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.

@aimikoda

<<<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。

@iX00AI

<<<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。

@iX00AI

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.

@GeorgeWuAI

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

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.

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

@johnAGI168

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。

@KusoPhoto

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

@nimentrix

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.

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。

@cellinlab

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.

@KimAkiyama81

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.

@MaxfusionAI

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.

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。

@KusoPhoto

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.

@MaxfusionAI

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

@ZaraIrahh

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

@victoriawu77

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.

@iamsofiaijaz

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

@ai_gezgini

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

@ChillaiKalan__

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

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

@john_my07

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.

@Inshrah_ali_

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.

@ChangningL29508

Based on <User Portrait>, an exquisitely refined woman positioned at a private bathroom vanity, bathed in intense afternoon sunlight. Her posture is relaxed and languid, yet retains an unmistakable sense of elegance

@Reclyo | 記憶の現像

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

@Inshrah_ali_

"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."

@noman23761

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.

@ChillaiKalan__

A young woman takes a close-up selfie in a softly lit indoor room. A white door frame is visible on the left side of the frame, while beige curtains and a hanging towel appear on the right. Soft natural daylight fills the room. Her dark hair is tied back, with a few loose strands framing her face. She wears small hoop earrings and a white ribbed sleeveless tank top. She begins with a calm, natural expression while looking directly into the camera. CAMERA A single fixed close-up selfie framing is maintained throughout the video, captured at arm’s length and focused on her face and shoulders. No zooming, pushing, or reframing occurs. Only subtle natural handheld micro-sway and gentle breathing motion are present. The camera remains locked on her while the miniature characters perform within the shot. CHARACTERS On her right shoulder (left side of the frame) stands a miniature flame-style swordsman inspired by Rengoku: warm orange-and-crimson spiked hair, golden eyes, a dark fitted martial uniform, a pale cloak with an ember-burned glowing lower edge, and a slim katana faintly wrapped in fire. On her left shoulder (right side of the frame) stands a miniature martial artist inspired by Akaza: short magenta-pink hair, glowing cyan geometric markings across his face and muscular bare torso, dark cropped martial trousers with a sash, and wrapped fists. ACTION The swordsman draws his blade, which ignites with a burst of fire and drifting embers. The martial artist smirks and throws a rapid punch, releasing an expanding ring of cyan energy. The swordsman dashes across her loose hair, leaving behind a glowing ember trail, and unleashes a wide flaming arc slash. The martial artist ducks beneath the attack, slides along her shoulder, and counters with a flurry of afterimage punches emitting flickering cyan light. They leap from shoulder to shoulder, circling around her neck and behind her head while exchanging attacks: a spinning fire slash, a cyan shockwave block, and a quick clash where fire and cyan energy collide in a small brilliant flash. In the final exchange, the martial artist lunges but overshoots and lands lightly back on her shoulder. The swordsman plants his burning blade and holds a calm, confident pose as the embers gradually fade. All visual effects remain miniature and contained, naturally integrated into the room’s lighting with realistic glow, reflections, and environmental interaction. REACTION The instant the blade ignites, her eyes briefly glance toward the fire and widen slightly. As the cyan energy ring expands, she forms a subtle impressed half-smile and releases a gentle breath. As the characters race through her hair, her gaze smoothly follows their movement from left to right. During the bright clash of fire and cyan energy, she reacts with a tiny composed expression—a small breath and a quiet “wow” mouth shape. When the swordsman settles into his final pose, she looks directly at the camera with a soft, delighted smile. Her reactions remain restrained, natural, and believable throughout. No exaggerated movements or loud laughter. SOUND Diegetic sound only: - Soft indoor room ambience - Gentle fabric rustling from the tank top - Subtle movement of loose hair - Low crackles and whooshes from the flaming blade - Soft hums and snaps from the cyan energy - A quiet bright pop during the energy clash - Her subtle breathing and impressed exhale No background music. No non-diegetic soundtrack. STYLE Photorealistic indoor environment, soft natural daylight, handheld selfie-camera realism, natural facial expressions, smooth premium-quality 3D character animation, consistent miniature scale, believable interaction with hair and tank-top straps, realistic fire and cyan energy lighting effects, commercial-grade visual quality, highly detailed rendering, family-friendly presentation, viral social-media aesthetic.

@oggii_0

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.

@0xbisc

<<<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。

@iX00AI

replace the character from Video1 with the girl in Image1

@0xROAS

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.

@MetaBynny

Create a hyper-realistic live sports broadcast screenshot-style image. Use the uploaded authorized face reference as the exact identity reference for the adult female main character. Preserve her facial structure, eye shape, eyebrows, nose, lips, skin tone, smile, and natural expression as closely as possible. Scene: A Morocco vs Brazil football match in a packed international stadium at night. The main character is seated in the spectator stands, captured during a live crowd-reaction cutaway by a professional long-zoom broadcast camera. She is centered in the frame, smiling confidently, relaxed, and looking slightly toward the pitch. Visual style: Real live-TV sports broadcast frame, compressed telephoto perspective, 600mm lens look, shallow depth of field, realistic stadium lighting, mild motion blur, broadcast compression artifacts, slight digital noise, natural skin texture, light sheen from stadium lights, dense crowd behind her. Wardrobe: A sexy but public-appropriate fitted

@ulazaiofficial

Animate only the background and atmospheric elements — subject, typography, and outfit remain completely locked. Slow rolling smoke haze drifts horizontally across the lower third of the frame behind her, low-opacity, dreamy. Red rim light behind her subtly pulses brighter then dimmer once over 5 seconds, like a slow heartbeat. Tiny gold sparkle particles float upward slowly from bottom edge. Film grain flickers naturally. Cream "FRIDAY" letters behind her have an almost imperceptible texture shimmer. Camera fully locked off, no pan, no zoom. 24fps, 5 seconds, cinematic nightclub mood. Negative: subject moving, face changing, lips moving, hands deforming, text warping.

@DeenNash_Fu

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.

@auqibhabib

Style: Hyper-realistic live NBA broadcast footage, authentic televised sports coverage, realistic arena lighting, telephoto broadcast lens compression, shallow depth of field, imperfect live-camera framing, natural crowd reactions, realistic skin textures, subtle compression artifacts, slight interlacing grain, live TV color grading. Duration: 14 seconds Aspect Ratio: 16:9 Camera: Fixed live broadcast camera only, no cinematic cuts, no camera movement. IMPORTANT: The scene must feel EXACTLY like a real NBA live TV Kiss Cam broadcast. The woman: — unbelievably attractive Korean woman in her 20s — long black hair — flawless skin — elegant glamorous makeup — luxurious aura — sophisticated red low-cut summer outfit — subtle jewelry — natural smile and realistic reactions The man: — overweight unattractive man — casual black jacket — glasses — awkward but wholesome energy IMPORTANT AUDIO RULE: ABSOLUTELY NO SOUND OR DIALOGUE FROM THE COUPLE. The couple never speaks. Only arena crowd cheering and distant stadium ambience. Broadcast details: — realistic NBA scoreboard overlay — sports network watermark — live broadcast graphics — crowd in background — realistic arena LEDs — slight motion blur — realistic televised image quality [00:00-00:03] Fixed Kiss Cam shot appears on the arena jumbotron. The woman notices the camera and immediately laughs shyly while casually waving her hand “no” toward the screen. The overweight man beside her looks shocked and confused, then smiles nervously. Crowd begins cheering loudly. No talking from either person. [00:03-00:06] The crowd cheers louder encouraging them. The woman smiles warmly while glancing at the man. He looks overwhelmed and frozen in disbelief. The broadcast camera slightly struggles to keep framing centered realistically like a real live operator. [00:06-00:09] The woman suddenly grabs the man’s cheeks gently and kisses him. The man becomes completely shocked and overjoyed, eyes wide, almost emotionally frozen. Arena crowd erupts cheering and laughing loudly. Realistic shallow depth of field isolates them from crowd. [00:09-00:12] The woman pulls away laughing silently and gives a playful thumbs up directly toward the Kiss Cam. The man still looks stunned and unbelievably happy. Crowd continues cheering loudly while broadcast overlays remain visible. End exactly like a real televised NBA Kiss Cam moment. [00:12-00:14] The man looks in awe and surprise to the camera , the woman smiles with shyness. Audio: ONLY loud NBA arena ambience, crowd cheering, distant announcer echo, stadium reactions, sneaker squeaks, arena music muffled in background. ABSOLUTELY NO dialogue, whispering, laughing audio, or vocal sounds from the couple. Negative prompts: No cinematic movie look, no dialogue, no talking, no subtitles, no unrealistic beauty filter, no anime style, no perfect framing, no dramatic camera movement, no unrealistic reactions, no extra people interacting directly with camera.

@craftian_keskin

'Refer to the facial features of the model in @ image1. The model, wearing the outfits in the @ image 2 @ image 3 @ image 4 @ image 5 @ image 6, gets close to the camera and poses playfully, coolly, cutely, in surprise, and handsomely, with each pose wearing a different

@Patrick

1 0-3s 脸部极致特写，五官精致立体，眼神冷艳锁定镜头，刀马舞起手式：双手从脸颊两侧快速划到胸前定点，指尖动作干净利落 15秒竖屏9:16，24fps，8K超高清，真人写实电影质感，画面稳定无闪烁。顶级颜值东亚年轻女性，五官精致立体，皮肤细腻通透有自然光泽，清透明艳氛围感妆容，发丝根根分明。冷艳自信眼神全程锁定镜头，双手从脸颊两侧快速划至胸前定点，刀马舞起手手势动作干净利落，指尖细节清晰。柔和环形补光，面部光影柔和无死黑，清晰明亮眼神光，镜头轻微匀速向前推进，主体始终在画面中心，第一人称互动感，色彩自然饱和，细节拉满 冷艳冲击，强定帧 开场第一声重鼓卡点，手势动作完全贴合鼓点 2 3-6s 上半身中近景，展示肩颈线条与流畅手臂，刀马舞核心切手手势，配合肩部卡点律动，身体轻微左右摆动，全程眼神不离开镜头 竖屏9:16，24fps，8K超高清，真人写实质感，画面稳定。身材线条流畅紧致的年轻女性，肩颈线条优越，身穿修身显瘦黑色短款上衣，动作连贯丝滑，刀马舞核心切手手势，配合肩部卡点匀速律动，身体随节奏轻微左右摆动，眼神始终锁定镜头。暖调氛围光，明暗层次分明，镜头缓慢水平横移，主体全程在画面中心，无畸变，动作无卡顿穿模 利落卡点，节奏递进 连续3个轻鼓点，每个切手动作精准踩中鼓点 3 6-9s 全身全景，完整展示优越身材比例与舞蹈律动，刀马舞标志性双手划圈+身体wave组合动作，脚步卡点小幅度移动，整体动作舒展有力 竖屏9:16，24fps，8K超高清，真人写实电影质感，画面稳定无抖动。优越头身比女性，腰腹线条紧致，腿部线条修长，身穿修身高腰黑色长裤，动作连贯丝滑无卡顿，刀马舞标志性双手划圈+身体wave组合动作，脚步配合节奏小幅度卡点移动，动作舒展有力。现代极简轻奢白色背景墙，柔和顶光+侧光补光，光影层次丰富，镜头缓慢匀速向后拉远，主体全程保持在画面中心，无穿模变形 舒展大气，节奏拉满 重鼓爆发点，wave动作最高点精准踩中重鼓 4 9-12s 手部+腰胯局部特写，刀马舞指尖定点细节动作，配合腰胯轻微卡点摆动，突出身材曲线与手势细节，动作干净精准 竖屏9:16，24fps，8K超高清，真人写实质感，画面稳定。刀马舞指尖定点细节动作，手指修长纤细，指甲干净精致，配合腰胯轻微卡点摆动，腰腹线条紧致流畅，动作精准利落。柔和侧光勾勒身体轮廓，镜头轻微跟随手部动作匀速移动，焦点始终在手势与身体线条上，画面清晰无虚化 细节拉满，高级质感 连续轻鼓点，每个指尖定点动作踩中鼓点 5 12-15s 从全身快速推镜回到上半身+脸部特写，刀马舞收尾定型手势，挑眉+自信浅笑定格，眼神全程锁定镜头，动作干净收尾 竖屏9:16，24fps，8K超高清，真人写实电影质感，画面稳定无闪烁。顶级颜值身材女性，刀马舞收尾定型手势，双手在胸前利落定点，挑眉自信浅笑，眼神全程锁定镜头，动作干净收尾。柔和环形补光，面部光影柔和，镜头从全身快速匀速推近至上半身脸部特写，最终画面定格在脸部特写，主体始终在画面中心，无畸变，动作连贯无卡顿 收尾炸场，记忆点拉满 最后一声重鼓卡点，定型动作与鼓点完全同步，定格3帧

@AYi_AInotes

Use @ Image 1 as the first frame of the scene. The camera rotates and pushes in. The character suddenly looks up. The character’s facial features should be based on @ Image 2. They begin to roar loudly, full of excitement with a touch of comedic flair, referencing the facial

@Feyber | AI & WEB3

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

@VORTEX_Promos

Young woman from Untitled Element, maintaining her look, dark hair, nose ring, black top/jacket. Scene: A bustling, sunlit London square with blurred pedestrians in the background. Style: High-quality, realistic street photography, shallow depth of field, natural lighting. Lighting: Bright, natural daylight, soft sunlight reflecting off pavement and buildings. Audio: Ambient city sounds, distant traffic, footsteps on stone, sudden scuff of shoes, quick rising sound. [0-4s] The subject is walking confidently toward the camera through a busy London square, with blurred figures moving behind her. Her hair moves naturally with her gait. Camera: Smooth handheld follow shot, moving backward at the same pace as her walk. Action: She walks with a steady rhythm, glancing left and right, appearing relaxed and self-assured. Lighting: Bright, even natural daylight. [4-7s] The subject stumbles unexpectedly on the pavement. She quickly loses her balance and falls to the ground, hands hitting the pavement to break the fall. Camera: Static, tracking her descent, then holding low. Action: She trips, falling forward. Her hands and knees make contact with the pavement. Lighting: Sharp sunlight catching the sudden motion. VFX: Minor dust particles kicked up from the ground. [7-10s] In one fluid, rapid motion, she pushes herself back up to a standing position, brushing off her jacket as she stands. Camera: Quick, subtle tilt up with the movement, then stabilizing. Action: She springs up instantly, using her core strength. She smooths her jacket and hair in a hurried, embarrassed motion. Lighting: Bright sun illuminating her face as she stands. [10-13s] She glances around rapidly, eyes darting to see if anyone noticed her fall, then immediately forces a bright, calm smile to compose herself. Camera: Slow push-in to a medium close-up, focusing on her expression. Action: Her face transitions from a brief moment of shock to a polished, confident expression. She looks directly into the camera lens with a nothing happened smile. Lighting: Warm, soft natural light on her face. [13-15s] She turns slightly and resumes walking away from the camera, blending back into the crowd. Camera: Slow pull-out to follow her as she walks away, keeping her in frame. Action: She continues walking with a brisk, natural step, putting distance between her and the spot of the fall. Lighting: Natural daylight, soft lens flare as she moves forward. Avoid: Identity drift, teleporting limbs, distorted face during the fall, unnatural rapid animation.

@alzina3691

The Original Team 7: Kakashi, Naruto, Sasuke, and Sakura sharing a rare, joyful moment together.

@YaseenK7212

<Image1>の女性を正面から固定カメラで撮影した映像。 女性の表情を下のAUコード(Facial Action Coding System)の順番に1秒ごとに表情を変えて。 AU-46 AU-34 AU-28 AU-9 AU-38 AU-44 カメラは固定。女性はしゃべらない。

@eijo_AIart

Convierte cada frame de en video y conéctalos. Video estilo vlog emocional. Tremor de mano natural. Hombre joven español. Música de fondo emocional.

@MiguelMaestroIA

Adjusts necklace slowly, then looks straight up into camera with direct eye contact. living room couch corner, soft ambient lighting, f1.3 handheld. Warm tan, natural glowy skin. faint ambient sounds of the space, breath just audible, lo-fi barely underneath, voice as the hero.

@brandiseer