Minimax H3 Guitar Audio-Sync Performance Prompt

integrated_multimodal_description: <Image 1> is the exact starting frame. <audio 1> is the exact supplied opening music and rhythm reference. Realistic cinematic nighttime music-video performance, 16:9 widescreen. Use <Image 1> as the exact visual starting frame. Preserve the exact same young male singer, facial identity, curly hair, plaid shirt, white T-shirt, dark jeans, electric guitar, metal folding chair, abandoned drive-in theater, old drive-in speaker poles, large movie screen, wet ground, nighttime environment, lighting and overall composition. The man remains seated in the same location near the old drive-in movie screen. IMPORTANT - HUMAN REALISM: The man must look like a REAL HUMAN BEING photographed with a cinema camera. Preserve natural facial structure and identity from <Image 1>. Natural visible skin texture. Subtle pores. Tiny natural skin imperfections. Realistic lips. Natural eyes. Individual hair strands. Natural facial highlights and shadows. NO plastic skin. NO waxy skin. NO porcelain appearance. NO beauty-filter smoothing. NO airbrushed face. NO artificial AI-perfect facial texture. NO excessive facial sharpening. NO glossy synthetic skin. His face should retain subtle real-world imperfections throughout the shot. GUITAR PERFORMANCE - VERY IMPORTANT: <audio 1> is the exact performance, tempo and timing reference. The electric guitar heard in <audio 1> controls the man's guitar-playing motion. He is visually playing along with the actual guitar performance heard in the supplied recording. His picking/strumming hand responds directly to the audible guitar rhythm. The hand uses SMALL, CONTROLLED and NATURAL wrist-and-hand movements across the strings. Do NOT use large exaggerated arm strumming. Each visible picking or strumming movement should feel motivated by the individual guitar attacks and rhythmic pulse heard in <audio 1>. When the guitar rhythm becomes stronger, his picking hand responds with slightly stronger movement. During softer passages, his picking movement becomes smaller and more restrained. Do NOT simply repeat a generic constant strumming animation. The motion should change naturally with the supplied guitar performance. His fretting hand remains naturally wrapped around the guitar neck. As the guitar part progresses, his fretting fingers make believable changes in position along the fretboard. The fingers press naturally against the strings and occasionally shift to new plausible chord or note positions in coordination with the musical phrasing. Do NOT attempt exact note-for-note fingering. PRIORITY: believable rhythm, believable timing, natural hand contact with the instrument, and realistic musician body language. The goal is NOT perfect guitar transcription. The goal is to create the convincing visual impression that this man is actually performing the electric-guitar part heard in <audio 1>. HAND AND GUITAR CONSISTENCY: Both hands remain physically connected to the guitar correctly. His picking hand remains near the strings and pickups. His fretting hand remains naturally positioned on the neck. No random finger waving. No impossible finger positions. No floating fingers. No fingers passing through the guitar. No extra fingers. No fused fingers. No disappearing hands. The electric guitar remains rigid and physically consistent throughout the shot. The guitar body, neck, strings, pickups, bridge, tuning pegs and proportions never deform, bend, melt or change. BODY PERFORMANCE: He is emotionally absorbed in the music. His body subtly feels the rhythm of <audio 1>. Small natural shoulder movement. Very slight head movement following the musical pulse. Occasional subtle torso movement. His posture remains relaxed and believable for a guitarist seated on a metal folding chair. He does NOT dramatically rock backward and forward. He does NOT bounce excessively. He does NOT perform exaggerated rock-star movements. The performance is intimate, restrained and emotional - a man alone at an abandoned drive-in playing music connected to memories of a lost love. FACIAL PERFORMANCE: He is NOT singing during this opening test. His mouth remains naturally relaxed. No lip-sync. No talking. No random mouth movement. His expression is thoughtful, slightly melancholy and emotionally absorbed in the music. Occasionally his eyes may naturally glance downward toward the guitar, but he should not constantly stare at his hands. Keep the performance subtle and realistic. CAMERA: Keep the camera CLOSE because facial consistency is important. Use a cinematic medium-close composition. Frame him so we clearly see: his face, upper torso, electric guitar body, picking/strumming hand, and enough of the guitar neck and fretting hand to clearly understand that he is playing. Do NOT crop away the picking hand. Do NOT crop away the fretting hand. Do NOT pull back into a distant wide shot. Begin from the exact framing of <Image 1>. During the performance, use ONE very slow, subtle cinematic push toward him. No dramatic camera movement. No orbit. No crane movement. No handheld shaking. No rapid cuts. No changing camera angles. The camera movement should be almost unnoticeable, allowing the guitar performance and emotion to carry the shot. As the camera slowly pushes closer, his face gradually becomes slightly more prominent while BOTH hands and the important portions of the guitar remain visible. ENVIRONMENT: It is nighttime at an old abandoned drive-in theater. The large weathered movie screen remains behind him and softly out of focus. Old drive-in speaker poles remain visible in the surrounding environment. Wet pavement and small puddles create subtle realistic reflections. The drive-in remains completely empty. No audience. No vehicles. No pedestrians. No additional musicians. No extra people. The environment remains still and lonely. LIGHTING: Cool natural blue nighttime ambience. Subtle warm practical illumination from portions of the old drive-in environment. Soft realistic light falls across his face. Natural facial shadow detail. Subtle highlights reflect from the electric guitar. Wet pavement catches small reflections from the surrounding light. Maintain realistic exposure on his face throughout the entire shot. Do NOT make the nighttime environment so dark that his face or hands become difficult to see. STYLE: Photorealistic live-action music video. Real cinema-camera photography. Natural skin texture. Realistic hands. Realistic electric guitar. Shallow cinematic depth of field. Subtle natural film texture. No excessive digital sharpening. No artificial CGI appearance. No glossy AI appearance. No dreamy fantasy effects. No slow motion. TIMING: Use the complete supplied opening audio section. The guitar performance should continuously respond to the rhythm and phrasing of <audio 1> from beginning to end. The shot remains patient and cinematic rather than introducing unnecessary action. AUDIO: <audio 1> is the ONLY music reference. DO NOT generate replacement music. DO NOT add new guitar music. DO NOT add additional instruments. DO NOT add vocals. DO NOT add dialogue. DO NOT add ambient soundtrack or cinematic score. Use the supplied audio as the performance timing reference. The primary test is whether the man's visible guitar-playing motion convincingly follows the guitar rhythm contained in <audio 1>.