LogoAhaPrompt
  • Prompts
  • Featured
  • Models
  • Submit
  • Blog
AhaPromptAhaPrompt

AI Prompts for Images, Video & Audio — Every Model, One Library

Built withLogoNEXTY.DEV
Explore
  • All Prompts
  • Featured Prompts
  • Image Prompts
  • Video Prompts
  • Audio Prompts
  • AI Models
  • Submit a Prompt
  • Blog
Languages
  • English
  • 中文
  • 日本語
  • 한국어

Copyright © 2026 AhaPrompt All rights reserved.

Privacy PolicyTerms of Service
HomeAI Prompt LibraryAI Video PromptsMonster Lifts Woman in Tunnel Horror

Monster Lifts Woman in Tunnel Horror

ByteDanceSeedance 2.5ByteDancevideo

Woman, monster, and environment must belong to the same clearly computer-generated AAA fantasy game CG; the woman's facial close-ups still retain digitally sculpted features, art-directed skin shading, and clumped modeled hair, without switching to live-action photography, cosplay, ordinary gameplay, 2D animation, or cel shading. Environment: a narrow, low, rough underground tunnel, gray-brown rock and earth walls interspersed with weathered wooden posts and horizontal wooden supports, continuous frames forming clear depth, the ground is uneven hard earth with scattered small stones, the air has slight dust haze. The woman stands at the near end of the tunnel, the monster approaches along the same passage directly in front of her, with no forks, doors, or other characters between them. Overall cold dark gray-brown, the only clear lighting comes from the flashlight in the woman's hand: slightly warm white light illuminates the monster ahead and the rough walls, and the weak light reflected from the walls makes the woman's eyes, facial volumes, and clothing readable; do not add separate portrait lights, lanterns, or firelight. At the beginning, use the flashlight's intermittent brightness changes and brief near-black frames to create fear, with faint wall contours preserving space; after the monster gets close, the lighting stabilizes, allowing the final grab, lift off the ground, side position, and open-mouth action to be clearly visible. Character A: the only clearly adult woman, light skin tone, slim to proportionate build, longer oval face, brown eyebrows, light-colored eyes; brown hair tied low back, with a few loose strands at the temples and beside the ears. Wearing a plain loose gray-olive long-sleeved hooded sweatshirt, the hood hanging at the back of her neck, dark charcoal gray pants and understated dark shoes; the clothes are soft everyday fabric, with no armor, skirt, or weapon. Maintain the same face, hairstyle, hoodie, and pants. Her right hand always holds the only short black cylindrical flashlight, the lamp head at the front of her fist, the beam emitting only from the front glass opening, at first shining along the direction of her extended right arm into the tunnel; later when the woman is lifted, her right hand still holds the same flashlight, right elbow bent, the flashlight remaining in front of her waist and abdomen, lamp head facing forward and upward toward the monster's chest, neck, and lower half of its face, with scattered light and wall reflection illuminating the woman's face. Her left arm at first stays tensely at her side. The flashlight does not switch hands, is not duplicated, does not leave her hand, and the lamp head never turns back to shine on herself. Character B: the only slender non-human monster clearly larger than the woman, directly presenting its real face from its first appearance, with no mask or mask-removal action. The skull is narrow and long, the forehead high and round, most of the top of the head bare, with a few long black strands remaining on the sides and back of the neck; deep-set pale gray-yellow eyes with small dark pupils, the nose area is a dark triangular nasal opening, with no normal protruding fleshy nose. The cheeks, long narrow jaw, and neck are covered with vertical sinew patterns from red-brown to dark flesh-pink, the lips are extremely thin, revealing tightly packed upper and lower rows of long ivory-colored pointed teeth, the oral cavity deep and dark. The whole body likewise has a complete red-brown sinew surface, slightly wet and reflective, with no bleeding; rib contours prominent, waist and abdomen very narrow, spine ridge raised, shoulder and hip angles clear. The two arms and two legs are abnormally long but with clear joint connections, large hands with slender separated fingers, bare feet narrow and long with clear toes. No clothes, armor plates, horns, weapons, or huge claw blades. It adapts to the tunnel height with head and shoulders leaning forward and hips and knees flexed, always maintaining the same body size and proportions, and cannot suddenly become larger when approaching. 0.00–2.00 seconds: begin immediately from an unstable chest-up close-up at a front-side angle of the woman, right arm extending the flashlight deep into the tunnel, the light producing brief glare at the edge of the frame; her eyes wide, lips slightly parted, head and shoulders making small tense movements, her gaze always searching the dark passage beside the camera, not staring at the lens to perform. The image briefly darkens and recovers, the camera with restrained handheld slight shake. Her face maintains a refined AAA game-character face model, clear brow ridge and cheekbone volumes, restrained skin detail, and clumped modeled hair; the reflected light in the darkness matches game CG materials, without turning into a live-action actor. 2.00–5.00 seconds: cut to a tunnel POV in the direction of the woman's gaze, rough walls pressing close on both sides, continuous wooden supports leading into the distance. First let the flashlight briefly reveal the empty passage and ground, then enter brief near-black, then from a slightly tilted angle again reveal the same row of wooden supports; the camera sways slightly with her flashlight-holding hand, without a long forward movement. In this section the far end remains hard to identify, and no clear full-body monster shot is inserted early. 5.00–6.00 seconds: quickly cut back to a tighter close-up of the woman's face, eyes suddenly opening wider, throat swallowing, mouth opening, right arm still raising the flashlight forward. She hears movement ahead but freezes in place, does not run away. This close-up continues to use the same sculpted CG face, game-character skin shader, and cohesive hair clumps, with identity, clothing, and lighting direction unchanged. 6.00–9.00 seconds: first press into brief darkness, leaving only rapid footsteps and breathing ahead; then cut back to the tunnel POV, using two short, clear illuminations to show the same unmasked red-brown monster running toward the woman. In the first glimpse, it is among the distant wooden frames, upper body leaning forward, long legs alternately driving forward, two long arms asymmetrically spread to help balance; the image darkens again, footsteps continue approaching; in the second glimpse, it has already passed the wooden post position from the previous glimpse, clearly closer, with the other leg stepping forward, its head and face always oriented toward the woman. Each time the light comes on, the actual forward stride and body displacement must be visible, not leg movement in place, running backward, or duplicating two monsters. The two running moments belong to the same single approach within the same tunnel, the monster's body size unchanged, with darkness covering the middle distance. 9.00–10.50 seconds: the image again becomes almost completely dark, footsteps and heavy breathing rapidly approaching from directly ahead. The camera remains at the same observation position near the woman, without switching scenes, and without adding punches, wall impacts, or other attacks in the darkness. 10.50–12.00 seconds: when the flashlight illuminates again, the monster has suddenly already occupied the frame at close range, still retaining the same red-brown long face, triangular nostrils, pale eyes, and pointed teeth. It completes the final running step, head and shoulders rapidly thrusting forward, mouth opening to emit one short hoarse non-verbal roar, the black strands on the sides of its neck swinging with the forward lunge; the light from the woman's flashlight illuminates the teeth and lower jaw from below, with bright glare and rapid approach forming a sudden reveal. The camera briefly recoils, but the monster stops its step directly in front of her, does not pass through her, and does not hit the camera. 12.00–15.00 seconds: closely following the close-range reveal, cut to a same-side medium-wide shot, fully showing the woman still standing on the ground, and the monster's continuous process of reaching out, grabbing, and lifting. The monster first plants both feet steadily, extends its right arm toward the woman, its right hand gripping both sides of her neck from the front, fingers closing around, and only after clearly establishing contact does it bend its elbow and lift upward. The woman's body first rises with the grip, her feet then leave the ground, legs and hem swaying slightly with delay; use the same shot to clearly show the soles going from contact to suspension, not using a cut to make her already hanging in midair. She does not kneel or fall, her left hand instinctively grabs the monster's right wrist, her right hand still holds the only flashlight in front of her waist and abdomen, the lamp head angled upward toward the monster. The monster's left arm hangs naturally outside its own body, not joining as a second grabbing hand. This is a supernatural horror action, and the image does not show bodily injury: the woman's neck maintains its original length and complete contour, not flattened, not twisted off, with no strangulation marks or wounds; head, neck, and body remain properly connected throughout. The monster maintains its original height and proportions, lifting her to face level by stabilizing its legs and raising its right forearm, the woman's feet about half a meter off the ground, without stretching its body longer, and without letting the monster break through the tunnel ceiling. 15.00–17.00 seconds: the camera quickly tracks laterally along the same side of the two and arcs around to a clear side medium-wide shot, the horizon kept level; this is moving to a side observation, not rotating the image ninety degrees. The woman is on the left side of the frame, the monster on the right, facing each other; her feet are suspended, torso vertical, the monster's right hand still gripping the same position and bearing weight, its left hand still hanging at its side, her left hand still gripping its right wrist, her right hand still holding the flashlight. The side view clearly presents the distance between the two faces, the forearm gripping the neck located below the face, not blocking the mouth horizontally. The monster opens its own mouth toward her head: the upper jaw tilts slightly back with the head, the lower jaw opens downward along non-human joints, the oral opening continuously expanding in the shot enough to accommodate her entire head. Only the mouth undergoes the supernatural large opening; the eyes, nasal cavity, forehead, top of the head, and the rest of the body still remain the same single monster; the mouth corners do not tear, and no second face or second mouth is generated. The opening gradually surrounds the contour of her head, but at this point there is still a clear gap between them. 17.00–20.00 seconds: maintain the same side shot in continuous filming, the camera gently moving closer to a side medium shot where the monster's mouth, right-hand grip, and the woman's upper body can still be seen. The monster's right hand steadily supports her suspended position, then brings its opened mouth toward her head, the woman's head entering the monster's enormous oral cavity from the front, the tip of her nose, face, forehead, and back of the head being obscured in sequence by the oral edges, until her entire head is enclosed within the monster's opened mouth. This is the same complete head being obscured by the mouth, not the head suddenly disappearing, shrinking, detaching, or transferring onto the monster. The side view preserves her neck connecting to the head, the hoodie shoulder line, and suspended body, proving the head and neck are still connected; the monster's right hand still remains outside the mouth gripping below her neck, not reaching into the mouth, not switching hands, not letting go. The monster's mouth remains open, teeth maintaining a gap from her, not biting down, not chewing, not swallowing the body; she is not injured, with no blood, wounds, tears, or decapitation. The monster's oral cavity shows only a deep dark space, without showing an interior mouth close-up or bodily injury. Her hem and legs still have slight inertial swaying, her right hand's same flashlight continues shining from in front of her waist and abdomen toward the monster's chest and neck, and the light source does not shift because her head is obscured. 20 seconds ends directly on the live image of the complete head enclosed by the monster's opened mouth, the body still suspended and intact, without adding landing, death, biting down, escape, or follow-up action. Speed and continuity: the entire piece in normal time, natural speed, with no slow motion, time stretching, speed changes, freeze frames, or slow playback. The opening alternation of light and dark and reaction cuts build tension, the mid-section's two running flashes rapidly shorten the distance, followed by the sudden close-range reveal, the monster's right hand contacting the neck, the woman being lifted off the ground, the camera moving to the side, the monster opening its mouth wide and enclosing her head, completed continuously in this causal order. Only the same adult woman and the same unmasked monster, the scene always the same tunnel; the monster maintains its red-brown real face throughout, with no white smiling-face shell. The woman continuously goes from standing to suspended, without kneeling; the monster does not press her forehead or pry open her mouth, and what finally opens wide and encloses the head is the monster's own mouth. The monster's right hand maintains the same grip from grabbing the woman's neck to the end, the left hand does not participate; the woman's left hand grabs the monster's right wrist, her right hand holds the flashlight, and the ownership of all four arms is clear. There is always only one flashlight, remaining in the woman's right hand, pointing forward into the tunnel before the lift, and after the lift remaining in front of her waist and abdomen angled forward and upward, not dropping, not switching hands, not duplicated, not becoming a ground lantern. In the side shot the woman remains on the left, the monster on the right, without crossing the axis or switching sides; after the head is obscured by the mouth it is still connected to the body, and does not reappear elsewhere. All woman close-ups, monster, and environment maintain a unified pre-rendered AAA fantasy game CG aesthetic. Strictly prohibited background music: at no time in the entire piece may background music, film score, music track, melody, rhythmic percussion, chorus, song, musical sustained tone, or tonal atmospheric bed be generated. Only diegetic audio synchronized with the image and physically belonging to the scene is allowed: faint air movement in the tunnel, the woman's tense breathing and swallowing, hoodie fabric friction, the rapid sound of the monster's bare feet on hard earth and small stones as it runs forward, approaching heavy breathing, one hoarse non-verbal roar at close range, the sound of the monster steadying its steps on the ground, slight friction of skin and collar during the grab, the woman's short startled breath as she is lifted, irregular rattling from the mouth and throat and heavy exhalation as the monster opens its mouth, and the natural tunnel echoes corresponding to these sound sources. No bone cracking, tearing, crunching, or chewing sounds. In the darkness only on-scene footsteps and breathing continue, and the impact of the sudden reveal comes from real monster vocalization, without adding musical stingers. The monster's sounds are synchronized with its mouth and throat movements, not turning into a continuous bass score, drone, or chorus. No dialogue, no narration, no intelligible words, no songs, no subtitles; do not use pulsing sounds, orchestral hits, melodic sound effects, or rhythmic sound effects to fill the absence of music, and do not arrange footsteps and breathing into drum beats. The appearance of any background music or score is judged as unqualified. music=0; no_music=1; strict_no_music=1; audio=diegetic_only; native full-frame, with no black bars, on-screen text, titles, readable markings, interface, watermark, or end card.

Details
Type
AI Video Prompts
Aspect Ratio
16:9
Duration
0:20
Updated
Sep 21, 2026
Category
Horror3D RenderFantasy
Source

How to use this prompt

  1. 1Copy the full prompt with the copy button above.
  2. 2Open Seedance 2.5 by ByteDance, or your preferred AI video generator.
  3. 3Paste the prompt and keep the camera and motion terms — they steer the cinematography.
  4. 4Match the example's settings (16:9 · 0:20 · Horror · 3D Render · Fantasy), then iterate — small wording changes shift the output a lot.

Frequently asked questions

Which AI model generated this video?

This clip was generated with Seedance 2.5 by ByteDance. The prompt on this page is the exact text used to create it.

What settings does this prompt use?

The example was generated with Seedance 2.5 using: 16:9 · 0:20 · Horror · 3D Render · Fantasy. Reusing these settings gives the closest match.

How do I get similar results?

Copy the prompt as-is first, then change the subject while keeping the camera, motion, and lighting terms. Video models are sensitive to wording, so expect a few runs.

Can I modify this prompt?

Yes. Prompts work best as starting points — swap scenes, adjust pacing terms, or change the aspect ratio to fit your project.

More Seedance 2.5 prompts

0:10
ByteDanceSeedance 2.5
WHITE DRAGON ASCENSION | 10s | 16:9 Use image1 as SANZO. Keep his exact face, hair, skin tone, physique, tattoos and outfit. Ultra-realistic live-action Hollywood action. Practical stunts, real katana combat, realistic physics, natural smoke and cinematic lighting. No CGI, anime, cartoon or game look. LOCATION: Infinite white cyclorama with glossy reflective floor, soft diffused light, no horizon or props. OUTFIT: All-white tactical shinobi outfit with hood, half-mask, layered robes, armor, belt, tabi boots and flowing fabric. WEAPON: ONE white-handled katana on LEFT WAIST, fully sheathed. SANZO draws it once. Blade and handle leave the saya together. Saya becomes EMPTY and remains visible. No duplicate weapon or handle. Katana never returns. CREATURE: Giant aggressive celestial dragon made of dense swirling white smoke, with horns, whiskers, mane and bright white eyes. 0–2s: SANZO runs through the white void as the smoke dragon chases him. FPV and low tracking shots. Jaws snap behind him. He combat-slides beneath the jaws. Slow motion, eye close-up, 2-frame freeze. 2–3.5s: During the slide, SANZO draws the katana. Empty saya stays visible. He performs cartwheel → butterfly twist → forward somersault and lands low. 3.5–8.8s: SANZO unleashes KAGE RYUJIN GIRI — CELESTIAL EXECUTION. The dragon coils, dives, bites and tail-whips. SANZO counters with flash steps, flips, twists and aerial slashes. Each slash tears through the smoke; the dragon instantly reforms. Use fast camera moves, crash zooms, speed ramps and heavy impacts. 8.8–10s: Final dive. SANZO performs an aerial corkscrew, somersault and butterfly motion, then delivers a powerful upward diagonal slash. 2-frame freeze. Dragon breaks into white smoke ribbons and disappears. SANZO lands in a strong ninja stance, katana in RIGHT hand, blade down. EMPTY saya visible on LEFT WAIST. Fade white. NEGATIVE: CGI, anime, cartoon, game graphics, glow, beams, duplicate katana, duplicate handle, sheathing, clipping, floating weapon, blur, plastic skin, watermark, logo, subtitles, text.
Details
0:30
ByteDanceSeedance 2.5
Third-person archaeological action-adventure game, with exploration, traversal, environmental puzzles, cinematic combat, supernatural relic abilities, and seamless transitions between gameplay and scripted events. **Environment:** An enormous lost Khmer-inspired temple complex partially submerged beneath a turquoise freshwater lake deep in the Cambodian jungle, with monumental stepped sanctuaries rising from the water, collapsed bridges connecting ruined towers, enormous guardian statues entwined with tree roots, waterfalls pouring from fractured ceremonial channels, dense tropical vegetation growing through abandoned courtyards, schools of fish swimming through flooded galleries, and mysterious bronze-and-jade machinery hidden beneath the civilization's ruins. Jungle-covered limestone cliffs surround the lake. The gameplay begins above water among sunlit ruins before descending into a massive submerged sanctuary where an ancient guardian awakens. **Visual style:** Photorealistic Unreal Engine 5 archaeological adventure gameplay, premium AAA action-adventure presentation, highly detailed ancient architecture, realistic water simulation, cinematic global illumination, volumetric underwater lighting, physically accurate materials, lush vegetation, detailed character animation, realistic cloth and hair physics, environmental particles, dynamic shadows, sophisticated VFX, smooth 60fps movement, restrained motion blur, and seamless cinematic transitions without losing the feeling of actual playable gameplay. **Player character:** A 25-year-old female archaeologist and explorer with an athletic feminine build, an expressive face, defined cheekbones, brown eyes, and long dark-brown hair tied into a single braid. She wears a fitted turquoise sleeveless tank top, short brown expedition shorts leaving her legs bare, a brown leather belt with two matching thigh holsters secured by thigh straps, fingerless gloves, rugged brown lace-up boots, and a compact brown backpack. Two matching silver semiautomatic pistols with dark grips sit in the holsters, one on each side. Both pistols remain securely holstered during running, climbing, rope traversal, swimming, and mechanism interaction, leaving both hands free. She draws them only after climbing onto the final arena, holding one pistol in each hand during combat. An ancient bronze-and-jade relic attached to her left forearm allows the player to manipulate forgotten mechanisms and briefly control water currents. Keep her face, braid, outfit, both pistols, holsters, equipment, and proportions consistent throughout. **Gameplay camera:** Maintain a responsive over-the-shoulder third-person perspective during traversal and combat, allowing the camera to dynamically widen during large environmental reveals, move closer during narrow traversal sections, orbit slightly during combat encounters, and transition into brief cinematic framing during major scripted moments before smoothly returning control to the player. **Gameplay UI:** Maintain a minimal fixed interface with player health and stamina in the upper-left corner, a circular compass and objective marker in the upper-right corner, contextual interaction prompts near interactable objects, and ability icons in the lower-right corner. UI elements remain anchored perfectly to the screen throughout camera movement. **Core gameplay progression:** The player traverses collapsing ruins above the lake, discovers a hidden entrance beneath the water, dives into a submerged temple, activates an ancient mechanism using the bronze-and-jade forearm relic, accidentally awakens a colossal stone guardian, escapes through a collapsing underwater chamber, reaches the surface, and transitions directly into a dramatic boss encounter on a ruined platform. **Audio design:** Powerful cinematic game score mixed with environmental audio including lake waves, distant jungle birds, waterfalls, stone movement, climbing impacts, underwater ambience, muffled debris, swimming movement, ancient machinery, magical energy pulses, creature roars, pistol shots, weapon handling, UI feedback, and environmental destruction. **Negative guidance:** No subtitles, no dialogue, no logos, no excessive HUD elements, no first-person perspective, no futuristic technology, no gore, no blood, no dismemberment, no broken anatomy, no inconsistent character clothing, no random camera teleportation, no excessive motion blur, no low-detail environments, no cartoon graphics, no turn-based combat. **[00:00-00:04] THE LOST JUNGLE SANCTUARY:** Begin directly in third-person gameplay with the camera positioned behind the explorer sprinting along the top of a massive ruined temple causeway suspended above brilliant turquoise water while the flooded sanctuary stretches beneath jungle-covered cliffs. As sections of ancient stone begin collapsing behind the character, the player accelerates, jumps across a widening gap, catches the opposite ledge with both hands, pulls upward, and continues running while waterfalls cascade between enormous temple structures in the distance. The camera briefly widens during the jump to reveal gigantic submerged statues visible beneath the transparent lake before smoothly returning behind the player. SFX: running footsteps, stone cracking, rushing waterfalls, lake waves, climbing impacts, adventurous score building. **[00:04-00:08] COLLAPSING BRIDGE:** The player reaches a fractured stone bridge just as the entire structure begins collapsing toward the lake, forcing the explorer into a high-speed traversal sequence where she sprints across falling sections, leaps onto a tilted pillar, briefly scrambles up a carved temple wall, then launches toward a hanging rope attached to an abandoned wooden lifting crane. The character catches the rope and swings across a massive gap while chunks of architecture crash into the lake beneath her, producing enorm
Details
0:30
ByteDanceSeedance 2.5
Create a 30-second Pixar-quality 3D animated ASMR comedy short aboard a warm, lantern-lit pirate ship galley. STYLE: Premium cinematic 3D animation, expressive characters, polished feature-film quality, warm amber lighting, realistic food textures, cinematic depth of field, playful slapstick humor, gentle ship movement and crisp immersive food ASMR. Characters: A large, burly, bearded pirate chef wearing a worn apron, and a mischievous bright-green parrot constantly trying to steal ingredients. Keep both characters visually consistent throughout. 0–4s Extreme close-up of the parrot stealing a garlic bulb. The pirate's hand suddenly slams beside it. They freeze and stare at each other. Brief record-scratch silence. The pirate flicks the parrot away; it spins through the air and lands on a pot rack pretending nothing happened. 4–8s The pirate rapidly chops garlic with crisp ASMR. The parrot tiptoes toward a tomato. Garlic hits hot oil with a huge sizzle, startling the parrot and sending it tumbling off the rack. Metal cups clang. 8–14s Fast cinematic cooking montage: tomatoes sizzling, herbs being torn, olive oil pouring in golden slow motion, sauce bubbling and the pirate confidently stirring the skillet. Layer detailed chopping, sizzling, pouring and bubbling ASMR. 14–19s The parrot spots the food and secretly tries to drag the skillet away. Its tiny body strains comically across the wooden floor. The pirate slowly turns around and stares. The parrot freezes while still holding the handle, then innocently whistles and lets go. 19–24s The pirate finishes cooking with a dramatic skillet toss. Steam rises as the glossy dish is plated. The parrot watches hungrily, trying to look innocent. 24–30s Instead of scolding the parrot, the pirate prepares a tiny plate of sauce and bread and slides it across the table. The parrot happily bounces and eats beside him. They exchange a satisfied look as the ship gently sways. End with a wide cinematic shot of the cozy galley glowing under amber lanterns, subtle ocean sounds and wooden ship creaks, with one soft playful accordion note fading out. No dialogue, no subtitles, no text. Maintain strong character consistency, natural physics, smooth animation, cinematic framing and detailed food ASMR throughout.
Details
0:20
ByteDanceSeedance 2.5
Create an exactly 20.00-second, native horizontal 16:9 video at 24 fps, filling the frame with no permanent black bars. STRICT MONOCHROME PALETTE ONLY: pure black, charcoal, ash gray, metallic silver, brilliant white. No colored magic, red fire, blue lightning, warm skin tones, or colored lighting. Strong white rim light must keep bodies, muscles, feathers, and cloth readable inside the darkness. ENVIRONMENT: A huge ash-covered forest ravine with jagged black rock, twisted dead trees, dark gravel, broken stone, exposed roots, shallow mist pools, drifting ash, leaves, and debris. A massive circular storm vortex continuously rotates overhead while narrow brilliant-white light shafts pierce the clearing. Keep geography consistent: warrior in the central clearing, dead trees framing both sides, ravine rising behind him, storm directly overhead. WINGLESS WARRIOR: Exactly one adult male warrior. Tall, muscular athletic build, broad shoulders, shaved or very short hair, stern exhausted expression, correct human anatomy. Bare torso, weathered dark leather trousers, layered waist wrap, short torn cloth panel, fitted forearm wraps, heavy dark boots. Clothing is wet, ash-covered, and reacts naturally to wind. He has NO sword, spear, shield, gun, wings, feathers, cape, supernatural limbs, or magic. He fights only with hands, forearms, controlled kicks, body rotation, dodges, and grappling counters. WINGED WRAITHS: Exactly six adult-sized humanoid wraiths. Each has one head, one torso, two arms, two legs, and EXACTLY ONE symmetrical pair of black feathered wings attached only to its back. Lean coherent anatomy, charcoal-gray skin, clawed hands and feet, ragged black waist cloth. Wings use layered primary and secondary feathers and bend correctly during dives, power strokes, recovery strokes, braking, and takeoff. The lead wraith has a pale bone-like face and one short broken horn. The other five are darker. Maximum one or two wraiths attack the warrior at close range at any moment; the others remain clearly separated in the air. TIMELINE: 0.00-2.20 Begin inside fast-moving storm clouds. Camera dives downward through several separated flying wraith silhouettes. Show complete wing cycles: downward power stroke, folded recovery, feathered braking. One foreground wing passes close to camera and reveals the wingless warrior in the clearing below. He turns toward the descending threat and takes a stable defensive stance. White light shafts cut through the mist. 2.20-4.20 Low rear three-quarter shot behind the warrior. One wraith folds its wings and dives toward his left shoulder with claws extended. He sees the shadow, bends his knees, ducks below the attack, plants his right foot, rotates his hips, grabs both forearms, and redirects the creature sideways using its own momentum. It spreads its wings, recovers, and exits safely screen-right. At approximately 3.50 seconds, insert ONE near-black shutter impact frame at contact, immediately returning to visible action. No fade and no missing motion. 4.20-6.40 A second wraith skims low from screen-right. Fast side-tracking shot. It claws toward his chest. Warrior steps diagonally backward, blocks the wrist with his left forearm, redirects the claw outside his body line, and pushes the shoulder with his right hand. A nearby wing briefly wipes across foreground without intersecting him. The wraith passes and climbs back into the air. 6.40-8.60 Camera follows the departing creature upward, performs one controlled approximately 30-degree roll, then levels into a wide overhead storm reveal. All six wraiths circle the clearing at different heights while the warrior stands alone at center. Brilliant white shafts separate their silhouettes. Atmospheric movement briefly feels slightly slower, with feathers, ash, and mist suspended, but the warrior's breathing and foot adjustments remain natural speed. At approximately 6.40, while a wing obscures the lens, insert ONE single-frame near-black shutter transition, revealing the same geography. 8.60-10.80 Return to ground level. One wraith attacks clearly from the front while a second descends from behind and above; both paths remain readable. Warrior pivots away from the rear claw attack without jumping, shifts weight onto his left leg, and delivers one compact right-foot kick into the front attacker's torso. The front wraith recoils and opens its wings. The rear attacker misses, passes behind him, and climbs away. Remaining support wraiths stay separated high in the background. 10.80-13.40 The pale-faced lead wraith descends directly in front, performs two powerful braking wingbeats, briefly touches the ground, then grips the warrior's upper arms from the outside. Fingers, shoulders, neck, and arms remain visually separate with no merging. The lead wraith beats downward and lifts both bodies upward. The warrior's boots leave the ground ONLY after the grip is secure. Dust and ash expand outward below them. Camera spirals upward around the pair while the other wraiths circle at a safe distance. 13.40-15.80 Use SHORT SELECTIVE SLOW MOTION ONLY HERE. Warrior hooks his left forearm around the lead wraith's right wrist, pulls his knees inward, and rotates his hips. One support wraith attempts a passing claw strike; the warrior kicks it in the shoulder with his right boot, knocking it away. He then drives his right elbow into the lead wraith's chest. Its fingers visibly release one-by-one until it completely lets him go. At approximately 13.80, insert ONE single black impact frame at the elbow strike, immediately returning to visible action. Return to natural speed after approximately 15.20. War
Details
0:35
ByteDanceSeedance 2.5
Use the uploaded reference image as the exact character reference. Keep the same face, hair, outfit and appearance throughout. The woman stands beside the giant white ice dragon, then rides on its back as it flies over snowy mountains and a frozen river. They reach an ancient stone shelter where she explores while the dragon protects her. Cinematic camera movement, epic wide shots, realistic motion, glowing blue eyes, snowfall, blue atmosphere with warm firelight, photorealistic fantasy movie quality, 16:9, no background music.
Details
0:30
ByteDanceSeedance 2.5
Create a 30-second, 16:9 photorealistic third-person survival-horror gameplay sequence set during a zombie outbreak in an American city in daylight. Show continuous playable action, responsive aiming, close encounters, environmental interaction, a weapon change, and a confrontation with a larger infected enemy. **Environment:** A late-1990s Midwestern American downtown devastated by a recent outbreak. Red-brick buildings, corner stores, old sedans, abandoned police cruisers, a stalled city bus, damaged traffic lights, loose newspapers, broken shop windows, and temporary street barricades. Several ordinary zombies wander between vehicles while others respond to the player's movement and gunshots. A damaged convenience store connects the main street to a rear delivery yard containing a parked delivery van, refuse containers, and an exterior metal service staircase attached to the opposite brick wall. Establish one connected city block and maintain its layout throughout. **Visual style and lighting:** High-end AAA survival-horror gameplay with photorealistic faces, detailed clothing, convincing animation blending, accurate contact shadows, physically grounded materials, and smooth 60fps movement. Bright overcast daytime, a pale clouded sky, neutral colours, soft shadows, and readable street detail. Daylight enters the shop through its broken front windows and open rear doorway. Interiors are naturally darker, with gentle exposure adaptation as the player moves through them. Restrained motion blur and natural material reflections. Maintain the appearance of an actual playable game throughout. **Player character:** The same handsome 25-year-old male police officer throughout. He has a lean athletic build, a clean-shaven face, blue-grey eyes, and straight ash-brown hair with a long side-parted fringe. He wears a dark navy short-sleeved police uniform shirt, a fitted dark blue protective vest with plain shoulder patches, matching navy tactical trousers, black knee pads, black gloves, a black duty belt, and worn black boots. His clothing is dusty and slightly scuffed but remains intact and consistent. His expression is alert and tense; his reactions are quick, practical, and grounded. He begins with a black semiautomatic pistol already in his right hand. His left hand supports the pistol while aiming and becomes free when he lowers it for physical interactions. A pump-action shotgun is already secured diagonally across his back on a sling, visible from the opening frame. An empty pistol holster is attached to his right hip. At the specified weapon-change moment, he visibly holsters the pistol before bringing the shotgun forward. Afterwards, the pistol remains in its holster and he holds the same shotgun with both hands. Equipment never appears spontaneously or changes into another weapon. **Enemies:** Ordinary zombies are infected townspeople in varied, faded everyday clothing, with pale skin, vacant expressions, unsteady balance, and irregular reaching movements. Give each visible zombie a distinct appearance and independent movement. They react physically to impacts and remain where they fall. The larger infected enemy appears only in the delivery yard: a towering, heavy humanoid with an uneven silhouette, grey mottled skin, one enlarged shoulder, and torn industrial workwear. Its anatomy remains covered and intact. Its weight and momentum distinguish it from the smaller zombies. **Gameplay camera:** One continuous over-the-shoulder third-person gameplay camera following the officer. It tightens slightly during aiming, widens for traversal and nearby threats, and follows changes of direction smoothly. Keep the character's body, weapon, and immediate route readable. The camera follows him physically through the shop doorway and into the yard without passing through walls. During combat it stays behind his aiming direction, maintaining a clear view of his target. No cuts, montage inserts, external establishing shots, first-person view, or separate enemy reaction shots. **Gameplay UI:** ONE small, thin player-health bar fixed in the upper-left corner is the only persistent overlay. A small circular button icon containing the letter A appears exactly once beside the car hood before the vault, then disappears as the action begins. The rest of the screen remains clear throughout, including the larger enemy encounter. Player health changes only if an enemy visibly injures him. **Core gameplay progression:** The officer fights through a blocked street, vaults an abandoned car, escapes a close zombie grab, crosses a damaged convenience store, uses a movable display rack to obstruct pursuit, emerges into its delivery yard, changes from pistol to shotgun, avoids a heavy infected enemy's charge, fires back, and retreats up the visible service staircase while keeping the enemy in sight. **Audio design:** Tense survival-horror game music beneath distinct environmental sound: distant sirens, wind between buildings, scattered car alarms, shoes on asphalt and broken glass, zombie breathing and groans, pistol shots, rattling shop fixtures, weapon handling, heavy impacts, shotgun reports, and metal stair footsteps. Sound changes naturally inside the shop and returns to open-air acoustics in the yard. No spoken dialogue, narration, or subtitles. **[00:00–00:04] THE BLOCKED STREET:** Begin immediately behind the officer moving briskly between an abandoned police cruiser and a stalled city bus. An infected man steps out from beside the bus and advances into his path. The officer plants his feet, raises his pistol with a two-handed grip, and fires two quick shots into the approaching zombie's upper torso. The impacts make it stagger sideways against the bus, opening a route past it. The player immediately lowers the pistol and mo
Details
0:30
ByteDanceSeedance 2.5
Create a 30-second Pixar-quality 3D animated miniature construction comedy where dozens of tiny construction workers build and decorate a giant cupcake. VISUAL STYLE: Premium cinematic 3D animation, adorable miniature world, bright pastel colors, warm golden lighting, ultra-detailed CGI, realistic food textures, shallow depth of field, smooth cinematic camera movement and satisfying visual details. Cheerful, playful and wholesome atmosphere. CHARACTERS: Tiny construction workers wearing colorful safety helmets and work uniforms. Keep their appearance and scale consistent throughout. 0–5s — ESTABLISHING Wide cinematic aerial dolly-in toward a giant cupcake sitting on a table. Dozens of tiny workers arrive with miniature cranes, forklifts, mixer trucks and construction vehicles. They quickly organize around the cupcake and begin preparing the site. Soft cheerful music, tiny engines, wheels and construction sounds. 5–10s — FROSTING Medium tracking shot as a miniature mixer truck pours silky pink frosting over the cupcake. Workers spread the frosting smoothly with tiny trowels, carefully covering the entire surface. Close-ups show the glossy frosting flowing and being leveled perfectly. ASMR: creamy pouring, soft scraping and tiny tool sounds. 10–17s — TOPPINGS Close-up cinematic montage. Miniature conveyor belts deliver fresh strawberries, blueberries, chocolate chunks and colorful rainbow sprinkles. Workers carefully position each topping with tiny tools and teamwork. Sprinkles fall in satisfying slow motion and sparkle under the warm lighting. Add subtle conveyor sounds, tiny footsteps and light magical chimes. 17–23s — CHERRY LIFT Low-angle cinematic shot of a huge shiny red cherry being lifted toward the cupcake by a miniature construction crane. Workers pull ropes and guide it carefully into position while the crane slowly rises. Build playful suspense with crane motor sounds and a gentle orchestral rise. 23–30s — FINAL REVEAL The cherry lands perfectly on top. The workers celebrate as colorful confetti explodes into the air. Some jump, others wave their helmets while tiny construction vehicles honk. Camera performs a smooth 360° cinematic orbit around the completed cupcake, revealing the beautifully decorated frosting and toppings. End on a satisfying hero shot with warm golden light, cheerful music, tiny cheers and a soft celebratory musical finish. No dialogue, no subtitles, no text. Maintain consistent character scale, realistic food physics, smooth animation, detailed miniature interactions and premium cinematic quality throughout.
Details
0:35
ByteDanceSeedance 2.5
Create a cute, ultra-realistic 3D cinematic vertical video (9:16) featuring a tiny adorable peach-shaped creature with a soft fuzzy pastel-pink body, tiny black glossy eyes, a small cute mouth, rosy cheeks, tiny arms and feet, and a small green leaf on top of its head. The little peach creature is in a beautiful sunlit forest surrounded by green grass, trees, leaves, and warm natural sunlight. It discovers a honeycomb hanging from a tree branch and happily collects fresh golden honey with a tiny spoon. A small bee flies around it and briefly lands near its face. Show the creature enjoying the honey, walking through the forest, then returning to a cozy rustic wooden kitchen. It prepares a refreshing glass of fruit-and-honey drink by adding ice cubes, lemon slices, colorful fruit pieces, and golden honey into a transparent glass. It gently stirs the drink with a spoon and happily drinks it. Make the character extremely cute and expressive, with soft plush-like fuzzy details, realistic textures, adorable movements, natural facial expressions, cinematic depth of field, warm golden-hour lighting, beautiful bokeh, detailed forest environment, smooth camera movements, macro close-ups, realistic shadows, and premium high-quality 3D animation. Keep the same character design, face, proportions, colors, leaf, and appearance consistent throughout the entire video. No text, no watermark, no distorted anatomy, no extra characters. Style: Pixar-like cute 3D + photorealistic textures + cinematic macro photography + cozy fantasy aesthetic.
Details
Browse all Seedance 2.5 promptsExplore AI Video Prompts