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.
