Dari X · Motion Transfer
Image-to-video AI prompts
Start from one still image and describe what should move. These prompts show how creators animate photos and illustrations into short clips: what to say about the subject, which camera move to add and how to keep faces and products from drifting.
Kling 4.0 photo booth strip loop where a roommate climbs between the frames
Made in @higgsfield_ai Use [Image1] as the first frame and [Image2] as the last frame. They are the same image, so the clip loops seamlessly. [Overall Settings] Cinematic, a vertical photo booth strip of four frames on white photo paper, flash lighting, film grain, natural skin texture. Real, lively acting: the Turkish roommate is cheeky, the Brazilian roommate amused; everyone in every frame stays alive, blinking, laughing and reacting the whole time. The impossible thing: the four frames are four connected little rooms. The Turkish roommate is alive inside them and climbs over the white borders from one frame into the next, while each frame keeps its own moment and pose. Only he crosses the borders, one border at a time, always upright and feet first, like a person climbing over a low fence; nobody is ever upside down or dragged, everyone else stays in their own frame, and everyone keeps the size of the frame they are in, with arms and legs of normal length. The strip and the camera stay still. Bodies, faces and hands keep their shape, and the place keeps its exact shape; only the one impossible thing changes. Everything moves at natural, real-time speed, brisk and lively, with real weight. [Sequence of Events] 0-2s: In frame 1 the Turkish roommate looks down at the slice of pizza in frame 3, grins, and swings his legs over the white border. 2-5s: He climbs down feet first into frame 2 and squeezes past his own silly-faced self, who stops and stares. 5-8s: He steps down into frame 3 and takes a huge bite of the pizza his roommate is holding up, and the roommate gasps. 8-11s: In frame 1 the Brazilian roommate, now alone, waves at him to come back, laughing. 11-15s: The Turkish roommate climbs back up through frame 2 into frame 1, chewing happily, while the pair in frame 4 lower their sunglasses to watch. 15-18s: Back in frame 1 the Brazilian roommate wipes the tomato sauce off his friend's mustache and they both burst out laughing. 18-20s: Everyone settles back into their original poses in all four frames, matching the first frame exactly. [Audio] A bouncy retro funk tune; the clunk and flash pop of a photo booth; muffled chewing and laughter; street noise outside the booth; the rustle of photo paper. No dialogue, no subtitles, no on-screen text.
Bubble pops revealing rubber duck
he pops the last large bubble and instead of a note a small yellow rubber duck drops out of it
Made with Seedance 2.5 on makeugc
Create a 30-second horizontal 16:9 photorealistic Red Bull rallycross commercial: MILA pours Red Bull into her white car, its paint transforms, she wins a three-car race. Paint is the sole fantasy; physical action stays convincing. MILA wears the COMPLETE @image4 racing suit FROM FRAME ONE to the ending. Both rivals have different body models and liveries. Visible spectators and a visible start signal establish a live event. Exactly 12 timed shots, natural speed, no slow motion. Can beside filler from frame one; paint finished by 8.70; launch signal 11.20. Preparation/grid/ending cuts omit elapsed time. No extra scenes. REFERENCE ROLES @image1: real slim 250 ml Red Bull can, exact packaging. Transparent margins are empty canvas. @image2: MILA's car BEFORE, plain white. @image3: SAME car AFTER, exact navy/silver/red livery. @image4: CLOTHING ONLY. Dress the living MILA in this complete long-sleeve suit FROM FRAME ONE; match cut, fabric, colors, zipper and neckline. No mannequin. @image5: RIVALS ONLY. LEFT red/white Peugeot WRX, RIGHT yellow/black Audi RX. Match full RACE BODYWORK/liveries, one each; ignore sheet layout. Images 2/3 define ONLY MILA's car, never rivals. Preserve all bodywork/hardware. Integrate references into scenes, not isolated layouts or fixed camera angles. MILA MILA — a beautiful American Instagram-style brunette model and performer, 20. Long dark-brown hair in a high ponytail, glossy lips, expressive eyes, soft glam makeup and delicate sparkly stud earrings. Slim athletic figure with an extremely large, very full bust with pronounced forward projection, exceptionally large, full rounded buttocks, a narrow waist, flat stomach and lean arms and legs. Her bust has much greater volume than a typical large bust, visibly oversized relative to her narrow ribcage. Keep the increased volume concentrated in her bust and buttocks; preserve her slim shoulders, waist, arms and legs. Preserve her face, adult age, hair color and body proportions across every shot. Fit the suit to her body rather than changing her proportions to match the empty garment reference. Realistic skin texture and natural anatomy, support and gravity. No plastic skin, doll face, body reshaping or facial identity drift. She is confident, composed and slightly playful in the opening; focused while driving; visibly pleased at the end. Small natural expressions, realistic blinks and breathing. No exaggerated screaming or continual posing. COSTUME AND RACING EQUIPMENT Complete fitted ONE-PIECE @image4 suit in Shot 1: sleeves DOWN TO WRISTS, navy matte fabric, red side/thigh panels, silver-white shoulders/trim, fitted waist/hips/legs, real seams. Show sleeves/red panels through opening, pour and flap closure. No sleeveless top, dress or later costume change. Silver zipper partly open in reference deep V, prominent cleavage. Opaque fabric supports bust without reducing volume; secure fit, no clipping, transparency or exposed underwear. SAME neckline/zipper before and after racing. ONE small Red Bull emblem on upper LEFT sleeve. No words, extra logos, sponsor patches or numbers. Plain black racing ankle boots. Bare hands outside racing. Driving adds plain black gloves, navy full-face helmet with clear visor, fastened black multi-point harness OVER THE SAME SUIT. Hair tucked under helmet. Only this equipment changes across time cuts; suit remains identical. CAR, CAN AND PROPS Full-size reference car: four wheels, fixed geometry/wheelbase, left-hand drive, one driver. Only paint/graphics change; hardware/glass/carbon/wheels stay fixed. Headlights off. Engine OFF during pour/paint; starts with MILA seated at grid. Fuel filler remains on LEFT REAR QUARTER at the reference's circular flap. Flap already open, inner cap removed in Shot 1. Fixed metal neck inside the original recess, mouth tilted slightly upward; never enlarge the opening. Pour DIRECTLY from can into neck. No funnel, hose or adapter. One chilled CLOSED slim Red Bull can: hand-scale, intact cylinder/label, hinged tab, real condensation/reflections. Liquid exits opened top beside tab, never an invented spout. Closed unbranded metal case beside filler, dry top at hand height. Cut omits setting can upright on case and securing inner cap; Shot 3 closes flap. Partly-full can stays there during race, retrieved for ending. No cooler/duplicate can. Exactly TWO @image5 World RX SUPERCARS: RED: Peugeot 208 WRX, red/white angular livery. YELLOW: Audi S1 EKS RX quattro, yellow/black livery. BOTH: ultra-wide race fenders/track, vented bumpers, carbon splitters, hood extractors, roof intakes, large full-width wings, visible cages, small competition wheels/thick tires. Preserve race hardware/gravel clearance. No stock road cars or street tuners. Fixed distinct models/liveries; factory grille badges only. No sponsors, numbers, Red Bull graphics, extra cars or rival close-ups. LOCATION AND VISUAL STYLE Closed stadium rallycross venue, pines beyond: slightly damp asphalt, fine compacted gravel, barriers/catch fencing, broad shallow RIGHT bend with room for two lines, modest gravel crest. No puddles/heavy mud; tire-raised dust never masks action. OCCUPIED grandstands at start/finish and gravel section: several hundred spectators at natural scale, varied seated/standing groups, a few cheering and waving plain flags. No cloned looping crowd. Stands visibly populated in launch, crest and finish backgrounds; spectators stay behind fences. Consistent curbs, grid boxes, one start-light gantry and a few marshals, no dense signage. SAME paved apron for opening/ending, case off racing line; grid elsewhere on same course. Consistent architecture/crowd locations. Bright overcast daylight, soft shadows, neutral skin, consistent sky; tactile skin, fabric, metal, glass, rubber, carbon and gravel. DV 16mm tape camcorder handheld feel. Subtle texture, natural motion blur, purposeful motorsport angles, strong parallax, weighty acceleration. Readable faces/logos/action, plausible cameras. No film borders, beauty filter, plastic CGI, videogame overlays, orange grading, pyrotechnics, neon scenery, fake flares or excessive smoke. STORYBOARD — EXACTLY 30 SECONDS SHOT 1 | 0.00–1.20 | THE WRONG FUEL: IMMEDIATE HOOK MILA already wears the COMPLETE long-sleeve @image4 suit beside the white car's LEFT REAR filler, CLOSED cold can upright in right hand. FRAME ONE shows navy/red suit, wrist-length sleeves, drink beside open flap and exposed neck: unexpected use immediately clear. Close waist-up three-quarter view includes complete head, face, neckline, label and white bodywork. Moderate depth of field, face unobstructed. At 0.15 left index finger lifts tab ONCE: CLICK/hiss, tab stays attached. Small confident smile toward filler. Can OPEN by cut. No introductory posing or second opening. SHOT 2 | 1.20–4.20 | POV FROM INSIDE THE FILLER Fixed POV from a tiny camera just inside the UPPER inner edge of the metal filler neck, looking outward and slightly upward. The curved rim frames the edges; daylight reveals MILA's recognizable face as she leans toward the opening. Her face remains outside, beyond the rim. Her right hand brings the OPEN can into the upper-right of frame. Natural perspective, no fisheye or camera movement through metal. Keep the can outside the neck, pouring edge about 1 cm above its upper lip. Tilt slowly: a SHORT, thin pale-gold stream falls from the can's drinking opening through the LOWER foreground into the neck, below the lens. Keep her eyes and mouth visible above and beside the stream. Fixed metal geometry, steady wrist, gravity-driven flow; no floating liquid, flow through metal or splashes on the lens. Pour a SMALL portion. Rotate upright to stop the stream, allow the last drop to enter, THEN withdraw the can. Some drink remains. One uninterrupted pour. Left hand stays clear. SHOT 3 | 4.20–5.20 | CLOSE THE FILLER Cut omits setting can upright on case and securing inner cap; her hand is now free. Close exterior view: press hinged outer flap flush once, withdraw hand. Car white; suit sleeve visible. Nothing trapped between flap/body, no clipping. SHOT 4 | 5.20–8.70 | SURFACE ENERGY TRANSFORMATION Front-left three-quarter view, smooth 0.8 m dolly, whole car visible, real parallax. Car stationary, filler shut, engine off. Same apron/light; MILA/case offscreen. Start WHITE. An amber pulse at the closed filler releases fine bright filaments clinging to body contours. They branch over arches, doors, hood and roof, reflecting briefly in nearby paint. Navy pigment blooms in irregular connected patches ON THE PANELS. Exact @image3 silver/red graphics develop in place as the effect reaches them. Smooth glossy lacquer, fixed panel geometry and logos; each area changes once. Glass, wheels, carbon unchanged. No straight edge, vertical bar, split-screen, comparison slider or screen wipe. Effect confined to body panels; scenery unchanged. No drips, smoke or fire. Full @image3 by 8.30, filaments extinguish; camera keeps gliding to 8.70. No cut or frozen hold. SHOT 5 | 8.70–10.60 | LATER AT THE GRID Time jump: finished car stationary at grid. Boarding and adding helmet/gloves/harness happened offscreen; SAME opening suit, no wardrobe transformation. Cockpit close-up: already helmeted, gloved, harnessed, recognizable eyes behind raised clear visor. Lower visor once, right hand back to wheel; both hands ready before launch. Starter catches, held launch revs and small chassis vibration. Eyes on road; no clipping or hair through helmet. SHOT 6 | 10.60–14.00 | LIGHTS OUT, THREE-CAR LAUNCH Low wide three-quarter view behind trackside barrier, obliquely ahead of grid. All THREE distinct cars at same line/heading: Red Bull center, RED Peugeot WRX and YELLOW Audi RX either side, complete @image5 race builds. Start-light bar and populated stand clearly visible above them. Red bulbs already lit at 10.60; ALL go DARK together at 11.20. All cars launch on this single visible cue and main musical beat. No early movement, repeated signal or extra countdown shot. Engine surge, brief tire chirp, rear suspension loading, subtle nose lift, forceful acceleration in separate lanes. No wheelie, burnout or smoke cloud. Pan as they surge past; strong parallax, natural blur, crowd reacting behind fencing. By cut: RED leads by one car length, Red Bull second, YELLOW third. Real wheel rotation and forward momentum; no teleporting or sideways launch. SHOT 7 | 14.00–15.20 | GRAVEL IMPACT Low trackside insert: MILA's near-side tires cross asphalt onto gravel, small stones thrown backward from contact, suspension responding. Wheels stay circular/attached, car moves forward, camera outside path. Race order unchanged. SHOT 8 | 15.20–20.00 | ONE VISIBLE OVERTAKE ONE locked elevated wide view shows the approach, entire shallow RIGHT bend and exit. Road wide enough for two separate lines. All cars travel toward the same exit. RED leads by one car length on the OUTSIDE arc. Red Bull is already on the open INSIDE/right side relative to travel, still behind; YELLOW trails both. MILA never crosses through RED to reach this line. Brief straight-line braking, smooth smaller-radius turn, progressive acceleration out. Only slight rear slip, no prolonged sideways drift. RED stays on its wider arc; visible lateral clearance throughout. Show continuously: Red Bull's nose catches RED's rear quarter, draws level, moves ahead, then its REAR bumper clears RED's FRONT bumper. Pass complete by the end. Stay on the inside exit line; do not cut across the rival. YELLOW remains third. No camera cut, hidden position swap, collision, corner teleport, rival stopping or dust masking the pass. Both cars maintain believable forward momentum. SHOT 9 | 20.00–21.00 | COMMITMENT Cockpit insert: focused eyes through clear visor, small vibration/breathing, both gloved hands controlling mounted wheel. Eyes on course; same helmet, harness and seat. Race order unchanged. SHOT 10 | 21.00–24.00 | WINGS, FOR AN INSTANT Low lateral tracking includes approach, ONE modest crest and landing slope continuously, occupied stands beyond fencing. Front wheels rise, rears follow; all four briefly airborne UNDER ONE SECOND, low arc and sustained forward speed. Tires meet descending road; suspension compresses, rebounds once, settles. Weighty car, no hovering, flip, wing deployment, broken wheels or altered road. Rivals remain behind, never suddenly alongside; orientation coherent. SHOT 11 | 24.00–27.00 | FINISH ORDER LOCKED wide three-quarter view of the finish stripe and road on both sides, populated grandstand clearly visible. An official behind the barrier waves a checkered flag; spectators react naturally. Do not pan away with the winner. Red Bull crosses first, RED after a clear short gap, then YELLOW. All cross the SAME stripe in the SAME direction and keep going. Preserve race dust and each distinct model/livery. No scoreboard, confetti or posing on track. SHOT 12 | 27.00–30.00 | MILA AND THE BRAND: LATER Time cut to original apron, car parked and race-dusty. MILA beside left side; helmet/gloves removed offscreen, ponytail restored, SAME long-sleeve suit/neckline as opening. Already holding SAME OPENED can at waist, raise ONCE to shoulder, label toward camera, fingers below wordmark. Small satisfied smile, relaxed breath. No reopening or drinking. Medium framing: complete head with headroom, face, neckline, can and door graphic. Hold final half-second only; no end card or added text. AUDIO AND EDITING No dialogue, voiceover or subtitles. One continuous bass-and-percussion instrumental: restrained preparation, builds through launch revs, brief musical pullback before lights out, main beat at 11.20. Never restart at cuts; no giant cinematic booms. Immediate tab CLICK/hiss, liquid trickle, flap click, short paint sweep, starter, layered turbo rally engines. Launch tire chirp and crowd swell; load-dependent pitch, short gearshift cuts, turbo whistle, gravel, firm landing. Natural pass-by Doppler/distance, no F1 shriek or constant explosions. Crowd matches occupied stands, louder at launch/finish, quieter from apron. Keep mechanical detail under music; racing sound recedes at final time cut. FINAL CONTINUITY PRIORITIES One MILA in the SAME long-sleeve suit from FIRST to LAST frame; one can; one reference car changing paint once. Two @image5 rivals: RED Peugeot WRX and YELLOW Audi RX, full race bodies/liveries. Stable identity, proportions and geometry; coherent direction across cuts. One can opening, one direct pour, flow stopped before withdrawing; no extra fingers or intersecting objects. Equipment/location change only at specified time cuts. Reference branding on MILA's car/can/sleeve and rivals' small factory badges only; no extra sponsors, captions, UI, speedometer or watermark. Deliver exactly 30 seconds: surface-energy transformation, visible lights-out launch, lively race atmosphere, one earned overtake, one grounded jump and MILA's confident ending.
Character 360-degree studio turn
The same man from the reference stands on a plain light-grey studio background and slowly turns 360 degrees in place, clockwise, at a steady speed: front, side, back, side, front. The person rotates, the camera does not move. Full body in frame, arms relaxed, neutral expression, feet stay on the same spot. Soft even studio light. Same face, hair, outfit and proportions in every frame.
High-Intensity Motorcycle Commercial
15-second high-intensity motorcycle commercial, ultra cinematic, aggressive editing style, perfectly synced to music beats, fast cut rhythm with explosive transitions, luxury performance motorcycle advertisement. Heavy use of speed ramping, whip pans, crash zooms, motion blur, and dynamic camera shakes for impact. Beat 1 (Intro Hit) Extreme close-up of motorcycle LED headlight turning on in total darkness, sudden light ignition, quick push-in with subtle lens flare burst. Beat 2 Rider puts on helmet, visor slams down, sharp sound-synced cut, tight close-up with slight camera shake for impact. Beat 3 (Build-up) Engine ignition close-up, mechanical vibration intensifies, fast orbit camera movement, metallic tension buildup. DROP 🔥 Beat 4 Motorcycle launches forward violently from standstill, tire grip explosion, dust burst, aggressive rear tracking shot with speed ramp. Beat 5 High-speed mountain drift through sharp corner, motorcycle leaning hard, drone whip-pan following movement, heavy motion blur, cinematic tension. Beat 6 Fast urban night sprint through real city streets, warm street lights, rapid FPV forward rush, crash zoom transitions between street sections, gritty realistic tone (no neon, natural lighting only). Beat 7 (Mid-air energy peak) Drone orbit shot around motorcycle crossing bridge at extreme speed, wind pressure visible, environment wide scale reveal, fast rotational camera movement. Beat 8 (Impact shot) Ultra-low roadside pass-by, motorcycle rushes past camera at extremely close distance, strong whoosh effect, heavy motion blur, slight camera shake impact. Beat 9 (Hero landing) Cinematic crane-up reveal at mountain overlook, golden hour sunset, motorcycle slowly settles, calm contrast after chaos, epic final hero frame. 🎬 Style Direction (Important) Ducati / BMW Motorrad / Top Gear cinematic aggression, Netflix automotive intensity, IMAX-scale realism, grounded physics, no cyberpunk, no neon, pure mechanical power + real-world adrenaline.
Stylized Martial Arts Dance Crew at Night
A group of stylized, caricatured men perform. Lead: Wing Chun master in a black traditional tunic with white cuffs, bowl cut with flared ends, and thick mustache. Crew includes: man with large afro in brown suit, bald man with long side hair in maroon suit, albino man with long white hair, and a stout man with a ginger bowl cut and large mustache. Setting: Cobblestone plaza at night under harsh artificial light. 0-10s: Characters take turns walking toward the camera with expressive gestures. 10-20s: Group performs a synchronized martial arts dance with sharp arm movements. Handheld camera style, deep shadows, cinematic night lighting.
Grayscale Depth Map Motion Reference
Grayscale depth map of a person performing actions: standing, saluting, turning, walking, and holding an object. High contrast subject against dark interior background. Smooth motion.
Glittering hat fashion light film
Use the uploaded image as the opening frame. Create a 10-second cinematic fashion film in 16:9. Keep the same single figure, wide glittering hat, centered close-up, shadowed eyes, facial shape, and black background throughout. 0–3 seconds: Begin almost still. Silver points shimmer across the hat and shoulders. A narrow warm light traces the face under the brim. The camera slowly pushes in as a restrained electronic pulse builds. 3–6 seconds: On a clear bass hit at exactly 3 seconds, the backlight changes from red and icy blue to violet and emerald. The figure raises their chin slightly. A wave of colored reflections travels across the hat and shoulders; the face stays mostly in shadow. 6–10 seconds: The beat grows fuller with crisp percussion. The lips shift subtly from bright red to deep plum. The figure turns their head just a few degrees toward the light, then holds a striking final pose as the camera settles closer. End on a clean musical hit. Audio: Original dark electronic fashion music, around 100 BPM, deep bass, sparse synths, crisp percussion, no vocals. Synchronize the color change and stronger beat at 3 seconds. Add a faint shimmer sound as the light crosses the hat. Controlled, natural motion; high contrast, fine film grain, polished cinematic lighting. Preserve the subject and composition. No cuts, extra people, visible eyes, warped face or hat, text, or added logo.
Carved wooden bird flies from palm
the wooden bird flaps its carved wings, lifts off his palm, and flies up out of frame. He watches it go, then looks at the knife.
If I had doubts before, they’re gone now.
Create a photorealistic 12-second vertical video, 9:16, in one continuous shot. REFERENCES Use reference image 1 for the woman's identity, face, hairstyle, physique, clothing, and jump rope. Use reference image 2 for the interior, window, evening Paris skyline, colors, and lighting. Place her naturally in front of the window with matching perspective and lighting. CAMERA AND FRAMING Locked-off camera, straight-on view. Keep her entire body visible from head to shoes throughout the video, including every jump. Frame her as closely as possible while leaving enough room above her head, beneath her shoes, and around the rotating rope. Her face should remain clearly readable, and the floor beneath her feet must be visible. No cropping, camera movement, zooming, cuts, or close-ups. TIMELINE — EXACTLY 12 SECONDS 0.0–2.5 seconds: She stands facing the camera, holding both jump-rope handles in one hand, the cord hanging naturally. With a confident, playful expression, she says in clear English: “Now, let's see who's better.” Natural delivery and accurate lip sync. 2.5–3.0 seconds: A clear half-second pause. She maintains eye contact with the camera. 3.0–3.8 seconds: She smiles and says: “Ready? Let's go!” 3.8–5.0 seconds: She transfers one handle into her other hand, ending with exactly one handle in each hand. She naturally positions the middle of the rope behind her heels, ready for a forward swing. Show the entire preparation continuously, without the rope teleporting or changing shape. 5.0–6.0 seconds: She performs exactly two normal-speed, two-foot jump-rope jumps. One full forward rope revolution per jump. Both feet clear the rope together, with small, controlled jumps and soft landings. 6.0–8.0 seconds: Smoothly transition into slow motion for exactly two seconds of screen time. Maintain identical framing. Show a continuous movement sequence that includes descent, visible contact with the floor, slight ankle and knee flexion as she absorbs the landing, and a clear push-off through her forefeet into the next jump. Ground contact and push-off must be unmistakable. Show realistic gravity, body weight, muscle response, and subtle natural secondary motion of soft tissue, hair, and clothing. These movements follow the impact with believable inertia. The rope rotates continuously and passes beneath her feet during the airborne phase. No floating, frozen poses, exaggerated bouncing, rubbery anatomy, or abrupt changes in body proportions. 8.0–9.7 seconds: Return smoothly to normal speed. She performs two more complete jumps, then stops deliberately with both feet planted on the floor. Her wrists stop turning, and the rope settles naturally in front of her. She continues holding one handle in each hand. 9.7–12.0 seconds: Standing still, she looks directly into the camera with a playful smile and slightly breathless delivery: “Who do you think is better?” Finish the sentence before the video ends. Her entire body remains visible. REALISM AND CONTINUITY Natural smartphone-video appearance, realistic skin texture, consistent evening lighting, and grounded contact shadows. Preserve her identity, physique, clothing, and the environment throughout. Maintain a single rope of consistent length with two handles. Physically plausible rope tension, wrist rotation, foot clearance, balance, and floor contact. No rope passing through her body or shoes, no extra limbs or fingers, no duplicated handles, and no sliding feet. Slow motion changes playback speed only; it does not change her movement style or the camera position. AUDIO All dialogue is in English, with accurate lip sync. Subtle room ambience, natural breathing, rope swishes, and synchronized shoe impacts. Sound slows naturally during the slow-motion segment. No music, subtitles, on-screen text, or added logos. REFERENCE
Armored knight time-stop alley fight
Rain chase→blind spot ambush→time stop counter→collapse burst. Character reference, Seraine from @[image 1]: silver white tousled short hair, a side fringe covering half of one eye, grey blue eyes, a pale and severe face. She wears silver black plate armor, the breastplate and pauldrons covered in gilded scrollwork relief, a white quilted underlayer with a long skirt, a holy sword at her hip and a cross kite shield slung on her back. Keep her face, hair, armor patterning and sword design consistent for the whole shot. The camera starts as a shoulder rig riding tight on Seraine and moves with her. A wet gothic stone alley on a rainy night, magic rune lamp signs hanging along both walls refracting through the rain into mottled patches of deep blue and dark gold, standing water on the ground reflecting broken light. Seraine, in her silver black gilded holy armor, is being run down from behind by several mechanical puppet knights, her stride fast and hard like a cheetah, the gilded runes in her armor joints flickering cold white light with every step. The shoulder rig bumps and shakes slightly with her pace, and raindrops hit the front of the lens and leave hazy water trails. Several mechanical puppet knights, iron cast faceplates with glowing dark red mana cores set into their chests, ambush at the same moment out of the visual blind spots thrown by the rune signs and from behind the thick stone pillars on both sides of the alley. The camera snaps back fast and runs a 360 degree orbit, sweeping across the silhouettes closing in from every side, and lands on a close up of Seraine's face. Rainwater runs off the tips of her silver white hair, her eyes cold and sharp, and she throws up a hand and releases a deep blue time field. Time stops dead in that instant and holds for only about 1 second. Raindrops hang and freeze into ice crystals, and a knight's arm raising a halberd locks rigid halfway up. The camera then dives into that almost frozen space. Seraine draws the holy sword at her hip with a reverse grip, and the moment the blade clears the scabbard the gilded runes along its spine light up one by one from hilt to tip, the whole sword wrapped in a layer of flowing gold white holy light, fine cold blue arcs burning along the edge. She triggers the blink rune array in her armor and her body bursts apart into a blinding stream of cold white light, flickering at high frequency between the knights. Every blink pulls a strong directional motion blur trail behind her and leaves several silver grey translucent afterimages fading out, and each reappearance lands with a harsh white flash and scattering shards of light. The suspended ice crystal raindrops are smashed by the light stream into glittering points. Diagonal cut, horizontal slash and rising thrust run together in one combo, and every stroke leaves a gold white curved blade arc hanging in the frozen air instead of fading, strings of golden sparks bursting where the edge scrapes iron plate. Her left hand takes a knight by the throat in a reverse grip and drags him off the ground, a deep blue energy bolt gathering in her palm and shattering the mana core in his chest in midair. The combo is clean and decisive. Close ups catch the flowing rune light and arcs on the blade, the current flickering at the rune ports in her arm armor joints, and the mechanical rigidity of the knights' iron faceplates. The high speed blink section carries heavy motion blur and light trail smear throughout, while only the frozen raindrops and the knights stay sharp, for an extreme contrast between fast and slow. After the last knight is dealt with, Seraine stands in the middle of the alley with the holy sword angled down and presses the rune port on her arm armor to release the time field. The dammed flood of time pours down at once, every gold white blade arc hanging in the air falls at the same moment, and the knights she cut split apart along those cut lines together. The cores in their chests burst from the inside and collapse into a wide spray of mechanical debris and gilded iron plate scattering across the ground, and the light on the holy sword slowly draws back in.
Winged warrior's red-light storm duel
Storm last stand→crack awakening→feather blade volley→red blade cleave. Character reference, VESRA from @[image 1]: waist length silver hair, red eyes with red eyeshadow, black cracks bursting sideways from the corners of her eyes toward both sides (not tear tracks running down); a black armored corset with cutouts at the sides of the waist and on the legs, a thigh band on her right leg, a pair of black wings on her back with dark red inner feathers, and a red energy longsword. No horns on her head. Keep her face, the direction of the cracks, the armor patterning and the sword design consistent for the whole shot. Red light system (global rule, runs by the second): from 00:00 to 00:09 there is no red light anywhere in frame, and her blade and armor plates are cold grey steel. At 00:09 the cracks at the corners of her eyes and her pupils light up red first. At 00:11, when the feathers fire, the entire edge of every feather lights up a clear dark red, and the feather blades drag clearly visible red trails through the curtain of rain; the red in this beat must take up a real area of the frame, not a thin edge you can barely see. At 00:15, once the sword is back in her hand, red light spreads along the already formed blade from the guard toward the tip, fully covering it by 00:17. After 00:27 the red on the sword draws in to a single thin line along the edge without going out completely, and that thin red line is still visible at the end. Apart from her sword, her eyes, the cracks and the feather edges, no other red light source appears in frame. Brightness (global rule, runs by the second): from 00:00 to 00:03, apart from the few frames where lightning flashes, the frame is almost fully black, showing only the edge outlines of the figures and the broken pillars with no detail at all. From 00:03 to 00:08 it is a little brighter than the first 3 seconds but still very dark overall, and shapes are read by the reflections off the standing water on the ground. From 00:09 to 00:14 her cracks and feathers are the only light in frame. From 00:17 to 00:24 the red light lights up the entire middle ground. From 00:25 to 00:26 the red light of the explosion fills the whole frame, its brightest point close to pure white overexposure; this is the brightest beat of the piece and must be clearly brighter than the stretch from 00:17 to 00:24. From 00:27 to 00:30 it falls back to dark, with only the faint glow of embers left on the ground. The camera starts low, pressed against the wet stone surface, with a stretch of her black wing always pinned along the bottom edge of the frame. The top of a ruined gothic cathedral in a rainstorm, a broken bell tower platform hanging high in the air, the ground covered in fallen pillars and rubble, standing water reflecting the lightning. From the first frame VESRA holds the longsword in her right hand, the blade clearly visible and, for now, cold grey steel with no red light at all. A giant stone winged demon reaches a huge claw down from the top of the frame and clamps onto her pauldron, the claw staying in frame the whole time, and flings her against the broken pillars again and again, the sword staying in her right hand throughout. The instant she crashes into the water the longsword is knocked out of her palm: you can see it leave her fingers and spin across the surface of the water, coming to rest in the water an arm's length to her left, and it lies in that exact spot from then on until she takes hold of it again. The camera never leaves the ground, tracking sideways with the direction she is thrown, and rain hitting the front of the lens leaves water streaks. The camera pushes in along the surface of the water to her face: silver hair plastered to the side of her face, blood mixed with rain running down. She looks up, and the black cracks at the corners of her eyes spread and widen toward both sides, red light showing through from deep inside them. She digs her fingers into the cracks in the stone under the water and pushes her upper body up. The black wings on her back snap open to their full span, and right after that the feathers peel off the wing surfaces row by row and become dozens of black feather blades fired all at once, each one dragging a vivid dark red trail through the curtain of rain, driving into the stone demon's chest and both wings, forcing it back half a step and punching several holes through its stone wings. The camera pans with the feather blades through the rain and passes a close up of a single feather blade in flight. Once the feather blades are in the stone demon, the camera travels back along the ground from the stone demon to her side and settles on her right hand and the sword an arm's length away, with no cut in between. She reaches out, takes hold of the hilt and lifts the sword out of the water. The sword's length, width and outline follow the character sheet strictly and stay exactly the same from the moment it is in her hand to the end of the piece, never growing longer, never deforming and never producing an extended light blade. Once her grip is steady, red light spreads along the already formed blade from the guard toward the tip, fully covering it by 00:17, and after that only its brightness changes. The stone demon rips the feather blades out of its chest and lunges, and she drops her center of gravity and passes under its belly. Through this pass the blade stays a metal sword wrapped in red light, the guard, the edge and the tip always distinguishable, and the sword does not grow longer for even a single frame. When the tip scrapes the stone, what lights up is the stone itself: sparks and a red scorch mark stay on the ground behind her, and that scorch mark belongs to the ground, not to the sword, and is not connected to the blade. The camera follows this pass at ground level. After passing through she turns and leaps, and the camera circles halfway around her, sweeping in turn across her back, her open black wings and the head of the stone demon as it turns. At the peak of the jump she brings the sword down with both hands, the red sword light tearing open the whole curtain of rain, and cleaves the stone demon apart on a diagonal from shoulder to waist, top to bottom. A ring of dark red energy bursts out from the cut and pushes outward in a circle, blasting all the surrounding raindrops apart into mist. The stone demon's body breaks apart along the cut, the grey white inner stone grain showing at the break, big chunks of stone and broken pieces of its wings crash into the water and throw up huge splashes, and the rubble rolls across the ground until it comes to rest. VESRA lands in the foreground at the edge of the platform, her back to the camera, black wings half folded, the tip of her sword angled down at the ground, a thin red line still left along its edge. The camera slowly pulls back, the visual weight stretching out toward the rain flooded abyss behind her, and the frame returns to dark, with only the embers in the cracks of the rubble still glowing. Frame requirements: the camera moves continuously through the whole piece with no edit cuts of any kind. The sword is a solid metal blade wrapped in a layer of red light, not a light blade made of pure light, and the blade length stays constant; at no point may it turn into an evenly glowing column of light with no visible edge. The rain streaks, splashes and mist of the storm should feel physically real, light falloff should follow real optics, and movement paths should obey gravity and inertia. The stone demon is grey black stone all over, with the inner stone grain showing at the break. The outfit follows the character sheet strictly, and the armor patterning, the position of the thigh band and the shape of the wings do not change.
Otter riding a dragon at high speed
Perfect visual consistency, unchanging style, Fluid extreme speed drone tracking shot. disorienting camera. blistering high-speed action, extreme fluid keyframes, smear frames exploding across every movement, whip-pan camera tracking, pure unbroken motion, every limb and cloth fold drawn with razor-sharp timing and weight. otter riding a dragon, clearly having fun. smooth, 2.5D hand drawn, consistent style, smear frames, foreshortening, at an angle to the viewer. Expensive Pixar-, Ghibli-, and Disney-level animation quality with amazing movement
Blue serum bottle macro commercial
A high-end, aesthetic commercial shot of **Bioderma Hydrabio Hyalu+ Serum**. * **Scene Details:** * A clear blue glass serum bottle with white text and a white dropper cap. * Extreme close-up shot of the glass pipette dispensing a clear, hydrating liquid drop onto smooth skin. * Smooth application of the serum glowing on skin, highlighting its hydrating texture. * Macro shot of air bubbles floating inside the transparent blue bottle liquid. * **Lighting & Style:** Studio lighting, clean aesthetic, ultra-sharp focus, cinematic macro commercial product showcase, pristine visual quality, 8k resolution.
Cartoon cat investigates mysterious trembling box
Style: Stylized 3D cartoon (think Luigi's Mansion meets Spider-Man: Into the Spider-Verse). Rich textures, dramatic cinematic lighting, and exaggerated, expressive character physics.Scene 1 (0.0 – 2.5s) | The DiscoveryVisual: A wide-eyed, fluffy cartoon cat freezes in a dark, dusty attic. Its glowing green eyes lock onto a massive, trembling cardboard box covered in "DO NOT OPEN" tape. Camera: Dynamic Push-in. Starts wide, then violently whips forward into an extreme close-up of the cat’s dilated pupils, reflecting the shaking box.Scene 2 (2.5 – 5.0s) | The ApproachVisual: The cat creeps forward on tip-toes. Suddenly, a massive, jagged shadow rises from behind the box, looming over the walls like a multi-legged monster. Camera: Low-Angle Tracking Shot. The camera skims along the floorboards right in front of the cat's paws, tilting up sharply to reveal the terrifying, growing shadow.Scene 3 (5.0 – 7.5s) | The SoundVisual: CREAK! The box lid violently pops open an inch. A puff of glowing green dust explodes out. The cat’s fur stands completely on end, sparks of static electricity flying. Camera: Orbit Arc Shot. The camera rapidly spins $360^\circ$ around the cat at high speed, capturing its sheer panic from every angle as the dust settles.Scene 4 (7.5 – 10.0s) | The Final StretchVisual: The cat decides to investigate. It reaches out a single, trembling paw toward the glowing gap in the box. A low, rumbling growl vibrates through the room. Camera: POV Crane Down. Looking directly from the inside of the dark box up at the cat’s approaching paw, plunging downward as the gap narrows.Scene 5 (10.0 – 12.5s) | The ClimaxVisual: The box bursts open completely! Glowing eyes flash from the darkness. The cat gasps, flying backward through the air in slow-motion cartoon terror. Camera: Zolly (Hitchcock Zoom). The background stretches dramatically while the cat stays fixed in the center of the frame, amplifying the sudden shock.Scene 6 (12.5 – 15.0s) | The TwistVisual: Time snaps back to normal speed. A tiny, adorable, glowing robotic toy mouse hops out of the box, happily squeaking and chasing its own tail. The cat faceplants into a pile of pillows in the background, looking utterly exhausted. Camera: Whip-Pan to Static. The camera rapidly whips away from the flying cat to lock onto the tiny mouse, ending on a crisp, comedic still shot.
Seedance 2.5 emerald luxury perfume ad from model and bottle references
A luxury perfume commercial. @ Image 1 = model reference; @ Image 2 = perfume bottle reference. Keep both consistent throughout the video. Rich emerald environment, minimalist luxury, high-contrast lighting with soft golden accents, glossy reflections, macro product cinematography. Elegant, controlled motion. **0–2s:** Start immediately with the woman clearly visible in an emerald silk dress, centered in a strong fashion pose, holding the **Frameo** perfume bottle near her chest. Her face, dress, and bottle are clearly visible in the first frame. Luminous emerald backdrop with soft golden light and gentle highlights on her face and silhouette. Bright, rich, premium atmosphere. No dark shadows, no gray background, no empty frame, no fade-in. **2–4s:** Cut to a close-up. She raises the Frameo bottle and sprays once toward her neck. Fine mist catches the golden light. She lowers the bottle and gently touches her collarbone. Smooth, elegant movement, sharp reflections, and emerald transparency. **4–7s:** Cut back to a wider shot. She slowly turns and walks forward as the camera tracks backward. Her emerald silk dress and hair move naturally. The emerald environment expands around her, with subtle mist and golden light streaks flowing through the scene. **7–10s:** Cut to a medium fashion shot. She pauses and slowly turns toward the camera with a confident gaze. The camera makes one elegant arc around her while golden highlights trace her silhouette. Refined cinematic movement. **10–12s:** Cut to a macro product shot. The Frameo perfume bottle floats and slowly tilts in the emerald space, catching golden highlights. Elegant liquid reflections, delicate vapor trails, and subtle amber particles enhance the luxurious presentation. **12–13.5s:** Cut back to the model for one final tight fashion shot. She gently turns her head toward the camera, with her hair and dress moving softly. Elegant, confident, and captivating. **13.5–15s:** Cut to the final hero packshot on a pure black background. The Frameo perfume bottle stands centered, illuminated by refined emerald highlights and a thin golden rim light. The tagline **“A Scent That Tells Your Story..”** fades in beneath the bottle, spoken clearly by a refined female voice. Clean, sophisticated luxury finish. **Consistency requirements:** Use the exact Frameo bottle from @ image 2 and the same woman from @ Image 1 throughout. Preserve the bottle's shape, cap, color, proportions, and branding. No logo changes, no misspelled text, no extra products, and no unnecessary visual effects. Cinematic 4K quality, realistic materials, smooth transitions, premium fragrance-advertising aesthetic.
Even zombies have snack cravings. Nobody is safe when the snacks are thi
The opening frame is Image 1 and the snack the girl is eating is Image 2 From 0–0.5 seconds, use a medium shot to establish the setting: the girl is sitting alone on the sofa in a dimly lit living room. The only light in the room comes from the television, which is playing a Resident Evil zombie movie. The camera then moves in closer, showing her clutching a large bag of snacks. She watches the movie nervously while mechanically stuffing snacks into her mouth. Image 3 Cut to a close-up of the girl. A pale, blood-stained hand quietly rests on her shoulder, slowly reaching out from behind her and directly into the snack bag in her arms. Her entire body freezes. She slowly turns her head. Reverse angle: a zombie is standing behind her. Once the girl comes to her senses, she immediately hugs the snack bag tightly. The monster refuses to give in and reaches over to snatch it away. This tug-of-war over the snacks should last for a long time and be very funny. Suddenly cut to a medium shot: Image 4 the two of them are now sitting side by side on the sofa, watching television and eating snacks together. The camera zooms in on a close-up of the product.
Seedance 2.5 urban sunset drive with custom matte-black 911
Create a 30-second cinematic urban sunset driving sequence using the two reference images strictly. REFERENCE LOCK: [1] THE DRIVER — angular face, tan skin, curly black hair, goatee, black t-shirt, dark cargo pants, black boots. [2] THE CUSTOM 911 — matte black widebody Porsche 911, white "911" graffiti, BBS wheels with red brake calipers, red underglow, rear wing, dual center exhausts. VISUAL STYLE: Arcane and Spider-Verse 2D/3D hybrid artwork, hard-edge brushwork, stepped 12fps animation cadence, golden-hour sunset vs. neon city lighting. No music, only footsteps, ignition, flat-six roar, tire screeches, and gear shifts. 0–5 SECONDS — PUDDLE & IGNITION Low-angle shot of red underglow reflecting in a puddle as the Driver's [1] black boots step toward the Custom 911 [2]. Close-up: hand pulls handle → Driver [1] sits → turns ignition key → grips wheel. CUT. 5–10 SECONDS — LAUNCH & MIRROR GLANCE Dual center exhausts [2] blast white smoke as red underglow ignites. Hand shifts gear → Custom 911 [2] launches under elevated train tracks. Cockpit POV tilts up at the bridge, then snaps to the Driver's [1] eyes in the rearview mirror. 10–18 SECONDS — INTERSECTION DONUTS Top-down rotating shot as the Custom 911 [2] spins 360-degree donuts between yellow taxis. Close-up of the BBS wheel and red caliper [2] spinning violently, throwing sparks and red-lit smoke before rocketing away. 18–25 SECONDS — UNDER-TRUCK PASS & FENDER CAM Black boot [1] slams the gas pedal; hand upshifts by the glowing radio. Low camera shoots underneath a passing truck's chassis as the Custom 911 [2] streaks past. Cockpit camera pushes through the windshield onto the hood [2] with white anime speed-lines, cutting to a tight rear-fender camera locked onto the spinning wheel lip in thick pink-red smoke. 25–30 SECONDS — HIGHWAY LOOP & LIGHT TRAILS High aerial shot: the Custom 911 [2] drifts around a curved highway overpass, pouring twin trails of crimson tire smoke and glowing red taillight streaks toward the sunset skyline.
Seedance 2.5 on Dreamina_AI Prompt: Create a 15-second vertical 9:16 li
Create a 15-second vertical 9:16 live-action dance video using the person in @ Image1 Setting: a high school classroom — desks, chairs, chalkboard. One continuous take: no zooms, no cuts. - Prioritize @ Image1 for the face, hairstyle, outfit, colors, and overall silhouette - Only one person in the frame - Not intense breakdancing — a short live-action dance MV where a high school student casually dances along to the music, just for fun - Don't repeat the same choreography; mix in steps, turns, hand movements, footwork, profile angles, and swaying hair - Amateur camerawork, as if a friend is filming on an iPhone — handheld shake, slightly off-center framing that loosely follows the dancer
Seedance 2.0 mini honey badger animated continuation with character voices
Create a 15-second animated continuation starting exactly from the uploaded final frame of the corrected Part 1. Use this single image as the visual reference for both characters, their poses, environment, lighting, and art style. Characters: 1. Honey badger: preserve the stout upright body, dark bluish-purple fur, cream-white fur cap, small ears, thick limbs, long tail, and shoulder strap visible in the image. No axe. Initially seated astride the dragon immediately behind his mane. Serious, frightened during flight, then relieved and exasperated. 2. Goofy Chinese dragon: preserve the long serpentine blue body, yellow-gold mane, cream belly, long whiskers, round eyes, oversized buck teeth, and small limbs visible in the image. No wings. Inexperienced, innocent, and absurdly confident. Style: Cute traditional Chinese ink/watercolor cartoon, soft paper texture, expressive ink outlines, watercolor shading, clean silhouettes, smooth readable hand-drawn animation, and expressive cartoon comedy. Match the opening image’s colors, proportions, warm daylight, and layered mountain scenery. No 3D or realistic CGI. VFX: Thin watercolor cloud wisps curl around the dragon during the turn and reveal a sunlit grassy terrace beside a mountain lake. Wind gently trails the mane and whiskers backward. Subtle grass movement and a small dust puff during landing. No magical aura, lightning, transformation, or explosive effects. Setting and continuity: Start in the exact positions and flight direction shown in the uploaded frame. The rock face is ahead; an open route passes around its outer edge toward SCREEN RIGHT. A broad grassy terrace lies beyond the rock at a slightly lower elevation. Show this continuous route: approach, turn around the rock, descend to the terrace, land. Keep camera angles on the same side of the action axis and preserve predominantly LEFT-TO-RIGHT travel. No reverse flight, teleportation, or sudden changes of location. Critical anatomy and contact: The badger has exactly TWO arms and TWO hands attached to his own shoulders. During every airborne shot, both hands grip the dragon’s upper back immediately behind the mane. No pointing. Keep the near-side hand at its visible contact point; the far-side hand may remain naturally occluded. No badger hands or arms appear beside the dragon’s face or beneath his jaw. The badger’s hips stay seated on the same section of the dragon’s back, with legs securely astride it. The dragon’s head, neck, torso, and tail follow one continuous curved flight path without stretching or tangling. The badger releases his grip only after the dragon is fully stationary on the ground. Dialogue and voice direction: All dialogue is spoken in ENGLISH with clear, funny animated-character voices. Honey badger voice: A compact, slightly gravelly mid-low cartoon voice, dry and skeptical, rising sharply into alarm. Clear articulation, never a monstrous growl. Dragon voice: A bright, rounded, slightly nasal cartoon voice with a smiling, innocent delivery. Sound like an enthusiastic young adult, not a baby. His confidence is completely sincere. Use consistent voice identities throughout. Natural conversational pacing, no overlapping speech. Only the speaking character moves his mouth for speech; the other reacts silently. Accurate English lip sync while preserving animal mouth anatomy, especially the dragon’s two oversized buck teeth. Speak only the exact lines below. No narration, extra dialogue, or additional vocalizations. SHOT 1 — 0–3s: Camera: Side-tracking medium two-shot matching the opening frame. Show both faces and the approaching rock edge. Dragon action: Keeps looking ahead, eyes wide with uncertainty. Continues forward flight and asks: “Which way?” As the badger finishes answering, begins a gentle bank toward the open route on SCREEN RIGHT.
What if McDonald’s delivery used a flying Tesla Roadster?
10-second, 9:16, 24fps, ultra-realistic POV smartphone video, one continuous shot. Use the uploaded reference images as strict visual references: Reference 1: Chongqing Hongyadong night-view window composition. Reference 2: same female courier, hovering white Roadster, and food handoff composition. Reference 3: final McDonald’s fries, drink, and burger close-up. Use the uploaded white Tesla Roadster image as the strict vehicle reference. Keep the same silver-white body, low wedge-shaped silhouette, dark panoramic glass, black wheels, rear wing, and overall proportions throughout. Use the uploaded female portrait as the strict character reference. Keep the same young adult East Asian woman, same face, long wavy chestnut-brown hair, fair skin, makeup, and body proportions throughout. The entire video is filmed from a first-person POV inside a high-rise apartment in Chongqing at night, looking through an open window toward glowing Hongyadong, the river, bridge, and illuminated skyline. 0–2.5s Start with the Hongyadong night view matching Reference 1. One hand reaches toward the open window. The white Roadster appears from the upper-right background and flies smoothly toward the window. Soft blue-white hover light is visible beneath the car. Keep the camera almost fixed with only subtle smartphone micro-shake. 2.5–6.5s The Roadster slows down and hovers steadily directly outside the window, matching Reference 2. The passenger-side door is open. The same female courier sits inside wearing a stylish red-and-yellow McDonald’s uniform and cap. She smiles naturally and extends a simple tray toward the viewer. On the tray are only: one red McDonald’s fries carton, one white drink cup with straw, one burger box. The viewer’s two hands reach forward and receive the tray. Keep the handoff slow, clear, and physically believable. No floating food. No sudden object changes. 6.5–10s The viewer now holds the food in the foreground, matching Reference 3. The fries, drink, and burger box stay large, sharp, and stable in the center foreground. In the background, the same Roadster gently accelerates away from the window and flies over the Hongyadong skyline. End with the McDonald’s meal dominant in frame and the Roadster smaller in the distance. Visual style Ultra-realistic viral social ad, natural smartphone POV, realistic hands, realistic food textures, glossy car reflections, warm golden Hongyadong lights, deep night city atmosphere, subtle blue hover glow, realistic depth of field, believable motion and physics. Strict consistency Same woman. Same face. Same hair. Same Roadster. Same Hongyadong setting. Same McDonald’s red-and-yellow packaging. Avoid No Paris. No Eiffel Tower. No KFC. No Cybertruck. No generic sports car. No car transformation. No wings or rotors. No extra people. No duplicated hands. No duplicated food. No warped packaging. No floating objects. No chaotic camera movement. No cartoon CGI. No subtitles. No watermark. No UI.
No drone. No crew. No expensive setup.
Create a realistic 360-degree drone shot that slowly pans far away from the character, revealing the entire environment like the opening shot of a blockbuster movie.
Creature breaks out of cinema screen
THIS IS ONE SINGLE CONTINUOUS UNBROKEN SHOT FROM FIRST FRAME TO FINAL BLACKOUT. No cuts, transitions, fades, dissolves, or hidden edits. Any cut is a generation failure. 12-second ultra-realistic 9:16 smartphone video inside a packed luxury cinema. Shot on iPhone 17 Pro, handheld micro-shake, HDR, realistic low-light detail, deep focus, natural motion blur. No text, captions, logos, UI, or watermarks. SCENE: Warm amber cinema lighting, cream seats, dark central aisle, enormous curved screen. Audience packed on both sides, quietly watching. CHARACTER: Young South Asian man, 22–24, dark hair, light stubble, black turtleneck and black jeans. Face from. Seated beside the center aisle throughout. Camera always remains physically in his hand until the final impact. 0–3s: Camera faces the cinema screen. An ancient flooded underground ruin fills the movie screen. Through dark water, an enormous skeletal humanoid creature slowly rises, dripping, with elongated arms and a distorted skull. It walks directly toward the screen. 3–5s: Without any visual boundary, the creature physically steps OUT of the movie and onto the real cinema carpet. Water splashes onto the aisle. It is nearly ceiling-height. Audience members gasp, laugh nervously, and raise their phones. The creature continues slowly toward them. 5–7s: Camera naturally swings toward our character. His expression changes from amazement to nervous disbelief. He looks at the creature, then back at the camera. Camera smoothly swings back toward the aisle. The creature is now terrifyingly close. 7–9s: Low handheld angle as the creature passes between the seats. Wet footprints appear on the carpet. Everyone films it. Phones glow across the auditorium. Heavy footsteps vibrate the seats. Nobody runs yet. 9–10s: The creature suddenly FREEZES. Its head violently rotates toward our character. Its jaw tears open impossibly wide and releases a deafening supernatural ROAR. The physical pressure wave hits the entire auditorium simultaneously. Lights flicker, seats shake, people scream and recoil. 10–12s: The character's hand involuntarily jerks from the shock. The phone remains in his loose grip while the camera violently whips through random real fragments: screaming audience, ceiling lights, blurred creature, seats, glowing phones, carpet, creature lunging closer. No editing, only uncontrolled physical camera movement. His grip finally fails. Phone tumbles, spins once, violently strikes the seat. INSTANT BLACK SCREEN from physical impact. Complete silence. No fade. PHYSICS: Creature crosses from screen into reality seamlessly with identical perspective, lighting, scale, shadows, and floor contact. Water physically transfers from the movie world onto the real carpet. Every audience reaction follows the same roar pressure wave naturally. LIGHTING: Cool blue-green screen light mixed with warm amber cinema sconces. Creature becomes increasingly illuminated by real auditorium lighting after leaving the screen. Violent light flicker only after the roar. AUDIO: Subterranean water ambience, audience murmurs, wet footsteps, rising tension, sudden deafening roar with microphone clipping, synchronized screams, chaotic handling noise, phone impact, then absolute silence. STYLE: Photorealistic viral found-footage realism, imperfect smartphone cinematography, believable human reactions, realistic physics, terrifying scale, immersive spatial audio, no artificial cinematic cuts.
Seedance 2.5 Arcane-style Muay Thai fight from three reference images
Create a 30-second cinematic Muay Thai fight sequence using the three reference images strictly. REFERENCE LOCK: [1] FIGHTER #1 (BLACK SHORTS) — preserve the exact angular face, messy black hair, shirtless muscular build, white hand wraps, black shorts, and bare feet. [2] FIGHTER #2 (WHITE SHORTS) — preserve the exact angular face, messy brown hair, shirtless muscular build, white hand wraps, white shorts, and bare feet. [3] THE ARENA — preserve the exact traditional Muay Thai stadium, warm overhead spotlights, hanging banners, and weathered ring with red and white ropes. VISUAL STYLE: Premium Arcane-inspired 2D hand-painted digital artwork, hard-edge brushwork, thick painterly strokes, dramatic lighting, subtle 2.5D depth. Gritty underground Muay Thai atmosphere. Realistic weight and impact. No music, only heavy breathing, skin-on-skin strikes, canvas footsteps, and arena ambience. 0–5 SECONDS — RING STARE-DOWN Inside the warm, spotlight-lit arena [3], Fighter #1 [1] and Fighter #2 [2] stand in the center of the ring. Low-angle camera tracks upward along Fighter #1 [1]: bare feet → black shorts → taped fists → focused eyes. Both fighters raise their guards into classic Muay Thai stances. CUT. 5–10 SECONDS — OPENING STRIKES Fighter #2 [2] lunges forward with a fast jab-cross combo and a heavy low kick. Fighter #1 [1] checks the kick with his shin and counters with a snapping body kick. Sweat and dust burst off their skin under the overhead lights [3]. 10–15 SECONDS — CLINCH & KNEES Both fighters lock into a tight neck clinch. Fighter #2 [2] drives a brutal knee into Fighter #1's [1] ribs. Fighter #1 [1] twists their grip, off-balancing Fighter #2 [2], and lands two rapid counter-knees. 15–20 SECONDS — ELBOW EXCHANGE They break the clinch and trade razor-sharp close-range elbows. Slash from the right — Fighter #1 [1] leans back, grazing past his chin. Spinning back-elbow from Fighter #1 [1] — Fighter #2 [2] blocks high and stumbles back against the ropes [3]. 20–25 SECONDS — AERIAL ASSAULT Fighter #2 [2] rebounds off the ropes with a flying knee. Fighter #1 [1] sidesteps at the last millisecond and pivots hard on his bare foot. Close-up of Fighter #1's [1] eyes locking onto the opening. 25–30 SECONDS — THE KNOCKOUT SMACK! Fighter #1 [1] unleashes a devastating roundhouse kick directly to Fighter #2's [2] jaw. Fighter #2 [2] crashes onto the dusty canvas [3] as Fighter #1 [1] stands tall, chest heaving under the spotlights.