  14. 014
    ÀBDŪLLÂH (@itxabdullaa)post 2086376512404828463
    TEXT
    View original post on X ↗

    Prompt · 424 English words · 2,892 characters · historical-snapshot-public-card

    SHOT 1: ECU, 85mm macro push-in / Phone screen reads 7:59:59 as her finger hovers over the alarm; the second flips to 8:00 and the screen glitches for a split second / SFX: alarm pulse, digital tick, subtle glitch.
    SHOT 2: WS, 24mm handheld whip / She jolts upright in bed, instantly alert, as morning light flickers unnaturally across the room / SFX: mattress bounce, sharp breath, low electrical hum.
    SHOT 3: MCU, 50mm snap pan / Match cut to her splashing water onto her face; she looks into the mirror and briefly sees herself still asleep in bed behind her / SFX: faucet rush, water slap, heartbeat hit.
    SHOT 4: Insert, 85mm rack focus / Her toothbrush pauses halfway to her mouth as the bathroom clock suddenly jumps from 8:01 to 7:58 / SFX: bristle scrape, clock click, bass pulse.
    SHOT 5: Interior fridge POV, 24mm wide / Door bursts open; she reaches for milk, but the carton is suddenly replaced by a small glowing object she doesn't recognize / SFX: fridge hum, bottle clink, mysterious electronic tone.
    SHOT 6: Insert, 50mm handheld / Smash cut: the glowing object lands on the kitchen counter; she touches it and the entire room freezes mid-motion / SFX: touch ping, room-tone drop, deep whoosh.
    SHOT 7: MCU, centered 50mm push-in / Everything snaps back; she checks the clock — 8:00 exactly — and realizes she's back at the beginning / SFX: clock beep, heartbeat, sudden silence.
    SHOT 8: Bird’s-eye, 35mm overhead / Rapid match cuts show three versions of the same morning overlapping: waking, dressing, grabbing keys — each version slightly different / SFX: layered footsteps, fabric whip, key jingle.
    SHOT 9: MS, 35mm tracking / She suddenly stops mid-run in the hallway as another version of herself rushes past in the opposite direction / SFX: footsteps, jacket rustle, breath.
    SHOT 10: Insert, 85mm focus pull / Her phone vibrates; a message appears: “DON’T TAKE THE METRO.” She looks up, confused / SFX: notification buzz, distant train rumble.
    SHOT 11: WS, 24mm lateral tracking / Instead of entering the metro, she turns toward a bright staircase as the station behind her rapidly empties / SFX: footsteps, fluorescent buzz, train brake screech.
    SHOT 12: MS to CU, 50mm glide / She reaches the rooftop; the city suddenly reveals dozens of identical versions of her moving through different streets below / SFX: wind rush, distant traffic, rising cinematic tone.
    SHOT 13: ECU, 85mm push-in / Her phone clock hits 8:00:00 again; she looks directly into camera as the entire city freezes / SFX: digital tick, heartbeat stop.
    SHOT 14: WS, 24mm rapid pull-back / Hard smash cut: her bedroom from above — the bed is empty, the alarm is still ringing, and the phone screen now reads 7:59:59 / SFX: alarm, low rumble.
    SHOT 15: ECU, 85mm macro / The phone screen glitches; a notification appears: “LOOP 04 — BEGIN.” Smash to black / SFX: digital glitch, single bass hit, silence.
  15. 015
    Anissa (@simplyannisa)post 2086361039797395487
    TEXT
    View original post on X ↗

    Prompt · 418 English words · 2,818 characters · historical-snapshot-public-card

    Create a 30-second photorealistic vintage 16mm documentary set in rural Umbria, Italy, summer 1982. Make it feel like a beautiful forgotten family film shot on Kodak 16mm: warm sun-faded colors, fine analog grain, subtle film flicker, dust, tiny scratches, gentle light leaks, soft halation, slight gate weave, organic focus breathing and imperfect handheld camera movement. 4:3 aspect ratio, no modern cinematic polish.
    
    Main character: A naturally beautiful Italian woman, early 20s, slender, warm olive-fair skin, hazel-brown eyes and long dark honey-brown hair loosely tied with a cream ribbon, soft flyaway strands. She wears an elegant ivory linen midi dress with tiny muted terracotta and dusty-blue floral prints, fitted waist, soft puff sleeves, square neckline and fabric-covered buttons, a thin vintage leather belt, tan ankle-strap sandals, tiny pearl earrings and a delicate gold necklace. Natural makeup, no modern accessories. She carries a woven wicker basket with bread, peaches, figs, basil and white wildflowers.
    
    0–6s: She walks through a picturesque medieval Umbrian village lane, touching ivy-covered stone walls. Terracotta roofs, green shutters, red geraniums, ceramic pots and an old Fiat 126 surround her. Her floral dress and hair move gently in the afternoon breeze.
    
    6–12s: She enters a small village piazza. An elderly baker carries fresh bread, women sit outside a bakery, a boy rides an old bicycle and a cream Vespa rests beside a stone wall. The baker smiles and gives her a small loaf. She laughs softly. The handheld camera briefly loses focus before finding her again.
    
    12–17s: A little girl drops wildflowers. The woman kneels gracefully, gathers them and returns the bouquet with a warm smile. The child smiles shyly. Nobody acknowledges the camera.
    
    17–23s: She leaves the village along a path bordered by olive trees, golden grass, poppies and ancient stone walls. The camera moves beside her as her ivory floral dress flows naturally. Birds suddenly rise from a nearby field.
    
    23–28s: She reaches an overlook above beautiful Umbrian hills: vineyards, olive groves, golden fields, stone farmhouses and distant medieval hill towns in warm summer haze. She rests against an old wooden railing, watches the valley and gently tucks windblown hair behind her ear.
    
    28–30s: She picks up her basket and walks away through the olive trees. The camera stops naturally and holds on the empty golden landscape. A subtle film flicker ends the footage.
    
    Overall aesthetic: romantic Italian summer, elegant vintage fashion, authentic 1982 village life, beautiful natural woman, warm golden sunlight, realistic skin and fabric texture, documentary realism, imperfect human camera movement, genuine Kodak 16mm archival texture. No modern objects, no digital look, no AI-smooth skin, no posing.
  16. 016
    Shara I Ai Video Creator (@itsshara_ai)post 2086339231488872478
    TEXT
    View original post on X ↗

    Prompt · 816 English words · 5,258 characters · historical-snapshot-public-card

    Prompt seedance 2.5 - Photoreal live-action cinema, shot on large-format anamorphic lenses, heavy volumetric fog and slow falling snow, near-monochrome frozen palette of pale ice-blue, bone-white and wet slate grey with almost no saturation anywhere, ONE single molten-gold accent colour and nothing else, flat overcast light with no sun and no hard shadows, extreme scale contrast between figure and structure, shallow depth of field on close-ups, deep aerial perspective with distant layers fading into white, fine natural film grain, high-budget science fiction epic, restrained colour grade with no punch. Completely original character and creature design that must not resemble any existing film, game or animated property.
    
    16:9. 20 seconds, SEVEN shots, slow and deliberate. Motion starts on frame 1, no opening freeze. Nobody speaks, no lip movement, no dialogue.
    
    CHARACTER LOCK — identical in every shot: a lone figure of indeterminate age, slight and still, wrapped in a heavy floor-length coat of thick bone-white felt with a deep fur-lined hood pulled up. Frost crusts the shoulders and hem. Ash-white hair, wet and pushed back from the face. Pale skin, frost on the eyelashes, a calm unreadable expression. Under the coat, plain dark layers and worn leather gloves. No armour, no weapons, no insignia, no markings on the forehead, no jewellery, no facial piercings. The only colour anywhere on this character is the molten gold light in the eyes, and the eyes stay closed until shot four.
    
    COLOSSUS LOCK — identical in every shot: an immense kneeling stone figure half-swallowed by ice, so large that only its bowed head, one shoulder and one upturned open palm rise above the frost line. Weathered granite, deep erosion channels, moss and ice packed into every seam. Its face is worn almost smooth by centuries — no expression, no teeth, no horns, no demonic features, just a quiet ruined face with its eyes closed. Thin veins of dull gold run through the cracks in the stone, dormant.
    
    WORLD LOCK: a drowned city frozen solid — ruined towers, snapped bridges, industrial pipework and heavy cables strung between structures, all sheathed in ice and fading into white fog within a hundred metres. No people anywhere. No text, no signage.
    
    SHOT 1 — 0.0s to 3.0s — EXTREME WIDE, long lens, camera drifting very slowly: the frozen ruined city under fog, and rising out of the ice at its centre the colossus's bowed head and one enormous open stone palm. Snow falls steadily. The scale is overwhelming and the frame is almost entirely grey and white.
    CUT.
    SHOT 2 — 3.0s to 6.0s — WIDE, very slow push-in: a single tiny figure in a bone-white coat stands motionless at the centre of the colossus's open stone palm, no larger than one of its fingernails. Fog rolls between them.
    CUT.
    SHOT 3 — 6.0s to 9.0s — CLOSE PORTRAIT, static, shallow depth of field: the figure's face inside the fur hood, eyes closed, frost gathered on the lashes, breath clouding and drifting away. Absolute stillness. Everything behind them is soft white nothing.
    CUT.
    SHOT 4 — 9.0s to 12.0s — EXTREME CLOSE, static: the eyes open. They burn a deep molten gold, the first and only colour in the entire film, casting a faint warm glow onto the frost on their skin. Hold on this.
    CUT.
    SHOT 5 — 12.0s to 15.0s — WIDE LOW ANGLE, camera slowly rising: the figure now stands on a rough slab of dark stone hovering silently high above the frozen city, coat streaming sideways in the wind, the colossus's bowed head behind them in the fog.
    CUT.
    SHOT 6 — 15.0s to 17.5s — MEDIUM, static: the figure raises one open gloved hand slowly and deliberately toward the city far below. Nothing dramatic. Just the gesture.
    CUT.
    SHOT 7 — 17.5s to 20.0s — EXTREME WIDE, camera locked off: thin veins of molten gold race outward through the ice and up through the colossus's cracks, and across the whole city the frozen towers, bridges and cables detach from the ground and rise silently into the air, hanging suspended in the fog. The frame holds on the floating city, still snowing.
    
    Seven cuts at 3.0s, 6.0s, 9.0s, 12.0s, 15.0s and 17.5s. No dissolves, no fades, no speed ramping. Camera movement is always slow and controlled. Continuous subtle motion within every shot — falling snow, drifting fog, breath, streaming cloth — nothing ever fully freezes.
    
    AUDIO: low sustained wind across open ice, deep groaning ice under pressure, snow ticking on fabric, one long sub-bass swell as the eyes open, a rising low resonant hum as the gold spreads, and the deep grinding of enormous mass leaving the ground at the end. No voice, no dialogue, no narration, no music.
    
    NEGATIVE: anime, manga, cel-shaded or stylised animation, ninja, headbands, forehead protectors, cloaks with printed patterns or clouds, ringed or patterned irises, orange or spiky hair, facial piercings, any resemblance to an existing film, game, comic or animated character, weapons, blood, gore, injuries, visible crowds or bystanders, warm sunlight, blue sky, saturated colour anywhere except the gold, gradients, lens flares, on-screen text, captions, letters, words, numerals, readable signage, logos, watermark, cartoon, 3D render, video game cinematic look, slow motion, speed ramping, opening freeze, static first frame.
  17. 017
    Noor 🌸 (@noor_ul_ain43)post 2086322183492763687
    TEXT
    View original post on X ↗

    Prompt · 498 English words · 3,141 characters · historical-snapshot-public-card

    SHOT 1: ECU, 85mm push-in /  on the phone screen as it shakes on rumpled sheets / SFX: alarm, sheet rustle.
    
    SHOT 2: WS, 35mm handheld jolt / Rhythmic cut into her jolting upright through side light, throwing the blanket aside, and planting her feet on the floor in one rushed motion, still in a sleep tee and lounge shorts / SFX: mattress bounce, blanket whip, sharp breath.
    
    SHOT 3: MCU, 50mm slide / Cut on action into face wash at the sink, droplets catching the top light / SFX: faucet rush, water slap.
    
    SHOT 4: Insert shot, 85mm lens focus / Match cut into the toothbrush held at a natural forward brushing angle against the front teeth; hand relaxed and upright, mint foam and mirror eye / SFX: bristle scrape, sink drip.
    
    SHOT 5: Interior fridge view, 24mm wide / Object pass into the camera inside the fridge looking out as the door snaps open and her hand darts in, blue light framing a hurried grab for breakfast ingredients / SFX: fridge hum, bottle clink, shelf scrape.
    
    SHOT 6: Insert shot, 50mm handheld / Rhythmic cut into egg and toast hitting the pan under warm practical light / SFX: butter sizzle, chop tap.
    
    SHOT 7: MCU, centered 50mm push-in / Match cut into one rushed bite, a quick clock glance, and an immediate rise from the chair / SFX: crunch, ceramic clink, chair scrape.
    
    SHOT 8: Bird’s-eye, 35mm overhead / Match cut on action as the sleep tee disappears under a fitted top and tailored jacket; then her keys, transit card, and bag get scooped up in one messy grab / SFX: fabric whip, key jingle, zipper pull, bag rustle.
    
    SHOT 9: MS, 35mm pan / Camera slips into a rushed outfit change as the sleep tee disappears under a fitted top and tailored jacket; then her keys, transit card, and bag get scooped up in one messy grab / SFX: fabric whip, key jingle, zipper pull, bag rustle.
    
    SHOT 10: Insert shot, 50mm overhead / Match cut into lace-up shoes slamming on as the laces yank tight in one impatient pull / SFX: sole thump, lace tug, short breath.
    
    SHOT 11: WS, 24mm parallel / Whip pan transition into her, now in the tailored outside outfit, rushing through the apartment corridor into bright light without breaking stride / SFX: latch click, rapid footsteps, hallway air.
    
    SHOT 12: MS to CU, 35mm glide, 85mm push-in / Sound bridge into the metro interior as she grips the pole and slips through just before the closing doors, reflected chrome streaking around her and the city blurring outside / SFX: train rattle, carriage screech, door warning chime, light breath.
    
    SHOT 13: Insert to MCU, 50mm snap zoom / Smash cut to the office entrance as her access card hits the reader, the glass door unlocks, and she slips through before dropping into her chair and opening her laptop / SFX: badge beep, door click, laptop chime.
    
    SHOT 14: OTS, 35mm handheld / Rhythmic cut into her fingers racing across the keyboard with blue monitor light illuminating her face / SFX: keyboard clicks, notification sounds, mouse click.
    
    SHOT 15: WS, 24mm pull-out / Match cut back to the bedroom composition from the opening shot as she collapses onto the bed after a long day / SFX: body drop, fabric rustle, heavy exhale.
  18. 018
    WasifAI (@doctorwasif)post 2086315451970433265
    TEXT
    View original post on X ↗

    Prompt · 310 English words · 2,337 characters · historical-snapshot-public-card

    Use <<image>>only for the WOMAN’s face, identity, hair, skin texture, and body proportions. Do not copy its background, clothing, lighting, or composition.
    
    30s cinematic thriller, photorealistic. Rainy gas-station mini-mart after a car crash. Controlled handheld camera, fluorescent practicals, intermittent red/blue police lights, wet asphalt, haze, realistic sweat/grime, shallow DOF, film grain. No music.
    
    CAST: WOMAN throughout: torn dark jacket, jeans, scraped forearm, messy half-loose hair, sweaty, aggressive and adrenaline-fueled. CLERK: tired 40s man, green vest/flannel, cautious. STRANGER appears only in S9, dark silhouette, face never visible. No other people.
    
    DIALOGUE RULE: Korean, natural quiet speech, perfect lip-sync. Action must completely stop before speaking; speaker faces camera/front 3/4 with unobstructed mouth and remains still during the line. No VO/off-screen speech. S9 silent.
    
    S1 0–2.5: Woman bursts in, grabs unlabeled water from cooler, rushes to counter.
    
    S2 2.5–5: Slams bottle down, stops, faces camera: “붕대 있어요? 빨리요.”
    
    S3 5–7.5: Clerk cautiously gets bandage kit, stops, faces camera: “저기… 괜찮으신 거예요?” Places kit down.
    
    S4 7.5–9.5: Woman grabs kit, stops: “신경 꺼요.” Clerk backs away.
    
    S5 9.5–12: She sits by window, opens kit and wraps forearm. Police lights/wreck briefly visible outside. No dialogue.
    
    S6 12–14.5: Finishes bandage, stops, faces camera: “…살아있네.” Then drinks water.
    
    S7 14.5–16.5: Watches police lights through rainy glass, sets bottle down. No dialogue.
    
    S8 16.5–18.5: Hears something, clenches fist, rises and faces door. No dialogue.
    
    S9 18.5–22: Stranger bursts in and grabs her. Brief raw struggle—she twists free, elbows/shoves him, shelf rattles, bottle rolls, she forces him outside. His face never visible. No dialogue.
    
    S10 22–25: She reaches door, stops, looks back at clerk: “문 잠가요. 아무도 안 들여보내고.” Then exits.
    
    S11 25–30: She sprints through rain, jumps into dark sedan, starts instantly, reverses and speeds away from the police and crash. Police car passes the now-empty station too late. Door remains open/swinging.
    
    CONTINUITY: Same woman/face, store layout, door, red OPEN sign, water bottle and bandage progression throughout. No duplicated props/people, no weapons/blood/gore, no subtitles/text/logos/watermarks, no beauty retouching, no slow motion/speed ramps.
  19. 019
    WeWant Mars (@madhuribhai)post 2085896875295785430
    TEXT
    View original post on X ↗

    Prompt · 538 English words · 3,710 characters · historical-snapshot-public-card

    🌊 Concept: The Last Lighthouse Keeper
    
    Create a 30-second ultra-realistic cinematic video titled “THE LAST LIGHT”, set on an enormous isolated lighthouse during a violent midnight ocean storm.
    
    The entire video must be ONE SINGLE UNINTERRUPTED CONTINUOUS SHOT lasting exactly 30 seconds. No cuts, no scene transitions, no teleportation, no time skips, no duplicated characters, no sudden environment changes. Every movement must connect naturally from the previous moment.
    
    0–5 seconds — Establishing approach
    
    Begin with an extremely low cinematic camera flying just above a violently turbulent black ocean at night. Huge waves rise several meters high, illuminated intermittently by distant lightning. Torrential rain falls diagonally across the frame. The camera races toward a gigantic ancient lighthouse standing alone on a jagged rock formation.
    
    The lighthouse beam slowly sweeps through the storm, briefly illuminating rain, sea spray, birds, and enormous waves. Thunder flashes reveal the scale of the environment.
    
    The camera approaches the lighthouse at high speed and naturally rises along its outer stone wall, following the structure upward.
    
    5–10 seconds — Entering the lighthouse
    
    As the camera reaches a shattered window near the top, it smoothly flies through the opening without cutting.
    
    Inside is a massive circular lighthouse chamber containing an enormous rotating Fresnel lens. The mechanical gears are turning slowly, covered with condensation and tiny droplets of rain.
    
    An elderly lighthouse keeper wearing a heavy weathered coat rushes into frame carrying an old oil lantern. His clothes and hair are soaked from the storm.
    
    He looks toward the enormous rotating light mechanism and realizes something is wrong.
    
    The main lighthouse beam suddenly flickers.
    
    10–16 seconds — The failure
    
    The camera continuously circles around the keeper as he climbs a narrow spiral staircase toward the light mechanism.
    
    Outside the windows, lightning repeatedly illuminates the ocean.
    
    The lighthouse beam becomes weaker.
    
    The keeper reaches the mechanical control system and desperately begins turning a large emergency brass wheel.
    
    The machinery resists.
    
    Metal gears grind realistically.
    
    Water leaks through cracks in the stone walls.
    
    The entire tower subtly shakes as a gigantic wave crashes against the rock below.
    
    16–23 seconds — The impossible moment
    
    The keeper finally forces the mechanism back into motion.
    
    The giant Fresnel lens suddenly ignites with an intense warm golden beam.
    
    The camera moves extremely close to the rotating lens, passing around it as the beam sweeps across the storm.
    
    Every time the beam crosses the ocean, enormous waves become visible for a split second.
    
    A distant cargo ship appears dangerously close to the rocks.
    
    The lighthouse beam reaches it.
    
    The ship immediately changes direction.
    
    The keeper watches silently through the rain-covered window.
    
    23–30 seconds — Cinematic climax
    
    The camera smoothly exits through the same window and pulls rapidly backward into the storm.
    
    The lighthouse now stands brilliantly illuminated against the enormous black ocean.
    
    The beam rotates continuously across the sea, cutting through rain and fog.
    
    Lightning strikes somewhere in the distance, revealing the entire ocean for one breathtaking instant.
    
    The camera rises higher and higher while maintaining visual continuity.
    
    The lighthouse becomes smaller beneath the gigantic storm clouds.
    
    One final beam sweeps directly toward the camera, briefly filling the entire frame with golden-white light.
    
    End naturally with the light passing across the lens while the storm continues behind .
    
     — like a lost scene from a $200-million Hollywood survival thriller.
  20. 020
    BMX (@bmx_ai13)post 2085859028677361923
    TEXT
    View original post on X ↗

    Prompt · 554 English words · 3,665 characters · historical-snapshot-public-card

    Create a photorealistic cinematic 10 second video in 16:9. Nighttime. Two young adults stand face to face at arm's length, one man and one woman, shown mostly in clean side profile at the center of frame. They wear simple pale short sleeve shirts and dark trousers. Their bodies stay calm and nearly still, with tiny natural breathing, blinking, hair movement and subtle shifts of weight. A translucent ribbon of luminous energy flows continuously from one mouth to the other like visible breath, combining clear glasslike fluid, pale electric blue, soft violet, amber and gold. The energy has believable volume, refraction, internal particles, faint vapor, soft motion blur and warm spill light across lips, cheeks, noses and eyes. It must feel physically present in the air, not like a graphic overlay. Use a 35 mm cinematic lens, eye level camera, medium full two shot, shallow but natural depth of field, realistic skin texture, accurate hands, stable faces, natural anatomy, subtle handheld micro movement and a very slow forward drift. Keep the couple locked to the same screen position while the environment changes around them through seamless motivated transitions. Preserve identity, hairstyle, wardrobe, body proportions and energy direction throughout. 0 to 1 second, a narrow dim corridor with repeating ceiling lamps and deep central perspective, cool cyan fluorescent light, textured floor and gentle haze. 1 to 2 seconds, the corridor opens into a wet concrete parking passage, green cyan lights reflected in puddles, then briefly into an open rooftop at night with distant city bokeh and deep blue sky. 2 to 3 seconds, return smoothly to a shadowy corridor. Their hands naturally meet and hold low between them while the glowing stream remains uninterrupted. 3 to 4 seconds, transition into a longer industrial passage with repeating white fluorescent fixtures, strong vanishing point and cool blue shadows. 4 to 5 seconds, the space becomes a late night retail aisle, shelves appearing softly at the edges while central perspective and subject positions remain matched. 5 to 6 seconds, transition into a worn apartment or motel hallway with patterned floor, muted green walls and isolated ceiling lights. 6 to 7 seconds, move back into a wet underground passage with glossy reflections. Let the pair naturally exchange left and right screen positions using a concealed match cut, without body warping. 7 to 8 seconds, briefly reveal the open rooftop again, then glide back into the corridor. Their joined hands are visible for a moment. 8 to 9 seconds, alternate between wet garage and corridor using soft light blooms as transition masks. 9 to 10 seconds, settle in the corridor as the energy grows slightly brighter, then steadies, ending on a quiet suspended moment. Lighting stays low key and practical, dominated by cyan, teal, deep blue and muted green, with amber energy as the only warm key light. Add realistic exposure breathing, fluorescent flicker, wet reflections, subtle lens bloom, fine film grain and natural motion blur. Avoid plastic skin, over sharpening, face morphing, extra fingers, duplicate limbs, floating objects, impossible reflections, rubbery motion, sudden camera jumps, text, logos or interface elements. Music and sound: atmospheric electronic score in a dark dreamlike tone, slow pulse around 78 BPM, soft analog synth bed, distant sub bass, airy glass textures and a restrained heartbeat rhythm. Add quiet fluorescent room tone, distant city ambience and a delicate shimmering breath sound following the energy ribbon. Build slightly from second 7, then resolve into a soft suspended tone at second 10. No vocals.
  21. 021
    ivy (@notiiivy)post 2085832004415938848
    TEXT
    View original post on X ↗

    Prompt · 202 English words · 1,322 characters · historical-snapshot-public-card

    CAMERA: Handheld smartphone vertical 9:16 selfie video optimized for TikTok and Reels. The 5-second video begins with her holding the camera close in selfie mode, looking directly at her own reflection on the screen with a relaxed, subtle smile. She then smoothly raises the camera high above her head to capture a steep high-angle shot of herself. Natural selfie composition, subtle handheld shake, slight exposure breathing due to the bright sun, and realistic unstaged phone-like movement.
    
    LOOK: Bright, natural outdoor sunlight, realistic glowing tanned skin tones, subtle lens flare, authentic and completely unstaged summer vacation vlog aesthetic.
    
    STYLE: A casual, intimate 5-second vacation selfie clip. Relaxed and confident. She blinks naturally against the bright light, checks her reflection in the camera, and playfully lifts the lens up.
    
    CHARACTER: A young woman matching the reference image. Deeply tanned glowing skin, brown hair tied back, with tortoiseshell sunglasses resting on top of her head. She wears small gold hoop earrings, a very delicate gold chain necklace, and a bright light-blue bikini top.
    
    SETTING: Outdoors on a bright sunny day. She is resting on a white plastic lounge chair with a light-blue towel draped behind her. A light-colored tiled patio floor is visible in the background.
  22. 022
    Kinovi.AI (@kinovi_ai)post 2085821064370933885
    TEXT
    View original post on X ↗

    Prompt · 614 English words · 3,916 characters · historical-snapshot-public-card

    All dialogue is in English. VISUALS:
    
    Global Camera & Style Directives: Handheld mini DV camcorder footage filmed by the subject herself. The aesthetic strictly adheres to authentic late 1990s/early 2000s consumer camcorder quality, characterized by slight hand shake, occasional auto-focus hunting, imperfect framing, and natural zoom adjustments. The footage features a soft, tape-like image quality, subtle grain, realistic auto-exposure shifts from bright kitchen daylight, natural skin tones, and mild motion blur. The style is a cozy, relaxed kitchen vlog with candid moments and natural body language. No copyrighted characters, logos, brand names, or recognizable public figures anywhere in frame.
    
    Scene 1: Propped medium shot, fixed camera angle. The setting is a small, bright kitchen counter bathed in natural afternoon daylight. A young Mexican woman (in her late 20s, wearing a plain apron over a simple top, hair tied back) steps into the frame. She reaches out to adjust the camcorder lens, pulling her hand back and smiling warmly directly at the camera.
    
    Scene 2: Handheld extreme close-up. The camera bobbles and hunts for focus briefly as she films a warm, steaming pan of rich, dark red enchilada sauce. She uses a pair of tongs to dip a fresh corn tortilla into the red sauce, coating it completely.
    
    Scene 3: Handheld POV shot. She pans the camera down to a plain, clean ceramic plate. With one hand awkwardly holding the camera, she uses her other hand to roll the sauce-soaked tortilla around a generous portion of shredded beef.
    
    Scene 4: Propped medium shot. The camera rests on the counter again. She finishes arranging a neat row of three freshly rolled red beef enchiladas on the plate. She generously sprinkles bright green shredded lettuce and crumbled white cheese (queso fresco) over the top of the vibrant red sauce. She steps back, looks down at the plate, and smiles with a quiet, tidy energy.
    
    Scene 5: Medium close-up. She picks up a fork, effortlessly cuts a piece of the enchilada, and takes a satisfying bite while looking into the lens. She closes her eyes briefly in delight, giving a genuine, happy nod to the camera.
    
    Scene 6: Warm ending shot. She chews happily, smiles warmly, and reaches her hand forward. Her palm covers the camcorder lens, plunging the screen into total darkness as the recording ends. No fade to black.
    
    AUDIO & DIALOGUE:
    
    Global Audio Directives: The audio profile mimics a raw, untreated consumer camcorder microphone recording. There is a constant, low-level hiss of analog tape. Gentle, authentic Mexican acoustic music (such as a soft Mariachi or Norteño ballad) plays quietly in the background from an off-screen radio. The focus is on satisfying, gentle cooking ASMR sounds and casual, quiet dialogue.
    
    Scene 1 SFX: The loud, mechanical clack of a plastic camcorder button being pressed, followed by a slight, muffled rustling of the microphone as she adjusts it. Scene 1 Dialogue: Woman (smiling, speaking quietly and casually): "Let's make some dinner."
    
    Scene 2 SFX: The rich, satisfying sizzle and bubbling of the warm enchilada sauce. The soft, wet splash as the tortilla hits the liquid.
    
    Scene 3 SFX: The wet, slapping sound of the sauce-covered tortilla being placed onto the ceramic plate. The soft rustling of the shredded beef being handled.
    
    Scene 4 SFX: The crisp rustle of fresh lettuce being sprinkled, followed by the soft, tactile crumbling sounds of the cheese hitting the wet sauce. Scene 4 Dialogue: Woman (admiring her plate): "Looks so much nicer this way."
    
    Scene 5 SFX: The gentle scrape of metal tines against the ceramic plate. Scene 5 Dialogue: Woman (muffled slightly, happily chewing): "Mmm... perfect."
    
    Scene 6 Dialogue: Woman (smiling warmly): "See you later." Scene 6 SFX: The loud, booming rustle of a hand covering the microphone, followed immediately by a sharp CLICK that cuts the audio to dead silence.
  23. 023
    Rahul Nanda (@rahulnanda86)post 2085818664855732490
    TEXT
    View original post on X ↗

    Prompt · 371 English words · 2,295 characters · historical-snapshot-public-card

    Ultra-realistic split-screen action sequence .9:16 vertical video**
    
    The video is divided into two panels throughout:
    
    Above half:** the finished cinematic action scene on top of a moving train.
    
    Below Half:** a wider behind-the-scenes view showing how the same action is being filmed on set — the train rig, moving background screen / LED wall showing fast-moving landscape, cameras, crew, stunt coordinators, director, and lights. The contrast should be fun and impressive: left side looks like the final film, right side reveals the filmmaking process.
    
    The fight is between Aly and Sia, two intense young women in a brutal rooftop train fight. The train is racing over a bridge above water. Strong wind, hair whipping, clothes moving, metallic train roof vibrations.
    
    0–3 sec: Start mid-fight. Aly and Sia are already exchanging fast punches and kicks on top of the moving train. On the left, it looks like a high-budget action film. On the right, we see the same action being filmed on the train set, with a moving scenery screen behind them and a camera operator tracking alongside.
    
    3–7 sec: Sia swings hard at Aly. Aly dodges. Use a mind-blowing bullet-time moment as Sia’s missed strike throws her off balance and she nearly slips off the train edge. Wind tears at her body as she struggles to recover. On the right side, show the same bullet-time rig and crew setup from a wider angle.
    
    7–11 sec: Aly regains control and lands a hard hit on Sia. Sia falls over the edge and is now hanging onto the side of the moving train, legs flying in the air over the water below. Huge danger, strong speed effect. On the right side, show stunt wires, safety crew, and cameras capturing the fall.
    
    11–15 sec: Aly drops to her knees at the train edge, leans down, and punches Sia hard. Sia loses her grip and falls into the water below. Immediately after, the right side widens further into a slightly elevated full-set reveal: train rig, LED background, cameras, crew, director, all visible, showing how the whole sequence was achieved. End on that cool behind-the-scenes filmmaking reveal.
    
    Style: ultra-realistic, high-energy, slick action, strong wind, dynamic movement, clear choreography, split-screen throughout, exciting mix of finished movie and on-set reality, no comedy, no cartoon feel.
  24. 024
    MadMax (@madmax_series)post 2085806641979494424
    TEXT
    View original post on X ↗

    Prompt · 965 English words · 6,398 characters · historical-snapshot-public-card

    Create a 20-second photorealistic, family-friendly jungle adventure in 16:9 widescreen.
    FORMAT AND POV:
    Text-to-video. One continuous, uninterrupted first-person POV recording with no cuts, transitions, montage, slow motion or changes of viewpoint.
    The camera is a handheld DSLR operated by an unseen safari guest sitting in the centre of the back seat of an open-top jeep. The lens looks forward between the two front seats. The camera continues recording throughout the entire adventure.
    GROUND-LEVEL ENVIRONMENT:
    The first frame begins inside a dense tropical jungle at ground level. All four tyres of the jeep are travelling along a wet, muddy trail surrounded by thick vegetation. Puddles, exposed roots, ferns and hanging vines are visible ahead.
    The vehicle remains on the jungle floor. The environment feels humid and immense, with soft morning sunlight filtering naturally through the canopy.
    CHARACTERS:
    Exactly two adult women sit in the front of the jeep.
    The curly brown-haired woman drives from the front-left seat. She wears a dusty grey tank top and practical adventure clothing.
    The straight black-haired woman sits in the front-right passenger seat. She wears a dark olive expedition shirt and practical safari gear.
    Keep their faces, hair, clothing, proportions and seat positions consistent. Both women remain safe and stay inside the jeep for the entire video.
    CONTINUOUS ACTION:
    The recording opens with the jeep already moving along the muddy jungle trail. Its tyres splash through shallow puddles while vines gently brush the sides of the vehicle.
    Colossal elephants slowly emerge from the misty vegetation ahead. They are recognisable modern elephants with realistic anatomy, natural skin and believable movement, but several times larger than normal. Their enormous legs resemble moving pillars among the jungle trees.
    The jeep carefully drives between the elephants. One elephant places its enormous foot into a puddle beside the vehicle, producing a spectacular splash of muddy water. Another elephant gently extends its trunk over the open jeep and sprays a fine shower of water across the passengers and camera lens. The surprised women duck, then laugh with amazement as the peaceful elephants continue through the jungle.
    A deep gorilla call echoes behind the jeep.
    The camera operator quickly turns around. One gigantic but curious silverback gorilla steps onto the jungle trail. It has realistic anatomy, natural wet black fur and powerful physical weight. It notices a canvas supply bag filled with colourful tropical fruit swinging from the rear of the jeep.
    The curious gorilla begins bounding along the trail behind the moving vehicle, interested only in the fruit bag. It keeps a safe distance from the passengers while moving through the vegetation with impressive speed.
    The camera whips forward again. The brunette driver looks back briefly, smiles nervously, accelerates and shouts:
    “Hold on!”
    The jeep moves faster through the jungle. Mud sprays from the tyres, hanging leaves sweep past the lens and the passenger grips the dashboard with excited laughter.
    The camera turns backward once more. The gorilla reaches the loose canvas strap, gently pulls the fruit bag free and immediately slows down. It sits in the middle of the trail, happily examining the fruit as the jeep continues away. The encounter feels exciting and playful rather than hostile.
    The jeep drives into a shallow jungle river and splashes toward a bright clearing. Sunlight blooms across the wet lens. Both women laugh with relief while the camera returns to the forward view between their seats.
    Suddenly, leaves rustle on the riverbank above them. One enormous jaguar, approximately the size of a rhinoceros, makes a spectacular graceful leap from one side of the river to the other, passing directly over the open jeep.
    The jaguar is a realistic modern animal with golden fur, black rosettes, natural feline anatomy and fluid movement. It does not land on the vehicle or touch the passengers.
    As the jaguar passes overhead, its long tail sweeps extremely close to the lens. The startled operator’s wet hand loses its grip on the DSLR. The camera slips harmlessly over the side of the jeep and drops into the shallow river while continuing to record.
    The POV enters the water with a large splash. Bubbles flow past the lens as the camera gently sinks and rolls. Through the rippling surface, show the jeep continuing safely across the shallow river while the giant jaguar stands calmly on the opposite bank, looking back.
    End underwater with rising bubbles, refracted sunlight, muffled laughter and the enormous jaguar’s distorted silhouette above the surface.
    CAMERA STYLE:
    Authentic handheld DSLR safari footage with moderate natural shaking, quick human reaction pans and realistic movement created by the travelling jeep.
    Use brief autofocus hunting, natural motion blur, water droplets on the lens, realistic exposure adjustment and convincing underwater refraction. Keep every important animal action understandable.
    All camera movement must be physically motivated by the jeep or the camera operator. Maintain one continuous recording.
    AUDIO:
    Natural environmental audio only. Include the jeep engine, wet tyres, jungle birds, insects, rustling leaves, elephant footsteps, water splashes, the elephant’s soft rumble, the gorilla’s distant call, excited reactions, the driver saying “Hold on!”, laughter, rushing river water and muffled underwater bubbles.
    No music, narration or additional dialogue.
    VISUAL STYLE:
    Extremely photorealistic live-action footage. Realistic human skin, individual hair strands, wet fabric, elephant skin, gorilla fur, jaguar fur, scratched vehicle metal, muddy tyres, tropical leaves, atmospheric mist and natural water behaviour.
    The animals remain recognisable present-day animals, simply enlarged to an extraordinary scale. Their sizes remain consistent relative to the jeep.
    The emotional progression is wonder, playful excitement, fast movement, relief and a final breathtaking surprise.
    TECHNICAL LOCK:
    One continuous POV take. Ground-level jungle travel throughout. Exactly two women, several peaceful giant elephants, one curious giant gorilla and one giant jaguar. Consistent characters, vehicle and animal anatomy. No elevated roadway, external camera angle, duplication, transformation, subtitles, logos, watermarks or on-screen text.

Showing 24 of 181 matching cases.

How to use the Seedance 2.5 archive

Treat the prompt as a production brief.

01

Start from a traceable source case

Use the paired public X post and verbatim prompt as one reference record. The collection orders those records newest-first by X Post ID and does not rewrite, popularity-rank, or claim ownership of creator material.

02

Keep continuity instructions explicit

Name the identity, wardrobe, object, geography, screen direction, lighting, sound, and motion details that must survive the sequence. Remove adjectives that do not change a frame or an audible event.

03

Review the sequence before expanding it

Inspect physical behavior, shot transitions, subject consistency, audio, pacing, and delivery fit. Revise the smallest failed instruction before adding more cuts or visual effects.

Model labels and available inputs can change. Confirm the current model and controls in the workspace before production.

Content context

Seedance 2.5 video prompts

Seedance 2.5 prompt · AI video prompts · video generation prompt library

These third-party public reference cases preserve captured prompt text and X attribution. They do not prove current model access, supported controls, output quality, rights clearance, licensing, or repeatability.

Reader notes

Before you generate.

Where do the Seedance prompts and examples come from?

The source snapshot contains 291 receipt-validated records. The canonical prompt-length gate publishes 181 and quarantines 110; prompt text is preserved verbatim, each published case links to its matching post and author, and first-frame posters are generated from the validated source video.

Does Generate preserve a selected Seedance prompt?

Yes. The complete direction and the Seedance 2.5 template identity are carried into the generation URL for review in the workspace.

Continue the work

Take a prepared brief into the workspace.

Continue with “Try it free” to confirm the current product context and next production decision.

Try it free