Все промпты Видео

Ultra-realistic 15-second selfie video of the exact woman from the reference image (precise facial structure, skin tone, hair, features, expression locked 1:1 — zero identity drift). Setting: inside a luxury mansion living room. Marble columns, ornate white ceiling with detailed molding, large crystal chandelier, soft grey walls, elegant grey couch visible behind her. Background remains completely identical and static the entire time — no scene change, no camera movement beyond natural handheld micro-sway. Camera: selfie mode, held close to her face, slightly wide lens (≈24-28mm equivalent). Natural indoor daylight coming from the front/side, soft and flattering. Extremely crisp focus on her face with shallow depth of field; background gently falls off. Handheld natural motion only. Action sequence (strict timeline): 0.0–3.5s She looks into the lens, warm genuine smile, and speaks clearly: “Simbaaaa... simba come here... I'm making a video for Instagram, they wanna see you... good boy...” 3.5–7.0s From behind the couch, a large fully realistic adult male lion slowly walks into frame. Soft, deliberate paw steps on the floor. Tail swaying gently. He sniffs the air as he approaches. He moves toward her right shoulder. 7.0–9.5s She notices the lion over her shoulder, turns her head slightly, and laughs nervously while still holding the phone steady. 9.5–13.5s The lion rubs his massive head against her cheek and neck exactly like a giant affectionate cat. Soft low growl/snort. Then he gently licks her face with a large realistic tongue. She laughs genuinely and says: “Aww good boy...” 13.5–15.0s She continues smiling and laughing lightly as the lion stays close, nuzzling. Hold on the intimate interaction. Extreme realism requirements: Visible skin pores, fine facial hairs, natural micro-texture, subtle stubble if present in reference, realistic subsurface scattering and soft shadows on skin. Lion: dense individual fur strands, accurate mane and body spots, realistic whiskers, wet black nose, detailed eyes, authentic tongue texture and saliva sheen when licking. Natural physics on fur movement, weight, and contact. Perfect facial consistency of the woman throughout - no morphing, no warping, no age/skin change. Technical & style: Ultra-sharp 8K detail, 64K micro-detail rendering, clean natural color grading, cinematic yet documentary realism, zero flicker, zero temporal warping, zero face distortion. Soft natural indoor light only. Reference image locked for character identity.

Create a 15-second photorealistic cinematic office video featuring the same young professional woman with the provided reference face, wearing the same beige blazer and white shirt throughout. Wide office shot. She sits at her desk, reviewing a file while holding a pen. Laptop, papers, and tea are on the desk. Camera slowly moves closer. She flips through the file, reads carefully, and marks an important point with her pen. She puts down the pen, picks up her tea, takes a small sip, and returns the cup to the desk. She turns toward her laptop and starts typing. Side-angle shot focuses on her hands and laptop. Camera slowly pulls back, showing her focused on work in the modern office. Style: Photorealistic, cinematic, warm morning light, natural expressions and movements, realistic hands, smooth camera motion, shallow depth of field, professional corporate atmosphere, 4K, 16:9. Important: Keep the same face, hairstyle, beige blazer, white shirt, character appearance, and office environment consistent in every shot. No text, subtitles, logos, or sudden transitions.

A young snowboarder drops into an alpine terrain park, carves smoothly down the slope, performs a controlled 180° jump and freestyle butter, then finishes with a clean stop. Ultra-realistic winter sports documentary, physically accurate snowboard physics, authentic human movement, natural English lip-sync, bright winter daylight, immersive mountain ambience, and seamless story continuity throughout.

Create a cinematic, photorealistic lifestyle video of a young East Asian woman in a cozy modern apartment by the sea. The video has a warm, natural morning atmosphere with soft daylight coming through large windows, realistic skin texture, subtle facial expressions, natural body movements, shallow depth of field, and smooth cinematic camera motion. Scene 1 — Bedroom: A young woman with long straight dark hair, wearing a light beige/pink satin pajama set, sits on the edge of her bed looking sleepy. She gently yawns and rubs her eyes. The bedroom is minimal and modern, with a neatly made bed, wooden furniture, soft curtains, and large windows letting in diffused natural light. Scene 2 — Bed: She pulls and adjusts the duvet, then sits and stretches slightly on the bed. Capture her natural sleepy morning routine with realistic movements and a calm atmosphere. Scene 3 — Leaving Bedroom: She stands up and slowly walks toward the bedroom doorway. The camera remains cinematic and slightly distant, showing the warm wooden interior and softly illuminated bedroom in the background. Scene 4 — Cooking: Cut to the kitchen. Close-up of a black electric sandwich/waffle-style press on the kitchen counter. The woman pours smooth light-brown batter into the heated mold. Use detailed macro shots of the batter flowing into the appliance. Scene 5 — Preparing Food: She operates the sandwich maker on the kitchen counter and carefully checks the food while cooking. Show realistic hand movements, steam/heat details, kitchen reflections, and natural daylight coming through the nearby window. Scene 6 — Eating: She opens the appliance and removes a freshly cooked golden-brown waffle/pastry. She holds it with both hands, takes a bite, then smiles naturally with a satisfied expression. Visual style: photorealistic, cinematic lifestyle commercial, natural morning lighting, warm neutral color palette, realistic Asian facial features, authentic skin texture, detailed hair strands, realistic fabric physics, soft shadows, subtle film grain, shallow depth of field, professional cinematography, smooth transitions, realistic handheld camera movement, 4K quality. Camera: combination of medium shots, close-ups, macro food shots, slow push-ins, gentle tracking shots, and shallow-depth-of-field portrait shots. Mood: cozy, peaceful, warm, relaxing morning routine, premium lifestyle advertisement. Aspect ratio: 16:9 Duration: approximately 20 seconds No text, no subtitles, no watermark, no logo, no distorted hands, no extra fingers, no unnatural facial movements, no cartoon/anime appearance.

Create a 30-second cinematic dance sequence as if directed for a high-budget international music film. DIRECTOR'S VISION The film takes place inside a massive minimalist studio at night. The space is almost completely dark, with carefully controlled #FF4900 orange practical lighting creating a striking visual identity. The atmosphere should feel sophisticated, dramatic, and expensive. There is one adult female dancer. She remains the exact same person throughout the entire sequence. Her face, hairstyle, wardrobe, proportions, and styling never change. OPENING — 0:00–0:05 Start on an extreme close-up of the dancer's face. She stands completely still. Only a thin orange light crosses her face. Hold the shot for a moment before slowly pulling the camera backward on a dolly. The music begins quietly. She makes the first controlled movement. BUILD — 0:05–0:12 Cut to a 50mm medium shot. The dancer begins a precise contemporary choreography. The camera moves sideways with her rather than simply pointing at her. Let the movement of the camera and performer feel connected. Orange practical lights gradually illuminate behind her. Use shallow depth of field and a subtle focus pull from the background to her eyes. MOMENTUM — 0:12–0:20 The music becomes more energetic. Transition into a 35mm tracking shot. The camera slowly circles around the dancer while she performs a sequence of turns, controlled footwork, coordinated arm movements, and a brief jump. Do not over-edit. Let the choreography breathe. Use natural motion blur and realistic physical movement. HERO MOMENT — 0:20–0:26 Move into a wide 24mm shot. The dancer moves toward the center of the enormous studio. As she reaches the beat, hundreds of small orange lights activate across the architecture behind her. The camera performs a slow crane movement upward, revealing the scale of the environment. The dancer remains the visual focus. ENDING — 0:26–0:30 Everything suddenly becomes quiet. Return to a 50mm shot. The dancer stops and looks directly toward the camera. Hold the composition for two seconds. The orange lights behind her slowly fade except for one strong backlight. Camera gently pushes in. Cut to black. CINEMATOGRAPHY High-end feature-film cinematography, motivated camera movement, deliberate framing, realistic lens characteristics, controlled depth of field, natural motion blur, subtle film grain, realistic exposure, sophisticated contrast, volumetric atmosphere, practical lighting, physically accurate reflections. PERFORMANCE DIRECTION The dancer should perform like a professionally trained performer. Movements are precise, confident, rhythmic, and natural. No exaggerated body motion. No unnatural poses. CONTINUITY One performer throughout. Perfect facial consistency. Identical hairstyle, wardrobe, accessories, proportions, and appearance in every shot. Stable anatomy and hands.

Create a 15-second ultra-realistic cinematic YouTube-style fashion vlog featuring the girl from the uploaded reference image as the exact character reference. Preserve her facial identity, eye color, skin tone, hairstyle, body proportions, and overall appearance throughout the entire video. The video begins with a handheld selfie-style shot inside her cozy bedroom. She looks directly into the camera and says with playful indecision, “I’m going to a party tonight, but I seriously have no idea what to wear.” She looks toward her wardrobe, walks behind the curtain, and quickly returns wearing a stylish cropped top with a mini skirt. She flicks her fingers toward the camera — snap! Her outfit instantly transforms into a fitted crop top with high-waisted jeans. She looks down at herself, poses, then gestures toward the camera as if asking, “This one?” Another finger flick — snap! The jeans transform into a trendy short skirt with a different top. She spins once, lets the skirt move naturally, then gives a playful uncertain expression. She flicks again — snap! Her outfit changes into a stylish party dress with heels and accessories. She strikes a confident pose, checks herself in the mirror, then looks back at the camera with an excited smile. For the final beat, she rapidly flicks her fingers once more and changes into a completely different glamorous party outfit. She looks at the camera, points at herself, then gestures “Which one?” with a playful expression as the camera pushes in. Fast seamless outfit transformations, no jump cuts during the actual changes, realistic fabric morphing, natural hair movement, consistent bedroom environment, handheld creator-vlog energy, expressive reactions, quick camera movements, smooth whip pans, natural daylight mixed with warm bedroom lighting, realistic skin texture, cinematic depth of field, photorealistic, ultra-detailed, 4K HDR, 24fps, 16:9. Audio: Natural room ambience, footsteps, wardrobe movement, finger snaps with satisfying transformation sound effects, subtle upbeat vlog-style background music, natural spoken dialogue. No subtitles, no logos, no watermark, no distorted hands, no duplicate people, no face changes.

A cinematic, realistic short video of a stylish young woman with long wavy brown hair and bangs, wearing a beige trench coat over a white top and light pants, carrying a brown leather shoulder bag. She steps out of an elegant blue door of a classic European building onto a sunlit cobblestone street lined with plants and flower boxes. She walks confidently down the charming Parisian-style alley. She approaches and enters a cozy cafe with wooden doors and glass windows labeled something like “CHANEL ALEX” or similar. Inside the warm, inviting cafe with exposed beams, pendant lights, and a marble counter, she orders an “Ice vanilla latte, please” from a bearded barista in an apron. A close-up of a golden, flaky croissant on a white plate with a fork. She sits by the window, happily sips the layered latte from a clear glass mug, closes her eyes in enjoyment, and says “That’s the good stuff.” She then takes a big bite of the croissant and says “Perfect start to the day.” Final shot of her walking down a bustling cobblestone street in golden morning light, holding the coffee and half-eaten croissant, smiling and looking at the camera. Soft natural lighting, warm tones, shallow depth of field, high detail, lifestyle aesthetic,

A frustrated young male creator sits alone in a dark creative studio, staring at a completely blank computer monitor. He rests his hand on his forehead, looking stuck and out of ideas. The room is moody and cinematic, with soft monitor glow and deep shadows. The blank screen suddenly begins transforming into a vivid cinematic world. The camera smoothly pushes toward the monitor and transitions seamlessly inside it, revealing an enchanting fantasy forest filled with enormous ancient trees, glowing purple-pink foliage, exotic plants, soft mist, and a crystal-clear stream reflecting warm rays of sunlight. Magical particles float gently through the air as the camera slowly travels forward through the forest. The scene then dramatically transitions into a sleek futuristic black supercar speeding through a winding mountain road at dusk. The car accelerates aggressively around the curves, tires producing subtle smoke and sparks, glowing red taillights reflecting across the wet asphalt. Massive mountains surround the road with a bright full moon in the background. Ultra-cinematic commercial look, photorealistic details, dynamic camera movement, smooth transitions, volumetric lighting, atmospheric fog, realistic reflections, shallow depth of field, dramatic contrast, premium VFX, realistic motion blur, 4K quality. End with a powerful tracking shot behind the supercar as it disappears into the mountain road. Duration: 15 seconds. Aspect ratio: 16:9. No text, no logos, no watermark.

Anime-style video depicting the preparation of avocado toast in a sunlit kitchen. •Scene 1 (0:00 - 0:01): Close-up of hands cutting a ripe avocado in half on a wooden cutting board with a knife, then using a spoon to scoop out the pit.
 •Scene 2 (0:02 - 0:03): Oil is poured from a clear bottle onto a slice of bread frying in a skillet over a gas flame, followed by a wooden spoon stirring boiling water in a pan to poach eggs.
 •Scene 3 (0:04 - 0:06): Mashed avocado seasoned with pepper is spread over toasted sourdough. Two poached eggs are gently placed on top, garnished with halved cherry tomatoes, sliced radishes, fresh microgreens, and seasonings.
 •Scene 4 (0:07 - 0:08): A young women with messy dark hair and glasses sits at a sunlit kitchen table, enjoying a bite of the avocado toast and taking a sip from a coffee mug.

[Goal] Generate a documentary-style live-action short video. The subject is a 'man with 7/3 parted hair'. The main event follows the man escaping a volcanic crater, until a wide shot reveals the true nature of the world. [Character] The man corresponds to both @image1 and @image2. @image1 defines the hairstyle, body type, navy suit, white shirt, and red tie. @image2 defines his facial features, black round glasses, and front teeth. Only one man should be in the output. [Setting] The crater refers to @image3 (lava lake shape, rock position, steam). The breakfast table refers to @image4 (wood grain, white mug shape and texture). The circular outline of the crater in @image3 and the mug in @image4 are treated as the same shape. [Subject Profile] 168cm tall, thin body. Mouth remains closed, no dialogue. [Text] The man runs across black rocks surrounded by a lake of molten lava. Steam rises and red splatters jump. The footage is live-action documentary style with visible pores, suit fabric texture, and reflections on glasses. Composed of 4 scenes with fixed camera cuts. [Stage 1] 0-6s: Close-up of the face reflecting red light on glasses, starts running away from camera. [Stage 2] 6-14s: Running across rocky terrain, jumping over glowing cracks, ends crouching low on a rock. [Stage 3] 14-21s: Top-down bird's-eye view, standing small on a rock in the center of the red lake as steam rises. [Stage 4] 21-27s: Widescreen shot reveals the crater is actually the inside of a white mug on a wooden table. A silver spoon descends from above. [Audio] Low sustained string notes, lava sounds transitioning to the sound of a spoon hitting ceramic and kitchen ambience in stage 4. [Consistency] Keep appearance and suit consistent throughout. No other people. No table elements visible until stage 4. [Prohibitions] No opening mouth, no speaking, no text/logos, no moving camera during scenes, no changing clothes.

High-quality anime footage. A silver train traveling at high speed through a red canyon at sunset. From 0.0 seconds, the protagonist is sprinting at full speed on the roof; no introductory still images or stances are placed. All actions are in real-time. Fast footwork, weight shifts, weapon contact, reaction forces, and subsequent movements connect without interruption. [Reference/Character Fixation] material:129768 is the face/identity reference, serving as the standard for facial and personal identity. Same person in all cuts, same slender jaw, blue eyes shape and iris color, long moonlight-silver hair, bangs, blue rose and butterfly hair ornaments, their placement fixed. material:129769 is the outfit/full-body reference. Black high neck, black lace sleeves, deep navy short cape, blue gemstone brooch, gold/silver fine decorations, navy pleated midi skirt, black lace-up boots, moon-patterned bag, slender silhouette fixed. Bag is tight to the right hip. Priority if references conflict: face/eyes/hair priority to material:129768, outfit/decorations/body below the neck priority to material:129769. Final facial expression change: eyes soften → brows lower slightly → eyelids narrow once → mouth stays closed → gaze returns forward. Allowed changes are only facial expressions, gaze, breathing, combat stance, and natural hair/cloth sway. No character changes, facial averaging, outfit swaps, left-right reversals, clones, or additional protagonists. [Equipment Fixed] The single-edged blue-silver sword held by the protagonist is one (one sword), the black iron greatsword held by the Skeleton King is one (one greatsword). The number of swords in the video is fixed at two. One dark navy scabbard fixed to a belt on the protagonist's left hip. At the start, the sword is already drawn in the right hand, the scabbard is empty, and the left hand is free. Slender single-edged blade (blade, guard, handle) and greatsword (blade, guard, handle) maintain a single structure of the same length. Protagonist grips handle with right hand, King grips handle with both hands. In rotations and parries, the entire weapon moves as one unit, not just the tip. No proliferation or exchange of weapons, handles, guards, or scabbards. [Enemy Fixed] Only three general skeletons. As skeletons/undead, they have skulls, exposed ribs, spine, pelvis, long phalanges, blue orbital light, and torn black cloth. No weapons, they grab from three heights simultaneously. Only one Skeleton King. As a skeleton/undead, he has a skull and ribcage two sizes larger, a black iron crown fixed to the skull, thick black iron armor, a tattered dark navy cloak, strong blue orbital flames, and a black iron greatsword. No shield. Appears only after the three general soldiers fall. All enemies maintain solid bone, cloth, and iron materials until the finish, not replaced by crystals or light figures. No mixing of general and King traits, no duplication of enemies. [Rendering Fixed] Use only 3D toon/cel-look. Centering on material:129768 and material:129769, high-density material expression capable of distinguishing thin blue-gray outlines, two to three layers of toon shading and soft gradients, clear moonlight silver, dark navy, royal blue, sharp highlights on silver hair, velvet, lace, metal, gemstones, and glass. Character-first palette / character-specific palette: prioritize the protagonist's royal blue as character-specific key light and dark navy as character-specific shadow. Background is low-saturation background, cyan only as auxiliary for contact light. High density up to exterior ribs, window frames, seats, straps, handrails, connecting doors, and floor reflections. No thick outlines. No single-layer flat cel painting. No generic 3D anime faces. No smooth plastic CG materials. No low-density backgrounds. No live action. No semi-live action. No dull colors. No mixing of styles. [Common Axis of Motion and Cinematography] Combat is one continuous trajectory. Roof advance, drop into window, low evasion under bone arms from three directions, passage through siege center, continuous sword arc, trajectory bent outward by King's greatsword, inward turn, swap of front/back positions, horizontal return, diagonal upward finish, and sheathing all share the same movement line. Trajectory deforms by contact, no stopping to reset stance. Camera systems switch between low rear-three-quarter attacker tracking, diagonal vehicle exterior, front retreat, over-the-shoulder counter, short orbit/axis change, diagonal impact push-in, and side medium close-up according to purpose. Low angle height is 0.4m for roof/floor actions, 1.2m for over-the-shoulder, 1.35m for sheathing. Foreground occlusion by seats, window frames, bone arms, and blades allowed momentarily; parts of the body may leave the frame during speed. Vanishing axis of the background always flows forward with the train, and cuts are linked by foot grounding, bone arm passage, sword crossing, weapon contact, and body passage direction. [Speed, Action Deadlines, Sound] Full-body movement is real-time. Hit stop at contact is max 1 frame. Move supporting foot, waist, ribcage, and weapons from the start of each cut, passing through listed intermediate times in order to reach the specified state by the end time. Time intervals are not used for interpolation of a single pose before contact or the same sword crossing. Do not substitute speed with only sparks, hair, or cloth; while they remain, the person, enemy, and two weapons must move to the next position based on the floor. Synchronize metal roof footsteps, wind pressure, glass shattering, bone arm wind cutting, dry sound of bone hitting floor, short metal collision of sword and greatsword, armor cracking, and the final sheathing sound to visible events. No dialogue, subtitles, logos, UI, or watermarks. Cut 1: 0.0–2.0s | Sprinting full speed on the roof Low rear 3/4. Protagonist runs four steps forward on the roof ribs; with each boot grounding, the supporting leg, pelvis, shoulder, and blade move along the same propulsion axis. Roof ribs and canyon recede at high speed, hair and cape flow sharply backward. The reaction force of the fourth step is used to jump off the right edge of the roof to the side of the train. At 2.0s, the protagonist's head, shoulders, waist, and both legs are all on the exterior side of the intact window glass; no part of the body has yet entered the inside of the window frame. Cut 2: 2.0–5.0s | Breaking the window from the outside, passing the entire body inside 2.0–3.15s is the diagonal front camera outside the train. Lens and protagonist are outside the window, showing the silver body panels, exterior edge of the window frame, and empty interior through the glass. Protagonist approaches the window surface from outside, maintaining the body's progress vector in one direction: outside -> glass surface -> inside. At 2.0s, the entire body is completely outside, window is intact. At 2.7s, the entire single-edged sword in the right hand is swung in a short horizontal arc, and the blade near the tip hits the center of the outward-facing glass surface. A radial crack opens only after impact at 2.8s, and glass shards fly toward the interior, away from the exterior camera. At 3.1s, head and right shoulder enter through the window frame from outside, while waist and legs remain outside. Switch to interior diagonal front at 3.15s using flying glass shards as a momentary foreground occlusion. Leave the broken window behind the protagonist, passing waist, both knees, and both boots through the window frame from outside to inside by 3.7s. At 4.2s, the entire body including both boots is completely inside, landing low on the aisle floor. By 5.0s, the waist and ribcage cross two floor seams, running two steps forward to connect to the next siege. Cut 3: 5.0–6.2s | Momentarily deflecting bone arms, entering three-way attack lines Camera retreats from protagonist's left diagonal front, chest height 1.2m, placing protagonist on the right side of the screen at knee-up size. Using the connecting door at the front of the train as the vanishing axis, show the bone arm extending from left to overhead, the bone arm extending from right to below knee, the bone arm approaching chest height from the front, and the diagonal front gap remaining in the center all in the same frame. At 5.4s, protagonist's right foot grounds on the next floor panel. Compress knees briefly, move waist and ribcage forward. At 5.6s, there is a gap of about 10cm between the forearm of the high bone arm from the left and the guard side of the blade. At 5.7s, the guard side makes momentary contact with the bone forearm, and only after contact is the bone arm flicked toward the overhead exterior. With that reaction force, the protagonist folds the entire sword along the right hip, ducks the head and left shoulder under the high bone arm, and enters the next evasion. At 6.0s, left shoulder passes the high bone arm, right knee clears above the low bone arm. At 6.2s, the moment the flicked long phalanges cross in front of the lens serves as occlusion to pass to the next viewpoint. Cut 4: 6.2–7.5s | Ducking under top/bottom bone arms, passing through the center of the siege When occlusion clears, camera moves to protagonist's right shoulder rear, height 0.75m, capturing full body, supporting leg, one single-edged sword, and three ribcages at close depth. Change background vanishing axis diagonally from front door to the left rear window row. At 6.2s, protagonist catches the floor with right sole while keeping the sword tucked along right hip. At 6.6s, push pelvis ahead of the supporting leg with the right foot kick, quickly pulling the back left foot over the low bone arm. At 7.0s, tilt upper body to the left to slide the front phalanges outside the right shoulder. Three sets of bone arms begin to cross behind the protagonist. At 7.5s, protagonist's head, both shoulders, and waist completely pass through the center of the triangle formed by the three, and the left foot grounds on the next floor panel. Cut 5: 7.5–8.8s | Changing supporting foot, entering continuous sword arc Starting from left foot grounding, camera moves briefly from right shoulder rear to low left diagonal front, lowering height from 0.75m to 0.45m. Pull character size from knee-up to full body, returning background vanishing axis from left rear window row to front connecting door. At 7.5s, left knee is compressed briefly. At 7.8s, pelvis passes over left foot, starting clockwise rotation. At 8.1s, entire sword in right hand enters a single waist-high arc from the right hip, with blade, guard, and handle moving on the same axis of rotation. At 8.5s, the same single blade line passes continuously through the front of the three crowded ribcages. Protagonist does not reset stance for each enemy, passing body through in the same direction as the arc. At 8.8s, protagonist's waist completely crosses the three's siege line, right foot moves toward the floor ahead. Cut 6: 8.8–10.3s | Leaving the collapse of the three behind while running through Retreat from low left diagonal front, placing protagonist's full body to the right of center. Using broken window row and connecting door as depth axis, keep protagonist and the three behind in the same frame. At 8.8s, right foot grounds, reaction force carries left foot forward. Only after the sword passes do the three ribcages and pelvises begin to unravel simultaneously. At 9.2s, protagonist completely clears the range of the three's fingertips. The three do not fall in order but collapse into a pile of bones simultaneously behind the protagonist's passage line. At 9.7s, waist and ribcage cross two floor seams, sword begins to return forward from right rear follow-through. At 10.3s, next right foot grounds before the connecting door, connecting to King's appearance simultaneously with the dry sound of three sets of bones finishing their fall to the floor. Cut 7: 10.3–11.0s | Instant connection of King's appearance to downward arc Simultaneously with right foot grounding, connecting door is pushed open from inside, Skeleton King enters the aisle in one step. From low diagonal front, capture supporting leg, King's full body, and the entire black iron greatsword in the same frame. At 10.3s, King's lead foot crosses the door threshold. At 10.6s, without stopping the greatsword gripped in both hands overhead, move from the step-in to a vertical downward arc. Protagonist, while maintaining forward momentum, stands the sword in right hand in front of body. At 11.0s, leave about 10cm gap between the descending greatsword and the single-edged sword, passing to next contact with both waists and supporting feet in motion. Cut 8: 11.0–11.5s | Instantly releasing first contact From protagonist's left shoulder rear, height 1.15m, capture both weapons entirely, the gap before contact, and protagonist's right foot in the same frame. At 11.0s, there is a gap between the two blades. At 11.2s, the base of the greatsword blade and the guard side of the single-edged sword hit for the first time at one point. Place a hit stop of max 1 frame at the moment of contact, synchronizing short metallic sound and bluish-white sparks at the impact position. From next frame, reaction force passes to protagonist's wrist, elbow, shoulder, ribcage, waist, and right foot; right foot kicks the floor. At 11.35s, the two blades begin to separate. At 11.5s, gap between blades opens to the width of one blade; without holding the crossed pose, protagonist's right shoulder begins to enter inside the greatsword. Cut 9: 11.5–12.6s | Passing inside, swapping front/back positions With a short axis orbit crossing the contact point, camera moves to protagonist's right side, height 0.7m, showing both full bodies, both weapons, and floor seams. Behind falling sparks from 11.5s, waist and ribcage advance clockwise, sword continues to move away from greatsword. At 11.8s, right shoulder passes inside the greatsword. At 12.1s, waist and pelvis clear the King's side, left foot grounds on next floor panel. At 12.4s, front/back positions of protagonist and King are completely swapped. At 12.6s, King begins to turn shoulders, waist, and both feet to follow protagonist, passing the remaining rotation from the downward arc to the next return strike. Cut 10: 12.6–14.0s | Changing tracking rotation to horizontal return strike Camera retreats from protagonist's right diagonal front, height 0.95m, along the attack line, capturing King's full body, entire greatsword, and protagonist's supporting leg simultaneously. At 12.6s, King steps to a different floor panel with lead foot, rotating shoulders and waist using reaction force from floor through both soles. At 13.2s, entire greatsword takes over that rotation to start a horizontal return arc. Protagonist does not retreat, places left foot half-step outside the aisle, and moves the middle of the single-edged sword into the path of the greatsword. At 13.6s, there is about 10cm gap between the two blades. At 13.8s, middle of the greatsword blade and middle of the single-edged sword hit at one point. Hit stop max 1 frame. At 13.9s, two blades have already separated. At 14.0s, left foot changes lateral pressure to forward speed, passing that reaction force to the next attack to connect to passage. Cut 11: 14.0–18.5s | Passing through the opposite side with return reaction, entering finishing trajectory Low diagonal viewpoint with a seat as momentary foreground. At 14.0s, two blades move in different directions while separating, leaving only sparks. At 14.5s, left foot catches the floor outside the aisle, compressing the knee briefly. At 15.2s, pelvis under lateral pressure advances ahead of supporting foot, protagonist's ribcage and waist pass the King's sword-arm side. At 15.8s, front/back relationship of protagonist and King is updated again, protagonist emerges diagonally behind the King. King is not left behind, turning entire greatsword and torso toward protagonist to follow. At 16.4s, right foot grounds on floor behind the King. At 17.2s, use grounding reaction force to change clockwise body rotation into a single sword trajectory returning diagonally upward. At 18.0s, entire sword approaches front of intact black iron armor, still maintaining about 10cm gap. At 18.5s, pass the moment where blade and body are advancing while leaving a gap to the finish. Cut 12: 18.5–22.8s | Finishing with a diagonal upward strike, beginning collapse Short push-in from protagonist's diagonal rear, height 0.8m, capturing entire sword, front of black iron armor, and both supporting legs. At 18.5s, armor is intact with a gap between it and the sword. At 18.7s, the middle of the sword passes diagonally upward across the front of the black iron armor. Place a hit stop of max 1 frame only at contact. At 18.8s, only after sword passage does a thin blue crack run through the armor. At 19.2s, King's blue orbital flames vanish. Protagonist does not stay at contact position, moving sword follow-through and waist outside the King by 19.6s. At 20.0s, both of King's knees lose support. At 20.8s, armor torso tilts forward, greatsword tip approaches floor. At 21.6s, one knee and greatsword tip touch floor, synchronizing metallic sound. At 22.8s, pass the uncompleted fall of King's torso and greatsword toward the floor to the next Cut. Cut 13: 22.8–26.8s | Leaving collapse behind, connecting to sheathing preparation Camera retreats from protagonist's left diagonal front, height 1.1m, capturing protagonist knee-up and falling King in background. At 22.8s, protagonist places right foot on floor ahead, leaving the falling King behind. At 23.4s, both of King's knees and armor torso hit floor. At 24.0s, black iron greatsword falls sideways and stops on floor, synchronizing heavy dry metallic sound. At 24.2s, protagonist takes first step. At 24.8s, second step crosses floor seam. At 25.4s, protagonist uses walking reaction force to half-turn toward the fallen King, returning sword in right hand to side of body. At 26.2s, left hand supports scabbard on left hip, right hand begins to rotate entire sword toward scabbard mouth. At 26.8s, tip aligns just before the actual scabbard mouth, passing to next Cut without having inserted it yet. Cut 14: 26.8–30.0s | Finishing for sure with sheathing Lateral diagonal close-up capturing face, both hands, and scabbard mouth on left hip. At 26.8s, left hand supports scabbard, right hand rotates entire sword to accurately align tip with scabbard mouth. At 27.2s, tip enters scabbard mouth, thereafter blade fits in real-time without interruption. At 29.7s, guard fits tight to scabbard mouth, synchronizing with dry metallic 'clink' sound to complete sheathing. Three sets of bones, fallen King, and sideways greatsword remain static in the background. Simultaneously with sheathing completion at 29.7s, perform the short facial expression change mentioned above. At 30.0s, cut in the definite state just before the right hand leaves the handle.

Use [Reference Image] as the sole protagonist character reference. Targeted for Seedance 2.5, 16:9 ratio, 30 seconds, 60fps. Generate the entire video as a single continuous ultra-high-speed cinematic one-cut. Edit cuts, scene transitions via blackouts, fades, and sudden location changes are prohibited. Every change throughout the 30 seconds must have a 'physical reason for moving from the previous frame to the next.' Connect the character's gaze, body rotation, running, jumping, hand movements, ghost summoning, ghost flight, camera orbits, entry into the ghost's mouth, aerial freefall, web shooting, wall adhesion, tension, swinging, and aerial rotation into a single continuous motion trajectory. The tempo is extremely fast, with visual accents occurring every 0.3 to 1.0 seconds, but it must absolutely not be high-speed editing of multiple unrelated shots. The key is that 'everything is physically connected for the full 30 seconds despite the ultra-high speed.' From start to finish, the protagonist, ghosts, or the camera must always be in motion. [Most Important Concept] The vivid anime girl from the [Reference Image] exists directly within a AAA-grade photoreal live-action futuristic city. Only the protagonist must not be turned into live-action. Maintain the original 2D anime/high-end digital illustration quality of the [Reference Image] for 30 seconds, while depicting only the city, architecture, sky, glass, metal, roads, light, shadows, reflections, fog, water vapor, distant scenery, air, web lines, and environmental physics as thorough photoreal live-action. Create visual beauty through the heterogeneous coexistence where she 'clearly looks like an anime character, yet receives light from a real live-action city, runs through real space, and flies with webs from real buildings.' Keep the protagonist's outline sharp, but do not make her look like a sticker pasted on the background. Reflect directional light from the live-action environment, reflected light from the floor, color bleeding from buildings, and shadows from obstructions onto the anime shading, and establish grounding shadows on the live-action floor, color and silhouette reflections on glass, and natural occlusion by live-action objects in the foreground. [Protagonist Consistency] Completely maintain the adult female character from the [Reference Image]. Maintain the bright blue hair, bangs, side hair, tied hair, large red ribbon, red and white hat, white pom-poms, heart-shaped sunglasses, purple-to-pink lenses, small earrings, white fur, black mini dress, red nails, and rings. Do not change the face, eyes, hairstyle, hair color, body proportions, costume, or accessories midway. Maintain sharp, high-quality 2D cell anime + digital illustration texture, clear line art, blue/red/white colors, and smooth cell shading. However, do not make her a flat image; maintain 360-degree physical consistency as the same person even in profile, back view, low angle, overhead view, or aerial rotation. Give natural delay to the hair, ribbon, white fur, and costume according to speed, wind pressure, and acceleration. [Ghost Consistency] Use the white ghost present in the [Reference Image] as the basic design for the summoned entities. Maintain the soft semi-transparent white-to-pale-light-blue body, round cute silhouette, red-to-pink eyes and mouth, and pale pink cheeks, making them charming companions rather than scary spirits. Summoned individuals should be of the same type but not perfect copies, with small individualities in size, expression, tail curve, and flight pattern. Mass spawning is prohibited. Always increase one by one in the early stages, up to a maximum of 5. They fly three-dimensionally around the protagonist at different heights, distances, and speeds. The ghosts also maintain the same anime-world texture as the protagonist, but the photoreal city behind them should be naturally visible through transparent parts via transmission and refraction. [Stage | NEO FUTURE CITY] A giant futuristic city entering the blue hour from evening. Simple building rooftops are prohibited. The starting point is a giant aerial public plaza floating in the middle of a super-high-rise building complex. It is hundreds of meters above the ground, with multiple high-rise buildings connected by glass sky bridges, magnetic transit rails, giant structural beams, and aerial walkways. AAA-grade sci-fi movie-quality photoreal live-action texture. Giant glass facades, titanium, wet black stone floors, concrete, semi-transparent panels, movable louvers, subtle luminous traffic guidance lines, and unmanned transit systems moving at high speed in the distance. Do not use excessive cyberpunk neon. Establish it as a plausible futuristic architecture. In the sky, there are giant three-dimensional roads and magnetic rails, aerial transit vehicles in the distance, and natural evening light shining through thin clouds, casting blue and gold reflections on the glass buildings. Place high-rise buildings at 20-50m intervals on the left and right for web swinging in the second half, clearly showing exterior walls, beams, and antenna structures where webs can attach. [Basic Camera Design] AAA-grade action movie + high-end sports commercial filming quality. Full-size digital cinema camera. 18-21mm for high-speed movement, 24-28mm for character close-ups, and ultra-wide-angle macro-like impact when entering the ghost's mouth. 60fps. Maintain a shutter speed that allows reading high-speed motion, adding natural motion blur only in necessary directions. Prohibit meaningless 360-degree rotations, random rolls, or AI-like sudden zooms. Always set a center of motion for camera rolls, banks, and orbits, such as the protagonist, ghosts, or web tension. Do not keep the speed constant; repeat rapid acceleration -> ultra-close-up -> orbit -> momentary speed difference -> re-acceleration to create a camera rhythm that doesn't become monotonous even at high speed. [0.00-3.50s | Girl running suddenly + First ghost summon] Intense movement from the first frame. The protagonist from the [Reference Image] is running at full speed toward us in a giant futuristic aerial plaza. The external camera retreats at high speed from a low angle about 1.5m in front of the protagonist, lower than the waist. The protagonist is laughing happily, with her white fur, red ribbon, and blue hair swaying violently backward according to the speed. The anime protagonist's shadow flows at high speed on the wet live-action floor, and the colors of the blue hair and red ribbon reflect momentarily on the surrounding glass. Around 0.70s, the protagonist swings her right hand to the side without stopping her run. A 2D paint stroke, like a single stroke of red, blue, and white paint, is drawn in the live-action space, and the moment it forms an arc, the first ghost pops out vigorously from the stroke with a 'pon!' sound. It's not a magic circle. It's a flashy but short drawing effect. The ghost flies alongside the protagonist's shoulder, and the protagonist smiles while looking sideways, saying 'Can you keep up?' In Japanese, with perfect lip-sync. The ghost bounces up and down happily, but the protagonist does not stop at all. [3.50-7.50s | Summoning one after another while running] The protagonist runs at high speed, weaving through the structural beams and transparent panels of the aerial plaza. The camera orbits rapidly from the front to the left, and the protagonist also rotates her body halfway while running. Cutting the air diagonally with her left hand, a second one appears from a bluish-white stroke, 'pon!'. Flicking her wrist, a third one appears from a short red paint splash. Swirling her arm overhead, a single white ribbon-like stroke cuts through space, and a fourth one appears from its tip. Finally, thrusting both hands forward once, a slightly larger fifth one appears at the point where thick blue, red, and white brushstrokes intersect. Do not generate mass quantities at once. It must visually increase from 1 -> 2 -> 3 -> 4 -> 5, and previously summoned individuals do not disappear. The five ghosts fly at high speed at different heights and radii (overhead, beside the shoulder, beside the waist, ahead in the sky, behind), forming a three-dimensional spiral motion centered on the protagonist. One ghost passes very close to the camera lens, through which the protagonist and the photoreal city appear refracted through its semi-transparent body, but this is not used as an edit cut. [7.50-10.20s | Giant ghost moves to the front] The protagonist accelerates further toward the edge of the aerial plaza. The front is a giant urban space dropping hundreds of meters down, but she does not slow down. The five ghosts also increase their speed, and the largest one jumps out from beside the protagonist to the front, rapidly growing to about 3-4m in diameter while flying backward. Maintain cuteness and basic design. The giant ghost looks at the protagonist and shouts 'Here we go~!' in a bright, cute voice, with mouth movements perfectly synchronized. The mouth opens wide as the line ends. The inside of the mouth is not just a black hole, but a space where red, blue, white, and pink 2D paint swirls at a furious speed. The protagonist laughs and says 'Eh, there!?' in surprise, but doesn't stop running. Strong suction is generated from the giant ghost's mouth, pulling the protagonist's blue hair, red ribbon, and white fur forward, and the small ghosts also flow in the direction of the suction. The camera moves behind the protagonist and is physically pulled into the giant ghost's mouth along with her. [10.20-12.20s | One-time Giant PAINT IMPACT] The protagonist kicks off the edge of the plaza and jumps, plunging into the giant ghost's mouth due to the momentum and suction. Only at the moment of passing through the edge of the mouth, generate the flashiest single effect of the 30 seconds. Giant 2D paint strokes of red, blue, white, and pink, liquid ink, cell anime speed lines, and rough brush splatters circle the entire photoreal live-action screen at a furious speed, forming a PAINT IMPACT as if the movie film itself was momentarily repainted with a giant brush. Do not make it an explosion, magic circle, laser, or particle explosion. The camera doesn't stop and physically breaks through the paint layer. Do not make the inside of the mouth a long tunnel; pass through in less than a second, and the far upper sky of the same futuristic city appears beyond the paint layer. The paint splits left and right at high speed, and the protagonist and camera are ejected into the city sky at once through the rift. This is the only large-scale effect change; do not repeat transitions of this scale afterward. [12.20-14.50s | Ejection into city sky] The protagonist is thrown hundreds of meters into the sky above the photoreal futuristic city. Far below are three-dimensional roads, giant glass buildings, magnetic transit rails, and moving vehicles. The protagonist does not fly freely; after the upward inertia from the ejection is lost, she enters a clear gravitational fall. The camera dives from the side of the protagonist to go underneath her body, looking up at her from a low angle against the background of the city. The five ghosts from before pop out one after another from around the protagonist and rejoin her. Only the ghosts can fly freely in the air. One ghost aligns right next to the protagonist, and she laughs and shouts 'Whoa, so high!' while falling. The ghost also opens its mouth and laughs happily. The protagonist immediately switches her expression and fixes her gaze on a high-rise building ahead to the right. [14.50-18.00s | 1st Web Shooting -> Adhesion -> Tension -> High-Speed Swing] A giant glass and metal exterior building is ahead to the right. While falling, the protagonist swings her right arm forward from the shoulder and snaps her wrist sharply. She clearly shoots a single thin, strong white-to-pale-blue web line from her wrist/hand position. The web is depicted as a semi-transparent high-strength fiber existing within the live-action space. It doesn't appear suddenly; show the entire process of the tip extending rapidly from the hand, crossing the air, and reaching the exterior wall of the building ahead to the right. It adheres with a 'pachi!' sound, with very small live-action dust at the point of adhesion. Immediately after, the line pulls taut. First, the right arm is pulled in the direction of the tension, followed by force transmission to the shoulder, chest, waist, and legs. The downward falling speed is converted into forward speed, and the entire body enters a giant pendulum orbit centered on the web adhesion point. The camera also follows, banking strongly to the right. The five ghosts chase the protagonist at high speed: one in front, two on the sides, and the rest behind. The ghosts themselves do not use webs. [18.00-21.00s | Ultra-high-speed swing brushing against the building + Dialogue] The protagonist reaches the lowest point of the swing at maximum speed. Ultra-close approach to the live-action building wall, within 1-2m. Reflections of the anime protagonist and ghosts run at a furious speed on the glass surface. The protagonist leans her body sideways and bends her legs to avoid building protrusions by a hair's breadth. The camera enters the narrow gap between the wall and the protagonist from diagonally behind, emphasizing the speed and sense of distance with a 21mm wide angle. One ghost catches up right next to her and asks 'Wanna go faster?'. The protagonist, still looking forward, happily says 'Of course!'. Perfect lip-sync. Even during the conversation, never stop the high-speed swing, hair, ribbon, fur, or background flow. Immediately after the camera rapidly approaches the protagonist's face from the side, she opens her right hand to release the first web. The tension disappears, and the body is ejected diagonally upward at high speed by the accumulated inertia. [21.00-24.00s | 2nd Web + Further speed increase] Maintaining the momentum from being thrown into the air, the protagonist quickly rotates her body halfway. The camera also performs a meaningful orbit of only about 120 degrees around the protagonist, capturing her face from diagonally above in front. Another high-rise building appears ahead to the left, and the protagonist extends her left arm to shoot a second web line. Clearly show the process of the tip traveling through the air and actually adhering to the upper exterior wall of the building on the left. 'Pachi!'. The line pulls taut, the left arm is pulled, and tension is transmitted to the shoulder, torso, waist, and legs, abruptly changing the direction of travel to the left. The protagonist draws a giant arc, passing at high speed under the aerial transit rails of the futuristic city. The camera also rolls left in the direction of tension, and the horizon tilts significantly with physical reason. The ghosts chase her while crossing each other at high speed around the protagonist. A larger ghost aligns beside her and asks 'Can you still go~?'. The protagonist shouts 'I'm going to speed up even more~!' while smiling cutely in the wind. Make this heard clearly as a major line in the second half. Even while speaking, she maintains the left-hand web, and her body continues its maximum-speed swing. [24.00-27.00s | Web release -> Big jump into the city sky] The protagonist enters the upward side of the second swing, rising all at once to near the building rooftop. At the moment she can best convert speed into height, she opens her left hand to release the web and is ejected into the air even higher than the rooftop by the accumulated kinetic energy. The five ghosts also rise simultaneously. During the ascent, the protagonist extends one leg far forward, twists her body about 180 degrees, and spreads her arms. The blue hair, red ribbon, and white fur follow with a large delay due to the strong wind. The camera rises violently from directly beneath the protagonist, overtakes her, and then moves to the front, facing her while retreating. Behind her is the giant photoreal futuristic city spreading hundreds of meters below. The protagonist's ascent speed decreases, naturally transitioning into free fall. The five ghosts also begin to gather around the protagonist while adjusting their speed. [27.00-30.00s | Cute posing in the air + Painting effect] Finally, no shutter, camera, lens, or aperture is used. While falling through the city sky, the protagonist faces her body toward the camera, with the five ghosts arranged three-dimensionally on the left, right, overhead, at her feet, and behind. She smiles mischievously, brings her right hand to the side of her face to make a small V-sign, lightly bends her left leg, and enters a cute and confident aerial pose characteristic of the [Reference Image]. However, she does not remain perfectly static; falling, hair, ribbon, costume, and the floating motion of the ghosts continue. One ghost beside her shoulder also bends its body in a pose mimicking her. Another ghost smiles at the camera. The protagonist undoes the V-sign and draws a large stroke in the air with her right index finger. A vivid blue-red-white-pink 2D paint line emerges from her fingertip, perfectly synchronized with her arm's trajectory to draw a giant arc. The line circles three-dimensionally around the protagonist and the ghosts, forming an abstract drawn silhouette reminiscent of a one-stroke heart and star, but do not make it text or a logo. The five ghosts are not disappeared, but gather at high speed around the protagonist while each drawing a small color tail toward the paint line. The camera zooms in on the protagonist, and she gives a final wink. The photoreal futuristic city, the vivid 2D anime girl, the white ghosts, and the giant brushstroke running through the air reach maximum density in the same frame. At 29.70s, the protagonist thrusts her V-sign slightly toward the camera, and the ghosts all strike cute poses around her at once. The paint line circles the outer edge at high speed, decorating the frame. At 29.90s, a giant red, blue, white, and pink stroke crosses very close to the lens but do not black out. At 30.00s, end with the final frame as the vivid moment when the anime girl from the [Reference Image] and the five ghosts take a cute pose in the center of a giant hand-drawn effect, high above the photoreal futuristic city. Fading out is prohibited. [Sound/Music] Fast-tempo bright electro-pop x futuristic breakbeat from the beginning. Prohibit overly heavy EDM. Use tight kick, clean bass, crisp percussion, short digital synth, playful pluck, and detailed glitch accents to balance the protagonist's cuteness and high-speed action. Sync a short 'pon' or 'shu' to the movement every time a ghost is summoned, with music layers gradually increasing as more are summoned. Ghost voices should be cute, light, and slightly airy, but avoid excessive echo. The protagonist has the bright, uninhibited, and slightly mischievous voice of a young adult woman. Do not use a toddler's voice. Dialogue is only at specified locations. 'Can you keep up?', 'Here we go~!', 'Eh, there!?', 'Whoa, so high!', 'Wanna go faster?', 'Of course!', 'Can you still go~?', 'I'm going to speed up even more~!'. Do not repeat the same lines. Do not speak spontaneously at other times. Do not confuse the protagonist and the ghosts. Everything is perfectly lip-synced. Low suction sound + high-speed paint swoosh for the suction into the ghost's mouth. A strong single accent in the music only for the giant PAINT IMPACT around 10 seconds. Release wind pressure significantly the moment she is ejected into the city sky. Web shooting 'shupa', wall adhesion 'pachi', short low-frequency sound when tension occurs, and increase wind noise pitch according to swing speed. Sync a dry brush swipe to the protagonist's finger movement for the final painting effect. [Absolute Priorities] Maintain the protagonist from the [Reference Image] as the same person from start to finish. The protagonist remains an anime character for 30 seconds, without being photorealistic, 2.5D, or 3D. The background is a thorough AAA-grade photoreal live-action futuristic city. Intentionally leave the heterogeneous texture difference between the protagonist and the live-action background. However, establish light, shadow, reflection, grounding, occlusion, wind, and speed physically as a single space. No camera props should appear. Do not take selfies. Do not generate photos. In the beginning, she summons ghosts one by one with her own hand movements, increasing up to 5 without deleting existing ones. Summoning is a short 2D paint expression. The only large-scale effect change is entering the giant ghost's mouth. The giant ghost opens its mouth immediately after saying 'Here we go~!', and the protagonist and camera view are physically sucked into that mouth. Continuously eject from the mouth to the sky above the same futuristic city. The protagonist does not fly freely but falls with gravity. Always shoot web lines from the protagonist's wrist/hand, showing the entire process of the tip flying to a building, adhering, the moment the line pulls taut, and the process of tension being transmitted from the arm to the whole body, converting the falling trajectory into a swing. Establish 'shooting -> adhesion -> tension -> swing' at least twice. Ghosts fly on their own beside the protagonist and exist until the end. Establish natural conversation between the protagonist and ghosts even during high-speed movement. Finally, synchronize the cute pose of the protagonist + 5 ghosts in the air with the giant 2D paint line she draws with her fingertip. [Prohibitions] Protagonist turning into live-action, 2.5D, 3D animation, game CG, plastic 3D, face changes, hair color changes, hairstyle changes, costume changes, disappearance of accessories, disappearance of red ribbon, disappearance of sunglasses, disappearance of white fur, protagonist duplication, turning into a different person, age changes, additional human characters, turning ghosts into scary entities, zombies, or evil spirits, blood, gore, merging protagonist and ghosts, extra arms, extra legs, extra hands, 6 fingers, finger fusion, body twisting, joint failure, random teleportation, normal edit cuts, mid-scene blackouts,

Seedance Prompt | Price Hiked. I. Core Positioning: Cinematic photorealistic quality, pure ancient Chinese Xianxia aesthetic. Style: High-end ensemble deadpan comedy, classical martial arts character blocking, escalating negotiation rhythm, Rule of Three, precise reaction shots, Arri Alexa film look, clear facial micro-details, delicate film grain, natural volumetric light. Core comedy reversal: An enemy tries to bribe the Junior Sister to sell out the Senior Sister's weakness; instead, both sisters collaborate to hike the price and take the enemy's money. II. Reference Control: Character identity anchors (@Image 1 Senior Sister, @Image 2 Junior Sister), Environment DNA integration, Environmental Principles (neutral but vivid, no plot interference). III. Character Settings: ID A Senior Sister (25-30, calm, dignified, white Hanfu, silver sword), ID B Junior Sister (20-25, smart, braided hair, green Hanfu, steel sword). Supporting: Enemy Swordsman (confused), Elderly Master (authoritative finisher). IV. Core Props: Silver ingots (consistent), Long swords (identity markers). V. Comedy Structure: Mislead (30 taels), Progression (Senior Sister asks for 80), Reversal ("Afraid I'd lose out"), Finisher (Master takes 30%). VI. Storyboard Script: 0-5s (Enemy offers 30, Junior Sister asks for more), 5-10s (Senior Sister asks for 80, enemy is confused), 10-15s (Reversal revealed, money taken, Master passes by to take a cut). VII. Performance Rhythm: Deadpan serious for sisters, escalating confusion for enemy, casual authority for Master. VIII. Cinematography: 16:9, Arri Alexa texture, stable geography, natural parallax. IX. Audio: Synced Mandarin, clear pauses, ambient spatial sounds. X. Technical Specifications: 15s duration, landscape, multi-shot continuity, realistic physics, organized via Seedance 2.0 multi-modal standards. XI. Negative: blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props

Seedance Prompt | Just for the Sound I. Core Positioning Cinematic realistic quality, pure ancient Chinese Xianxia aesthetics. Style: High-end deadpan comedy with elegant martial arts character blocking, silent film reaction timing, socially awkward humor, and restrained absurdity. Visual Tone: Arri Alexa film quality, stable facial micro-details, fine film grain, natural volumetric light. Narrative Structure: Epic expectation → Confident but wrong understanding → Mundane truth → Authority figure's final remark. The logic uses 'polite response/pretending to understand' translated into ancient settings without modern items or slang. II. Reference Control 1. Character Anchors: ID A (Senior Sister) based on Image 1; ID B (Junior Sister) based on Image 2. 2. Environment: Shared DNA (terrain, architecture, scale, textures, etc.) across 3 shots to ensure a vivid, believable, and continuous world. III. Environmental Principles Neutral, naturally running background (wind, water, etc.). Background does not trigger comedy or plot; it only provides physical existence and spatial continuity. IV. Character Settings - ID A (Senior Sister): 25-30, elegant, white silk hanfu, calm, serious, overly polite. Humor comes from her 'serious' but wrong understanding. - ID B (Junior Sister): 20-25, green linen hanfu, smart, quick reaction. Humor comes from her being the first to realize the absurdity. - Supporting: Solemn enemy leader (solemn/fast speaker), Senior Master (distant, solemn, final remark), and two disciples. V. Core Narrative Logic Enemy leader delivers an epic challenge. Sister nods seriously. Everyone thinks she accepted. She then whispers to B: 'What did he say?'. She only nodded because 'he spoke for so long, I had to give a response.' Master adds: 'At least she's very polite.' VI. Storyboard 0-5s: Epic challenge. Sister nods solemnly. Everyone is shocked. 5-10s: Mid shot. Sister whispers to B: 'What did he say?'. Everyone freezes. Sister explains she only responded out of politeness. 10-15s: Close up. Enemy asks if the duel is on. Sister says 'No, I was just listening.' Enemy breaks down. Master adds the final serious remark. Cut to black. VII. Performance Requirements Deadpan absurdity. Sister is sincere, not mischievous. Junior sister suppresses laughter. Enemy transitions from majesty to collapse. VIII. Action & Blocking Clear, concise, and readable movements using rhythm and reactions rather than exaggerated physical comedy. IX. Cinematography 16:9, stable composition, micro-expressions, Arri Alexa look. Use full/mid/close shots to build and subvert the epic tone. X. Sound & Rhythm Mandarin dialogue, precise lip sync, accurate comedic pauses. Background sounds exist but music is restrained. XI. Technical Specifications 15 seconds total. 16:9 aspect ratio. 3 continuous shots. Optimized for Seedance 2.0 Fast for character consistency. High realism in fabric and hair physics. XII. Negative Standard quality negatives (blurry, low res, bad anatomy, inconsistent character, morphing, etc.).

A cinematic, fast-paced scene of the beastman from the reference image riding a dragon and fighting approaching enemies.

Japanese full-color anime style. Japanese TV anime style. Cel-look anime. Anime-style screen capture focused on flat coloring. Noble's mansion. The long-haired blond character from Image 1 is sitting in a chair. The red-haired character from Image 2, the step-brother of the character in Image 1, is sitting in the chair opposite. 0-4s: View of the long-haired blond character from Image 1 from a high angle. 'Brother, what business brings you here today?' 4-8s: View of the red-haired character from Image 2 from a low angle. 'Withdraw from father's business, Reis.' 4s. 8-13s: Side view of the upper body of the long-haired blond character from Image 1. 'Did it displease you so much that I turned (the business's deficit) into a profit?' Eyes closed, quiet. Pan left. 13-17s: Close-up of the clenched fist of the red-haired character from Image 2. 'You're aiming for the head of the family, aren't you?' Trembling with rage. 17-20s: Front view of the upper body of the red-haired character from Image 2. Pointing at the screen and insulting: 'Even though you're just a concubine's child!' 20-21s. Water is poured over the head of the red-haired character from Image 2. 21-25s: Low angle view of the black-haired maid from Image 3. She has a looking-down gaze. The black-haired maid is holding a water pitcher with a looking-down look in her eyes. '...Excuse me. My hand slipped.' Cold stare. 25-28s: Scene where the red-haired character from Image 2 shouts 'You!' and raises their arm. Side view, image of the red-haired character from Image 2 from the shoulder up. 27-28s: Close-up of the red-haired character's shoulder from Image 2. The hand of the long-haired blond character from Image 1 firmly grabs the shoulder of the red-haired character from Image 2. The face of the long-haired blond character from Image 1 is not shown, only the hand grabbing the shoulder. 28-30s: In the foreground, half of the red-haired character's face from Image 2 is facing this way. In the background, the face of the long-haired blond character from Image 1. '...Please leave.' Speaking with intimidating force. The red-haired character from Image 2 is frightened by the intensity and their face turns pale. Japanese full-color anime style. Japanese TV anime style. Cel-look anime. Anime-style screen capture focused on flat coloring. Noble's mansion. 0-5s: View from behind of the red-haired character from Image 3 holding their wrist, shouting 'Ouch... Damn! You guys, just remember this!' and leaving the room. 5-6s: Diagonal view of the long-haired blond character from Image 2 and the black-haired maid from Image 4 standing side by side. They are watching the character from Image 3 leave. The character from Image 3 is not shown on screen. 6-9s: Long-haired blond character from Image 2 says 'Ah~, that felt good' while stretching. 9-14s: Side view of the black-haired maid character from Image 4 with eyes closed and head down, panning right. The black-haired maid character says in a calm voice, 'I am very sorry, Master. It was just a slip.' 14-19s: Smiling face of the long-haired blond character from Image 2. Low angle composition. 'Thank you, Elsa. You got angry for my sake, didn't you?' Moe background, sparkling. 19-25s: Close-up of the black-haired maid character's face from Image 4. High angle view. 'I-It's not like that, necessarily...' Head down, steam rising from head. Cheeks turning slightly red.

I. Core Positioning\nCinematic realistic texture, ancient Chinese fantasy aesthetics. High-end deadpan comedy style with silent film reaction timing and social awkwardness humor. Epic expectations vs. a mundane reality.\n\nII. Narrative Logic\nEpic Expectation: Enemy leader delivers a fast, solemn challenge. Senior nods seriously. Confession: Senior asks Junior, 'What did he say? It was too fast at the end.' Reason: Senior says, 'He talked so long, I had to give some response.' Authority Punchline: Master solemnly adds, 'At least she was very polite.'\n\nIII. Character Settings\nSenior Sister (Character A): Calm, dignified, overly polite but clueless. Junior Sister (Character B): Clever, quick to realize the absurdity. Enemy Leader: Serious, solemn, collapses under the logic fail.\n\nIV. Shot Script\n0-5s: Full shot of the epic challenge. Senior nods. 5-10s: Medium shot of the whisper between Senior and Junior. Opponent freezes. 10-15s: Close-ups of the verbal exchange and Master's ruling.

Restrained Documentary footage, single continuous take, no cuts. Real, natural steady footage, intimate close-up framing.nuanced understated, An Italian woman, twenty-eight years old, dark hair loosely framing her face, sharp blue suit, open collar, close-up dead center, matches the confirmed opening frame exactly: soft window light from one side, muted neutral grade, shallow depth of field, She speaks in a near-whisper with a noticeable Italian-English accent, voice flat, controlled, unhurried, every word calculated and released with total economy, nothing given away. She holds the frame from the opening image, composed and still, the smallest flicker of restraint beneath an otherwise unreadable calm. Soft room tone, quiet breath, distant ambient hum. No music or soundtrack, diegetic sound only. The camera holds the opening frame's exact composition for the first four seconds (0–4s), an all but invisible push-in beneath complete stillness. She holds, unmoving but for a single natural blink (4–6.5s), then speaks, barely audible, flat and even, accent faint in the vowels: "Who told you my name is Jill?" (6.5–8s), a long still pause, breath suspended, before "Tell me. Please." (8–9.5s), the words dissolving to near silence. Final beat: she remains motionless, eyes steady, lips closed, expression unreadable, stillness unbroken (9.5–10s). Face identity stable throughout, one natural blink only, performance held to the barest minimum of visible effort.