One reference image holds a five-shot K-pop performance together

This prompt scripts a fifteen-second K-pop rap video across five timed shots, moving from a Seoul street to a desert with a giant mecha to a tight subway close-up. It suits anyone testing how far a single reference image can hold a performer's face and outfit together across wildly different settings in one generation.

Model: Seedance 2

create a video based on reference @ audio montage, multi-shot cinematic music video, do not use a single camera angle or single cut, cinematic lighting, photorealistic, 35mm film quality, professional color grading, sharp focus, high detail texture, film grain, depth of field mastery, ARRI ALEXA aesthetic facial character and clothing for @ img1