🎬 Loading...
    Prompt

    For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced. integrated_multimodal_description: [Shot 1] Live-action, vertical 9:16, bright rural noon—a full-figure medium already locked to <Picture 1>: the nude country girl (S1) already sits on the low stacked-stone wall, legs already spread, feet dangling, dark hair pulled back, looking toward camera; earthen houses, tiled roofs, green mountains, blue sky as in the still. She already raises one arm and waves toward the distance, then breaks into a happy open-mouth laugh, torso tipping backward. Her whole seated body stays readable. No spoken lines. The camera holds with tiny amplitude at slow speed. [Shot 2] At 00:03.200, the camera stays on her full figure as the laugh throws her further back: hands leave the stones, she loses balance and falls backward off the wall toward the houses, breasts and hair lifting with the drop. Not a valley-wide. The handheld frame follows her fall with tiny amplitude at slow speed. [Shot 3] At 00:07.000, the camera holds a medium of her nude body on the ground just behind the wall, still laughing breathlessly, the stone wall, village houses and mountains all in frame, and holds to 00:08.000—never a landscape-wide. No on-screen captions, titles, subtitles, or extra lettering. overall_soundscape: Her laugh, stone scrape, a soft thud, distant village hush, cicadas. No burned-in text. non_diegetic_music: none.

    Generation Settings

    Parameters used to generate this content

    CFG Scale1
    Sampler
    Euler
    Steps8
    Info
    Video
    Likes
    0
    Created
    8/28/2026
    Source
    CivitAI
    Actions