Cyberpunk Ice-Blue Character Awakening

style: visual: "Japanese watercolor-style full-color anime" editing: "Fast cuts every 0.5 seconds" animation: "High frame count, smooth 24fps" tone: "Sensual but not direct, visualizing temperature, humidity, and heartbeat" project: id: "fetish_montage_v3_with_broll" format: "vertical_9x16" fps: 24 shot_duration: "0.5s" total_shots: 28 total_duration: "14s" ratio: "fetish 22 : b-roll 6 (approximately 3.5:1)" broll_philosophy: role: "Breathing, symbolism, externalization of emotion" placement: "Immediately after consecutive fetish cuts, or at emotional turning points" rule: "Avoid direct sexual expression; convey heartbeat, temperature, humidity, and tension" broll_categories: nature_micro: - "A raindrop trails down the window" - "A candle flame sways, on the verge of being blown out by a breath" - "A crack runs through ice with the sound of it splitting" - "A single petal falls onto the table" - "Water droplets on a spiderweb tremble" - "Cigarette ash falls silently" - "Steam rises and dissipates" - "A single insect flies around a streetlamp at night" object_symbol: - "Close-up of a wall clock's second hand. It seems about to stop" - "The ceiling reflected on the black surface of coffee" - "A shoe discarded on the floor. Only one" - "Creases on an empty bed" - "A phone ringing endlessly. No one answers" - "Two cigarette butts in an ashtray. One has lipstick on it" - "Light leaking through a door gap" - "An empty chair reflected in a mirror" texture_landscape: - "Wet road at night. Headlights blur and bleed" - "Flickering neon sign" - "Shisha charcoal pulsing red" - "A distorted face reflected on a metal surface" - "The imprint of a hand sinking into a leather sofa" - "The surface of bathwater rippling" body_abstract: - "The blanket rises and falls faintly with the heartbeat" - "Only a person's shadow moves along the wall" - "A person's outline through glass. Focus drifts" - "A face reflected inside a water droplet" sequence: - id: 01 type: "fetish" action: "Lift the hair, exposing the nape of the neck" scale: "macro" - id: 02 type: "fetish" action: "Bite the lower lip, then slowly release it" scale: "extreme_macro" - id: 03 type: "b-roll" category: "object_symbol" action: "The wall clock's second hand ticks forward one second" intent: "Make the viewer aware of time stretching and compressing" - id: 04 type: "fetish" action: "Unbutton the cuff, rolling up the sleeve once" scale: "macro" - id: 05 type: "fetish" action: "The collar shifts slightly, casting a shadow on the collarbone" scale: "macro" - id: 06 type: "fetish" action: "Trace the rim of a glass with a fingertip. A drop of condensation falls" scale: "extreme_macro" - id: 07 type: "b-roll" category: "nature_micro" action: "The candle flame sways once, largely" intent: "Metaphor for breathing. Peak of tension" - id: 08 type: "fetish" action: "Remove an earring. Immediately after, hair falls onto the shoulder" scale: "macro" - id: 09 type: "fetish" action: "The foot slips out of the heel" scale: "macro" - id: 10 type: "fetish" action: "The throat moves slightly. Swallowing" scale: "extreme_macro" - id: 11 type: "b-roll" category: "texture_landscape" action: "Shisha charcoal glows red, pulsing like a heartbeat" intent: "Externalization of the heartbeat" - id: 12 type: "fetish" action: "Slowly exhale smoke from the mouth" scale: "macro_side" - id: 13 type: "fetish" action: "The shoulder blade moves quietly beneath thin fabric" scale: "macro_back" - id: 14 type: "fetish" action: "Hold a pen cap between the teeth and slowly pull it off" scale: "extreme_macro" - id: 15 type: "b-roll" category: "body_abstract" action: "The blanket rises and falls faintly with breathing" intent: "A brief pause in tension. A hint that it will continue"

A stunning action packed scene following a little robot running away from soldiers, drones and other things that are trying to get him. Chase cam, dystopian futuristic cyberpunk environment, cinematic lighting. The camera follows the robot from behind, chase cam style. Every now and then the robot looks behind him and the entities chasing it are shown.

Duration: 15 seconds | Aspect Ratio: 16:9 | Style: Authentic UGC / iPhone selfie-vlog, handheld, natural light, slight motion blur, TikTok/Reels energy — NOT cinematic. Product Reference: Use the uploaded ramen bowl image as the only product reference. Keep the broth color, noodle thickness, toppings, egg placement, chashu slices, and bowl appearance identical throughout every shot. Camera: iPhone 15 Pro handheld with front/back camera switching, realistic autofocus hunting, natural handheld movement, slight exposure shifts, warm apartment lighting. Character Description Name: Yuna A young Japanese woman in her early 20s with soft natural beauty, shoulder-length dark hair tied loosely, subtle makeup, oversized gray hoodie, cheerful personality, filming casually inside a cozy apartment kitchen. Shot Breakdown SHOT 1 (0–2s) — Selfie holding the ramen bowl. Dialogue: "Late-night ramen again." SHOT 2 (2–4s) — Overhead reveal with steam rising. SHOT 3 (4–6s) — Close-up autofocus on noodles and broth. SHOT 4 (6–8s) — Chopsticks lifting noodles with a natural noodle stretch. SHOT 5 (8–10s) — Selfie bite reaction. Dialogue: "That's insanely good." SHOT 6 (10–12s) — Casual b-roll of the bowl while she reaches for another bite. SHOT 7 (12–14s) — Selfie holding noodles toward camera. Dialogue: "Worth every bite." SHOT 8 (14–15s) — Freeze frame with handwritten overlay: "ramen fix 🍜" Look & Feel Warm lighting, natural phone quality, authentic UGC pacing, jump cuts, realistic handheld movement. Negative Prompt cinematic look, luxury commercial, perfect framing, CGI noodles, unrealistic steam, plastic food, distorted chopsticks, extra fingers, warped hands, overprocessed HDR, text artifacts.

High-quality anime footage. The world setting is a refined modern fantasy academy, depicted as 2D hand-drawn slice-of-life conversation animation. Facial expression design must always be done in this order: eyes → eyebrows → eyelids → mouth → gaze. [Reference Images and Character Consistency] Image 1 is the reference image for Character A. Maintain the character depicted in Image 1 as the same person throughout the entire video. Use Image 1 only as a reference for Character A's face, eye shape, iris color, hairstyle, hair color, outfit, accessories, physique, silhouette, atmosphere, and character colors. Image 2 is the reference image for Character B. Maintain the character depicted in Image 2 as the same person throughout the entire video. Use Image 2 only as a reference for Character B's face, eye shape, iris color, hairstyle, hair color, outfit, accessories, physique, silhouette, atmosphere, and character colors. Do not reproduce the background, room, furniture, pose, camera angle, framing, or lighting arrangement of the reference images themselves. Only the following may change: facial expression, gaze, mouth shape, posture, breathing, and natural movement of hair and clothing. Do not blend the features of Character A and Character B. Averaging faces, swapping outfits, swapping hairstyles, turning them into different people, cloning, creating doppelgangers, and adding extra people are prohibited. Even if Image 2 contains a weapon or handheld item, Character B's hands must hold nothing. Only if Image 1 contains a non-combat accessory or small bag may it remain naturally on Character A. However, the bag must be fixed to the body side; holding it in the hand, opening it, or using it in action is prohibited. No weapons, large equipment, or glowing combat gear. [Props, Color Tone, and Atmosphere Adjustments] The location, seating position, conversation content, the action of dividing the bread, and the camera composition are fixed. On that basis, naturally adjust hair ornaments, brooches, ribbons, bags, and other accessories, props, color schemes, light impression, and background accent colors to match the reference images of Character A and Character B. Adjust the overall line color, shadow color, background accent colors, and color temperature of the afternoon light to match the character colors and atmosphere of Character A and Character B. However, maintain the bright, refined, and clean everyday feel of a modern fantasy academy; do not make it a dark combat space, horror, decadent, or extremely backlit. [Art Style Fixation] Thin, delicate colored line art; transparent two-to-three-layer colored shadows; soft gradients. Do not make saturation too low; naturally reflect the reference characters' inherent colors into the hair, eyes, clothing, reflected light, and background accent colors. Eyes have jewel-like iris depth and multiple small catchlights; hair has pearl-like multi-layered highlights. Draw hair, eyelashes, lace, embroidery, hair ornaments, accessories, and clothing wrinkles with high density. Fabric is rendered with distinct delicate textures for high-quality matte material, lace, metal, gemstones, and ribbons. The background uses the same 2D hand-drawn brushwork, drawing the cream-colored walls, wooden bench, plants, and distant school building with sufficient density. Thick lines, heavy outlines, simplified TV anime style, flat single-layer cel shading, low-density backgrounds, smooth 3D assets, semi-realism, photorealistic textures, heavy dulling, AI-average faces, and mixed art styles are prohibited. [Fixed Location and Character Placement] A wooden bench in the school courtyard after class. Character B is on the left side of the screen, Character A on the right. The two sit next to each other. Only Character A holds one round anpan (sweet bean bun) wrapped in thin paper, supporting it from underneath with the right hand. At the start, the bun is perfectly round with no bite marks or missing pieces. The fingers are placed under the paper wrapper, away from the eating position. Do not multiply the bun, the paper wrapper, or the fingers. [Cut 1] Camera position: front-center of the bench. Camera height: at the eye level of the two seated characters. Frame both characters from the front, from the chest up, at equal size, with the background vanishing axis receding between the two into the distance. Purpose: to establish the relationship between the two and that the bun belongs to Character A. Character B looks at the bun, then returns their gaze to Character A, brings both hands together at the chest, and leans slightly closer with the whole body. Eyes sparkling, eyebrows raised, eyelids opened in anticipation, making a coaxing mouth shape, gaze directed at Character A. Only Character B speaks in a bright, sweet voice: "Let me have a bite of that anpan." A brief pause, then coaxing further: "Please, it's the request of a lifetime!" Character A does not speak, but looks at Character B with an exasperated yet gentle expression. [Cut 2] Camera position: diagonally in front of Character A. Camera height: at the eye level of the two seated characters. Angle from over Character A's shoulder toward Character B, showing both faces and the bun in a medium close-up. The background vanishing axis shifts to the upper right. Purpose: to show the response, the offering hand, and the single bite action in one continuous sequence. Character A softens the eyes, lowers the eyebrows slightly, gently narrows the eyelids, forms a wry smile with the mouth, and directs the gaze at Character B. A small exhale, a brief pause, and only Character A speaks in a calm, gentle voice: "Honestly, you're hopeless. Just one bite, okay?" While finishing the line, Character A offers the single anpan in the right hand toward Character B's mouth. The owner remains Character A; it is not handed over. Before contact: the bun is perfectly round. There is a small gap between Character B's teeth and the bun. Contact: show the moment Character B leans in and the teeth touch the upper edge of the bun, taking just one bite. After contact: only a small crescent-shaped bite is missing from the bun, and Character B pulls the face away. Character A returns the same bun to the chest with the right hand. Do not bite the hand or fingers. Do not duplicate the bun, paper wrapper, or fingers. [Cut 3] Camera position: diagonally in front of Character B. Camera height: at the eye level of the two seated characters. Angle from Character B's side toward Character A, showing Character B slightly larger from the chest up, then briefly panning left to a chest-up two-shot of both. The background vanishing axis shifts to the upper left. Purpose: to place Character B's satisfied face and Character A's returning smile in the same final frame. Character B closes the mouth and chews twice, small bites, then swallows. After a brief pause, the eyes brighten, the eyebrows form a soft arc, the eyelids narrow happily, a satisfied smile forms on the mouth, and the gaze returns to Character A. Only Character B speaks in a buoyant, gentle voice: "Mmm, delicious!" Character A holds the same bun with one bite missing at the chest with the right hand, silently returning a warm smile. Keep both faces and the bun in the same frame, and cut at the moment Character B finishes the final vowel of "delicious" and both smiles are complete. [Audio] Generate two Japanese voices that match the characters' appearance, perceived age, and atmosphere. Character B has a bright, sweet voice; Character A has a calm, gentle voice. Do not swap speakers; deliver the three lines verbatim, without overlapping, and synchronize mouth movements with the vocalization. No dialogue other than the lines, no narration, no subtitles, no on-screen text. No BGM, no music. Only ambient sound and foley. Synchronize weak wind, distant birds, fabric rustling, the paper sound of the wrapper, and the small compression sound at the moment of the single bite into the soft bread with the visible actions. Do not add exaggerated chewing sounds. [Important Prohibitions] No speaker swapping, no simultaneous speech, no lip-sync errors, no duplication of the bun, no unsolicited handover, no eating more than one bite, no bite marks before eating, no deformation of fingers, no adding people, no foreground covering faces, no light spots in the center of faces, no subtitles, no logos.

High-quality anime footage. [Work Tone] An elegant, dreamlike afternoon lyrical anime set in a transparent summer glass greenhouse. The entire visual is unified as high-density 2D hand-drawn animation, focusing on quiet breathing, the movement of light, reflection and transmission per material, and delicate changes in expression. [Role of Reference Image] Use only Image 1. Treat Image 1 as a reference for a single appearing character, referencing only facial features, eye shape, iris color, hairstyle, hair color, costume, accessories, physique, full-body silhouette, atmosphere, and character-specific colors. Do not reproduce Image 1's own background, room, furniture, architecture, pose, hand position, camera angle, camera distance, framing, composition, or lighting conditions. Do not bring background elements from Image 1 into the greenhouse. Strictly maintain the same person as Image 1 as the same single character throughout the entire piece. Do not change facial contour, eye shape, characteristics of the left and right pupils, iris color, bangs, hair length, hairstyle, hair ornaments, costume structure, accessory positions, physique, perceived age, or character-specific colors. Only expressions, gaze, mouth, breathing, shoulder tension, hand movements, and natural hair and costume sway may change. Mixing features, averaging faces, turning into a different person, costume changes, disappearing accessories, hairstyle changes, cloning, duplication, and adding extra people are prohibited. [Art Style Fixation] As a condition separate from character identity, fix the entire visual as delicate, high-density 2D hand-drawn animation. Maintain thin, pale cool-toned lines, transparent multi-layered color shading, soft gradients, a faint luminous quality to skin, delicate highlights in hair, and multi-layered reflections in the eyes. Flowers, glass, tea, sky, clouds, white furniture, floor tiles, and greenhouse architecture are all drawn with the same density of hand-drawn brushwork. Do not use thick outlines, simplified TV anime style, flat single-layer cel shading, low-density backgrounds, smooth CG, 3D conversion, semi-realism, live-action conversion, or mixed art styles. [Elements to Vary According to the Character] Keep the location and events fixed; adjust only the design of small objects, accent colors, the impression of light, the tint of the tea, and a single small tabletop accent to match the character in Image 1. While maintaining the greenhouse's bright white and pale blue base, extract only one color from Image 1's hair color, eye color, costume color, and accessory color as a supplementary accent. Limit the accent color to the rim of the cup, a thin decoration on the saucer, a flower on the table, and a slight tint in refracted light; do not repaint the entire background with the character's color. The shape of the teacup and saucer may be slightly adjusted in design within the range of elegant, dainty, refined, or fantastical to match the impression of Image 1's costume and accessories. However, it is fixed that they are transparent glass, one cup, one handle, and one saucer. The tea maintains a transparent, warm color and may be gently adjusted to amber, pale honey, light rose, or a fantastical brown with a hint of pale blue-green, matching Image 1's character color. Do not make it cloudy liquid, opaque liquid, or fluorescent colors. Place only one tabletop accent. Choose the most natural single item from a citrus slice, a small sugar confection, a single flower, or a thin fruit slice, matching the atmosphere of Image 1. The accent must not multiply, move, or transform mid-scene. [Fixed Stage] The stage is a bright summer glass greenhouse. Maintain white window frames and roof framework, clear blue sky, white clouds, outside greenery and flowers, a white round table, a white metal chair, flower pots, and pale blue-gray floor tiles. Use white and pale blue as the base, with only the pale gold created by sunlight and the supplementary accent color extracted from Image 1. [Fixed Props] In the initial state, one transparent glass teacup contains tea, is not held by anyone's hand, and is placed at the center of one transparent glass saucer. One tabletop accent remains placed on the white round table. In the latter half, only the character herself holds the cup's handle with her right hand. Do not multiply, exchange, disappear, or transform the cup, handle, tea, saucer, or accent. [Opening Camera] The first camera is at an oblique front angle to the white round table, at the same low height as the table surface, facing toward the character's oblique front. Place the teacup and saucer large in the foreground, and clearly show the character's upper chest and face in the background. Align the background vanishing axis with the direction in which the floor tiles and the right-side window frame extend into the greenhouse's depth. Introduce the tea and the character in the same frame from the start. The character breathes gently, and only the hair tips, sleeves, and light costume decorations sway slightly in the greenhouse's breeze. [Light Generation] Thin clouds outside flow sideways, the sunlight opens up, and white sunlight passing through the greenhouse window glass transmits through the tea. Soft light patterns created by refraction through the tea and transparent glass appear from the saucer's rim onto the white table. The base color of the light patterns is pale gold, with Image 1's character-specific colors mixed in very faintly. The character notices the new light, releases a little tension from her shoulders, and turns her upper body very slightly toward the light. [Camera Movement Following the Light] The light patterns begin to flow continuously with the movement of the clouds, and the camera follows the light as a guide line. The camera position smoothly lowers from the oblique table front to near the floor, keeps facing the direction of light travel, and changes subject size from a close-up of the cup to a medium shot of the costume. The background vanishing axis shifts from behind the table to the oblique depth of the floor tiles. Render each material differently: thin transparent reflections on transparent glass, colored transmitted light in the tea, soft diffused light on white fabric, short sharp reflections on metal decorations, and faint mirror-like light on floor tiles. Continuing, the light moves successively from the white table to the floor tiles, to the hem or lower decorations of the costume, and to decorations around the waist. The camera rises from near the floor to chest height while still facing the character's oblique front, returning subject size from a medium shot of the costume to upper chest. The background vanishing axis transfers from the floor tiles to the window frame and roof framework extending toward the upper right. If Image 1's costume has no hem or waist decorations, do not add nonexistent decorations; instead, move the light in order over the actual costume's edges, fabric overlaps, chest area, cuffs, and hair ornaments. Background window frames, flowers, and chairs create gentle parallax to maintain the greenhouse's depth. [Expression Change] The light does not enter the center of the face; it only faintly outlines the shoulders, the outer edges of the hair, and the costume's contours. For the expression change, first show only the pre-existing catchlights inside both pupils brightening slightly at the same time, then the eyebrows rise a little, then the eyelids soften and relax, then the corners of the mouth naturally lift, and finally the gaze lowers to the tea, in that order. The camera maintains an oblique front upper-chest shot, showing Image 1's eyes, facial features, hairstyle, hair ornaments, and main costume decorations clearly. [Cup-Lifting Action] The character carefully pinches only the cup's handle with the fingers of her right hand and quietly lifts the transparent teacup from the saucer. Her left hand remains lightly resting on the edge of the white table. When the cup is held at a height slightly lower than her chest, small ripples form in the tea, and the greenhouse's white roof framework, blue sky, and flowing clouds reflect naturally onto the tea's surface. [Ending Camera] The ending camera is at the character's oblique front, at chest height, facing the tea surface and her face. Keep the character at upper-chest size, with the tea surface in the foreground and a real three-quarter face in the background. Align the background vanishing axis with the direction in which the white roof framework extends toward the upper right. Tilt the camera slightly downward, and the character quietly holds the transparent teacup at a position slightly lower than her chest. On the tea surface in the foreground, the greenhouse's blue sky and the same character's three-quarter face appear clearly once. The face on the tea surface is an optical reflection — not another person, a duplicate, or a second character. Maintain the same facial features, hairstyle, expression, and gaze direction as the real image in the background. The real image in the background maintains a gentle smile, the tea's ripples settle, and cut at the moment when the real image and the reflected image are both clear simultaneously. [Prohibited Items] Do not overlay light points, horizontal flares, or glass reflections onto the center of the face, the bridge of the nose, between the eyebrows, or the surface of the pupils. Do not obscure the face with light. Do not replace the background with Image 1's background. Do not change to any location other than the greenhouse. No text, subtitles, logos, or watermarks. No BGM, no music, no ambient sound, no foley, no sound generation.

High-quality anime footage. Expression progression: eyes -> brows -> eyelids -> mouth -> gaze. [Reference image and character lock] Same girl, same person, same identity in every shot. Use image 1 as the sole highest-priority reference for this girl's face, eyes, hair style, hair color, outfit, accessories, body type, and equipment. In every cut, strictly maintain the same single girl as in image 1. Do not reference text, UI, layout, background, pose samples, expression lists, or small drawn face variations within image 1. Even if image 1 contains multiple expression variants or small face samples, do not treat them as different people — use them only as variation information of the same person. Averaging the face, turning her into a different person, outfit swapping, duplication, cloning, and additional characters are prohibited. Allowed changes are limited to expression, gaze, mouth, pose, breathing, and natural hair/fabric movement. Expression changes must always be shown in the order: eyes -> brows -> eyelids -> mouth -> gaze. The face must strictly maintain image 1's: small soft oval shape, delicate jaw, large iris layered from purple to blue, magenta and cyan reflections, multi-layer catchlights, thin upper lashes, pale skin, long pink twin-tails, slanted bangs, purple flower and dark purple ribbon on the head. Maintain the outfit, accessories, body type, and equipment from image 1: deep purple short cape with antique gold trim and star-flower embroidery, white frilled blouse, black-purple corset, dark brown leather belt, short layered skirt, white thigh-highs, purple-black and antique gold boots, purple crystal brooch. Prioritize shapes, colors, and materials clearly visible in image 1; only fill in unclear areas naturally while keeping the same design. Props: a dark brown leather-bound grimoire with gold openwork and a purple crystal, a purple glass vial at the waist, and a purple crystal charm. There is only one grimoire. It is closed at the start, always supported by the left hand, and only the right hand opens the cover and turns a single paper page. The glass vial and charm remain fixed at the waist and are not used. [Fixed rendering: 3D toon/cel-look] Thin, controlled colored line art. Line color is not black but deep purple-brown. Shading uses 2–3 layers of toon shadows with soft mid-tone gradients. Color palette is centered on pink, deep purple, white, antique gold, and jewel magenta. Eyes are multi-layered, hair is pearlescent, metal and crystal have sharp localized highlights. Separate materials: matte skin, silky hair, woven cape fabric, thin white blouse fabric, leather for belt and grimoire, antique gold for ornaments, transparent crystal for gems and glass vial. Render at high density: face, lashes, hair strands, frills, gold ornaments, leather, magic sigils, wet stone floor, brass door, arched window. Thick outlines, single-layer flat cel shading, generic 3D anime faces, smooth plastic CG materials, low-density backgrounds, photorealistic, semi-photorealistic, dull colors, and mixed art styles are prohibited. [World and tone] Midnight royal magic archive. Wet black stone floor, tall arched windows, brass star-shaped locks, dark bookshelves stretching into the depths. Cinematic teaser using black negative space, ivory, deep purple, magenta, and antique gold geometric color fields. Ratio: suspense 60%, noir jazz 40%. Mysterious, urban, composed, agile. No horror, no heavy tragedy, no cheerful jazz MV. Core of the story: "One star has been stolen from the grimoire's emblem." Not combat — show the girl discovering the anomaly and tracing the remaining magical traces. [Camera and editing design] Camera state: position=three-quarter and over-shoulder; height=eye level then low angle; direction=tracks then push-in; subject scale=close-up to medium; vanishing axis=archive depth axis; purpose=to show the clue chain and reveal the missing star. Narrow split panels open into a vast archive space, creating a clear scale change. The camera moves to show the causality of each action. Iris anomaly in extreme close-up, clue progression in asymmetrical split screen, door unlocking with a low follow, approach to truth with a depth-direction push-in, final resolve stopping at a chest-up three-quarter front. Do not keep the subject locked to screen center during movement — use diagonal compositions, foreground occlusion, and depth differences. No soft dissolves or liquid morphs — connect everything with hard cuts, masks, wipes, and tile rearrangements. A single thin ivory line is drawn across a black screen, then transforms into the outline of image 1's right eye. Extreme facial close-up. In the iris, the star-flower emblem of the grimoire is reflected — one star silently disappears. The girl changes, in the order eyes -> brows -> eyelids -> mouth -> gaze, from a faint small smile to a wary, quiet expression, and drops her gaze to the grimoire at the lower right of the frame. The circular reflection in the iris rotates like an old astronomical record disc, becoming a hard circular wipe. The screen snaps into an asymmetrical two-panel split. The left narrow panel shows a close-up of the closed grimoire's metal fittings. The right large panel shows her boots and long cape hem advancing across the wet stone floor. Deep purple and magenta color fields, thin antique gold frames, assemble piece by piece. The girl stops her right fingertips a few centimeters from the grimoire's purple crystal. The crystal lights up once on its own, and from that ignition a thin magenta magical trace line extends from the crystal toward the door. The door remains closed until the trace line arrives. When the tip of the trace line exactly overlaps the center of the star-shaped lock on the door, the brass lock turns once and the door opens vertically. The door's vertical line becomes a hard vertical cut. From the opened darkness, a flat, non-human long shadow crosses the stone floor and wipes across the entire screen once. Do not give this shadow a face, body, or three-dimensionality. After the shadow passes, the girl opens the single grimoire supported by her left hand with her right hand and turns one paper page. The edge of the paper page hard-cuts to the next screen. On the page, only a geometric star chart appears — no readable text. Three thin frames snap into a tile arrangement, simultaneously showing the eye reflection, the star-shaped lock, and the broken magenta trace. The girl takes one step forward. A low rear camera rises to over-shoulder, revealing the massive arched window in the depth and a constellation missing exactly one star. The outline of a giant English letter "A" slides in from off-screen, becoming a hard letter mask through which only the next footage is visible. The girl turns her right palm upward, and a single star-flower magic circle unfolds above her palm. The circle consists of an antique gold outer ring, magenta fine lines, and a purple-crystal center — with exactly one star missing in black. From the missing point, a red-purple straight line runs sideways and hard-cuts to a chest-up composition. The camera whips sharply from the magic circle to her face. The girl, in the order eyes -> brows -> eyelids -> mouth -> gaze, understands the anomaly — not frightened, but shifting into quiet resolve. She dismisses the magic circle, closes the grimoire with her right hand, and places her right hand on the closed cover. The grimoire's purple crystal and the brooch each light up once in response. Finally, black, deep purple, and ivory rectangular tiles snap hard together to assemble a single frame. End type: pose lock. Left: the girl in chest-up three-quarter front. Right: sufficient black negative space. On the right, display the English title "LILIA ASTRA: THE STOLEN STAR" once, with completely correct spelling. Below it, display "COMING SOON" once. No other text, job titles, names, kanji, hiragana, katakana, pseudo-letters, or unreadable symbols. The girl holds one closed grimoire with her left hand, right hand resting on the cover, motionless. The flat shadow stops at the right edge of the frame. No new elements enter. Hold the title completely for two seconds. Cut on the exact frame where the tense chord and single drum hit finish their resonance. [Sound] Fully original 15-second title music. Do not imitate existing songs or melodies. Low drone, tense string pizzicato, cold synth pulse, low kick, sparse brush, short walking-bass fragment, short baritone sax, clipped brass accent. Opening: low frequencies and hi-hat. Low kick around 3 seconds. Jazz bass movement around 6 seconds. Short sax and brass riff around 10 seconds. At 13 seconds, place a tense chord and a single drum hit, holding the resonance until 15 seconds. No dialogue, narration, or singing. Sound effects sync to visible actions and occur only at that moment. Only when the leather-bound grimoire opens or closes: a short leather creak. Only when one paper page turns: a dry paper sound. Only when the brass star-shaped lock turns: a short dry brass ring. Only when boots land on the wet stone floor: damp stone footstep sounds. Only when the cape and hair move: light fabric rustle. Only when the purple crystal lights up: a thin crystal resonance. Do not confuse materials. [Prohibited] Different person, face collapse, eye color change, hair style change, outfit simplification, outfit swap, missing accessories, equipment multiplication, grimoire duplication, broken fingers, extra arms, additional characters, crowds, clones, face averaging, combat, explosions, blood, terrified expressions, evil spirits, horror lighting, photorealistic conversion, semi-photorealistic conversion, art style shift, thick outlines, low-detail backgrounds, plastic texture, soft dissolves, liquid morphs, excessive depth of field, camera shake, unreadable text, spelling errors, duplicated title, subtitles, logos, watermarks.

Ink-wash shrimp leaping into a futuristic city—a sheet of rice paper unfurls between skyscrapers in the night, eight black-and-white ink-wash shrimp leap out from the paper's surface, their bodies still retaining dry-brush strokes and ink blooms, shrimp whiskers transforming into glowing city rail lines, ink droplets becoming neon rain; the scene features a dramatic contrast in scale, strong depth, cinematic lighting, and a spectacle that stops the eye at first glance—no text, no watermark.

Hand-drawn Japanese 2D anime, warm cel shading, the kitchen of a cozy town diner. 15 seconds, 6 cuts shown slowly, about 2.5 seconds each. Close-up shots centered, appetizing and rich presentation: fat, gloss, steam, generous portions. 1 Directly above the cutting board: a knife slices thick-cut pork loin, marbled with white fat. 2 45-degree angle: meat is laid into a sizzling iron frying pan, oil splatters, edges curl up. 3 Macro: fat renders out, deep brown char marks spread. 4 Close-up: thick ginger-soy sauce is poured in, bubbling and reducing into a rich glossy glaze that clings to the meat. 5 From the side: the pan is shaken, every piece of meat coated in a mirror-like shine, steam rising. 6 Final: ginger pork piled high over a steaming bowl of white rice, sauce dripping down between the grains. Only the food and hands. No faces, no eating scenes, no text, no BGM, no narration. No photorealistic style, no 3D.