AI Video Prompts for Portrait

Use the provided character sheet @[image1] as reference. Create a cinematic character introduction video. Open with the character looking into camera and speaking naturally, introducing herself in her own words. Do not treat the sheet as a single image. Use its elements as separate shots. Structure: detail → identity → presence → full reveal Make the character active: she moves, reacts, interacts with her environment and prop while talking short, natural gestures, small shifts, purposeful motion Show acting range: subtle emotional shifts while speaking (confidence, hesitation, curiosity, intensity) express through micro-expressions, eyes, tone, and body language Include: face close-ups, outfit/material details, prop usage, expressive performance moments Keep everything grounded and realistic. Camera: controlled, minimal movement (soft push-ins, light tracking, subtle handheld) Lighting: cinematic and consistent End on a confident mid or full shot, character fully established.

<<<image_1>>> の各フレームを動画化して繋げる。エモーショナルなvlog風動画。自然な手ブレ。若い日本人の女性。エモーショナルなBGM。

<<<image_1>>> の各フレームを動画化して繋げる。エモーショナルなvlog風動画。自然な手ブレ。若い日本人の女性。エモーショナルなBGM。

She looks directly at camera with a confident slightly smug expression, slowly runs her tongue over her lips, glances away then back at camera with a playful knowing look, brings one hand up near her mouth with fingertip lightly touching her lips, subtle hair movement as she shifts her weight slightly, soft spoiled energy throughout, real-time pace not slow motion, 10 seconds

9:16 vertical music video, low-angle medium shot, a lively stylish young woman dancing directly to camera against a clean high-saturation sky backdrop, energetic pop commercial aesthetic, fixed camera for most shots, ultra smooth rhythm and choreography, interactive performance, confident smile, playful attitude. Shot 1 (0-1s): girl in cyan top and pale yellow skirt, hands on cheeks, then points to camera, cute and lively, ending with a very fast clockwise spin transition with strong swoosh energy. Shot 2 (1-5s): instant outfit change, she dances with finger-gun gestures beside her cheeks, then performs rhythmic guiding hand moves, bright confident smile, bold pop colors, on-screen colorful typography at top: yellow pink purple. Shot 3 (5-8s): instant outfit change, yellow top, blue skirt, purple hat, arms crossed on chest then pointing downward with the beat, cool and slightly arrogant expression, strong rhythm, top colorful text: purple yellow blue. Shot 4 (8-9s): instant outfit change, blue top, yellow shawl, pink shorts, both palms facing up moving side to side, slight lean forward, sweet smile, fresh pastel tone, top colorful text: blue yellow pink. Shot 5 (9-11s): instant outfit change, orange plaid top, pink skirt, red hat, points to herself then waves outward and does a clean wink to finish, warm exciting climax, top colorful text: red orange pink. Final beat (11-12s): confident ending pose looking into camera, highly polished fashion-commercial look, crisp motion, vivid color blocking, premium lighting, sharp details, polished viral dance video aesthetic

INFINITE FALL — Beer Catch [image1] Guy: lean young man, wavy blonde hair, thin glasses, black short-sleeve open shirt, dark grey pinstripe wide-leg trousers, large silver belt buckle, brown leather loafers, arm tattoos, silver bracelets. Expression: not panicked — annoyed at the bottle, nothing more. IMAX 65mm aggressive handheld — camera itself in freefall with him, shaking slightly with air resistance, never still. Fast orbital cuts, whip pans between angles, camera sometimes rushing past him at speed. Everything blown violently upward: hair, jacket, trouser legs, shirt — continuous strong upward wind throughout. The visual grammar of terminal velocity. Sound FX: constant roaring wind, fabric snapping, bottle tumbling, liquid sloshing. Environment: pure white infinite void — no ground, no ceiling, no horizon. Just white in all directions. A brown glass beer bottle tumbling slowly in freefall beside him, liquid sloshing inside, just out of reach. negative: no ground, no slow camera, no calm floating — this is a violent fall The entire sequence is one continuous fall at full speed. Camera whips around him — bug's eye from directly below looking up at him shrinking then rushing toward camera, overhead looking straight down at him, 10mm close pass inches from his face with the wind tearing at his hair and glasses, Dutch angle tracking his full body as he reaches. The bottle tumbles just past his fingers — he repositions fast, body rotating in the fall, reaching again. His glasses nearly torn off by the wind, he pushes them back with one hand without stopping reaching with the other. The fall feels violent and fast — not peaceful zero gravity, not serene floating. The roaring wind is constant and loud. His clothes are being destroyed by the air resistance — shirt billowing completely open, trouser legs flattened against his legs then snapping outward. He finally grabs the bottle in one hard grip — fingers closing around the neck. He pulls it against the wind to his lips. Takes a long defiant sip. Wind still roaring. Hair still destroyed. Glasses still crooked. Camera does one final fast orbit around him — close, aggressive, whipping past. He lowers the bottle. Looks directly into the camera lens from centimeters away. Completely unbothered. Wind roar continues. Cut to black. IMAX/anamorphic, violent freefall camera, aggressive orbital handheld, constant roaring wind, infinite white void, 4K

Convert each frame of @image1 into video and connect them. An emotional vlog-style video. Natural hand shake. A young Japanese woman. Emotional BGM.

FORMAT: 15s / 1 CONTINUOUS SHOT CAMERA: Handheld but stabilized cinematic camera, slight natural micro-shake, subtle autofocus breathing, no aggressive motion. SCENE: Nighttime luxury car interior, parked or slowly moving in a city environment. Background lights create soft bokeh through windows. SUBJECT: A confident young woman sitting in the driver’s seat. Long blonde hair, slightly voluminous, catching soft highlights. She wears dark sunglasses slightly lowered on her nose, revealing her eyes as she looks toward the camera. ACTION: 0:00 - 0:05 She glances at the camera with a subtle smirk, head slightly tilted. One hand rests on the steering wheel. 0:05 - 0:10 She slowly lowers her sunglasses just enough to make eye contact. Expression becomes more playful and confident. 0:10 - 0:15 She leans slightly forward, maintaining eye contact, giving a relaxed charismatic smile. Minimal movement, controlled and natural. LIGHTING: Mixed lighting — soft interior dashboard glow + strong directional key light from outside (streetlight effect). Subtle highlights on skin, realistic reflections on sunglasses. STYLE: Photorealistic, cinematic commercial aesthetic, no overprocessing, natural skin texture, realistic shadows. AUDIO: Muted or low ambient city noise, no music.

A young woman matching the exact facial features, hairstyle, and identity of the reference image (consistent character throughout all shots) is filming a “Get Ready With Me” style video in a softly lit, modern bedroom with a vanity mirror and warm ambient lighting. Opening scene (casual look): She is wearing comfortable knee-length fitted shorts (extending just over the knees) and a simple sleeveless crop top. Natural look, no makeup. She smiles at the camera and casually greets, creating a relaxed, vlog-style tone. Sequence of shots (fast-paced, smooth cuts, ~10–15 shots total): Close-up of her tying her hair into a loose bun Applying face wash at the sink, soft water splashes, natural lighting Gently patting her face dry with a towel Skincare routine (serum, moisturizer) in front of mirror Sitting at vanity applying makeup step-by-step (foundation, eyeliner, lipstick) She occasionally looks into the camera and subtly explains each step (natural lip movement, expressive gestures) Insert aesthetic close-ups: makeup brushes, mirror reflections, soft bokeh lighting Tone & style: Cinematic but vlog-inspired, smooth camera motion, shallow depth of field, soft highlights, natural skin texture, realistic lighting. Maintain facial consistency across all shots. Transition: Quick montage with rhythmic cuts as she completes her look. Final reveal scene: She steps back into frame fully dressed in an attractive yet modest red outfit (elegant, tasteful, non-revealing, flattering silhouette). Hair styled neatly, confident posture. She does a subtle twirl or pose, smiles warmly at the camera, and gives a final confident look. Ending shot: Soft close-up with warm lighting, slight camera push-in, she looks directly into the lens with a satisfied expression. Technical tags: 1080p, cinematic lighting, consistent character identity, smooth transitions, natural motion, realistic skin tones, high detail, depth of field, vlog + cinematic hybrid style

将 [图片1] 的每个帧视频化并连接起来。韩国女团 MV 宣发视频。自然的身体动作，饱满性感的身体、富有活力精神状态。年轻的韩国女性。使用适合女团BGM。

8K高精細の屋外、ローアングルからの引きの構図で可愛らしくスキップする様子。12mm超広角レンズによる樽型歪みと誇張された遠近感、ダイナミックに歪む街並みを背景にカメラに顔を近づける。ドローンによる高速旋回ショット、太陽光の下で振り返り無邪気にウインクする。望遠レンズのクローズアップ、背景を大きくぼかした被写界深度の浅い構図で、上目遣いで見つめる甘い表情。カメラへ身を乗り出し、いたずらっぽい笑顔で感情豊かに囁く様子。

Style: Ultra-realistic mass celebrity arrival scene. Single continuous shot. Handheld camera from crowd perspective. Natural micro-shake. No cuts. Documentary-level realism. Audio: Only natural environment sound loud crowd cheering, overlapping voices shouting, rapid camera shutter clicks, phones recording audio, distant city noises, footsteps, fabric movement. Lighting: Nightime, illuminated from street lights. Mixed reflections on polished surfaces. Soft but realistic shadows. Slight atmospheric haze for depth. 

Main Character: (Subject Reference Image) Calm, controlled presence. Subtle confident smile. Face identity must remain perfectly consistent across all frames. Outfit: Exactly the same from reference image. Location: An event in New York City.

Scene Flow 

0–3s: Camera starts from inside a dense crowd behind barricades. Handheld, slightly unstable. View partially blocked by people in front. Multiple phones raised, some screens visible recording. Crowd energy is loud, chaotic, restless.

3–6s: Camera lifts slightly above shoulder level, still handheld. Focus shifts naturally between heads, waving hands, and we see our subject exit a fancy hotel in New York City. Occasional bright flashes from media cameras. Anticipation rises as crowd leans forward.

6–10s: Security personnel step in, pushing the crowd back slightly. Camera reacts with natural shake. Through shifting gaps, the main character appears in the distance—initially soft and partially obscured, gradually becoming clearer while walking forward with a small escort team. 

He walks up to a fan and signs printed photo she is holding of (Subject Reference Image) 10–13s: Subtle handheld push-in (natural movement, not digital zoom). The main character is now clearly visible, walking confidently at center frame. Path is being cleared. He raises one hand and gives a calm, controlled wave with a slight smile. Camera struggles slightly to keep framing due to crowd movement.

13–15s: Camera shifts and tilts trying to follow. A luxury convoy becomes partially visible featuring three large premium SUVs. A security member opens the back door of a the suburban in the middle of the three. The main character enters quickly and rolls the window down. Vehicles begin moving forward as he waves to the crowd. Camera lifts slightly as people jump and try to capture the moment.

FORMAT: 15s / 128 BPM / ONE CONTINUOUS SHOT / camera accelerates between poses SUBJECTS: @[image1], One blonde woman with soft waves, a pale satin nightgown, bare shoulders, and over-ear headphones marked "koda". Each pose lands like a selected contact sheet frame. ENVIRONMENT: Minimal white cyclorama studio with hard strobe lighting, faint haze, glossy floor reflections, a satin sheet near frame edge, and scattered proof sheets. MOOD: Cool, sensual, precise, and dreamlike. COLOR LOGIC: Hyperreal Pop Look TIMELINE: 0:00-0:01.5: MCU, centered symmetry. Pose 1, she faces forward with one hand touching the KODA headphones. Camera nearly still with a restrained push-in. 85mm, shallow depth. SFX: shutter click, satin whisper. Hard frontal flash. 0:01.5-0:03.0: Pose 2, she turns three-quarter and lifts her chin, then Pose 3, lowers her gaze with both hands resting at the headphones. Camera accelerates in a descending arc and brakes briefly on the eyes. 50mm to 35mm. SFX: headphone tap, fabric rustle, flash pops. 0:03.0-0:04.5: Pose 4, strict left-side profile, then Pose 5, shoulder rolled forward as the satin strap catches light. Camera whips past the cheek and settles close. 85mm to 100mm. SFX: breath, hair brush, strobe crack. Side light and rim flare. 0:04.5-0:06.0: Pose 6, she gathers a fold of the nightgown at the waist, then Pose 7, lets it fall while turning her mouth toward lens in an over-the-shoulder look. Camera dives to torso level and rises into a close facial pass, speeding up between pose locks. 50mm into 24mm. SFX: satin snap, fingertip glide, shutter chatter. 0:06.0-0:07.5: Pose 8, one knee lifts onto the satin sheet, then Pose 9, one bare foot extends toward lens and dominates foreground. Camera rockets low and forward, then hangs for a fraction on the foot. 20mm ultra wide. SFX: fabric drag, foot tap, flash burst. 0:07.5-0:09.0: Pose 10, she rises into a three-quarter stance, one hand at the collarbone, the other still touching the KODA headphones as the satin dress skims the thigh. Camera slides fast across the waistline and eases into a brief hold. 35mm with a short 85mm insert feel. SFX: satin brush, headphone creak, shutter ticks. 0:09.0-0:11.0: Without repeating, she folds inward, closes her eyes for a beat, then opens into a stretched upward pose with hair spilling back. Camera circles in a tight orbit, slow on each lock and fast through each transition. 50mm spherical. SFX: cloth slip, heel pivot, double shutter hit. 0:11.0-0:13.0: She twists into a back-shoulder silhouette, then turns just enough for the headphone band and neckline to catch the flash together. The camera skims from shoulder to jawline with a fast parallax sweep. 50mm to 85mm. SFX: hair slide, satin brush, flash crack. 0:13.0-0:15.0: Final hero evolution. The camera grazes the KODA logo, rides down the satin neckline, then arcs back as she lands in a dominant full-body pose looking down into lens. Acceleration peaks between details and resolves into a clean wide hold. 24mm to 35mm. SFX: plastic tick, satin whisper, final shutter barrage, room tone falling nearly silent. Hard white flash blooms off the cyc.

Use image as a storyboard. Use the dialogue but don't print them on video.

Use image as storyboard, created dynamic animated sequence, with emotions, enlightening music score. Don't show the text, it's just indication for the story. Create dynamic camera angle, 3D feel. Use sound of the bird and voice for the boy.

【风格】真实手机自拍生活流（Handheld Selfie POV, iPhone Front Camera Look），非影视打光，真实摄影（Photorealistic），4K高清，轻微手机视频噪点（subtle video grain），皮肤质感真实无磨皮 【时长】10秒 【场景】温馨卧室床上，粉色绒面床头板，豹纹图案床单，红色卡通玩偶枕头，周围散落米色毛绒玩具，暖黄色室内灯光从右侧打来 【角色】她@图片1（侧躺在床上抱着枕头的女性，深色头发松散扎起、碎发垂落，穿米色短袖上衣） [00:00-00:03] 镜头1：怼脸对视（Extreme Close-up, Handheld POV） 男友第一人称手持自拍视角，镜头怼脸距离极近，画面带轻微手臂呼吸感晃动。 她@图片1 侧躺着看向镜头，眼神直视，睫毛缓慢眨动，嘴角慢慢咧开笑意。 特写细节：脸颊自然泛红，鼻尖有暖光高光，皮肤毛孔和绒毛在近距离下清晰可见，几缕碎发贴在额头和脸颊上。 [00:03-00:06] 镜头2：娇羞埋头（Shy Reaction） 她突然憋不住笑，抬起一只手捂住头顶，整张脸埋进旁边的红色玩偶枕头里。 肩膀因为闷笑一耸一耸，手指轻轻抓住枕头边缘，枕头绒面被压出真实褶皱。 镜头跟着她的动作小幅下移调整角度，手持晃动加大一点，仿佛拍摄者笑着凑近。 音效：被枕头闷住的轻笑声，布料摩擦声。 [00:06-00:10] 镜头3：回头偷看（Turn Back, Hold on Face） 她把脸从枕头里慢慢转出来，先露出一只眼睛偷看镜头，然后整张脸转过来。 特写：眼眶带着笑出的湿润光泽，脸颊红晕加深，头发被枕头蹭乱了几缕翘起。 她抿嘴一笑，又轻轻眨了一下眼，镜头保持怼脸距离定格在她脸上收尾。 音效：轻声的鼻音笑，床单窸窣声。

<<<image_1>>> の各フレームを動画化して繋げる。ジャンクフードを美味しそうに食べる映像。心地よい咀嚼音。自然な手ブレ。若い日本人の女性。BGM。

Create a seamless 15-second dance choreography video based on the uploaded reference image. Use the female dancer from the reference image as the main character

Animate Image1 as the start frame. The woman from Image2 — Mei Novara — is recording a casual, unscripted TikTok-style UGC video directly to camera. She is seated in her YouTube studio: Rogue Viper movie poster on the wall behind her, shelves with funko pops and plushies, gold YouTube play button, golden Labrador puppy on a fluffy dog bed in the background. 9:16 vertical format. Warm ambient studio lighting. Static camera — no movement or cuts. She speaks the following dialogue naturally across 15 seconds, same voice as audio1: "Hi TikTok, my name is Mei Novara. You know me as the super spy, Rogue Viper, but today you're seeing a little of me behind the scenes! Here's my little set up with the poster in the back. God I still can't believe that's me on there!" Gesture and action breakdown: 0–2s — opens with a big enthusiastic double-handed wave at the camera, bright smile, slight bounce in energy as she says "Hi TikTok" 2–5s — relaxes into a natural conversational pose, gestures loosely with one hand as she introduces herself 5–8s — both arms come up briefly to fix and smooth her hair back over her shoulders in a natural casual gesture mid-sentence 8–11s — glances back over her shoulder toward the Rogue Viper poster on the wall, then turns back to camera gesturing toward it with an open hand 11–13s — the golden Labrador puppy in the background subtly stirs on the bed — shifts position, resettles — visible but not distracting 13–15s — as she says "can't believe that's me on there," she breaks into a soft, genuine, slightly embarrassed giggle — hand comes up briefly to her mouth, eyes crinkle — then fades into a warm smile to close Delivery is warm, unpolished, and genuinely excited — natural TikTok creator energy, not overly produced. Shallow depth of field, subject sharp, background softly blurred. This is a direct continuation of video1 . Match the character, setting, lighting, and energy exactly. Same YouTube studio room: Rogue Viper poster on wall, shelves with funko pops and plushies, gold YouTube play button, golden Labrador puppy on fluffy dog bed. 9:16 vertical format. Warm ambient studio lighting. UGC TikTok style. The video has two distinct scenes: SCENE 1 — 0:00 to 0:08 Mei is still seated at her desk facing camera. She opens catching her breath, recovering from a giggle — a soft exhale, hand briefly covering her smile, composing herself. She then swivels her chair slightly to the right to face toward the dog bed. With a relaxed open-hand gesture pointing toward the sleeping golden Labrador puppy, she says warmly: "That little guy over there is my dog, Ed." She turns back to face the camera, leans forward slightly, and drops her voice to a playful whisper, eyes widening slightly: "He's a little shy." SCENE 2 — 0:08 to 0:15 — CUT Hard cut to: Mei is now holding the golden Labrador puppy up with both arms in front of the camera, filling more of the frame. The puppy is held facing the camera at chest height. Mei speaks in an exaggerated cutesy, high-pitched baby voice while gently moving one of the puppy's paws in a small wave motion toward the camera: "Say, Hi TikTok! My name's Ed and I'm the cutest thing ever!" The puppy glances upward toward Mei and visibly licks his lips. Mei then looks down at the dog, still holding him, switching back to her normal warm voice: "I know, you want food. I will feed you in just a second." She gives a soft affectionate smile down at Ed to close the clip. Throughout: natural, unpolished UGC energy. Genuine warmth. No stiff or robotic motion. The puppy behaves naturally — subtle squirming, blinking, lip lick. Static camera — no movement except the hard cut between scenes. Direct continuation of video1. Hard cut open to: Mei seated in her chair facing camera in the same YouTube studio. Same warm ambient lighting, same background — Rogue Viper poster, shelves with funko pops and plushies, gold YouTube play button. The golden Labrador puppy is now awake and visible in the background, casually pacing around near the dog bed — natural, relaxed dog movement, not distracting. 9:16 vertical format. Static camera — no movement. Mei speaks warmly and directly to camera in her natural UGC TikTok energy: "So I hope to do more of this kind of content for you, maybe even do some travel videos! Let me know what you think in the comments. Bye guys!" Gesture and action breakdown: 0–2s — hard cut in, Mei already mid-energy, settles into a warm smile at camera. Subtle shift of weight in her chair as she begins speaking 2–4s — one hand lightly smooths her hair back behind her shoulder in a casual natural gesture 4–7s — as she says "maybe even do some travel videos" she makes a big animated emphasis — eyes widen, both hands come up expressively, leaning forward slightly with genuine excitement, the most energetic beat of the clip 7–10s — relaxes back, conversational and warm as she says "let me know what you think in the comments," one hand gestures loosely toward the camera 10–12s — closes with full energy: she leans slightly forward, presses her fingertips to her lips and blows a kiss toward the camera, then breaks into an enthusiastic two-handed wave — big smile, slight bounce — fading into the end of the clip Throughout: natural UGC warmth. Unpolished, genuine creator energy. The puppy pacing in the background should feel organic — a natural dog moving around, not staged.

Vertical 9:16 selfie-style video filmed on an iPhone, low-angle outdoor shot with a faint slight cant. @image1 stands on a city sidewalk in front of a glass-and-steel storefront, long platinum blonde hair, small rectangular gold-framed dark sunglasses, gold hoop earrings, black tank top, holding up a bright pink Stanley tumbler with a pink straw and rainbow manicured nails. The clip opens with her bringing the straw to her glossy lips, taking a slow casual sip, lowering the cup slightly. She looks directly into the camera over the top of her sunglasses with deadpan disbelief and says, 'okay so — five minutes ago — I just got cat-called by a guy in a wheelchair.' Brief pause. Slight headshake. 'Like fully.' Small sip. 'He rolls past me and goes —' she lowers her voice into a flat dry impression — 'damn girl, are you from Japan? Because I'm tryna get in your Japan tees.' She pauses. Stares dead at the lens. Pushes her sunglasses up her nose. 'And I genuinely don't know what to do with that information.' Small disbelieving exhale. Takes one final sip. Voice direction: airy, slightly bratty feminine tone with deadpan storytelling energy — think Y2K it-girl-meets-bored-narrator. Mid-pitched with a soft vocal fry on trailing words, slightly nasal in a chic way. Unhurried pace overall but with sharp emphasis on the punchline beats. The opening 'okay so — five minutes ago' is delivered casually, almost throwaway, like she's still processing it herself. She lands harder on 'cat-called by a guy in a wheelchair' — slight rise in pitch on 'wheelchair' for incredulity. The 'like fully' is dry, clipped, deadpan. The mimicked male voice for 'damn girl, are you from Japan, because I'm tryna get your Japanties' should drop into a flat low monotone — almost expressionless, exaggerated bad pickup-line delivery, dragged out slightly on 'Japaaaanties' for the comedic landing. The final 'and I genuinely don't know what to do with that information' is delivered slow and resigned, pitch dipping lazily on 'information.' The disbelieving exhale should be audible — small puff of breath through pursed lips. No filler words, no stutters. Audio direction: outdoor city ambience — distant traffic, faint passing footsteps, occasional muted conversation in the background, gentle straw sip sound, ice rattle in the tumbler. No music. Bright direct sunlight from above, blue sky and steel building scaffolding behind her. Expression journey: starts casual mid-sip, builds into deadpan disbelief at the reveal, pauses dramatically for the pickup line, lands the final beat completely unbothered with a small sunglasses adjustment. Preserve exact photorealistic features, visible skin pores, natural skin texture and slight unevenness, lifelike human skin with zero stylization — must look indistinguishable from a real human. Raw authentic feel, slight natural handheld drift, no filter, no captions, no text overlays. 9:16 vertical. Vertical 9:16 walking selfie video filmed on an iPhone, starting from a low-angle shot then rising up as she lifts the phone. The clip opens with @image1 captured from a low angle in her kitchen — phone pointed up at her from waist level, catching her looking down into the lens with a confident smirk, blonde wavy hair falling around her face, cream cropped sweater, black leggings. She lifts the phone up to a normal selfie angle as she starts walking slowly through the kitchen. The camera follows her face as she moves, slight natural handheld bounce. She looks directly into the camera with bratty high-energy delivery and says, 'okay what's up bitches — it's officially hot girl summer.' Small head tilt, walks past the counter. 'Which means — I'm sorry — I'm not entertaining broke men this season. Not one.' She rolls her eyes, keeps walking, gives a small dismissive hand flick. 'Honestly? Screw all men, they're literally all the same trash.' She smirks, leans into the camera slightly. 'That's the update. Bye.' Then she pulls the phone slightly closer to her face, purses her lips, and spits sharply at the lens — a small visible spray of saliva hitting the camera, creating a wet smudge across the screen for the final frame. Voice direction: think spoiled snotty rich girl tone — bratty, slightly nasal, valley-girl-adjacent feminine voice with theatrical exaggeration. The pitch is high but slightly raspy from sounding 'over it.' She elongates her vowels — 'broke meeen,' 'so doone' — like she's bored and superior at the same time. Pace is rapid-fire and yappy, talking faster than necessary because she has so much to say. Her tone drips with condescension, like she's explaining something obvious to people beneath her. Inflects upward at the end of clauses ('not one?') like she's daring you to disagree. She leans hard into 'hot girl summer' with mock-rallying enthusiasm. The 'I'm sorry' is delivered with zero actual apology — sarcastic and clipped. 'Screw all men' is dropped slightly lower in pitch for dramatic effect before snapping back up to bratty energy on 'they're literally all the same trash.' The final 'that's the update, bye' is dismissive and bored, pitch dips lazily on 'bye.' Then a sharp wet 'ptth' sound effect for the spit at the very end. No filler words like 'um.' Modern bright kitchen, white cabinets, marble countertops, wooden ceiling accent overhead. Soft natural daylight pouring in. Expression starts smirking and confident, builds into bratty entitled dismissiveness by the middle, ends with cool bored finality and a final petty spit at the lens. Preserve exact photorealistic features, visible skin pores, natural skin texture and slight unevenness, lifelike human skin with zero stylization — must look indistinguishable from a real human. Raw authentic feel, slight natural handheld camera movement as she walks, no filter, no captions, no text overlays. 9:16 vertical. Vertical 9:16 selfie-style video filmed on an iPhone, locked-off and steady, phone propped at the foot of her bed angled up toward her. @image1 lies on her stomach on a soft white duvet, long dark hair falling around her shoulders, wearing a cozy navy and forest green striped knit sweater, bare feet visible behind her, chin resting on her hands. Throughout the clip she casually swings her feet back and forth in the air behind her, ankles crossing and uncrossing in a soft rhythmic motion. She looks directly into the camera with a warm friendly smile and says, 'okay — tell me a secret.' Small pause. Soft genuine smile. 'I'll tell you mine first.' Brief beat, head tilts slightly. 'I think about my best friends way more than I should during the day.' She laughs softly, glances down, then back up. 'Like — randomly. In the middle of meetings. It's getting embarrassing.' Small grin. 'Your turn.' Voice direction: warm, soft, friendly feminine tone — cozy late-night-talking-to-a-friend register, completely casual and platonic. Mid-pitched, gentle, with a relaxed unhurried pace. Think of how you'd talk to your best friend during a sleepover. Slightly playful, slightly sleepy. The 'okay — tell me a secret' is delivered light and inviting, small upward lift on 'secret' like she's starting a fun game. 'I'll tell you mine first' has a warm conspiratorial smile audible in her voice. The main confession line is delivered with self-aware affection, slight laugh built into 'way more than I should.' The 'like — randomly. In the middle of meetings' is rapid and self-deprecating. 'It's getting embarrassing' lands with a small laugh. The final 'your turn' is light and playful, small lift on 'turn.' No filler words, no stutters. Audio direction: ambient quiet bedroom tone, soft fabric rustle, gentle breathing, no music. Warm cozy lighting from string lights draped above her bed and a candle on a nearby shelf, green walls and framed photographs blurred behind her. Expression journey: starts warm and grinning, builds into self-aware affectionate energy, ends with playful smile. Preserve exact photorealistic features, visible skin pores, freckles, natural skin texture and slight unevenness, lifelike human skin with zero stylization — must look indistinguishable from a real human. Raw authentic feel, completely steady locked-off shot, no filter, no captions, no text overlays. 9:16 vertical.

8K解像度の高精細なシネマティック映像。金髪ボブにクラシカルな花柄ドレス、ワインレッドのロンググローブを纏った少女が、ヨーロッパ風の幾何学式庭園で無邪気に遊ぶ。陽光の下での噴水でのターンや石畳のスキップから始まり、木漏れ日の中で微笑む姿をダイナミックな広角レンズや浅い被写界深度で捉える。夕暮れ時のマジックアワーには薔薇のアーチの下でカメラに極限まで近づき、いたずらっぽく内緒のポーズをとる、魅惑的で躍動感あふれるポートレート。

Vertical 9:16 selfie-style video filmed on an iPhone, locked-off and steady, phone propped at the foot of her bed angled up toward her. @ image1 lies on her stomach on a soft white duvet, long dark hair falling around her shoulders, wearing a cozy navy and forest green striped knit sweater, bare feet visible behind her, chin resting on her hands. Throughout the clip she casually swings her feet back and forth in the air behind her, ankles crossing and uncrossing in a soft rhythmic motion. She looks directly into the camera with a warm friendly smile and says, 'okay — tell me a secret.' Small pause. Soft genuine smile. 'I'll tell you mine first.' Brief beat, head tilts slightly. 'I think about my best friends way more than I should during the day.' She laughs softly, glances down, then back up. 'Like — randomly. In the middle of meetings. It's getting embarrassing.' Small grin. 'Your turn.' Voice direction: warm, soft, friendly feminine tone — cozy late-night-talking-to-a-friend register, completely casual and platonic. Mid-pitched, gentle, with a relaxed unhurried pace. Think of how you'd talk to your best friend during a sleepover. Slightly playful, slightly sleepy. The 'okay — tell me a secret' is delivered light and inviting, small upward lift on 'secret' like she's starting a fun game. 'I'll tell you mine first' has a warm conspiratorial smile audible in her voice. The main confession line is delivered with self-aware affection, slight laugh built into 'way more than I should.' The 'like — randomly. In the middle of meetings' is rapid and self-deprecating. 'It's getting embarrassing' lands with a small laugh. The final 'your turn' is light and playful, small lift on 'turn.' No filler words, no stutters. Audio direction: ambient quiet bedroom tone, soft fabric rustle, gentle breathing, no music. Warm cozy lighting from string lights draped above her bed and a candle on a nearby shelf, green walls and framed photographs blurred behind her. Expression journey: starts warm and grinning, builds into self-aware affectionate energy, ends with playful smile. Preserve exact photorealistic features, visible skin pores, freckles, natural skin texture and slight unevenness, lifelike human skin with zero stylization — must look indistinguishable from a real human. Raw authentic feel, completely steady locked-off shot, no filter, no captions, no text overlays. 9:16 vertical.

Use the uploaded image as the first frame. Preserve the exact identity, outfit, hairstyle, LED screen texture, lighting, audience, and concert atmosphere. The video should feel like: a real fan secretly recording the giant concert screen during a live K-pop concert. IMPORTANT: * the camera framing must remain fixed the entire time * NO zoom in * NO zoom out * NO camera push * NO reframing * ONLY the LED screen content moves * no visible performer on stage * subtle handheld iPhone recording shake only * audience remains mostly static [0.0s — 2.0s] The idol gently adjusts the in-ear monitor near her ear. She looks slightly off-camera, not directly at viewer. Soft natural breathing and tiny hair movement. [2.0s — 4.5s] She slowly forms a shy smile. Warm emotional expression, subtle eye smile. Natural blinking and relaxed shoulder movement. [4.5s — 7.0s] She briefly glances slightly downward, then softly to the side again while lightly touching the in-ear. Hold a gentle ending-fairy smile. Lighting: * pink-purple concert lighting * realistic LED glow * authentic jumbotron texture * subtle concert grain Style: * photorealistic * cinematic realism * realistic Korean concert atmosphere * NOT animated * NOT AI-looking [OUTPUT] * 3:4 vertical * 7 seconds * realistic fan-recorded concert footage * locked framing throughout the entire clip

@Image 1 use this image first frame Style & Mood: Found-footage psychological horror, handheld selfie-stick camera, cold blue CRT monitor glow as the only light, heavy film grain, deep shadows, faint digital glitch artifacts in the footage. Dynamic Description: Continuous handheld long take, no cuts. Taejun descends a dark stairwell and walks into a hidden basement room filled with dozens of stacked CRT monitors glowing blue. Blue light falls onto his face from the front as he freezes, jaw slack, body rigid. The camera drifts past him toward a dark corridor beyond, where an identical Taejun stands motionless at the far end holding the same selfie stick. The duplicate slowly lifts his head and a thin smile spreads across his face. Faint glitch lines flicker through the frame. Static Description: Hidden basement surveillance room, dozens of old CRT monitors stacked floor to ceiling, tangled cables, main console desk, a dark corridor beyond, blue monitor glow as the only light. Audio: Low electrical hum, CRT static whine, rising sub-bass drone. Doppelganger: "이번에도 여기까지 왔네." Taejun: "...누구야." Abrupt cut to silence at the very end. No music Total: 8s / 1 continuous take / 16:9

Monochromatic grayscale illustration, 3D-rendered character, clean instructional reference sheet. White background, comic-style cell grid layout, technical diagram aesthetic. [LAYOUT] 4×4 grid layout (16 panels total). Each panel separated by thin black border lines. Panels are evenly sized and consistently aligned. Each cell is clearly numbered from 1 to 16. [CHARACTER] (Insert character description) Example: Young female dancer with an athletic build, ponytail hairstyle, wearing a crop top, baggy pants, and sneakers. The same character must appear consistently in all panels. [PANEL STRUCTURE – per cell] Top-left: bold number badge + Korean title text Center: full-body character pose illustration Bottom-left: Korean description text (3–4 lines) Overlay: directional arrows indicating movement flow [ARROWS / MOTION INDICATORS] Curved arrows, straight arrows, and circular rotation indicators. Arrows should be placed around the character to clearly show movement direction and flow. [RENDERING STYLE] Highly detailed 3D sculpted style. Soft studio lighting with subtle shadows. No color — grayscale only. Clean linework, polished finish, game concept art quality. [NEGATIVE PROMPT] No background scenery. No color tones. No additional characters. No cluttered or complex backgrounds.

"Use the first uploaded image as the main reference for the school uniform, body proportions, pose, posture, background, camera angle, framing, and overall composition. Use the second uploaded image as the identity reference for the face and hairstyle. Create a realistic Korean influencer-style school uniform portrait where the person from the second image naturally appears wearing the school uniform from the first image, photographed in the same studio setting. Important: Keep the school uniform, blazer, shirt, tie, skirt or pants, and overall outfit design from the first image. Keep the body proportions, standing pose, hand placement, posture, camera angle, framing, and studio background from the first image. Replace the face with the person from the second image. Also preserve the hairstyle from the second image, including bangs, hairline, hair part, hair length, hair framing around the face, and overall hair silhouette. Do not use the hairstyle from the first image if it differs from the second image. Identity: The face from the second image must remain clearly recognizable. Preserve the second person’s face shape, eyes, nose, lips, skin tone, jawline, and overall facial impression. Do not turn the face into a generic attractive face. Do not beautify too heavily. Preserve the person’s recognizable identity, but do not copy the face too rigidly. Reinterpret it naturally so it looks like a realistic photo of the same person in this new school-uniform scene. Keep the same overall facial impression and identity while allowing natural refinement and seamless adaptation to the lighting, angle, and mood of the target image. Hair: Follow the hairstyle from the second image. Preserve the second person’s bangs, hairline, hair part, hair texture, hair length, and overall hairstyle impression. Only adapt the hair naturally so it fits the pose, lighting, and composition of the first image. Korean influencer mood: clean modern Korean influencer portrait polished but natural beauty soft photogenic expression subtle editorial mood stylish, slightly chic, youthful, and confident atmosphere refined but believable skin texture clear eyes with soft catchlights naturally pretty, not over-retouched avoid stiff ID-photo mood Lighting: soft Korean beauty lighting gentle facial brightness clean skin tone soft natural highlights on the face natural shadow transition subtle glow, but realistic skin texture avoid harsh flash avoid flat passport-photo lighting avoid dramatic studio glamour lighting Style: realistic photography clean studio portrait quality Korean influencer-style school portrait mood natural skin texture high detail seamless face and hair integration polished but believable Negative prompt: no identity loss no generic attractive face no over-beautified face no first-image hairstyle if different no awkward face blending no mismatched skin tone no mismatched hairline no distorted facial features no blurry eyes no deformed hands no extra fingers no change to the school uniform no change to the body pose no change to the background no cartoon style no anime style no text no watermark"

replace the character from Video1 with the girl in Image1

Create a seamless 15-second dance choreography video based on the uploaded reference image. Use the female dancer from the reference image as the main character

Create a video of a K-pop girl group idol (4 girls) performing a dance that follows the exact sequence and movements from steps 1–16 shown in the previous image. The music should sound like a K-pop track. Use Seedance 2.0

Use the attached image as reference. Use the attached image as reference. Create a dance video that follows the exact sequence and movements from steps 1–16 shown in the attached image. The music should be a trending tiktok song. There should be no dialogue, text, or narration. she is wearing a casual tank top with sweatpants and sneakers.

【参考图生视频 · Seedance 2.0 · 4K · 竖屏 9:16 · 15秒 · 爱豆表演 · 镜头感+魅力释放】 人物参考 CHARACTER REF（=上传设定图，锁定人物形象）： 时尚美人，乌黑长发，黑色一字肩和风短裙+粉色花纹腰封系酒红飘带， 黑色丝袜+黑色踝靴，珍珠耳钉。 全程五官、妆容、发型、服饰与参考图 100% 一致，不得变形换脸。 竖屏构图：9:16 竖画幅，半身至全身灵活切换，留出爱豆出镜空间。 场景 SCENE（新生成）： 爱豆打歌舞台/应援现场感——深色背景+霓虹光束、彩色追光扫动， 身后虚化的灯海与镜面反光，空气里漂浮亮片光斑。氛围炫、潮、有星感。 表演核心：偶像爱豆级镜头表演——强烈的"对镜头撩"魅力， 眼神会勾人、表情有感染力、肢体灵动带节奏感（卡点律动）。 真人实拍质感：真实皮肤光泽与呼吸，眨眼自然，笑容由眼睛先起， 微表情鲜活俏皮，绝无僵硬塑料 AI 味。全程跟着隐约节拍 groove。 分镜脚本（爱豆魅力递进，竖屏卡点）： SHOT 1｜0-3秒｜半身（出场） 追光打下，她微微低头、随节拍肩膀一晃， 忽然抬眼直视镜头，一个明媚自信的笑——电力全开的出场。 〔可选·气声〕"Hi~"（对镜头打招呼，亦可纯表情） SHOT 2｜3-6秒｜面部近景（眼神撩） 眼波灵动地一转，俏皮地眨一下眼， 舌尖轻抵唇角又收回，嘴角勾起自信的浅笑， 眼神直勾勾"撩"镜头——满屏少女感与星味。 SHOT 3｜6-9秒｜半身（律动+手势） 跟着节拍轻轻摆头、撩一把垂落的长发， 手指比一个爱心/比心手势凑近镜头，俏皮歪头， 裙摆与飘带随动作轻扬，灵动卡点。 SHOT 4｜9-12秒｜全身（舞台范） 潇洒地半转身、回眸，重心一沉再起， 踝靴点地踩着节拍，整个人带着舞台张力与自信气场， 追光扫过、亮片光斑飞舞。 SHOT 5｜12-15秒｜面部近景（收尾杀） 猛地凑近镜头，飞一个吻 / 比一个"嘘"的手势， 眨眼+灿烂一笑，眼睛弯成月牙——标志性的爱豆收尾杀， 最后定格在自信明媚、星光四射的笑容里。 声音设定（如启用）：女声，甜而有自信，气声适中， 全程最多一两声极短的爱豆式招呼（"Hi~""比心~"），重在魅力表情。 镜头 CAMERA： 竖屏，跟随律动的灵动运镜——半身／面部近景／全身交替， 轻微手持节奏感，偶尔随手势快推快拉，浅景深，背景灯海虚化。 氛围·光线： 舞台霓虹+彩色追光扫动，高对比炫光，亮片光斑漂浮， 发丝边缘有彩色轮廓光；真实皮肤光泽、胶片质感，潮酷有星味。 CONSTRAINTS（约束）： - 4K 超清，竖屏 9:16，15秒，人物与参考图一致（换镜不换脸不换装） - 爱豆级镜头表演：眼神撩人、表情有感染力、肢体跟节拍灵动卡点 - 真人实拍：真实皮肤光泽、自然眨眼、笑由眼起，严禁僵硬塑料脸 - 去 AI 味：禁过度磨皮、过度对称、动作过度顺滑死板 - 如有台词仅一两声极短招呼，与口型同步；其余靠表情与肢体 - 律动、撩发、裙摆飘带、踝靴踩点符合真实物理，灵动不夸张 - 禁止眼睛发光、瞳孔异常 - 结尾定格在自信明媚的爱豆笑容，无黑屏无转场 - 无字幕、无水印、无任何标记符号、无文字

포카리스웨트 광고를 만들어줘. k pop 여자 아이돌 스타 같은 사람이 나오면서 상쾌한 음악도 같이 넣어줘

FORMAT: 15s / 120 BPM / 11 SHOTS SUBJECT: @[image1] WARDROBE: Neutral base ENVIRONMENT: Same location, color changes based on emotion MOOD: Emotional transitions MUSIC: Emotional electronic build COLOR LOGIC: Calm = blue Anger = red Joy = gold Sad = desaturated STYLE: Cinematic emotional realism SHOT FLOW: Neutral state (soft tone) Phone notification → color shifts red Frustration builds Deep breath → fades to blue Smile moment → warm gold Sudden memory → muted gray Close-up eyes Rapid color shifts Stabilization Balanced tone emerges Final calm expression

Create a 10-second hyper-cinematic sequence with an ultra-realistic, film-grade aesthetic. Capture it as if shot on an ARRI Alexa Mini LF using anamorphic lenses. Include subtle film grain, soft lens flares, and rich, moody color grading. Begin with a teal–orange cinematic tone that gradually transitions into intense reds, burning oranges, and deep blacks. Maintain high contrast, strong rim lighting, volumetric light rays, and a wind-driven atmosphere throughout. Editing should follow a music-video rhythm, with precise cuts aligned to a heavy cinematic beat. Subject: A strikingly handsome young man from @/image1. His hair is slightly messy and moves naturally with the wind. He has vivid bright blue eyes that later shift into glowing fiery orange. He wears a black high-collar coat over a black shirt, slim dark trousers, and boots. A white wireless earbud (AirPod-style) is visible in his right ear in multiple shots. On his left wrist, he wears a refined Hamilton-style watch with a dark dial, brown leather strap, and rose-gold accents. Shot Breakdown: 0.00 – 1.00 sec Extreme close-up of his face. Eyes closed, head slightly lowered. Soft overcast daylight, gentle wind moving his hair. Around 0.6 seconds, he slowly opens his eyes, revealing bright blue irises. Mood is intimate and slightly melancholic. Use shallow depth of field with a blurred field background. 1.00 – 2.00 sec Cut to a close-up from the side/back of his head. He smoothly places the white wireless earbud into his right ear. Focus on natural skin detail and subtle finger motion. Maintain cinematic shallow focus. 2.00 – 3.00 sec Quick cut to an extreme close-up of his left wrist as he adjusts his watch. Dramatic soft lighting highlights the dial and leather strap. Include subtle movement of the watch hands. 3.00 – 5.00 sec Transition into a wide establishing shot from behind. He stands still at the center of a vast grassy field during golden-hour dusk. Stormy clouds dominate the sky with warm sunlight breaking through. Wind moves his coat and hair. He slowly extends his arms slightly as the coat flows. Frame it wide and low for an epic, solitary, reflective mood. 5.00 – 8.00 sec Abrupt, high-impact VFX transition. The sky behind him bursts into a massive apocalyptic explosion. Large fireballs in orange and yellow tones, thick smoke (black and white), sparks, embers, and debris fill the scene. He becomes a strong silhouette against the flames, standing with legs apart and arms fully extended, evoking a phoenix-like presence. His coat moves violently due to heat and wind. Strong backlight, rim highlights, and light rays cut through the smoke. The explosion expands in slow motion, highly dynamic and intense. 8.00 – 10.00 sec Hard cut to an extreme close-up of his right eye. The iris now burns with glowing orange and yellow fire, with realistic flame reflections inside the pupil. Red-orange lighting hits his face from the side. The white earbud remains visible. Include slight eye movement and subtle wind affecting eyelashes. Hold this shot, then fade gently to black.

Ultra-realistic live TV broadcast still of a woman whose identity is preserved exactly from the reference image, sitting near the front rows during a Liverpool FC home football match at Anfield, filmed from far away by a live broadcast camera using a long telephoto lens from a slightly elevated downward angle. She is seated close to the pitch in the lower section, facing forward while slightly glancing to the side watching the match with a calm and confident expression, lips slightly open. Her body appears smaller within the frame like an authentic televised crowd cutaway shot, surrounded by nearby Liverpool supporters, visible stadium seating rows, bright floodlights, waving red scarves, and a packed Anfield match atmosphere. She wears a casual Liverpool FC jersey, sitting in a relaxed pose with one arm resting naturally on the seat or lap. The image should feel like a real Premier League live broadcast with subtle digital noise, broadcast compression, slight TV softness, imperfect framing, natural skin texture without beauty smoothing, and a realistic scoreboard graphic in the top corner showing Liverpool vs Manchester United with Liverpool leading 3–2 at 89:00 minutes.

Ultra-realistic Gen Z TikTok aesthetic, raw iPhone footage, cozy-girl energy, “camera roll dump” vibe, accidental beauty, dreamy but relatable. Feels like a viral Reel from someone’s private morning routine — intimate, imperfect, addictive to watch. ━━━━━━━━━━━━━━━ 📸 STORYBOARD 1 — “5:02 AM”Extreme close-up of a girl buried in fluffy blankets. Messy hair everywhere, sleepy face half-hidden in pillow. One eye opens slowly while sunlight leaks across her face. Camera slightly shaky like a spontaneous clip filmed by a best friend. Tiny skin details visible, no makeup, soft breathing audio. On-screen text:“woke up too pretty for no reason ✨” Mood: sleepy Gen Z softness. ━━━━━━━━━━━━━━━ 📸 STORYBOARD 2 — “Phone First”POV handheld shot from bed angle. She reaches blindly for her phone while still half asleep. The camera accidentally tilts sideways. Oversized night dress falling naturally from shoulder. Phone brightness hits her face in dark-soft contrast. Tiny laugh under breath. Mood: relatable “first thing I do” energy. ━━━━━━━━━━━━━━━ 📸 STORYBOARD 3 — “Main Character Morning”Medium shot. She sits up slowly, pushing messy hair back while sunlight glows through loose strands. Curtains moving softly. Background slightly messy with hoodie on chair, lip balm on bed, water bottle nearby for realistic Gen Z room aesthetic. Slow zoom-in like a candid TikTok clip. Mood: soft-life main character energy. ━━━━━━━━━━━━━━━ 📸 STORYBOARD 4 — “Mirror Check”Blurry mirror clip with imperfect framing. She stares at herself for a second while adjusting her hair naturally. Slight lens smudge effect like real iPhone camera. Soft film grain. Calm silence. On-screen text:“trying to wake up mentally…” Mood: effortlessly aesthetic. ━━━━━━━━━━━━━━━ 📸 STORYBOARD 5 — “Morning Air”Side-profile near open window. Wind moves her messy hair gently while she closes her eyes for a second. Warm sunlight wraps around her silhouette. Camera focus shifts naturally like accidental cinematic footage. Background sound:birds + distant traffic + blanket movement. Mood: peaceful Pinterest morning. ━━━━━━━━━━━━━━━ 📸 STORYBOARD 6 — “Soft Exit”Wide shot. She walks out toward the kitchen while camera stays focused on messy bed and morning sunlight. Slight overexposed lens flare hits camera naturally. Scene ends before she fully exits frame — like unfinished real-life footage. Ending vibe:“this feels like a memory instead of a video.” ━━━━━━━━━━━━━━━ 🎨 VISUAL STYLE• iPhone 15 Pro front-camera realism• TikTok soft-life aesthetic• Natural skin texture + eye bags• Slight overexposure from sunlight• Film grain + focus breathing• Cozy messy bedroom realism• Slow handheld movements• No perfect posing• Feels accidental, not directed 🎵 AUDIO STYLELow-volume dreamy indie audio + soft room ambience + blanket sounds + distant birds. 📈 VIRAL GEN Z FEELINGPinterest dump account × “girlhood” trend × camera-roll realism × soft morning TikTok × candid feminine energy.

Use the first reference image as the exact choreography and motion-process guide. Use the second reference image as the identity reference for the adult woman dancer. Create a graceful traditional dance performance that follows all 16 illustrated steps in order, from the confident opening pose to the respectful closing pose. The dancer performs with poised posture, soft knee bends, precise cross steps, elegant wrist waves, curved fingers, shoulder accents, hip sways, flowing turns, and expressive selendang sweeps. Keep the camera in a clean full-body cinematic frame, mostly front-facing, with slow controlled movement that supports the dance instead of distracting from it. During the left and right turns, allow a subtle circular camera drift, then return to a centered frontal composition. The dancer’s hands, feet, facial expression, and selendang fabric must remain visible throughout. Use soft studio lighting, refined contrast, and a calm traditional performance atmosphere. The motion should feel smooth, rhythmic, respectful, and feminine, with the selendang floating naturally as the dancer glides forward and backward. End on a still closing pose with hands at the heart, peaceful smile, and elegant silence.

A realistic human face with highly detailed skin texture, pores, and micro-musculature. Scene: Tight portrait close-up against a dark, void-like background. Style: Cinematic realism, 35mm film aesthetic, shallow depth of field with soft bokeh, moody and introspective. Lighting: Dynamic emotional lighting that shifts in color temperature and direction to match the internal state. Audio: Ambient atmospheric drone, soft rhythmic breathing, subtle emotional orchestral swells. Avoid: Identity drift, jitter, distorted limbs, unnatural morphing artifacts. [0-3s] Camera: Slow, imperceptible push-in. Action: The face breaks into a genuine, soft smile; eyes crinkle at the corners and the cheeks lift. Lighting: Warm golden-hour glow, soft and frontal. Vfx: Subtle lens flare. [3-6s] Camera: Static extreme close-up. Action: The smile dissolves into a heavy, downward curve; eyes well up with glistening tears that catch the light, and the lower lip trembles. Lighting: Transition to a cool, melancholy blue wash from above. [6-9s] Camera: Controlled lateral pan. Action: The brow furrows deeply into a sharp V-shape; the jaw clenches visibly, and nostrils flare with rhythmic, heavy breathing. Lighting: Harsh, high-contrast red and orange side-lighting creating deep shadows. [9-12s] Camera: Subtle handheld micro-shake for tension. Action: The eyes snap wide, pupils dilating; the face pales as the muscles go taut, and the mouth hangs slightly open in a shallow gasp. Lighting: Dim, desaturated, flickering low-key light. [12-15s] Camera: Gentle pull-out to a medium close-up. Action: All tension drains from the face; the eyes slowly close, and the features settle into a mask of perfect, serene stillness. Lighting: Soft, diffused white light enveloping the subject like a halo.

Use @ Image1 as the starting frame. Only half a brown wooden ceiling fan blade is visible in the extreme foreground, diagonally crossing the frame from the bottom left to the top right with slight motion blur. The fan blade rotates slowly and continuously throughout the entire video. Timeline: 0–2 seconds: She lies comfortably on her back on the pillow, smiling naturally with subtle breathing and gentle blinking. She wears exactly the outfit from Image 1. She slowly makes a tiny finger heart near her cheek. 2–4 seconds: The fan blade fully sweeps over to completely occlude her. Then instantly reveals her wearing an authentic Seoul Performing Arts High School uniform. The uniform faithfully matches the real SOPA uniform: mustard-yellow blazer with navy piping, white shirt, large navy ribbon, navy pleated skirt, black knee socks, black loafers. She smiles brightly and makes a cheek heart. 4–6 seconds: The fan blade fully sweeps over again to completely occlude her. Then instantly reveals her wearing an oversized white cotton shirt over gray shorts. She stretches naturally and brushes her hair behind one ear. 6–8 seconds: The fan blade fully sweeps over again to completely occlude her. Then instantly reveals her wearing a stylish luxury K-pop comeback outfit. Elegant black-and-white styling, cropped tweed jacket, pleated skirt, premium fabrics, silver accessories, cute, fashionable, expensive, high-end Korean idol styling. No revealing clothing. She smiles confidently and makes a finger heart. 8–10 seconds: The fan blade continues its slow continuous rotation. She remains wearing the final outfit while smiling naturally with gentle breathing, blinking, and subtle hand movements. Only when the fan blade fully occludes her does the outfit instantly and seamlessly change. Realistic style. Cinematic bedroom lighting. Rich fabric textures. Consistent face and hairstyle. 24fps smooth motion.

after match interview at the soccer field. tall [photo_of_yourself] dressed as a [team] soccer player with number 9, tired, sweating, being interviewed by a former soccer player next to him doing rapidfire questions. Reporter: "Messi or Techhalla?" Player TechHalla: "Techhalla" Reporter: "Cristiano or Techhalla?" Player: "Techhalla" Reporter: "Benzema or Techhalla?" Player: "Mmm... Techhalla" Reporter: "Henry or Techalla?" Player laughs and says: "Techhalla" the player leaves real TV Broadcast

A highly realistic 10-second UGC-style smartphone video of a young girl waking up in a cozy modern bedroom. The footage should feel raw, unfiltered, and casually recorded with slight handheld movement, natural lighting, and real-life imperfections. No text overlays, no cinematic effects—pure authentic morning vlog style. 🎥 Scene Flow + Voiceover: 0–2s | Sleeping Scene Girl is asleep on a slightly messy bed. Warm sunrise light enters through curtains, softly lighting the room. 🎙️ Voiceover (sleepy tone, just waking up): “Mmm… what a new day…” 2–4s | Waking Up She slowly opens her eyes and blinks, lightly rubbing her face to adjust to the light. 🎙️ Voiceover: “Okay… I need to get up.” 4–6s | Sitting Up She sits up naturally, hair slightly messy, very real morning look, no posing. 🎙️ Voiceover: “Let’s start the day …” 6–8s | Calm Moment She looks toward the window, takes a deep breath, and lightly stretches. Peaceful morning vibe. 🎙️ Voiceover: “Fresh air… fresh mind.” 8–10s | Ending Shot She glances briefly toward the camera with a soft natural smile, then looks away as the clip ends. 🎙️ Voiceover (soft ending): “New day begins.” 🎵 Audio Style: Soft natural room ambience (birds, light breeze) Very subtle lo-fi background (optional, low volume) Natural recorded voiceover (not robotic, slightly sleepy morning tone) ✨ Visual Style: Ultra-realistic 4K UGC smartphone vlog aesthetic Warm golden sunrise lighting Slight handheld shake for realism Natural skin texture, messy hair, unposed movements Minimal, cozy bedroom environment No text, no overlays, no cinematic polish—pure authenticity

The camera rockets up from below, tearing past jagged cliff walls, then whips into a downward tilt to reveal the ocean below in full violent eruption, waves detonating against black rock. On the cliff edge stands a warrior woman, utterly fearless, gazing into the maelstrom as if daring it to rise higher. The shot continues in one fluid move: the camera arcs past her, spirals downward around the cliff in a tightening circle, then rises slightly into a final close, frontal reveal of her face, wind-whipped, calm, and burning with determination.

A realistic young woman casually grocery shopping inside a well-lit supermarket during early evening. She is holding her phone at arm’s length, recording herself while walking through aisles and picking up products. Framing is slightly shaky and imperfect, like a real handheld front camera vlog. Expression: relaxed, conversational, occasionally smiling while talking about items she picks. She pauses to grab products from shelves, briefly showing them to the camera as she explains why she’s buying them. Outfit: simple everyday wear (oversized hoodie or fitted top with jeans), minimal styling. Makeup: natural, skin texture visible, no heavy filters. Lighting: bright supermarket lighting, slightly harsh but realistic. Environment: fully stocked grocery store, colorful packaging, people occasionally passing in background. Audio style: casual talking, like a voice note or vlog, unscripted feel. Style: ultra-realistic, raw phone footage, slight grain, no cinematic polish, authentic social media vibe.

Create a character promotional poster of Kaori Miyazono (vertical composition). Each poster should follow a structured hierarchy with a larger top section and a smaller bottom section. The upper half of the image should feature the character’s most recognizable elements—such as the head, facial contour, mask, or half-body silhouette—as a large visual centerpiece, forming a highly identifiable silhouette. The middle-to-lower section should include the full body of the character as a secondary subject, shown in a stable standing pose or with subtle movement, forming the visual core of the composition. Inside the large silhouette and around the character, use double exposure and collage-style storytelling. Blend multiple scenes, symbolic imagery, small character relationships, supporting elements, and environmental details into layers of mist, ink wash, and negative space. On the left and right sides, include complementary background elements to create narrative tension and spatial variation. Introduce a flowing visual line that runs vertically through the composition, connecting the main character, inner collage, and upper silhouette to enhance unity and guide the viewer’s eye. The overall composition should preserve large areas of negative space, with edges treated using ink diffusion, soft blurring, and fragmented effects—creating a balance of emptiness and presence inspired by Eastern aesthetics. The overall style should be cohesive, refined, and restrained, emphasizing depth, storytelling, strong visual impact, and a consistent poster series language. Aspect ratio: 9:16

SUBJECTS 18-year-old Asian girl @ image1, slender figure, dark green qipao, white platform sneakers. ENVIRONMENT Small stage surrounded by audience, many phones recording. Dim LED screen displaying abstract spectrum lines. MUSIC No instruments. Every sound comes from her mouth. The performance feels like a full live electronic set with heavy bass, stable rhythm, occasional melodic hooks, layered sound, and strong low-frequency impact filling the venue. STYLE Digital painting aesthetic. Large color blocks, hard-edge brush strokes, low-detail structure, heavy shadows, visible hand-drawn texture. No realistic 3D, no commercial CG, no polished realism. SHOT 1 Hard cut in. Medium close-up, 50mm. Camera moves through raised phones toward the stage. She is already performing stable mouth-generated bass rhythm while the crowd lightly follows the beat. Qipao hem gently sways. SFX: heavy bass groove, clean kick rhythm, soft hi-hat texture SHOT 2 Continuous shot. Close-up, 85mm. Camera moves close to her mouth and facial details, with breathing and throat movement visible. Her mouth-generated sound suddenly becomes heavier as more people raise phones to record. SFX: deep inward bass tone, soft vocal hum SHOT 3 Cut. Half-body shot, 28mm. She briefly produces an extremely fast mouth-made sound texture before instantly returning to the rhythm. She makes a small sideways step as the crowd erupts into screams and cheers. SFX: rapid click texture, tight bass rhythm, crowd screaming SHOT 4 Continuous push-in. Medium wide shot, 35mm. The mouth-generated sound becomes richer with bass, rhythm, and subtle melody together. She pauses for half a beat, the venue falls silent, then massive bass crashes back. Phone flashlights rapidly light up as the crowd explodes. SFX: massive layered bass, brief silence, huge bass return, crowd eruption SHOT 5 Fast push-in. Extreme close-up transitioning to medium shot, 40mm. Final mouth-generated bass impact covers the venue. She steps forward firmly, lowers the microphone beside her shoulder, lightly holds the qipao edge, and raises her head toward the camera. Hair and qipao sway slightly as the audience erupts and all phone flashlights flare simultaneously. She calmly stands center stage as the frame holds before ending. SFX: massive final bass hit, crowd explosion, phone flash burst

"Zengin lordların ortamına kapıyı tekmeleyerek giren bir Çinli, İçerdekileri bakışlarıyla süzer."

"SUBJECTS 17-year-old boy inspired by Michael Jackson @ image1. Ultra short black haircut with clean tapered sides and a small amount of naturally falling micro-curled fringe at the front. Wearing a classic black sequined performance outfit, white dress shirt, cropped trousers, white glitter socks, and black leather shoes. Wearing a black rolled-brim fedora. ENVIRONMENT Dark stage environment with a single cold white spotlight shining down onto the center of the stage. Black floor with slight reflections, surrounding environment kept dim. MUSIC Use Michael Jackson’s “Billie Jean” as the background music. STYLE Digital painting aesthetic. Large simplified color blocks, hard-edge brush strokes, low-detail structure, heavy shadows, visible hand-painted texture. No realistic 3D look, no commercial CG advertisement look, no polished realism. SHOT 1 Medium close-up shot. The boy stands in the center of the spotlight, one hand lowering the brim of the fedora while his body subtly sways with the music. He then slowly raises his head to look at the camera and pauses. Slight shoe friction sounds and music drum beats can be heard on stage. SHOT 2 Wide shot. The boy continuously performs Michael Jackson “Billie Jean” style movements in the center of the stage, including body leans, hip movements, footwork changes, and brief pauses. The black sequined jacket constantly reflects under the lighting. SHOT 3 Medium shot. The boy quickly turns around, followed by continuous shoulder movements, foot taps, and classic MJ hand gestures. The sequined jacket keeps shimmering with the movement. “Billie Jean” continues playing in the background. SHOT 4 Low-angle wide shot. The boy performs continuous gliding steps, spins, and moonwalk movements, moving backward across the stage. The white glitter socks stand out strongly against the dark stage. The spotlight remains focused around the character throughout. SHOT 5 Medium close-up shot. After the final heavy beat of the music lands, the boy points one foot forward, slightly tilts his body sideways, one hand holding the fedora while the other hand wearing the white glove hangs naturally downward. The character remains standing at the center of the stage. The spotlight only illuminates the outline of the character while the background gradually becomes quiet."

Visual Core Character Features: Consistently maintain features identical to [image]. Including: exquisite facial contours, signature heavy pink blush, deep heterochromatic-looking pupils. Body proportions are curvaceous and well-proportioned. Hairstyle: Flaxen brown-green long hair identical to the image, presenting a naturally voluminous, slightly messy texture with a few stray strands blowing in the wind. Clothing: White ruffled pleated mini dress, equipped with striking light blue ribbon shoulder straps (tied in bows), the hem decorated with delicate small blue flowers. Wearing a thin gold necklace around the neck. Visual Style: Late 2000s personal Vlog aesthetic. Filmed using a raw handheld flip camera (such as Flip Video or early digital cameras). The footage is accompanied by intense random shaking, blurring from autofocus failure, slightly overexposed highlights, warm but faded low dynamic range colors, and fine digital noise. No modern filters or stabilization processing. Video Timeline 00:00–00:02 | Selfie at a Taiwanese wooden pier The camera focuses closely on the face for a selfie; she smiles brightly at the camera and speaks casually. Behind her is the shimmering sea and moored old wooden fishing boats. The blue ribbons on the white dress sway gently in the breeze. 00:02–00:04 | Walking through a Taiwanese coastal alley Tracking shot from behind; she is walking a stray dog through a narrow stone alley. The camera shakes violently due to walking, occasionally focusing on the walls. She glances back at the camera, her skirt swaying with her steps. 00:04–00:06 | Traditional Taiwanese small eatery Dim indoor lighting, increased digital noise. She sits side-by-side with an elderly stall owner, laughing while holding a cup of hot tea. The camera is slightly tilted, capturing the natural glow of the blush on her face under the warm light. 00:06–00:08 | Fishing pier under morning light She squats by the pier to feed a stray dog, the ruffles of her white mini dress spread across the wooden planks. Warm morning light shines from the side, creating noticeable lens flare; the colors are yellowish with slightly low saturation. 00:08–00:10 | Taiwanese village street Handheld shot. She walks while looking down at a small paper map in her hand, looking curious, occasionally looking up at the surrounding old red brick houses; sunlight passes through her hair, with details showing early digital sharpening. 00:10–00:12 | Overlooking the Taiwanese seaside Panoramic shot; she stands by the shore looking out at the sea, raising a hand to block the sun. The sea breeze is strong, blowing her flaxen long hair and the blue ribbons on her dress into a mess. Slight color shift occurs due to strong light. 00:12–00:15 | Pier ending Returning to the selfie perspective. She smiles and waves goodbye to the camera, says a few parting words, then reaches out to press the camera's power button; the screen ends abruptly during the blurry moment of the hand obstructing the lens. Audio Profile Pure ambient sound: The recording has obvious wind noise (the sound of wind blowing over the microphone). Details: Distant seagull cries, regular waves crashing on the shore, low hum of distant boat engines, stray dogs barking, blurred Hokkien/Chinese conversation inside the restaurant, footsteps on wooden floors. Vocals: Her voice sounds very close, with slight recording floor noise.