🎬 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, high-end cosplay photography look—warm candle key, shallow depth, moody library haze—a high-angle medium already locked to <Picture 1>: the woman (S1) already cosplays Rem—short bright-blue bob with bangs over one eye, light-blue contacts, black-white checkered headband with white spikes, revealing black-white maid outfit with white ruffled collar and black bow, detached black sleeves with white cuffs; she is already on all fours on the dark wooden floor, hands flat, already looking up into the lens. Lit pillar candles around her; bookshelves soft in the back; golden candelabra upper right. She shifts her weight once, eyes still up. The woman (S1), soft: [Japanese] ご主人様…… The camera holds with tiny amplitude at slow speed. [Shot 2] At 00:03.200, the camera cuts to a dedicated close-up of her face only: blue eyes, bangs, checkered headband edge, candle glow on skin; not a full-body wide. The handheld frame holds with tiny amplitude at slow speed. [Shot 3] At 00:07.000, the camera cuts to a full wide shot and holds to 00:08.000: her complete cosplay figure still on all fours—Rem maid outfit, blue hair, hands on the floor, looking up—candles on dark wood, library shelves, warm orange cosplay tone all readable. No new dialogue. No on-screen captions, titles, or extra lettering. overall_soundscape: Candle wick crackle, wood floor hush, one short Japanese line, distant room air. non_diegetic_music: none.

    Generation Settings

    Parameters used to generate this content

    CFG Scale1
    Sampler
    Euler a
    Steps19
    Info
    Video
    Likes
    29
    Created
    8/26/2026
    Base Model
    LTXV 2.5
    Creator
    AiMetatron
    Source
    CivitAI
    Actions