How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video. integrated_multimodal_description: [Shot 1] 2D-animated in the exact style of <Picture 1>, a medium full-body shot begins locked to the composition of the reference: the hyena girl stands in a lively three-quarter pose against the plain background, long black hair with pink underside flowing, hyena ears under the black peaked cap with green band and gold star, yellow eyes, wide grin. She wears the black-and-green military-style jacket with gold buttons, utility belt, cargo pants, and black boots with green laces. A spotted tail curves behind her. One black-gloved hand holds a short baton raised, the other is raised in a peace sign. (S1) is the hyena girl. She has a bright, cutely manic voice. She shifts her weight, tail giving a sharp wag, and tips the brim of her hat with the baton hand in a quick, theatrical flourish. Still grinning, she speaks with rising energy: <d>[English] Friends, it has come to my attention that we have entered a turf war. There is a time when fate calls upon us to act and our time is now. Give those pink hat bastards not an inch of digital ground! Cry havoc and let slip the hyena girls of war! Hehee… or something. Anyway hat me guys!</d> She finishes with a bright cackle, peace sign held high, tail still moving. The camera performs a gentle, slow push-in of small amplitude that tracks her slight bounce and keeps her fully in frame. overall_soundscape: Close-mic’d female voice only — bright, cutely manic speech rising into a short cackle. Quiet room tone underneath. No other ambient noise. non_diegetic_music: N/A