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.
This clip was generated with Seedance 2.5 by ByteDance. The prompt on this page is the exact text used to create it.
The example was generated with Seedance 2.5 using: 16:9 · 0:20 · Horror · 3D Render · Fantasy. Reusing these settings gives the closest match.
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.
Yes. Prompts work best as starting points — swap scenes, adjust pacing terms, or change the aspect ratio to fit your project.