KitKat Break Family Commercial

Create a 15-second ultra-realistic cinematic pizza-making sequence featuring the girl from the uploaded reference image as the exact character reference. Preserve her facial identity, green-hazel eyes, long jet-black hair, skin tone, facial structure, and overall appearance consistently throughout every shot. Dress her in a stylish black apron over her white fitted T-shirt, with her hair tied into a practical low ponytail. The video opens with an intense close-up of her holding a freshly baked pizza slice toward the camera. She takes a confident bite as molten cheese stretches dramatically from the slice, steam rising around her face. She immediately turns toward the counter and begins making another pizza. She spins a round piece of dough high above her head, catches it perfectly, and slaps it onto the counter as flour bursts into the air. The camera follows the movement with a fast whip-pan. She rapidly spreads bright-red tomato sauce across the dough, then throws fresh mozzarella, ricotta, and pepperoni onto the pizza with energetic precision. Use fast macro cuts of sauce swirling, cheese landing, and pepperoni bouncing onto the dough. She slides the topped pizza into a blazing stone oven. Extreme macro shots show the crust rapidly puffing into huge leopard-charred bubbles, pepperoni curling into crispy cups, cheese bubbling and melting, and heat distortion shimmering around the pizza. She pulls the finished pizza from the oven, scatters fresh basil over the bubbling surface, then lifts one slice high. A huge molten cheese pull stretches between the slice and pizza as she gives the camera a confident satisfied look. Finish with a dramatic close-up of the golden blistered crust, melted cheese, crispy pepperoni, fresh basil, and steam filling the frame. Style: Premium cinematic food commercial, female chef protagonist, aggressive handheld camera, whip pans, smooth tracking, extreme macro food photography, dramatic blue-and-warm-amber lighting, realistic dough and cheese physics, natural steam, oven heat distortion, detailed skin and hair, shallow depth of field, cinematic film grain, photorealistic, ultra-detailed, 4K HDR, 24fps, 16:9. Audio: Natural diegetic sounds only — dough slapping, flour scattering, sauce spreading, toppings landing, oven roar, bubbling cheese, crust crackling, basil flutter, and final bite crunch. No music, dialogue, subtitles, logos, text, or watermark.

Create a 30-second authentic 1980s Japanese game-show broadcast sequence inspired by classic Japanese obstacle-course television. Realistic live-action footage, broadcast-camera aesthetics, natural handheld movement, analog film grain, slightly washed colors, chaotic energy, practical stunt physics, and no modern visual artifacts. No reference images provided; generate everything from this description. 0–5s — Wide Establishing Shot: A young Japanese man in his late 20s, wearing a red tracksuit and white safety helmet, sprints onto a massive horizontal rotating log above a deep muddy pit. The log spins continuously beneath him while several giant padded wrecking balls swing across the path. The camera tracks him with imperfect handheld broadcast movement. 5–10s — Medium Action Shot: The first wrecking ball swings toward him. He ducks desperately, rapidly shuffling his feet to maintain balance as the rotating log accelerates. His arms flail naturally, and muddy water splashes below where other contestants have fallen. 10–15s — Close Action Shot: A second padded wrecking ball strikes his shoulder, sending him spinning off balance. He drops onto his knees and desperately hugs the rotating log as his body slides around its wet wooden surface. Strong motion blur and realistic momentum. 15–20s — Dynamic Tracking Shot: He ends up hanging underneath the rotating log, gripping it with both hands while his legs kick through the air. He struggles to crawl toward the opposite platform as the log continuously rotates. His grip gradually weakens and his fingers slip. 20–25s — Major Impact: He finally loses his grip and falls into the deep muddy pit. He hits the water with a huge, physically realistic explosion of brown mud and water. The camera reacts with chaotic handheld movement as the splash briefly fills the frame. 25–30s — Comedic Ending Shot: He resurfaces completely covered in mud, helmet crooked and face stunned. He slowly raises one defeated fist toward the camera while the rotating log continues spinning behind him and a wrecking ball swings overhead. Maintain the authentic chaotic game-show atmosphere. Visual requirements: High-fidelity realistic live action, accurate rotating-log physics, believable human movement and impacts, realistic mud and water simulation, practical-stunt appearance, coherent character identity throughout, 1980s Japanese television broadcast grain, subtle analog noise, imperfect exposure, natural motion blur, period-accurate camera movement, no CGI-looking surfaces, no modern cameras, no futuristic elements, no text overlays, no subtitles.

Ultra-realistic summer café scene with subtle frozen-time VFX. One continuous 20-second shot. Natural handheld camera with a smooth backward track and one gentle side move. Bright daylight, warm terrace atmosphere, realistic shadows, soft film grain, no dramatic action styling. One adult man seated at an outdoor café table, wearing casual summer clothes. One adult waitress carrying a glass of beer on a tray. A few adult customers remain in the background. Sunny café terrace with small tables, umbrellas, chairs and a quiet city street. Photorealistic pause-time effect, simple body motion, stable anatomy, realistic glass handling, coherent background extras, natural summer atmosphere, seamless camera continuity, no fall, no injury, no direct body repositioning. 0-5s: Medium-wide tracking shot - The man waits calmly at his table. The waitress approaches with a cold beer on a tray. 5-8s: Gentle push-in - Her foot catches slightly on the edge of a chair. She loses balance for a moment. The beer glass begins sliding off the tray. 8-11s: Close-up - The man snaps his fingers. Time pauses instantly. The waitress becomes motionless in a tilted but stable pose. The beer glass and a few droplets remain suspended close to the tray. 11-16s: Slow side move - The man stands, calmly takes the suspended beer glass, places it on his table, then moves the chair slightly out of the waitress's path. He does not touch her. 16-20s: Push-in to medium close-up - He sits back down and snaps again. Time resumes. The waitress regains her footing naturally and looks confused when she sees the beer already on the table. The man smiles and says in English: "Perfect timing."

15 second vertical comedy clip, 9:16, photorealistic, shot like a real phone video that turns into a fast fashion montage. Cut driven, handheld, no music. MAYA. 27, olive skin, long chestnut brown wavy hair with sun lightened strands, dark brown eyes, gold hoops, layered gold necklaces, thin bracelets. Wears a fitted ivory sleeveless square neck top, high waisted colorful print resort trousers, thin tan belt, barefoot. Very expressive face. LENA. 28, tall, golden skin, long dark espresso brown glossy waves, hazel brown eyes, gold earrings, calm and confident. Same face, same hair, same body, same age in every shot. Only her clothes change. SETTING: a white motor yacht anchored in a calm turquoise Mediterranean bay. White sailboats in the distance, low rocky green coastline on the same side the whole time, cloudless blue sky, bright late morning sun from the same direction in every shot. White deck, steel railings, cream cushions, coiled ropes. Light sea breeze moves hair and fabric. STYLE: natural sunlight, real skin texture with pores, correct hands and fingers, real fabric movement, clear turquoise water, no beauty filter, no plastic skin, no heavy HDR. CAMERA: handheld with small natural shake. Fast whip pans and hard match cuts between outfits. Normal lens, no slow motion, no floating drone moves, no heavy blur. 0.0 to 1.6s Maya stands on the deck, medium close up, sea behind her. She stares off to the right, eyebrows up, mouth open, and leans forward. Maya says, flat and shocked: {No. Absolutely not.} Do not show what she is looking at. 1.6 to 3.0s Camera pushes in. Maya covers her mouth, then drops her hand and points hard to the right. Maya says: {You said ONE outfit!} On the word "outfit" the camera whip pans right along her arm. 3.0 to 4.6s The pan lands on Lena at the bow, wearing an oversized open white linen shirt over a black one piece swimsuit, black sunglasses, flat sandals, big woven tote. Beside her sit one large suitcase, a garment bag and two tote bags. Medium full shot, railing leading toward her. Lena says calmly: {It is one outfit.} Small pause, she lifts one finger: {For now.} 4.6 to 6.0s Hard match cut, same body position. Lena now wears a cobalt blue swimsuit with a white sheer sarong tied at her waist, hair damp at the temples, barefoot. She takes two steps toward camera and points at the water. Lena says: {Swim.} 6.0 to 7.4s A white towel sweeps past the lens, and behind it Lena now sits at a small deck table with fruit and sparkling water, wearing a coral orange halter dress, sunglasses on her head, woven handbag. She lifts the sunglasses slightly and smiles. Lena says: {Lunch.} 7.4 to 8.8s Hard match cut. Lena stands at the railing in an emerald green satin slip dress with gold statement earrings, same daylight. Wind lifts her hair, she turns her head toward Maya. Lena says: {Sunset.} 8.8 to 10.3s Fast whip pan across the cabin. Lena walks past camera in an ivory cropped blazer, matching wide leg trousers, champagne silk camisole, gold heels, small metallic clutch. Camera tracks back one second. Lena says: {Dinner.} 10.3 to 11.8s Hard match cut. Medium close up of Lena in a silver metallic evening mini dress with crystal earrings. She adjusts one earring, completely serious. Lena says: {Emergency.} 11.8 to 13.2s Smash cut to a tight close up of Maya, honestly confused, looking toward Lena. Maya asks: {What emergency?} 13.2 to 15.0s Cut back to Lena, medium shot, silver dress catching the sun, turquoise water, sailboats and green coast behind her. She slides her sunglasses on, gives a tiny smile to camera. Lena says: {Bad photos.} Maya laughs loudly off screen. Lena walks out of frame. Hard end, no fade. AUDIO: only real sound, meaning ocean, wind, boat movement, footsteps, fabric, bracelets, glass, laughter. Dialogue language: English, natural conversational delivery, never theatrical, never both women talking at once. No music at any point. No narration. No subtitles. Last frame: empty yacht deck at the bow, turquoise bay, sailboats and green coastline behind, bright sunlight, gentle water movement. No on screen text, no captions, no logo, no watermark. Negative prompt: music, score, subtitles, on screen text, watermarks, logos, brand names, extra people, two Lenas, two Mayas, changing face, changing hair, changing age, mixed or merged outfits, clothes morphing on the body without a cut, magical transformation, slow motion, drone shots, warped hands, extra fingers, plastic skin, beauty filter, oversaturated colors, moving coastline, changing sun direction, horizontal framing.

Use exactly 2 uploaded image assets. image1 = The adult female lead is the sole and highest-priority character identity reference. Strictly maintain her face, facial feature proportions, skin tone, hairstyle, body type, sense of age, overall temperament, clothing, and accessories. image2 = A Korean adult male wearing glasses is the sole and highest-priority character identity reference. Strictly maintain his face, facial feature proportions, skin tone, hairstyle, glasses, body type, sense of age, overall temperament, clothing, and accessories. Generate a 30-second, 16:9 landscape, 4K, 24fps, hyper-realistic live-action film-grade action comedy short. The scene is a high-rise modern top-floor office / luxury apartment-style space at night, with floor-to-ceiling windows overlooking the city nightscape. The interior includes an open living room, a long hallway, modern furniture, and mixed warm-cool lighting. No anime feel, no game CG feel, no cheap VFX, no slow motion, no pseudo slow motion. Action must be realistic, fast, clear, and cinematic. 【Premise】 This is a pre-choreographed, mutually consensual action comedy performance between two adult actors. The overall tone is light, playful, and competitive — no fear, threat, or coercion. It is not a life-or-death fight, not a vulgar skit, but a high-energy action comedy where "the female lead keeps attacking, and the male lead keeps dodging while disrupting her rhythm with playful cheek kisses." 【Core Dynamic】 The female lead is on the offensive the entire time. The male lead almost never truly fights back — he only dodges, repositions, moves in close, and backs away. His main "scoring method" is not punches or kicks, but using momentary gaps in the action rhythm to suddenly step in, deliver a quick, clear, playful cheek kiss, then immediately pull back. There are 5 cheek kisses total. Each one must be a clear comedic beat. After each kiss, the female lead becomes more annoyed and more serious, continuing the chase. 【Action Principles】 Female lead: Continuously presses forward, using jabs, hooks, elbow strikes, knee strikes, side kicks, high kicks, spinning kicks, turning attacks, and relentless pursuit. The further it goes, the more serious and aggressive she becomes. Male lead: Almost never throws a punch, never delivers real kick or punch counters, no heavy throws or slams. His main movements are only: dodging, retreating, sidestepping, ducking, leaning back, gliding, repositioning, redirecting attack paths, suddenly stepping in, cheek kissing, and immediately backing off. The structure must keep escalating repeatedly: Female lead attacks continuously → male lead dodges continuously → male lead seizes a tiny gap and suddenly delivers a cheek kiss → female lead gets angrier → she attacks again even more fiercely. This structure repeats 5 times. 【Camera Rules】 Action segments primarily use medium shots, medium-wide shots, wide shots, close follow cam, handheld feel, lateral tracking, and slight breathing-like camera shake, clearly conveying spatial movement. Before each cheek kiss, the camera first follows the rhythm of both performers' movements, capturing the male lead suddenly entering the female lead's close personal space. When each kiss happens, do not cut away suddenly, do not switch camera angles. Must use a fast, smooth camera push-in / dolly-in within the same continuous shot: Action medium shot → male lead suddenly steps in → camera rapidly pushes in to medium close-up / close-up → clearly showing the brief cheek kiss, the male lead's slightly smug expression, and the female lead's momentary shock or irritation → camera naturally pulls back as the two separate and continues following the chase. Each kiss lasts approximately 0.3–0.6 seconds, must be clearly visible but very brief. No stopping to strike a pose. 【Male Lead Expression & Personality】 The male lead maintains a composed, playful, slightly cheeky prankster vibe throughout. He is not angry and does not want to actually overpower the female lead; his enjoyment comes from continuously avoiding her attacks and then seizing a momentary opening to deliver a cheek kiss. After each successful kiss, he must show a very brief, natural, slightly smug expression: a subtle upward curl of the mouth, eyes carrying a hint of "you still haven't hit me" playfulness, occasionally a light eyebrow raise. Not lecherous, not sinister, no exaggerated villainous grin. First time: slightly pleased with himself. Second time: more obviously amused. Third time: starting to deliberately provoke. Fourth time: clearly knows the female lead is getting angrier, but still can't help showing a cheeky grin. Fifth time: after the kiss, clearly shows a guilty "I went too far" smile, then immediately runs away. 【Dialogue Rules】 The film has very minimal dialogue — only the following 4 Korean lines are allowed. Do not add any other dialogue, narration, or subtitles. After the first cheek kiss, the female lead says briefly, startled and annoyed: "야!" After the second cheek kiss, the male lead says while casually backing away with a playful tone: "또 실패." After the fourth cheek kiss, the female lead grits her teeth and suppresses her anger, saying: "너 진짜..." She doesn't finish the sentence before resuming her attack. After the fifth cheek kiss succeeds, the male lead immediately turns and runs away, shouting in a not-very-sincere casual tone: "미안!" The third cheek kiss has no dialogue at all — only a clear kiss sound, the female lead's expression, and the immediate chase create the comedic beat. All lines must strictly remain in the original Korean text above. No Chinese dialogue, no English dialogue, no auto-translation. 【Timeline】 0–4 seconds Action starts within the first 1 second. The female lead is already attacking relentlessly in the high-rise living room area, fast and sharp: jabs, spinning elbow strikes, mid-level kicks in continuous succession. The male lead barely throws any offense — he only sidesteps, ducks, glides, and leans back to dodge, moving very calmly. Camera follows closely, establishing the basic dynamic of "female lead keeps attacking, male lead keeps dodging." 4–6 seconds | First cheek kiss The female lead continues pressing forward, throwing a punch then a kick to close in on the male lead. After dodging, the male lead briefly steps in from roughly a 45-degree angle behind the female lead's side — not directly behind her. He then quickly delivers the first brief kiss on her right cheek. Must rapidly push in to a close-up of the face within the same shot, clearly showing the kiss. The female lead freezes for a moment, then says irritably: "야!" The male lead immediately backs off, showing his first smug, cheeky expression. 6–10 seconds The female lead is visibly angrier, raising her attack tempo. She uses low sweeps, high kicks, hooks, and spinning pursuits. The male lead keeps dodging, not counter-attacking, only retreating and evading, occasionally using very brief redirections to change the direction of her attacks, but never launching a real counter. 10–12 seconds | Second cheek kiss The female lead throws a high kick that the male lead barely dodges by ducking low. Seizing the half-beat as her leg comes down, he cuts in from the other side and delivers another kiss on her left cheek. Must again rapidly push in to a close-up of the face within the same shot, clearly showing the moment. After the kiss, he casually backs away saying: "또 실패." His expression is more obviously amused. The female lead gets angrier and immediately charges. 12–16 seconds The female lead begins chasing more fiercely, with bigger, faster, more aggressive movements. She continuously presses forward, spins, throws high kicks, chasing the male lead from the living room to the glass window and then turning toward the open walkway. The male lead almost only performs near-miss dodges: leaning back, slipping around close, ducking low, sidestepping away. The action must feel like "one more moment of hesitation and he would get hit." 16–18 seconds | Third cheek kiss After the female lead's two consecutive attacks miss, the male lead suddenly steps in at the instant she turns her head, delivering another shorter, more sudden, crisper cheek kiss. Still must rapidly push in to a close-up of the face within the same continuous shot, clearly showing the action. No dialogue here — only a brief natural "smack" sound and the female lead's expression. The male lead's expression now carries deliberate provocation and cheekiness. The female lead's eyes clearly turn fiercer, and she resumes the chase. 18–22 seconds The female lead's anger continues to build, and the pursuit becomes more vicious. She uses high kicks, spinning crescent kicks, and knee strikes to close in, almost without pausing. The male lead dodges throughout, retreating into the hallway, weaving around furniture edges, never counter-attacking — only reading her movements and narrowly avoiding them. The male lead's composure begins to carry a hint of comedic panic from being chased, but he still dodges very skillfully. 22–24 seconds | Fourth cheek kiss One of the female lead's attacks grazes past the male lead's face. Using the momentum of her attack, he suddenly steps in close and delivers the fourth cheek kiss. The camera again rapidly pushes in to a close-up within the same shot, clearly showing the action. The male lead still can't help showing a cheeky grin. The female lead grits her teeth, suppressing her anger, and says: "너 진짜..." Before she finishes the sentence, she immediately resumes the chase, not giving him a moment to breathe. 24–27 seconds The female lead enters her most intense pursuit state, with maximum speed and pressure. She throws high kicks and spinning attacks almost without pause, driving the male lead deeper into the hallway. The male lead still does not counter — only continuously retreating at the last moment, sidestepping, ducking, leaning back, like he's dodging for his life. 27–29 seconds | Fifth cheek kiss In the fastest chase and exchange of the entire film, the male lead looks like he's about to get kicked, but dodges at the very last instant, then suddenly and very quickly returns to the female lead's close range, completing the fifth — and most exaggerated, most cheeky — cheek kiss. Must use the clearest continuous push-in facial close-up, clearly showing the action. After the kiss, the male lead shows a guilty "I went too far" smile, then immediately turns and runs away, shouting with a hint of guilt and feigned casualness: "미안!" 29–30 seconds The male lead immediately flees deeper into the hallway. The female lead chases after him without hesitation, still ready to continue attacking. The camera follows both of them rushing out at high speed, and CUT TO BLACK on the clear sense that "this chaos isn't over yet." 【Performance Focus】 Female lead: On the offensive the entire time. Brief shock at the first kiss; increasingly irritated afterward; by the latter half she's essentially chasing him down. Her movements cannot be soft — they must carry real aggression. Male lead: Never truly counters — only dodges, steps in close, kisses once, then backs off. His expression goes from composed and playful to carrying a funny "I might have overdone it" look later, while still maintaining an expert-level ease of movement. Both must move like people who actually know how to fight — realistic movement, realistic momentum, realistic breathing, realistic fabric movement. 【Environment & Physics】 The space must be realistically usable: floor-to-ceiling glass, living room, open floor, long hallway, city nightscape. Light collisions with furniture edges, sudden stops and turns, gliding steps, and weaving around objects are allowed, but no large-scale destruction. No weapons, no guns, no bloody injuries. Action sound effects must be realistic: footsteps, air whooshes, fabric friction, breathing, spatial reverb. 【Sound】 No weird BGM, no piano-style scoring. An extremely subtle low rhythmic ambient bed is acceptable, but action and performance take priority. Key sound effects: footsteps, breathing, punch/kick air whooshes, fabric friction during close dodges, spatial reverb. Each cheek kiss must have a natural brief "smack" sound. The beat of stillness after each kiss must be clear, but no slow motion. 【Strict Prohibitions】 Do not portray the male lead as actively counter-attacking; Do not have the male lead throw consecutive punches or consecutive kicks; Do not shoot the action as mutual fighting; No prolonged standoffs; No slow motion; No animated feel; No game CG feel; No weapons; No blood; No extra characters; No subtitles; No watermarks; No daytime scenes; No old, worn-down, dilapidated scenes; No vulgar intimate scenes; No romantic long kisses; No mouth-to-mouth kissing; No kissing hair; No kissing ears; No kissing air; No facial clipping/merging; No character identity drift; No face distortion; No deformed limbs; No unclear action; Do not shoot the whole piece as a pure romance scene; Do not shoot the whole piece as a slapstick farce — the action itself must remain fast, professional, and cinematic.

HANOI TRAVEL VLOG — 30 SEC No reference image. The woman below is described in words and must be built from the text alone. SUBJECT: one Korean woman, early 20s, the only person the film follows. Small oval face with a soft jawline, large round eyes with double lids, a small straight nose, full coral-red lips, fair skin. Black wavy hair tied low at the nape and pulled forward over one shoulder, with loose strands left at the temples. A small gold hoop in each ear. Real Korean skin texture with visible pores — no doll-like AI smoothness, no beauty filter. The face established in the first shot is repeated exactly in every following shot: same features, same hair, same colour. She never morphs into a different person and no lookalike appears. OUTFIT (identical throughout): burgundy ribbed knit halter top, cream high-waist flared trousers, tan leather belt with a gold buckle, burgundy platform heeled sandals, a thin gold bracelet on one wrist. There is no changing shot. CAMERA: she is filming herself on her own phone. Most shots are selfies with her arm extended; objects and food are shot by turning the phone toward them. 16:9 landscape throughout, no black bars. 26mm phone lens, deep focus, neutral iPhone colour, handheld jolt on every step, autofocus landing a beat late, exposure lagging when she moves from bright to dark, a fingerprint smudge bleeding beside strong lights. No cinematic grading, no studio lighting, no glow fx. Background people stay out of focus and nobody looks at the camera for long. DIALOGUE: lines are short and land in one breath. An interjection plus one short sentence is fine, but never two complete sentences strung together. There is breath between them and they are never rushed into each other. Punctuation is used once — no doubled question marks or exclamation marks. The two Vietnamese greetings are not fluent — just phrases she has picked up. (0:00–0:02) — Hotel window, Hanoi morning reveal. Selfie, low angle. She shoves the curtain sideways and narrow tube houses under bundled cables open up behind her. The window blows out white, then the exposure catches up. Bright grin. Dialogue: "Xin chào~ 하노이 왔다!" Transition: Hard cut on beat (0:02–0:04) — Old Quarter junction, a river of motorbikes. Selfie, stepping out between the bikes. She swings the phone to her face while a stream of helmets and conical hats flows behind her, horns overlapping. Overcast daylight, deep focus. Dialogue: "이걸 어떻게 건너?" Transition: Fast cut on beat (0:04–0:06) — Street café. Selfie, arm short. She pushes a glass with condensed milk settled at the bottom toward the lens until it fills half the frame, eyebrows raised. Low backless stools, a stained yellow French wall behind. Transition: Snap cut (0:06–0:08) — Alley bánh mì cart. Insert, phone pointed down at her hands. A baguette split over the charcoal is handed to her in newspaper and she peels the paper down with her fingertips. Steam rises and a few sprigs of coriander stick out of the split. White tube light on the cart, a parked motorbike beside it. Transition: Cut on natural movement (0:08–0:09.75) — Huc Bridge reveal. She raises the phone from her face and tilts it up until the red wooden bridge crossing the lake fills the frame. Natural daylight, sky blown out behind a banyan tree. Her mouth opens slightly. Transition: Soft cut mid-upward motion (0:09.75–0:12) — Train Street café. Selfie. On a low stool beside the track she is holding a coffee glass in both hands; hearing it come she sets the glass down and pulls her stool back against the wall. She looks at the lens, then sideways, and her face collapses into a laugh as a train comes out of the far end of the lane and passes an arm's length away. Dialogue: "헐 진짜 온닷ㅋㅋㅋㅋ" Transition: Cut on the end of the laugh (0:12–0:13.75) — Old Quarter, the 36 streets. Follow from behind, phone low. She shoulders through the packed lane with the bánh mì, finishes the last piece and folds the newspaper away. Unlit lanterns and signs stacked tight overhead, people pushing past. Overcast afternoon light. Transition: Cut on forward movement (0:13.75–0:15.5) — Back seat of a cyclo. Her hands are empty now — the phone low at knee height in one hand, the rail in the other. The street slides past under the folded canopy, the driver's back swaying in front. She looks out, not at the lens. The music drops a beat, leaving only wheels and horns. Transition: Snap cut (0:15.5–0:18) — Phở shop. From here the image is camcorder: blooming tape, light noise, late focus. The camera is fixed at eye level across the counter, no phone or camera visible in frame. Medium. She sits down on a low blue stool under a hand-painted Phở sign. The owner sets a steaming bowl of beef phở down — thin-sliced beef, rice noodles, spring onion, a side plate of sprouts and basil. Dialogue: "쌀국수! 이거 먹으러 왔어~" Transition: Cut on the bowl landing (0:18–0:20) — Lifting the noodles. Macro, phone lowered to the bowl, shallow focus. She draws rice noodles up out of the clear broth with her chopsticks, steam climbing. The steam crosses the lens and one side of the frame hazes over and clears. Only the broth and the slurping at the next stool. Transition: Cut with the noodles still raised (0:20–0:22) — First mouthful. Selfie, handheld. She pulls in a big mouthful, closes her eyes and opens them. Her shoulders drop and she nods once at the lens. Just after sundown, the white fluorescent light of the shop. Dialogue: "미쳤다 진짜." Transition: Cut where her face softens (0:22–0:23.5) — The broth. Selfie, close. She lifts the bowl in both hands, tips it back, sets it down and lets out a breath. The lens fogs with steam. Sound only. Transition: Cut back to phone image quality (0:23.5–0:27) — Tạ Hiện beer street ★signature. She ste

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.

Duration: 14 Seconds | Aspect Ratio: 16:9 STYLE: Ultra-photorealistic REAL LIVE-ACTION, AAA Hollywood supernatural assassin action, premium realistic Semi-CGI VFX, ARRI ALEXA 65, IMAX, Panavision anamorphic. Fast controlled choreography, brief micro slow-motion ONLY for phase-dodge. CHARACTER: @Image1 = KAIA. Preserve exact face, hairstyle, body proportions and ORIGINAL CLOTHING. TWIN CURVED DAGGERS. Personality: COLD, FOCUSED, EFFICIENT, UNHURRIED—never frantic. LOCATION: Night atop a snowbound mountain fortress: stone battlements, frost-slick walkways, watchtowers, torch braziers under a full moon. Sentries patrol separately. Fortress stays quiet—NO alarm, crowd, or large battle. 00:00–00:03 — SILENT HUNT Camera already moving, low handheld pursuit behind Kaia as she crosses a frosted walkway. Two sentries patrol ahead along the battlement. She waits, motionless in shadow, until one turns his back. WHOOM— short burst of SWIRLING SNOW-ASH. Kaia's REAL BODY physically accelerates past him, trailing translucent frost-grey afterimages. She stops at blade range behind him. SHK-SHK— TWO precise dagger strikes. She catches and quietly lowers him. The second sentry begins turning—Kaia is already gone. 00:03–00:06 — BLIND SPOT Camera slides around a watchtower as the second sentry scans the dark, breath visible in the cold. Kaia silently emerges from his blind spot, pins his weapon arm— SHK-SHK. TWO precise strikes. She quietly lowers him and looks toward three sentries near the gatehouse, expression unreadable. 00:06–00:08 — PHASE-DODGE Kaia crosses silently behind the gatehouse sentries. One unexpectedly notices and swings at her FROM BEHIND. Camera rushes toward the incoming blade—MICRO SLOW-MOTION. Just before impact, Kaia's physical body visibly DISSOLVES into DRIFTING SNOW-ASH and pale moonlit vapor. The blade passes harmlessly THROUGH her swirling form. TIME SNAP—WHOOSH! The ash sweeps around the attacker as camera performs a curved whip-pan. Kaia visibly REFORMS directly behind him—feet → torso → arms → face → TWIN DAGGERS. He turns too late. CROSS-SLASH. ONE precise counter. Tiny camera impact bump. Kaia catches and silently lowers him. 00:08–00:11 — ASSASSIN CHAIN Two sentries remain. Kaia disappears behind a brazier instead of charging. One passes—snow-ash curls behind him. Kaia emerges: TWO STRIKES, catches him, then slips back into shadow. Final sentry sees a fading translucent afterimage and follows it, sword raised. Camera rotates around him—the REAL Kaia is already in his blind spot. SHK-SHK. ONE controlled exchange. She catches and quietly lowers the FINAL SENTRY. ALL ENEMIES ARE DEFEATED. NONE REMAIN. 00:11–00:14 — SILENT AFTERMATH Absolute quiet. Camera tracks backward along the battlement, slower than before. All defeated sentries lie silently along Kaia's infiltration path. Braziers still burn; gates remain intact; NO alarm. Kaia calmly wipes her TWIN DAGGERS and sheathes them. CLICK. Her eyes shift toward distant torchlight. Snow-ash curls around her feet. WHOOM— Kaia silently bursts into the storm. Camera rushes after her but catches only translucent frost-grey afterimages fading into the blizzard, then holds on empty, drifting snow. END. CORE ASSASSIN LOGIC OBSERVE → BLIND SPOT → SILENT APPROACH → PRECISE STRIKE → CONTROL FALL → DISENGAGE → NEXT TARGET. Never frontal brawling or prolonged blade exchanges. PHASE-DODGE: Incoming attack → micro slow-motion → blade almost connects → Kaia visibly dissolves into snow-ash → attack passes through → ash travels around attacker → Kaia visibly reforms at blind spot → precise counter. Use ONLY when directly attacked; do not spam. VFX / CAMERA / AUDIO Speed VFX: Drifting snow-ash + pale moonlit vapor + translucent frost-grey afterimages. During normal bursts, REAL Kaia always physically leads; VFX trails behind. Phase-dodge requires visible dissolve → ash travel → physical reformation. NO lightning, electrical arcs, or teleportation. Camera: NEVER static. Low pursuit, over-shoulder stalking, watchtower reveals, close reactions, reactive whip-pans, curved tracking. FAST during eliminations, immediately CALM afterward: QUIET → FAST → QUIET → FAST → QUIET. Audio: Wind, distant howling, torch crackle, soft footsteps on snow, fabric movement, subtle ash WHOOSH, dagger draw/impact, controlled body movement. No loud battle music or alarms. NEGATIVE: No frontal mass battle, prolonged blade exchange, running fight, lightning/electricity, teleportation, excessive phase-dodge, explosions/destruction, static camera, robotic movement, air-gap dagger hits, surviving enemies, face/body/clothing/dagger drift, broken anatomy, full-3D/game look, subtitles, logo, watermark.