Video-prompter for Music Video

A vertical cinematic shot of a woman wearing a pink short skirt in an indoor room manipulating an invisible portal with her fingertips. The space between her hands reveals a black-and-white manga illustrated version of her face and surroundings, perfectly aligned with the photorealistic world outside. The hand-drawn portal stretches, morphs across her face, and briefly expands full-screen before collapsing back into reality with a finger snap. Reference using GPT Image 2

The dancer in Image 1 is performing a sexy, cool, and intense soul dance. Start with gigolo movements, then transition into a cool soul dance. Dance coolly, alluringly, and happily to soulful music. A 15-second high-quality multi-cut music video. Use your best creativity for the editing, shot sizes, angles, and camera work for each cut. Set a background that fits this person and their dance. Now, show me the best 15-second soul dance MV. Since it's only 15 seconds, just focus on the dancing.

pixel art style, looping aesthetic, relatively still camera. I can no longer test the tires and heart I changed for you.

A powerful surreal psychedelic album-cover artwork that fuses all the reference images into one cohesive scene. In the center stands the rebellious cherub from the fourth image — chubby baby angel beauty groki ai x

Use the uploaded storyboard image as the exact visual reference for the sequence. Use the uploaded character image as the exact character reference. Preserve her facial identity, eye color, skin tone, long straight black hair, body proportions, makeup, and outfit consistently throughout every shot. She wears a hot-pink leather biker jacket over a white crop top, layered silver chain necklaces, gold star earrings, deep red lipstick, and dark oversized pants. Maintain the same recognizable performer in every scene. Create a 15-second ultra-realistic Y2K rap/pop music video inspired by early-2000s music television aesthetics, filmed with an exaggerated ultra-wide fisheye lens. The visuals should feel energetic, glossy, slightly surreal, and heavily stylized, with dramatic lens distortion, dynamic camera movement, and fast beat-synchronized editing. — Light-Up Reveal: Begin in complete darkness inside a long futuristic black corridor. The rectangular wall lights suddenly switch on one after another, creating a rapid chase effect toward the performer. She stands completely still in silhouette with her arms spread. On the final light hit, the overhead lights illuminate her face as she immediately begins lip-syncing directly toward the camera. — Fisheye Close-Up: Hard cut to an extreme fisheye close-up of her face. She leans aggressively toward the lens, performs confident hand gestures, points directly at the camera, and briefly pushes her palm toward the lens, making her hand appear dramatically oversized from the fisheye distortion. Chrome Room: Cut to a glossy futuristic white-and-chrome room. She performs a playful, confident dance with shoulder movements, small footwork, and sharp hand gestures. The camera smoothly slides sideways at knee height while chrome surfaces create strong reflections and parallax. 6–8s — Graffiti/Dollar Set: Hard cut to an abstract orange-and-lime studio filled with oversized glossy black geometric shapes featuring generic dollar symbols. She performs in profile while lip-syncing, then suddenly turns her head toward the camera on the beat. Her ponytail and jacket move naturally with the turn. 8–10s — Dancer Performance: Reveal two anonymous female backup dancers wearing glossy black full-coverage futuristic outfits and dark visor sunglasses. They flank the performer and perform synchronized Y2K choreography while she dominates the center, pointing toward the lens and bouncing confidently to the rhythm. 10–12s — Beam Dome: Cut to a dramatic low-angle shot. She stands on a small pedestal inside a dark futuristic dome as powerful white light beams switch on around her one at a time. She raises both arms and continues performing while the lights create intense silhouettes and lens bloom. — Chrome Macro: Extreme tilted fisheye close-up of half her face against a quilted metallic-silver wall. She gives a playful smirk and delivers a

Generate a single continuous shot.\n\n{ "setting": "Cozy minimalist indoor studio room with off-white walls and dark wood accents", \n "lighting": "Soft diffused warm cove lighting with subtle side fill", \n "weather": "Indoor ambient", \n "color_grade": "Warm natural tones with high-contrast digital overlay pops" }\n\n[SUBJECT ANCHOR — reiterate character visual descriptors]:\nThe young East Asian man with long straight black hair wearing a dark grey hooded windbreaker jacket with visible drawstrings.\n\n[00:00-00:02]: The young East Asian man in the dark grey hooded jacket holds her hood drawstrings near her chin, then smoothly raises both hands, expanding her fingers to form a crisp rectangular geometric frame in front of her eyes. Inside the hand frame, a dynamic 2D cel-shaded anime eye graphic instantly pops into view overlaying her real eyes.\n[00:02-00:04]: She shifts her hand frame downward across her cheek, changing the framing angle to reveal a sharp, manga-style eye and eyebrow graphic overlay that tracks locked between her fingers.\n[00:04-00:06]: Moving her hands upward in a rhythmic motion, a stylized 2D anime smiling mouth graphic appears inside a new lower-face hand cutout frame, matching her head angle.\n[00:06-00:08]: She restructures her gesture, using index fingers to point diagonally across her eyes and nose region, creating a triangular hand frame that displays a vivid triangular vector anime mask filter over her upper face.\n[00:08-00:10]: She flips the triangular hand frame smoothly to the opposite angle over her lower face, holding a horizontal anime artwork banner overlay between her fingertips as the clip holds.\n\n🎤 VOICE PERFORMANCE:\nNo spoken dialogue in this opening segment. The audio performance is anchored by the rhythmic atmosphere of the musical build-up, synced to snappy, clean UI movement sounds.\n\nAmbient: Quiet residential room acoustics with soft low-end air resonance.\nFoley: Sharp digital swoosh and UI snap effects frame-locked precisely to each hand expansion and overlay state shift at 01s, 03s, 05s, 07s, and 09s.\nMusic: High-energy electro-pop/cyberpunk synth melody building in rhythm and intensity.

# Main Prompt - Idol Full-Body Groove (Classroom Ver.) shot: type: r2v aspect_ratio: "9:16" camera: fixed, single continuous shot, no cuts framing: character occupies lower two-thirds of frame, medium shot from waist up, full arm extension should remain within frame character: reference: use attached reference image for full appearance (face, outfit, colors, proportions) art_style: preserve original character art style / cel-shading from reference, do not blend with background style motion: choreography_style: J-pop idol full-body groove - point dance hand accents combined with strong hip/chest movement, wide arm throws, and traveling footwork; energetic and dynamic, not restrained ground_rule: only beat_7 involves a brief hop; all other beats keep at least one foot grounded at all times, weight shifts through full leg and hip engagement rather than staying stiff sequence: - beat_1_2: wide step to the right with full weight transfer, both arms throw outward and up into a diagonal "V" shape, chest pops forward on the accent, hips follow the arm direction - beat_3: arms whip back down and across the body, torso twists with the motion, right hand ends in a sharp point toward the camera - beat_4: quick recover to center, small chest pop plus hip bump to the right on the offbeat - beat_5_6: mirror of beat_1_2 to the left - wide step, arms throw diagonally the other way, hips follow, chest pop - beat_7: energetic accent beat - one clean, controlled hop in place (both feet leave the floor briefly together, land together), arms pump downward on the landing for emphasis; this is the single high-energy peak of the sequence - beat_8: land, feet planted, body drops into a grounded groove - knees bent, torso rolls in a small body wave from chest to hips - beat_9_10: double point combo - right hand points forward with a step forward, immediately followed by left hand pointing forward with weight recovering back, hips keep swaying underneath - beat_11_12: full-body spin-out - a quick 180-degree turn using a pivot step (feet stay grounded, one foot pivots), arms sweep out during the turn, ending facing camera again with both arms opening into a wide "sparkle" gesture - loop: sequence repeats seamlessly from beat_1 tempo: upbeat, driving, high-energy idol-pop tempo; gestures are large and confident, transitions snap rather than drift motion_notes: no slow motion, no speed ramping, natural constant playback speed throughout; beat_7's hop must read as one clean controlled jump-and-land, not repeated bouncing; all other beats stay grounded with movement driven by hip/torso/arm amplitude rather than vertical lift setting: location: after-school classroom, empty of other students time_of_day: late afternoon / early evening, warm light through windows environment_details: rows of desks and chairs as soft silhouettes in the background, chalkboard

An emotionally charged, avant-garde Japanese anime opening sequence with playful, surreal, graphic visual direction. A cute anime girl moves through an endlessly transforming visual world. Multiple variations of the same girl appear, disappear, overlap, split apart, and replace one another, as if different versions of her personality and identity are competing inside the same opening sequence. Full-color Japanese 2D animation, expressive hand-drawn character animation, clean cel shading, highly polished sakuga, 24fps. [Core Visual Goal] Prioritize flatness, graphic design, symbolic clarity, and emotional coherence. The sequence should feel like a moving 2D graphic-design composition rather than a cinematic world. Every visual element must relate directly to the girl, her emotions, her body, her memories, or the story's central symbolic ideas. Do not introduce random decorative motifs or unrelated objects. Do not use imagery just because it looks stylish. Every repeated shape, symbol, prop, or visual metaphor must feel meaningfully connected to the same character and emotional theme. [Overall Visual Direction] Pop, surreal, stylish, cute, strange, slightly unsettling. Very flat visual design. Strong 2D composition over three-dimensional realism. Large areas of flat color. Minimal depth. Minimal volumetric lighting. Minimal environmental realism. Graphic staging over cinematic staging. The screen behaves like a moving poster, a motion-graphics illustration, or a transforming printed design. Backgrounds are simplified into flat planes, cutout-like layers, symbolic spaces, and graphic fields. When depth appears, it should be stylized and brief, used only for emphasis. Flat images may suddenly bend, stretch, fold, rotate, or transform, but they should still feel fundamentally graphic and planar. [Motif Control] Use only motifs directly derived from the main character and her emotional world. Allowed motifs should come from: her eyes, hair, hands, mouth, silhouette, clothing, accessories, shadows, reflections, mirrors, frames, ribbons, simple body fragments, personal symbolic objects, and abstract shapes that clearly evolve from these elements. Motifs may also come from a small number of central emotional symbols, but only if they are consistently repeated and clearly connected to the girl's identity. Avoid unrelated decorative symbols such as random stars, random flowers, random animals, random cosmic imagery, random surreal props, or arbitrary visual clutter unless they are specifically established as core motifs. Limit the motif vocabulary. Reuse the same small symbolic set across the entire sequence. The world should feel unified by recurring, meaningful visual symbols. [Character Direction] A cute

A confident white female rapper @[Image 1](image_1). Double bun braided hair styled high. Wearing a pink Zipp Republic jersey, layered gold chains and cross necklace, gold star-shaped drop earrings, and a small cross tattoo under the left eye. Standing firmly beside the rear quarter panel of a car, swaying weight from heel to toe to the beat. Expressing rhythm with both hands, using cutting motions, pointing, and gesturing as if stacking bars in the air. Vocal Profile: A white woman speaking in a London accent with a Nigerian lilt. Low chest-voice range, crisp consonants, and vocal delivery that strongly punches the end of each bar. Dropping volume to a low murmur between bars. Signature Tic: The moment the hook line starts, thrusting both hands forward to make a double point. However, the moment a bar lands perfectly, dropping shoulders back and raising the chin slightly half a beat before the next line begins. Eye Contact: Staring straight into the lens, blinking slowly and intentionally. In transitions, momentarily dropping the gaze to the man sitting on the car before returning to the lens. The character's appearance must match the reference image 100%. Do not change anything other than the character's appearance. @[Image 2](image_2) - Already image-referenced. White male, early to mid-30s. Short tight black hair, full black beard connected to a trimmed mustache, wide nose, thick lips, solid wide-shouldered build, and prominent tattoos on both forearms. Wearing a red Zipp Republic 2.0 jersey with white outlined graphics and '2.0' numbering on the chest. Layered gold Cuban link chains, black jeans, black low-cut trainers, and a gold watch on the wrist. Sitting on the trunk lid of a red car, placing both feet firmly on the rear bumper for balance. The upper body sways loosely in a relaxed state to the beat, nodding the head low with every snare hit before lifting it slightly. Tapping a thigh lightly with one hand to keep rhythm. Psychological Engine: Possessing a calm sense of intimidation and composure, not flaunting the performance but surrendering to the groove itself. Signature Tic: The chains catching the light with every shoulder roll, while the chin remains stable during nodding. The moment the rapper hits a punchline, turning the face toward her, holding that gaze for one beat before returning to his own rhythm. Eye Contact: Calm, half-closed eyes with a slow, relaxed gaze. Moving sight naturally between the rapper and the lens. The character's appearance must match the reference image 100%. Do not change any other elements. The characters appearing are Western/white only. Both perform singing/rapping with a Nigerian accent.

I walk down the stairs to the stage. I have a microphone in my hand and I sing a quiet song.

Style: Ultra-premium Gen-Z music commercial, hyper-realistic, cinematic 8K, high-end fashion campaign, energetic hip-hop track, fast beat-synced editing, viral social-media aesthetic, realistic skin and fabric textures, natural lighting, polished professional choreography, dynamic handheld + gimbal camera movement, crisp motion blur, bold kinetic typography, premium color grading, no CGI look, no cartoon style, no watermark. Main Character: A confident young female dancer with a stylish Gen-Z fashion look, natural makeup, expressive face, realistic hair movement, fashionable oversized streetwear mixed with luxury accessories. Keep her appearance, outfit, hairstyle, and identity consistent throughout. Scene 1 — 0–3s | Beat Drop Nighttime premium urban location with neon architecture and wet reflective pavement. Extreme close-up of her sneakers hitting the ground exactly on the first beat. Cut rapidly to her eyes, jewelry, hands, and confident expression. She looks directly into the camera. Typography hits the screen: “FEEL THE BEAT.” Letters appear with aggressive kinetic motion, slight zoom, shake, and rhythmic distortion synchronized perfectly to the music. Scene 2 — 3–7s | Dance Explosion Beat drops harder. She launches into a fast, highly polished Gen-Z hip-hop choreography: sharp footwork, body isolations, confident hand movements, quick turns and attitude-driven poses. Camera constantly changes: low-angle tracking → 360° orbit → close-up → wide shot → fast push-in. Use seamless match cuts between movements. Every camera transition lands precisely on the beat. Typography flashes between movements: “MOVE.” “ENERGY.” “NO LIMITS.” Large bold typography briefly fills the frame without hiding the dancer. Scene 3 — 7–11s | Viral Moment Music reaches its fastest section. The dancer performs the signature highlight move directly toward the camera. Camera pushes forward while she moves backward, creating a powerful perspective effect. Quick speed ramp into slow motion for one key movement, then instantly snap back to full speed. Add subtle realistic light streaks, reflections, lens flares, and environmental movement. Typography rapidly assembles around her: “THIS IS YOUR MOMENT.” Each word appears individually on beat with modern kinetic animation. Scene 4 — 11–15s | Hero Finish Final beat. She executes one final sharp move, spins, then stops confidently facing the camera. Music hits a clean final bass impact. Camera performs a dramatic cinematic push-in as the environment briefly falls into shallow depth of field. She gives a confident smile. Final typography appears huge and centered: “OWN THE MOMENT.” Small premium subtitle underneath: “MOVE DIFFERENT.” End on a clean freeze-frame hero shot with subtle camera movement, luxury fashion-commercial finish, realistic lighting, crisp details

15-second cinematic fantasy dark-pop music video, 16:9, 1080p/4K-quality look, ultra-photorealistic, premium high-fashion MV finish.

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

Landscape iPhone video, one unbroken 30-second take, no cuts. LOCATION / TIME Hongdae, Seoul, blue hour. The pavement is still wet from rain. Neon signage is just starting to come on. Use a long, straight stretch of shopfront-lined sidewalk with enough clear depth for the performer and camera to travel roughly 40 meters continuously. SOUNDTRACK This is a music video. The track is the entire audio. The music is NOT playing inside the scene. It is a finished studio recording laid directly over the footage in the edit, exactly like a professional music-video soundtrack. The music must be: - Clean - Loud - Full-range - Mastered - Immediate and front-of-mix - Filling the entire frequency spectrum, including deep sub frequencies Music style: K-pop dance-break instrumental at around 104 BPM. Musical elements: - Hard 808 sub - Tight, snappy claps - Sparse minor-key synth stabs - Layered female vocal ad-libs - Stacked vocal hooks with no intelligible words Energy progression: The track begins sparse and restrained, then transitions into a full drop that carries the entire second half. IMPORTANT AUDIO RESTRICTIONS: NO street ambience. NO traffic noise. NO footsteps. NO crowd noise. NO voices. NO wind. NO environmental sound. NO room reverb. NO outdoor echo on the music. The soundtrack must NOT sound like: - A phone speaker - A car stereo - A busking speaker - Music playing from a nearby store - Music heard from across the street No muffling. No distance effect. No bandpass filtering. The music must remain studio-clean, full-frequency, loud, and immediate throughout. THE PERFORMER A Korean woman in her early twenties. Appearance: - High ponytail - Oversized varsity jacket - Cropped tee underneath - Wide black trousers - Chunky sneakers She is a professional working music-video dancer and immediately reads as one through her movement quality. She travels forward for the ENTIRE 30-second take. She dances for the ENTIRE 30-second take. The forward walk itself is choreography. Walking is never used as a break between dance phrases. Movement vocabulary: - Hip-hop bounce with strong, visible knee action - Chest isolations - Rib isolations - Shoulder pops - Waacking arm circles - Sharp wrist snaps - K-pop point-choreography accents - Quick heel-toe footwork incorporated into her traveling steps Movement density: Maintain roughly 4 to 6 clearly visible choreographic accents per second. The movement remains sustained throughout. She NEVER drops into ordinary walking. Every accent should feel rhythmically connected to the soundtrack. Her movement amplitude follows the music: - Smaller and more contained during the sparse opening - Increasingly confident as the track builds - Biggest and most explosive during the final drop Performance behavior: She occasionally half-sings along to the track without producing audible diegetic vocals. She catches the camera lens, grins, breaks eye contact naturally, then reconnects with the lens. She feels confident, playful, spontaneous, and extremely comfortable performing directly to camera. THE CAMERA Handheld iPhone footage. Landscape orientation. One continuous 30-second shot. NO cuts. The camera operator walks backward ahead of the performer for the entire take, matching her forward pace. Camera height: Approximately chest height. Framing: Keep her centered and framed from head to sneakers for most of the take. Use a wide iPhone lens perspective. She must remain large enough in the frame that: - Her face stays clearly resolved - Her eyes remain readable - Her hands remain clearly visible - Her dance details remain easy to understand Camera behavior should feel authentically handheld: - Mild natural hand movement - Slight rolling-shutter wobble - Small framing imperfections - Autofocus hunts once or twice - Exposure subtly adjusts as she passes bright storefronts Wet pavement and asphalt reflect the neon signage and surrounding lights. DO NOT use: - Gimbal smoothness - Orbiting camera movement - Zooms - Camera rotation - Slow motion - Drone shots - Stabilized cinematic tracking CROWD BUILD 0-4 SECONDS The performer dances forward alone. Ordinary pedestrians are already moving naturally through the background and around her. Nobody appears to know what is about to happen. 4-9 SECONDS One guy who is already visible behind her begins catching the groove. He starts copying her shoulder choreography approximately half a beat late. His participation should initially feel accidental rather than staged. 9-15 SECONDS Three or four additional people gradually join. Each dancer must peel naturally out of the existing pedestrian flow. Entrances can come from: - The left side of the sidewalk - A visible shopfront - Further behind the performer - Other positions already established within the shot Nobody should suddenly materialize or enter from an impossible location. Each person was already somewhere logically present within the continuous environment. 15-21 SECONDS The group grows to approximately 12 to 15 dancers behind her. They remain loosely packed rather than forming a perfect formation. They copy her accents with slight ripple delays. The timing differences should make the sequence feel spontaneous and contagious rather than perfectly rehearsed. 21-30 SECONDS The number of dancers now HOLDS. Do not keep adding more people. Instead, increase the energy. The group gradually tightens into a loose wedge formation behind the lead performer. Choreographic intensity reaches its peak. The lead performer remains the unmistakable visual focus. FINAL 2 SECONDS She throws her hardest, sharpest choreographic accent directly toward the camera lens. Everyone behind her lands the same beat with her. The movement hits hard and feels satisfying. The shot does NOT freeze. The dancers remain physically alive after the accent. Bodies continue breathing and settling naturally as the 30-second frame ends. BACKGROUND PEDESTRIANS Some pedestrians NEVER join the choreography. They continue walking normally around the dancers. Their reactions vary naturally: - Slightly annoyed - Curious - Amused - Indifferent Some carefully edge around the growing dance group while continuing toward their destination. This contrast between dancers and uninvolved pedestrians is essential for making the moment feel real. PHYSICAL REALISM Grounded human biomechanics throughout. Every movement must show: - Visible weight transfer - Proper foot planting - Real momentum - Believable balance - Natural joint articulation - Correct body mechanics No sliding feet. No floating. No impossible limb motion. No rubbery joints. No unnatural acceleration. No teleporting people. No duplicated pedestrians. The lead performer stays the clear focus throughout the entire take. Maintain enough proximity and image clarity that her face, hands, expressions, clothing, and choreography stay clearly resolved even with the wide lens.

The bald man in black suit and fedora sings passionately into the vintage microphone, mouth moving expressively as he croons, hand gesturing with soul, body swaying slightly to the music, fedora tilted, the big band orchestra behind him playing brass

@Image1=MAINIMG @Image2=PIPIMG MAIN="MAINIMG unique subject"; MAIN_FACE="Main screen character facial identity"; MAIN_HAIR="Main screen character hairstyle base"; MAIN_BODY="Main screen character body proportions"; MAIN_C0="Main screen character original outfit base"; MAIN_ACC="Main screen character key accessory logic" PIPCHAR="PIPIMG unique subject"; PIP_FACE="Lower left character facial identity"; PIP_HAIR="Lower left character hairstyle base"; PIP_BODY="Lower left character body proportions"; PIP_C0="Lower left character original outfit base"; PIP_ACC="Lower left character key identification logic" WALL="Background wall layer"; FLOOR="Floor layer"; CHAR="Main screen character layer"; PIP="Lower left observation window layer" subject: "Read MAINIMG and PIPIMG only once and lock the two subjects respectively. MAIN only belongs to the main screen character; PIPCHAR only belongs to the lower left PIP window character. Both are independent characters, no confusion, no premature swapping, no mistaking PIPCHAR for MAIN, and no mistaking MAIN for PIPCHAR. For most of the video, Main screen = MAIN, lower left PIP = PIPCHAR, with a clear position swap only in the final high-speed transition." vocal: "Use the same original Japanese female lead vocal throughout; lyrics are not pre-written, freely improvised Japanese short phrases by the generation side; clear Japanese articulation and lip-sync; strong rhythmic hooks + short phrases + sustained notes; no quoting existing songs, no reading prompt words, no ah/oh/woo loops. No male lead vocals, no male-female switching, no changing singer due to character swaps." music: "150BPM intense Japanese dance music/Electronic House/High-speed Club; huge four-beat kick, tight snare/claps, rolling low frequency, sidechain synth bass, bright supersaw chord wall, metallic percussion, vocal chops, arpeggios, riser effects, impact. No slow intro. 0-13s each segment has clear downbeats and transition feel; 13-15s enter high-density chopped finale, and complete MAIN and PIPCHAR position swap at the end. The lead vocal remains the same female voice, no changing to male, no changing voice identity due to role swap." VOCAL_IDENTITY_LOCK: "0.00-15.00s always use the same original Japanese female lead vocal. Sound is an independent audio layer, does not change with visual character identity, appearance, gender performance, PIP content, or final role swap. Even if PIPCHAR enters the main screen, the female lead vocal must be completely continuous. No male lead, no male-female switching, no dual lead, no changing singer due to character swap." priority: "1 Main screen MAIN recognition established, 2 lower left PIPCHAR recognition established, 3 same female lead vocal throughout, 4 main screen continuous Japanese singing/dancing, 5 main screen sync 3-layer transition, 6 lower left PIP stability, 7 CHAR description change clearly visible, 8 camera, 9 final swap successful." MAIN_IDENTITY_DEFINITION: "MAIN consistency refers to character identity recognition, not identical pixel-level appearance. The goal is not a pixel-perfect copy of the source image, but for the audience to recognize it is the same MAIN regardless of style changes." MAIN_IDENTITY_LOCK: "MAIN fixed attributes: facial bone structure and feature relative positions; eye shape and expression tone; front hair structure and hairstyle base; head-to-body ratio, physique, body proportions; sense of age and overall temperament; key accessory logic. These form the core of MAIN recognition and must be maintained." MAIN_MUTABLE_ATTRIBUTES: "MAIN attributes allowed to change drastically: drawing style and medium; line language; coloring and shading; material representation; 2D/3D/Print/Craft processing; clothing color; clothing material; clothing details and decorations; stage-style modification of the same clothing base; local accessory enhancement or weakening; lighting effects and outline emphasis; degree of abstraction. As long as fixed attributes remain, these changes are valid." MAIN_FORBIDDEN_DRIFT: "MAIN Forbidden: turning into someone else; facial/feature reconstruction; hairstyle base disappearing; physique, age, or gender drifting significantly; unfamiliar clothing completely detached from original identity; key accessory logic disappearing." PIP_IDENTITY_DEFINITION: "PIPCHAR must also maintain consistent character identity. No matter how the angle, movement, or eating state changes in the lower left PIP, it must always be seen as the same PIPCHAR." PIP_IDENTITY_LOCK: "PIPCHAR fixed attributes: facial bone structure and feature relative positions; hairstyle base; body proportions; sense of age and temperament; clothing base and key identification points. The character in the lower left PIP window must always be PIPCHAR herself." identity_repeat: "MAIN and PIPCHAR must always be clearly distinguished. 0-13s main screen = MAIN, lower left PIP = PIPCHAR. Only the final swap segment allows swapping positions. The audio layer does not participate in this swap." MAIN_SCREEN_MODEL: "The main screen consists of three synchronized layers: WALL = back wall/facade; FLOOR = floor/stage floor/ground; CHAR = MAIN character body. The main screen uses a synchronized switching logic where WALL/FLOOR/CHAR enter new segments together at each major transition point." SYNC_RULE: "The main screen uses synchronized three-layer transitions, not complex asynchronous ones. Goal is execution priority, with each segment clearly changing scene." CHAR_RULE: "Main screen CHAR only refers to MAIN body. All main screen character changes only apply to MAIN: face/head/hair/neck/torso/arms/hands/waist/legs/feet/clothing/accessories. Must still be seen as the same MAIN after change." CHAR_TRANSFORMATION_REQUIRED: "Each MAIN description change must be immediately visible. Just changing color temperature, brightness, slight filters, or weak textures does not count as a change. Each time at least two of the following must change: line language, coloring, material, medium, clothing color, or clothing details." WALL_RULE: "WALL is only responsible for background walls/screens/posters/displays/installations. Mysterious large faces, huge eyes, abstract portraits, posters, screens, graphic character impressions, and huge MAIN close-ups are allowed as wall art, but only as wall images, not independent characters." FLOOR_RULE: "FLOOR is only for the ground. Allows huge facial images, huge eyes, abstract portrait LED floors, and fire/water/grass/neon grid/liquid metal/flower field/ice/prism/pixel ground/metaverse data platforms. These must stay on the ground and not become independent characters or change the MAIN body surface." BACKGROUND_EXTRA_RULE: "WALL and FLOOR can absorb two environmental languages: 1 Metaverse/virtual city/holographic data architecture/transparent UI space; 2 Pixel art/8-bit/16-bit/blocky game landscapes. These only apply to the environment layer and must not change MAIN identity." goal: "15-second high-density experimental MV. 0-13s main screen is a synchronized 3-layer MV of MAIN, lower left PIP is a strange additional video of PIPCHAR eating a burger on a black background. 13-15s final 2 seconds enter high-speed finale transition, finally completing the position swap between MAIN and PIPCHAR characters, but the lead vocal always remains the same female voice." dance: "MAIN performs high-energy club choreography at 150BPM: heel-toe fast steps, fast footwork, side shifts, hip beats, shoulder hits, chest pops, arm waves, locking, body rolls, diagonal moves, half-turns, rotations, bounces, high/low position changes, short jumps, rhythmic head turns. MAIN continues clear Japanese singing and dancing from 0.00-15.00s, never standing still, staying center stage until the final swap." dance_timeline: "0-1.5 heel-toe advance+shoulder hit+arm wave | 1.5-3 diagonal move+chest pop+half-turn bounce | 3-4.5 low side step+upward arm sweep+small spin | 4.5-6 fast two-step+torso twist+backward bounce | 6-7.5 side step+arm lock+forward rhythm | 7.5-9 high/low change+fast turn+hip beat | 9-10.5 running step+controlled spin+arm sweep | 10.5-12 reverse step+body roll+jump landing | 12-13 fast cross step+270 turn+move end | 13-13.5 high-speed A | 13.5-14 high-speed B | 14-14.5 high-speed C | 14.5-15 ultimate burst" MAIN_AUTONOMOUS_STYLE: "When MAIN description changes, the generation side must autonomously invent a new visual style distinctly different from the current one. Don't follow a fixed list. Freely change line language, color systems, textures, 2D/3D, print methods, animation media, craft feel, abstraction, clothing colors, and stage details. Goal is for the audience to see ‘the same MAIN described by another visual culture’." MAIN_STYLE_RANGE: "Directions include but not limited to: comic line drawing, high-contrast American graphic, pop art, retro hand-drawn animation, sticker-style, collectible model, plush, clay, paper-cut, collage, picture book, fashion illustration, 3D cel-shaded, paper pulp craft, pixelated, low-poly, mosaic, stained glass, neon, holographic, blueprint, graffiti, Art Deco, off-register print, silkscreen, etc." COSTUME_RULE: "MAIN clothing uses ‘fixed base, variable expression’ principle. Must keep original silhouette, core identification structure, and wearing logic. Changes allowed: colors, materials, decorations, stage enhancements, pattern density, sheen/reflection, layer additions/subtractions. Forbidden: completely switching to a stranger's clothing system or unrelated identity." COSTUME_CHANGE_REQUIRED: "MAIN clothing must have immediately visible stage changes. After 3s, each stage must clearly change color system, material, or details; can't just rely on lighting/temp/filters. Even if visual medium changes, the clothing itself must independently change." costume_vector: 'C0=original; C1=keep silhouette, change primary colors to bright stage colors, add highlight fabrics and decoration; C2=keep base, change to strong graphic two/three-tone blocks, add geometric borders; C3=keep base, change to deep black/dark main + high contrast bright borders, sharpen decorations; C4=keep base, change to pearlescent/iridescent/translucent future materials, different colors from C3; C5=clear white-gold finale outfit.' COSTUME_VISIBILITY_RULE: 'C1, C2, C3, C4, C5 must be clearly different. Failure to judge stage by clothing is considered a clothing change failure.' costume_timeline: '0-3 C0 | 3-6 C1 | 6-9 C2 | 9-12 C3 | 12-13 C4 | 13-15 C5 finale leaning' MAIN_STAGE_TRANSITIONS: 'Main screen 3-layer sync transitions advance by segment. WALL/FLOOR/CHAR enter a new overall segment together at each switch.' main_stage_timeline: '0-1.5 Stage1: WALL=pop art wall+abstract graphics+high contrast colors; FLOOR=huge stranger face LED floor; CHAR=close to original high-detail, light stage mod; Mood=Opening grab. 1.5-3 Stage2: WALL=poster collage/ad visual/torn edges; FLOOR=huge eyes/iris dynamic floor; CHAR=clear comic line or high contrast graphic; Mood=First major style change. 3-4.5 Stage3: WALL=folding screen style/gold ground/traditional painting; FLOOR=fire surface/heatwaves/cracks; CHAR=retro hand-drawn animation or picture book style; Mood=Traditional+Heat. 4.5-6 Stage4: WALL=large display wall/CRT matrix/projection; FLOOR=transparent water/ripples/mirror; CHAR=sticker or graphic poster style; Mood=Digital+Fluid. 6-7.5 Stage5: WALL=MAIN huge close-up face art; FLOOR=real grassland/blowing grass; CHAR=collectible model or 3D cel-shaded; Mood=Strongest MAIN identity emphasis. 7.5-9 Stage6: WALL=metaverse city/holographic buildings/UI/data arch; FLOOR=metaverse electronic platform/grid; CHAR=holographic/neon/future stage; Mood=Tech Nightclub. 9-10.5 Stage7: WALL=large pixel art wall/8-bit city; FLOOR=pixel ground/bricks/water; CHAR=pixel-leaning or low-poly but clearly MAIN; Mood=Gaming electronic feel. 10.5-12 Stage8: WALL=mysterious giant face/abstract portrait; FLOOR=liquid metal surface; CHAR=mosaic/stained glass/craft; Mood=Heterogeneous art. 12-13 Stage9: WALL=graffiti/misprint/neon sign mix; FLOOR=flower field to ice prism; CHAR=mixed media, finale outfit push; Mood=Finale build-up. 13-13.5 Burst A: high-frequency sync switch, compress space, enhance speed. 13.5-14 Burst B: continue sync switch, prepare for PIP intrusion. 14-14.5 Burst C: boundary destruction, screen erosion, swap starts. 14.5-15 Finale: complete MAIN and PIPCHAR swap, main screen subject becomes PIPCHAR, MAIN enters lower left PIP.' camera_lock: 'Main screen camera must move significantly in 3D space, not fixed station panning/tilt/digital zoom. Each segment must change X/Y/Z coordinates with visible parallax. No stationary shaking to fake orbiting, no digital zoom only.' orbit_rule: 'Each orbit must complete at least 90-degree change, focus segments 120-180. Clockwise/Counter-clockwise must be clear. Vertical orbits must rise from low to high over the subject.' frame_rotation: 'Screen rotation must be continuous 30-90 degrees or more, overlapping with orbit/push/pull, not random shaking.' camera_timeline: '0-1.5 front-left low clockwise 120 to right, knee to chest height | 1.5-3 continue clockwise 90 to right-back, high speed graze past shoulder to re-catch face | 3-4.5 back-low vertical orbit, over head to high-angle then descend forward | 4.5-6 front-right low counter-clockwise 150 to left-back, radius shrinks then expands | 6-7.5 high-angle counter-clockwise fast descend to ground-level graze | 7.5-9 ground sprint: dash from far to MAIN, sharp pull up at feet, over shoulder then 90 degree reverse orbit | 9-10.5 giant spiral: 120 orbit + rise + radius contraction + 60 roll | 10.5-12 super-high dive past shoulder to back then 180 flip back to front | 12-13 ultra-close to ultra-wide reverse flyover + huge WALL/FLOOR then high-speed push-in | 13-13.5 fast clockwise 90 orbit + 45 roll | 13.5-14 fast counter-clockwise 120 orbit + dive | 14-14.5 spiral 120 + 90 screen roll + screen tear | 14.5-15 complete swap from broken screen and relock new protagonist' PIP_RULE: 'Add a small PIP window in the lower left. Not a split screen, but an independent small PiP, approx 1/16 area (width/height 22-25%). Keep it small and clear, don't interfere with main screen. Fixed position, can have white line/glow border.' PIP_BACKGROUND: 'PIP environment fixed to pure black or dark void. No complex background or floor patterns. Goal is clear view of PIPCHAR eating a burger.' PIP_SUBJECT: 'Display PIPCHAR in the PIP window, not MAIN. This is an independent curious video. For 0-13s, PIP character must be PIPCHAR.' PIP_PURPOSE: 'Show PIPCHAR eating a burger from various angles on a black background. Atmosphere slightly comical/mysterious, like a random insert, but visually clear and cute.' PIP_ACTION_CORE: 'PIPCHAR holds a burger or thick meat patty and clearly eats: looking at it, lifting, biting, chewing, swallowing, biting again. Must clearly see eating, not just holding.' PIP_HAMBURG_RULE: 'Burger must be clearly visible (bun, patty, toppings). Key point is PIPCHAR seriously eating. No other food, no eating air, no just posing.' PIP_ANGLE_RULE: 'PIP shows PIPCHAR with eating action. Can slowly turn, rotate, or small continuous changes while keeping eating visible. Show front, 45, side, back-turn, half-body close-up, etc.' PIP_MOTION_STYLE: 'Minor movements only: turning, head tilting, lifting burger, biting, chewing. No major dancing. Focus is multi-angle continuous eating.' PIP_AUDIO_RULE: 'PIPCHAR does not sing or provide vocals. Does not take over song. Performs silent or low-presence eating. No impact on the female lead vocal.' PIP_TIMELINE: '0.8-2.8 front and left 45 eating, first clear bite | 2.8-4.8 left side and left-back 45, chewing while turning | 4.8-6.8 back and right-back 45, looking back while holding burger | 6.8-8.8 right side and right 45, another clear bite | 8.8-10.8 upper body close-up turn, highlight face and burger, clear chewing | 10.8-12.8 small continuous turntable-style observations, different angles continuous eating | 12.8-13.8 faster eating, sensing main screen abnormality | 13.8-15.0 PIP boundary sucked into main screen and expanded, PIPCHAR bursts out of lower left window to become main screen character.' PIP_STYLE_RELATION: 'Even if main screen changes are intense, prioritize PIPCHAR identification and eating visibility. Style can follow finale atmosphere but black background and burger are core.' PIP_MAIN_SEPARATION: '0-13.8s MAIN continues dancing/singing in main screen. PIP is just an additional layer. Both exist simultaneously without PIP interfering with MAIN facial visibility.' SWAP_RULE: 'Final swap is the core experimental event. 13.8-15.0 a clear position swap must occur: PIPCHAR breaks PIP boundary, expands via high-speed transition to main center; MAIN is compressed, shrunk, pulled into the lower left PIP window. After swap, main subject = PIPCHAR, lower left PIP = MAIN. Vocal identity remains unchanged.' SWAP_VISUAL_GRAMMAR: 'Use screen tearing, mirror flips, PiP expansion, window burst, layer penetration, character through-screen, rotate/scale, glitch, etc. Swap is not a simple cut but a visual spectacle.' SWAP_FINAL_STATE: 'By 14.7-15.0, new main subject must be PIPCHAR (optionally with burger); MAIN must be in the PIP window. Swap must be completed. Female lead vocal remains unchanged.' PIP_FAILURE: 'Failed if PIP window is too large, not black background, not PIPCHAR, no eating, or no final swap.' typo: 'Minimal dynamic text, single kanji or short English only. Candidates: Dance, Light, Sound, Instant / GO, UP'

A vibrant K-pop stage performance under bright purple and pink LED lights. Three young East Asian women idols with long dark hair stand in a line on stage, wearing headset microphones and stylish crop tops. Characters and outfits: Left idol: lime-green sleeveless top with white “BOYS LIE SPORT” text and heart logo. Center idol: baby-pink spaghetti-strap crop top with white piping. Right idol: navy-and-green horizontal striped collared crop top. Sequence — approximately 17 seconds: 0–2s: The three idols begin by dancing lightly and naturally in sync to the beat. The center idol flips her long hair and turns slightly while dancing. The right idol dances with a playful expression. Do not have them cover their faces yet. Soft stage lighting and large LED screens show a big red “5” and heart graphics in the background. 2–6s: While continuing their dance movement, all three suddenly bring both hands up to cover their mouths, reacting with genuine surprise and laughter. Their shoulders shake as they giggle and they gently bounce in place. The center idol laughs hardest, with her long hair naturally swaying. 6–12s: They continue the synchronized cover-mouth-and-laugh motion while still subtly dancing to the beat. Keep their bodies moving naturally rather than freezing in place. Their expressions are joyful, playful, and genuinely amused. Medium camera framing captures all three idols clearly. 12–15s: The dancing continues at 12 seconds as they smoothly transition from covering their mouths into making double peace signs with both hands raised near their faces. They keep moving rhythmically while smiling and laughing. The center idol briefly turns and then faces forward again. 15–17s: Final pose while the dance energy continues subtly — all three hold double peace signs near their faces, beaming directly at the camera with bright, cheerful expressions. Soft stage haze and colorful LED lighting create a high-energy yet adorable K-pop concert atmosphere. Visual style: high-quality live concert footage, sharp details, natural skin texture, realistic facial expressions, dynamic but soft purple-and-pink stage lighting, subtle handheld camera shake for realism, natural hair movement, believable body motion, polished K-pop performance cinematography, cute, energetic, wholesome atmosphere. Important motion requirements: The idols must dance first before putting their hands on their faces. Do not start with their hands covering their mouths. The dancing continues throughout the sequence, including after the 12-second mark. No frozen poses before the final moment. No text overlays.

My in universe anthropomorphic rock band "Velvet Garrote" playing live to a cheering crowd.

# Main Prompt - A: Clockwise Heart (Classroom Ver.) shot: type: r2v aspect_ratio: "9:16" camera: fixed, single continuous shot, no cuts framing: character occupies lower two-thirds of frame, medium shot from waist up character: reference: use attached reference image for full appearance (face, outfit, colors, proportions) art_style: preserve original character art style / cel-shading from reference, do not blend with background style motion: sequence: - beat_1_2: both arms raised, sweep in a slow clockwise circular motion like clock hands, starting from 12 o'clock position - beat_3: arms cross at chest height, hands open - beat_4: arms draw outward and down into a heart shape formed above the head, hold for half a beat - beat_5_6: small step-touch side to side (left-right), shoulders swaying gently in sync - loop: sequence repeats seamlessly from beat_1 tempo: moderate pop tempo, sharp but not rushed transitions motion_notes: no slow motion, no speed ramping, natural constant playback speed throughout setting: location: after-school classroom, empty of other students time_of_day: late afternoon / early evening, golden hour light through windows environment_details: rows of desks and chairs as soft silhouettes in the background, chalkboard faintly visible, window frames casting long soft shadows across the floor atmosphere: quiet, nostalgic, gentle contrast between the character's lively motion and the stillness of the empty room background: style: simple, uncluttered classroom silhouette, low detail so it doesn't compete with character motion rendering: keep visually separate from character line/shading style; desks/windows rendered with minimal linework, mostly shape and light, not full detail motion: static background, only ambient light shift (e.g. faint dust motes in the light beam), no moving elements lighting: warm golden-hour light streaming through windows from one side, soft rim light on character, gentle long shadows cast by desks expression: light, playful smile, eyes forward toward camera during heart pose

Define the character setting data in I1 as <A>. Even if I1 contains multiple perspectives, expressions, or clothing details of the same person, understand them all as design data for the same character. <A>'s face, hairstyle, body type, clothing structure, color scheme, and identity refer only to I1. Define the character setting data in I2 as <B>. (Same character consistency rule as above) <B>'s features refer only to I2. Define the character setting data in I3 as <C>. (Same character consistency rule as above) <C>'s features refer only to I3. <A>, <B>, and <C> must be three different people from start to finish. No face-swapping, no clothing changes, no mutual copying, and background crowds must not become copies of the three protagonists. The entire 30 seconds takes place in the central atrium of a large modern shopping mall; do not switch to a stage, street, studio, or other buildings. [Generation Goal] Generate a 30-second high-density shopping mall brand image commercial. The first 27 seconds play out as a high-spec Dance MV and public Flash Mob. At 27 seconds, the dance officially ends, and from 27-30 seconds, it abruptly transitions into a formal, bright, and overtly clean commercial outro. The core is not three isolated solos, but three protagonists completing a group choreography with clear roles that respond to each other, though rarely in unison. A: Flow / Orbit: Capoeira. Responsible for flow, circling, evasion, circular movement, and spatial connection. B: Center / Hook: Light modern Idol Dance as the base, adding Waacking arm lines and minimal Popping accents. Responsible for the readable hook, leading the crowd, and center guidance. C: Power / Punctuation: Breaking. Responsible for floor work, rotations, power moves, and punctuating musical phrases. The three collaborate via call and response, canon timing, and layered choreography. The audience must see they are dancing together, but not in a synchronized idol group style. Timeline: 0-9s: Establish character differences. 9s: First wave of Flash Mob starts. 15s+: Crowd size expands. 18s+: Escalators and 2nd-floor crowds join in. 24-27s: Peak climax. 27s+: All dancing stops; enter mall CM ending. [Space and Composition] Use wide horizontal space and architectural depth; don't crowd the three in the center for long. Initial Layout: A: Front-left area. B: Center-rear area. C: Front-right area. A uses left/mid-left zones with diagonal and circular paths. B stays as the visual anchor with full arm span space. C uses the right/mid-right floor area, ensuring enough radius for windmills, flares, and power moves. Background: Modern mall atrium with glass skylights, open galleries, escalators, stone floors, cafe areas, and plants. Bright, transparent, and realistic scale with natural reflections. Populate with shoppers, couples, families, and bystanders. [Detailed Movement Styles] - A (Capoeira): Movements must be based on a visible 'ginga' step. Not just acrobatic tricks, but a continuous rhythmic sway. Uses feints and circular kicks to create a 'dialogue' with the environment. - B (Idol/Waacking): Soft, approachable Idol dance for easy crowd imitation. Waacking expands the visual silhouette. Popping is used sparingly for beat hits. B provides the 'hook motif' that the flash mob eventually copies. - C (Breaking): Rotation-focused. Toprock and footwork serve as transitions into power moves (windmill, flare, backspin). Ends phrases with clear freezes. [Music and Sound] Style: Idol-friendly Brazilian breakbeat funk / dance-pop hybrid. Features bright dance-pop frame, funk bass, and Japanese female vocals. From 9s onwards, add human rhythmic layers like beatboxing, clapping, and a cappella harmonies as if generated by the crowd. [Camera Principles] Active but stable. Prioritize readability over flashy camera tricks. Show A's full leg arcs, B's arm gestures, and C's floor rotations clearly. Use cranes and orbits to capture the expanding crowd scale in the second half. [Shot Breakdown (1-10)] (Detailed descriptions of 10 shots covering the progression from intro to the 27-second climax, including specific dance moves for each character and the synchronized final accent at 27 seconds where the music stops for the commercial outro.)

spoken_language: Japanese motion: Normal speed, high density, smooth temporal resolution equivalent to 60fps [Reference Material] R1@image1 = Sole reference for person + full-body outfit. Maintains face, skin, eyes, hair, hair ornaments, body proportions, gender expression, age impression, outfit, decorations, accessories, shoes, materials, colors, and length for 30 seconds. Automatically adapts gender, appearance, skeleton, physique, expressions, gestures, and voice quality from R1. Does not inherit background, lighting, composition, or still poses. R2@image2 = Reference for stage, architecture, floor, wall, ceiling, background, furniture, decorations, props, ambient light, time of day, color temperature, and spatial layout. Do not add non-existent structures or people. [Completed Video] High-density K-POP performance by R1 (adult) in R2 live-action space. Maintain choreography, speed, footwork, waacking, body isolation, shoulder hits, chest accents, pivots, turns, and traveling. VFX analyzes R1's primary colors and randomly switches between INK, PAINTERLY, and PIXEL for each action. VFX follows arms, wrists, fingertips, feet, etc., with a 0.15–0.7s delay. Do not originate VFX from the chest or torso front. [Music/Song/Voice] 128 BPM, bright rhythmic K-POP × hip-hop. Dance actions synced to specific sounds. Character's singing and speaking voices automatically adapt to R1's appearance and persona. Full lip-sync for the song from 0–30s, except for three specific spoken dialogue sections where singing lip-sync stops and spoken lines are delivered. No repetition, extra lines, or subtitles. [VFX] Extract 2-4 prominent colors from R1. INK = translucent liquid ink; PAINTERLY = dry-brush ribbons; PIXEL = color blocks/trails. Randomly switch between the three. VFX follows specific body parts (shoulders, arms, feet) during movement. No VFX for body waves or chest hits. Do not overlap with face or chest. [30-Second Timeline] 00.0–03.0 | 50mm medium close. Spoken line: "Hey... won't you play until the moon is hidden?" 03.0–06.0 | 35mm full body. Shoulder hits, waacking, turn. 06.0–09.0 | Footwork, pivot, shoulder isolation. 09.0–12.5 | Traveling left, vogue geometry, finger to lens. 12.5–15.5 | Lateral tracking. Spoken line: "Keep those eyes only on me for now." 15.5–19.0 | Back tap, chest contract, 180-degree turn. 19.0–22.5 | 28mm wide-medium. Shoulder groove, hip accents, spiral arms. 22.5–25.0 | 40mm medium-full. Hand near hair, body wave. 25.0–27.5 | Foot switch, 180-degree pivot turn. 27.5–29.0 | Forward groove. Spoken line: "Caught you. I won't let you go anymore." 29.0–30.0 | Final pose, trailing VFX, fading. [Camera/Human Lock] Focal length changes. Clear grounding. Hands must always have 5 fingers each. [Avoid] Fixed gender/voice, inconsistent voice, subtitles, extra people, simplified choreography, face distortion, VFX on chest. [Top Priority] 1. Consistent R1 identity, 2. Natural voice adapted to R1, 3. R2 stage consistency, 4. Strict timing, 5. Continuous song lip-sync, 6. Perfect dialogue lip-sync, 7. No repetition, 8. R1-color-based random VFX, 9. 5 fingers per hand, 10. Realistic physics. [Reference Adaptation Lock] Do not fix gender. Maintain consistency based on R1 features. Seamless transition between singing and speaking.

You are a top-tier drone camera operator. Move the drone camera freely in all directions to capture dynamic footage. You are filming a live scene of twin idols. Capture it with camerawork that will surprise anyone who sees it. Maintain the twin characters from the reference image, photorealistic, 30 seconds. A massive arena live venue filled with tens of thousands of spectators. The entire venue is enveloped in heat and cheers. A twin idol unit is performing live on stage. The climax at the end of the show, the most exciting moment. Performing synchronized dance and performance in the center of the stage. Singing with big smiles, showing symmetrical choreography together, standing back-to-back, and laughing while making eye contact. The brilliance and presence of star idols. Professional concert film-level direction, realistic audience movement, natural cheering, dynamic camerawork, stage lighting, laser effects, confetti, ultra-high definition, cinematic, and the emotional atmosphere of a grand finale.

<image1> = Sole protagonist character reference. <image2> = Sole background/space reference. Hereafter, the protagonist's face, hairstyle, hair color, clothing, accessories, body proportions, age impression, and character design are all obtained from the character reference and maintained as the same person for 30 seconds. The background architecture, terrain, floor, walls, ceiling, sky, lighting, color temperature, time of day, depth, distant view, plants, water surface, fog, fabric, mechanical structures, decorations, etc., are all obtained from the background reference and maintained as the same space for 30 seconds. The original background of the character reference is not used. Even if there are people in the background reference, they are not used as new characters. This is a general-purpose structure that can be used as is just by replacing the favorite character image and favorite background image without redefining the specific characteristics of the person or background in text. There is only one protagonist. Do not confuse the roles of character and background. [Work Concept] A 30-second musical-style performance video where a single protagonist speaks quietly to the audience within a background world, and that acting itself changes into a rhythm, leading into cute, dangerous, and provocative authentic K-POP dance. Start with acting at the beginning. The protagonist is not completely stationary; gaze, breathing, toes, shoulders, neck, fingertips, and subtle swaying of hair or clothing exist first, and a small beat starts to enter the body midway through the lines. Instead of suddenly dancing after finishing the acting, it changes naturally as ACTING -> RHYTHM -> GROOVE -> FULL K-POP CHOREOGRAPHY. Connect the last word of the line to the first strong beat, using that word as a boundary to suddenly increase the exercise density of the entire body. The protagonist is not just cute; she understands she is being watched and enjoys it a little. There is a slightly dangerous ease in her soft expression, having a small devil-like charm where you don't know what will happen if you approach. However, do not make it a vulgar seductive expression. Create fetishism using the gaze, fingers, wrists, neck angle, shoulders, footwork, hair, clothing, accessory swaying, and distance from the camera.

A high-energy 15-second continuous iPhone-shot street dance music video on a busy modern Japanese city street. A stylish female singer-dancer walks continuously toward the camera while performing energetic contemporary choreography combining modern hip-hop, waacking, K-pop dance, commercial street dance, body isolations, shoulder grooves, chest hits, hip accents, arm waves, quick footwork, and expressive performance. She is both a singer and dancer. She genuinely enjoys the music, occasionally mouths the lyrics, smiles naturally, makes confident eye contact with the camera, and performs with strong musicality and charisma. IMPORTANT: The dancer must continuously DANCE while WALKING. Do not reduce the choreography to ordinary walking with occasional arm movements. Her feet continuously travel forward while her entire body actively responds to the music. The choreography should have HIGH MOVEMENT DENSITY throughout the entire 15 seconds. The flash mob must begin VERY EARLY and gradually grow throughout the shot. CAMERA: Shot entirely on a modern iPhone. Natural handheld smartphone cinematography. Realistic iPhone image quality. Sharp but natural smartphone detail. Slight natural handheld movement. Subtle smartphone stabilization. Natural exposure changes. Realistic autofocus behavior. Natural wide-angle perspective. No cinematic crane. No professional cinema camera. No gimbal-perfect movement. No dramatic lens effects. The camera operator continuously BACKTRACKS in front of the dancer while filming her. The camera moves backward along the city street while keeping the main dancer centered. The camera operator walks backward naturally but carefully. The main dancer remains full-body or near-full-body in frame. No cuts. No transitions. No orbiting. No camera rotation around the dancer. No zoom. No drone. No slow motion. ================================================== 0.0-1.5s | SOLO The scene begins immediately on a busy modern Japanese city street. The main dancer is already walking toward the camera and dancing. 0.0-0.5s: Right foot forward. Strong hip-hop bounce through the knees. Sharp shoulder hit. 0.5-1.0s: Left foot forward. Chest isolation followed by a shoulder roll. Her arms naturally swing into a short waacking movement. 1.0-1.5s: Right foot forward. Fast arm circle around the head. Hip accent. Small head nod toward the beat. She is clearly dancing, not simply walking. Several ordinary pedestrians are visible in the background. ================================================== 1.5-3.0s | FIRST DANCER JOINS The main dancer continues moving forward. 1.5-2.0s: Left foot forward. Chest pop → shoulder hit → arm sweep. A pedestrian walking behind her notices the rhythm and begins subtly copying the shoulder movement. 2.0-2.5s: Right foot forward. The main dan