MiniMax H3 × Music 3 で
無料ミュージックビデオ制作

Solo portrait of a semi-realistic anime girl, jet-black high ponytail with electric-cyan inner color streaks, glowing star-shaped hairpin, wearing a sleek futuristic visor headset with a small glowing antenna. She has a calm confident expression, sharp detailed ice-blue eyes, wearing an oversized black techwear bomber jacket with white panels and cyan glowing trim lines, white crop top, black gloves, holding a wireless microphone with a glowing cyan grille. Bright pure white background, high-key lighting, soft cool cyan rim light, loose painterly brushstrokes, intricate detail, depth of field, digital painting, highly detailed face, concept art, no background characters, centered. --ar 4:5 --stylize 300

Create a premium, modern high-fashion CHARACTER CONCEPT ART SHEET in a 16:9 widescreen layout on a near-black charcoal background.

THE ATTACHED REFERENCE IMAGE DEFINES THE ART STYLE AND THE CHARACTER — treat it as a strict style bible and reproduce its exact rendering technique and the exact same character in every figure on this sheet.

[STYLE — MIRROR THE REFERENCE EXACTLY]: Replicate the reference image's rendering verbatim: painterly semi-realistic anime digital painting, loose expressive brushstrokes, dramatic lighting, glowing electric-cyan neon accents, palette strictly limited to black, white, and electric cyan.

[STYLE PROHIBITIONS — ABSOLUTE]: no 3D render, no photorealism, no flat cel-shaded anime, no bold ink outlines, no chibi proportions, no style drift from the reference, no extra colors outside black/white/cyan.

[SUBJECT_DESCRIPTION]: The exact girl from the reference: jet-black high ponytail with electric-cyan inner color streaks, glowing cyan star-shaped hairpin, sleek visor headset with a thin boom microphone and a small glowing antenna, calm confident face with sharp ice-blue eyes. Outfit: oversized black techwear bomber jacket with white panels and glowing cyan trim lines, white crop top, black fingerless gloves, silver rings. Signature item: a wireless microphone with a glowing cyan grille. Her voice emits glowing electric-cyan sound-wave ribbons and geometric waveform shapes.

Layout Composition (Organize strictly into these sections):
1. LEFT PANEL: TURNAROUND & FACES
- MINI TURNAROUND: 3 small full-body vertical figures (neutral front, back view, side profile), identical outfit in all three.
- SILHOUETTE STUDY: 3 solid-white silhouettes matching the turnaround poses.
- EXPRESSION STUDY (Bottom Left): 4 close-up headshots (calm confident gaze, singing intensely with eyes closed, playful smirk, sharp performance glare).
2. CENTRAL PANEL: THE CENTERPIECE
- One giant, dominant full-body figure in a powerful mid-performance singing pose, mic raised close to her lips, cyan sound-wave ribbons swirling around her, maximum detail, perfect style-match to reference.
3. RIGHT PANEL: MULTI-POSE STUDIES
- POSE STUDY: 4 small-to-medium dynamic stances (unleashing a burst of cyan waveforms while singing, leaping mid-air with jacket billowing, crouching low holding the mic out to the camera, leaning back casually with hands in pockets), small handwritten-style labels.
4. BOTTOM RIGHT PANEL: DETAIL STUDY
- 5 small square crops: visor headset and face close-up, glowing star hairpin in hair, jacket's cyan trim and zipper hardware, fingerless glove with silver rings, the glowing microphone with a cyan sound-wave ribbon. Small handwritten-style labels.

No character name or logo typography anywhere on the sheet.

Stylized anime concept art of a massive luxurious concert arena at midnight, completely empty, no people, no crowd. A grand elevated center stage of black glass and polished chrome, a colossal curved LED screen glowing with electric-cyan waveforms, towering speaker monoliths, tiered VIP balconies with white marble and glowing cyan trim lines, crystal chandelier-like light rigs hanging from the darkness. Drifting stage fog, volumetric electric-cyan spotlights and lasers cutting through the dark. Palette strictly pitch black, stark white, and vivid electric cyan. Painterly semi-realistic digital painting, loose expressive brushstrokes, dramatic lighting, cinematic extreme wide establishing shot looking toward the stage, extreme depth. No characters, no photorealism, no 3D render. --ar 16:9 --stylize 300

Create a 16:9 widescreen stylized anime concept art painting of a massive, luxurious concert arena at midnight. The arena is completely empty — absolutely no people, no crowd, no performers. Scene: a grand elevated center stage made of black glass and polished chrome, a colossal curved LED screen glowing with electric-cyan waveform patterns, towering speaker monoliths on both sides, tiered VIP balconies with white marble edges and glowing cyan trim lines, and crystal chandelier-like lighting rigs hanging from the darkness above. Atmosphere: drifting stage fog, volumetric electric-cyan spotlights and laser beams cutting through the dark. Palette: strictly limited to pitch black, stark white, and vivid electric cyan — no other colors. Style: painterly semi-realistic anime digital painting with loose expressive brushstrokes and dramatic lighting, like high-end concept art. Composition: cinematic extreme wide establishing shot from the audience floor looking up toward the stage, with extreme depth. Absolutely no characters, no photorealism, no 3D render look.

K-pop girl crush, dark electro-pop, powerful female vocal, heavy bass drop, 110 BPM

Global Metadata: K-pop girl-crush style dark electro-pop. Around 110 BPM, minor key. Mood: fierce, confident, sleek stadium energy. Punchy modern production with heavy synth bass, sharp claps, and bright electronic stabs.

Vocal Details: Solo female vocalist in her early twenties, powerful and charismatic. Sharp rhythmic chant-like delivery on the verse, soaring melodic hook with layered harmonies on the chorus, occasional whispered ad-libs. English lyrics, crisp articulation.

Arrangement: Intro is sparse — a dark synth-bass pulse, claps and whispered vocal chops, with one heavy kick hit as an accent. Verse rides a tight punchy groove with rolling hi-hats. Pre-chorus builds with a rising synth riser and accelerating drums, then ALL music cuts to complete silence for one spoken line, followed by a massive bass drop into the chorus. Chorus is the biggest section: heavy kick pattern, huge synth bass, chantable hook with layered harmonies. Outro strips back to the bare pulse, one final whispered line, then a hard clean stop.

[Intro]
Yeah, turn the city lights low
Wave check, here we go

[Verse]
Step in the light with the neon glow
Black and cyan, run the whole show
Talk is cheap, I let the levels speak
One mic, one move, pushing past the peak

[Chorus]
Turn the silence up, let the wave run free
Every heartbeat locked to my frequency
Wave up, wave up, burning cyan bright

[Outro]
Signal sent, no coming back

Cinematic 2.5D animation, painterly semi-realistic anime style. Palette strictly limited to black, white, and electric cyan. NOT photorealistic, NO glossy 3D CGI, NO flat cel-shaded cartoon, no bold outlines.

WORLD: The venue is exactly the massive luxurious concert arena from <Picture 2>: black glass and chrome center stage, colossal curved LED screen glowing with electric-cyan waveforms, white marble VIP balconies, crystal chandelier light rigs, drifting stage fog, volumetric cyan spotlights.

CHARACTER: The young woman from <Picture 1>, exactly as designed: jet-black high ponytail with electric-cyan inner color streaks, glowing cyan star-shaped hairpin, sleek visor headset with a thin boom microphone, oversized black techwear bomber jacket with white panels and glowing cyan trim lines, white crop top, black fingerless gloves, holding a wireless microphone with a glowing cyan grille. Sharp ice-blue eyes, painterly matte skin. Her singing mouth movements are precisely synchronized with <Audio 1>.

INTRO & VERSE SHOT DESIGN (5 Filmic Cuts):
• SHOT 1 (0–2s | Macro Detail): Extreme macro close-up of the glowing cyan mic grille in darkness. On the whispered "Yeah", one soft cyan sound ripple pulses from the grille.
• SHOT 2 (2–4.6s | Reveal): Medium shot. She raises her head into a single spotlight on the grand stage, singing softly. On the words "Wave check", bold flat-graphic typography "WAVE CHECK" flashes beside her in electric cyan.
• SHOT 3 (4.6–9.5s | Verse Groove): Slow tracking shot as she walks up the glowing stage stairs singing; as she sings "Black and cyan", the cyan trim lines of her jacket ignite one by one in rhythm, the giant LED screen pulsing waveforms behind her.
• SHOT 4 (9.5–12.3s | Attitude): Close-up on her face. She sings "Talk is cheap" with a confident smirk directly into the camera, thin cyan waveform ribbons drifting around her.
• SHOT 5 (12.3–15s | Typography Stamp): Medium shot, giant flat-graphic audio level bars rising on the LED screen behind her as she sings "I let the levels speak". Then bold typography "ONE MIC." and "ONE MOVE." stamps across the frame in sync with the two vocal hits. Hold final frame.

Weighty natural animation, oversized jacket reacting fluidly to her movement, 24fps filmic motion, shallow depth of field. NOT photorealistic, no 3D render, no cel shading, no bold outlines.

Cinematic 2.5D animation, painterly semi-realistic anime style. Palette strictly limited to black, white, and electric cyan. NOT photorealistic, NO glossy 3D CGI, NO flat cel-shaded cartoon, no bold outlines.

WORLD: The venue is exactly the massive luxurious concert arena from <Picture 2>: black glass and chrome center stage, colossal curved LED screen glowing with electric-cyan waveforms, white marble VIP balconies, crystal chandelier light rigs, drifting stage fog, volumetric cyan spotlights and lasers.

CHARACTER: The young woman from <Picture 1>, exactly as designed: jet-black high ponytail with electric-cyan inner color streaks, glowing cyan star-shaped hairpin, sleek visor headset with a thin boom microphone, oversized black techwear bomber jacket with white panels and glowing cyan trim lines, white crop top, black fingerless gloves, holding a wireless microphone with a glowing cyan grille. Sharp ice-blue eyes, painterly matte skin. Her singing mouth movements are precisely synchronized with <Audio 1>.

CHORUS SHOT DESIGN (4 Cuts with Typography):
• SHOT 1 (0–1.5s | Launch): Low-angle shot. She strides toward the center of the grand stage as the music surges upward, rows of cyan stage lights and the chandelier rigs igniting one after another.
• SHOT 2 (1.5–7s | Chorus Power): Dynamic orbiting camera around her as she sings the chorus at full power, concentric cyan shockwave rings expanding from her with each beat, stage fog blown outward across the marble balconies.
• SHOT 3 (7–9s | Wave Up): Two rhythmic jump-cut punch-ins as she sings "Wave up, wave up" — bold flat-graphic typography "WAVE UP" stamps on screen twice, once per vocal hit, then a burst of bright cyan light floods the frame from the LED screen on "burning cyan bright".
• SHOT 4 (9–12s | Signal Sent): She lowers the mic, turns, and walks slowly away from the camera into the darkness of the stage while singing "Signal sent, no coming back"; typography "SIGNAL SENT." fades in beside her silhouette. Hold final frame.

Weighty natural animation, oversized jacket reacting to the shockwaves, 24fps filmic motion. NOT photorealistic, no 3D render, no cel shading, no bold outlines.

Cinematic 2.5D animation, painterly semi-realistic anime style. Palette strictly limited to black, white, and electric cyan. NOT photorealistic, NO glossy 3D CGI, NO flat cel-shaded cartoon, no bold outlines.

WORLD: The venue is exactly the massive luxurious concert arena from <Picture 2>: black glass and chrome center stage, colossal curved LED screen, white marble VIP balconies, crystal chandelier light rigs, stage fog swirling, strobing electric-cyan lasers.

CHARACTER: The young woman from <Picture 1>, exactly as designed: jet-black high ponytail with electric-cyan inner color streaks, glowing cyan star-shaped hairpin, sleek visor headset with a thin boom microphone, oversized black techwear bomber jacket with white panels and glowing cyan trim lines, white crop top, black fingerless gloves, holding a wireless microphone with a glowing cyan grille. Sharp ice-blue eyes, painterly matte skin. She does not sing in this clip — this is a pure instrumental performance climax, her movements locked to the rhythm of <Audio 1>.

INSTRUMENTAL FINALE SHOT DESIGN (4 Cuts, No Lip Sync):
• SHOT 1 (0–3s | Ignition): Wide shot of the grand stage. She spins the mic in her hand and starts moving to the beat, cyan lasers and the LED screen strobing faster and faster with the rising synths.
• SHOT 2 (3–6.5s | Frenzy): Speed-ramp orbiting camera accelerating around her dancing silhouette, cyan waveform ribbons spiraling tighter and tighter, frames flickering between normal and black/cyan inverted colors on the beat.
• SHOT 3 (6.5–7.8s | Peak): Everything peaks at once — she raises the glowing mic high overhead and a massive cyan shockwave dome erupts across the entire arena, the chandeliers and LED screen flaring white-cyan.
• SHOT 4 (7.8–10s | Blackout): On the sudden dead silence, every light and the giant LED screen shut off instantly. A single cyan rim light traces her silhouette in the darkness, she flashes a confident parting smirk, then the frame snaps to pure black. Hold black frame.

Weighty natural animation, 24fps filmic motion. NOT photorealistic, no 3D render, no cel shading, no bold outlines.

Cinematic 2.5D animation, painterly semi-realistic anime style. Palette strictly limited to black, white, and electric cyan. NOT photorealistic, NO glossy 3D CGI, NO flat cel-shaded cartoon, no bold outlines. No text, no typography, no letters on screen.

WORLD: The venue is exactly the massive luxurious concert arena from <Picture 2>: black glass and chrome center stage, colossal curved LED screen glowing with electric-cyan waveforms, white marble VIP balconies, crystal chandelier light rigs, drifting stage fog, volumetric cyan spotlights.

CHARACTER: The young woman from <Picture 1>, exactly as designed: jet-black high ponytail with electric-cyan inner color streaks, glowing cyan star-shaped hairpin, sleek visor headset with a thin boom microphone, oversized black techwear bomber jacket with white panels and glowing cyan trim lines, white crop top, black fingerless gloves, holding a wireless microphone with a glowing cyan grille. Sharp ice-blue eyes, painterly matte skin. Her singing mouth movements are precisely synchronized with <Audio 1>.

INTRO & VERSE SHOT DESIGN (5 Filmic Cuts):
• SHOT 1 (0–2s | Macro): Extreme macro close-up of the glowing cyan mic grille in darkness, one soft cyan sound ripple pulsing on the whispered vocal.
• SHOT 2 (2–4.6s | Reveal): Slow tilt-up from her boots to her face as a single spotlight fades in on her at center stage, singing softly with a calm gaze.
• SHOT 3 (4.6–9.5s | Verse Tracking): Smooth tracking shot following her as she walks up the glowing stage stairs singing, jacket trim lines igniting one by one, the giant LED screen pulsing waveforms behind her.
• SHOT 4 (9.5–12.3s | Attitude): Close-up. She sings with a confident smirk straight into the camera, thin cyan waveform ribbons drifting around her face.
• SHOT 5 (12.3–15s | Wide Power): Pull-back to a wide low-angle of the whole grand stage — spotlights snap on row by row in rhythm as she plants her feet and raises the mic. Hold final frame.

Weighty natural animation, oversized jacket reacting fluidly, 24fps filmic motion, shallow depth of field. NOT photorealistic, no 3D render, no cel shading, no bold outlines, no text.

Cinematic 2.5D animation, painterly semi-realistic anime style. Palette strictly limited to black, white, and electric cyan. NOT photorealistic, NO glossy 3D CGI, NO flat cel-shaded cartoon, no bold outlines. No text, no typography, no letters on screen.

WORLD: The venue is exactly the massive luxurious concert arena from <Picture 2>: black glass and chrome center stage, colossal curved LED screen glowing with electric-cyan waveforms, white marble VIP balconies, crystal chandelier light rigs, drifting stage fog, volumetric cyan spotlights.

CHARACTER: The young woman from <Picture 1>, exactly as designed: jet-black high ponytail with electric-cyan inner color streaks, glowing cyan star-shaped hairpin, sleek visor headset with a thin boom microphone, oversized black techwear bomber jacket with white panels and glowing cyan trim lines, white crop top, black fingerless gloves, holding a wireless microphone with a glowing cyan grille. Sharp ice-blue eyes, painterly matte skin. Her singing mouth movements are precisely synchronized with <Audio 1>.

INTRO & VERSE SHOT DESIGN (5 Cuts, Light-Driven):
• SHOT 1 (0–2s | Darkness): Wide shot of the pitch-dark arena. On the whispered vocal, a single faint cyan ripple crosses the giant LED screen, revealing her silhouette at center stage.
• SHOT 2 (2–4.6s | First Light): The crystal chandeliers flicker alive one by one above her as she starts singing, cold cyan light raining down through the stage fog.
• SHOT 3 (4.6–9.5s | Beat Sync): Medium shot; every beat of the music fires a pulse of light through the floor's cyan trim lines under her feet as she sings and steps forward in rhythm.
• SHOT 4 (9.5–12.3s | Waveform Halo): Close-up; glowing cyan waveform ribbons rise from the mic and orbit her head like a halo while she sings with a sly smirk.
• SHOT 5 (12.3–15s | Level Surge): Wide shot; the LED screen behind her erupts into towering equalizer-like light columns surging upward with her voice, spotlights flaring. Hold final frame.

Weighty natural animation, oversized jacket reacting fluidly, 24fps filmic motion. NOT photorealistic, no 3D render, no cel shading, no bold outlines, no text.

Cinematic 2.5D animation, painterly semi-realistic anime style. Palette strictly limited to black, white, and electric cyan. NOT photorealistic, NO glossy 3D CGI, NO flat cel-shaded cartoon, no bold outlines. No text, no typography, no letters on screen.

WORLD: The venue is exactly the massive luxurious concert arena from <Picture 2>: black glass and chrome center stage, colossal curved LED screen glowing with electric-cyan waveforms, white marble VIP balconies, crystal chandelier light rigs, drifting stage fog, volumetric cyan spotlights.

CHARACTER: The young woman from <Picture 1>, exactly as designed: jet-black high ponytail with electric-cyan inner color streaks, glowing cyan star-shaped hairpin, sleek visor headset with a thin boom microphone, oversized black techwear bomber jacket with white panels and glowing cyan trim lines, white crop top, black fingerless gloves, holding a wireless microphone with a glowing cyan grille. Sharp ice-blue eyes, painterly matte skin. Her singing mouth movements are precisely synchronized with <Audio 1>.

INTRO & VERSE SHOT DESIGN (5 Cuts, Narrative Entrance):
• SHOT 1 (0–2s | Approach): Behind-the-back shot in a dark backstage corridor; she walks toward the blinding cyan light of the stage entrance, ponytail swaying, whispering the opening vocal.
• SHOT 2 (2–4.6s | Step Out): She steps out onto the grand stage into the vast arena; the camera swings around to her front as she lifts the mic and begins to sing, fog parting around her boots.
• SHOT 3 (4.6–9.5s | Own the Stage): Tracking shot as she strides confidently up the glowing stairs to center stage singing, the giant LED screen waking up with cyan waveforms as if responding to her voice.
• SHOT 4 (9.5–12.3s | Eye Contact): Close-up. She sings straight into the lens with a fearless smirk, one eyebrow raised, cyan light dancing in her ice-blue eyes.
• SHOT 5 (12.3–15s | Claim the Throne): Wide hero shot at center stage — she spreads her arms as every spotlight in the arena snaps toward her at once. Hold final frame.

Weighty natural animation, oversized jacket reacting fluidly, 24fps filmic motion. NOT photorealistic, no 3D render, no cel shading, no bold outlines, no text.