🎬 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, vertical erotic short-drama look—soft warm light, wet-skin sheen—a tight medium close-up already locked to <Picture 1>: three young East Asian people already soaked in sweat. Left woman (S1) in a thin white spaghetti-strap top, eyes already closed, flushed cheeks, wet dark hair; right man (S2) shirtless, eyes open on her; a saliva strand already between their open mouths. Center-back woman (S3) already between them, looking down at their lips, mouth already parted, damp bangs. They already lean in and tongue-kiss, S1 and S2 only. All three faces stay readable. The woman (S1), against his mouth: [Chinese] 再近一点…… The camera holds with tiny amplitude at slow speed. [Shot 2] At 00:04.000, the camera cuts to a dedicated close-up of S1 and S2’s tongues—wet, slow, the saliva strand breaking and reforming; S3’s eyes at the top edge of frame. The handheld frame stays tight with tiny amplitude at slow speed. [Shot 3] At 00:08.000, the camera returns to a medium close-up of all three faces and holds to 00:10.000: S1 and S2 still tongue-kissing; S3 still between them watching, lips parted—wet skin, no room-wide. No new dialogue. No on-screen captions, titles, or extra lettering. overall_soundscape: Wet kiss, breath, one short Chinese line, close hush. 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