🎬 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] Soft semi-realistic anime illustration with gentle indoor daylight, a medium close shot begins from <Picture 1>, fully preserving the young woman’s appearance, including her black hair tied with pink ribbons, large blue eyes, flushed cheeks, pink oversized T-shirt, white shorts, and her seated posture on the bed. The room remains softly lit with cool blue-gray walls and natural morning light falling across the bed. The emotional context is a quiet, intimate everyday moment: she has just heard the viewer call to her or noticed the viewer looking at her, and she turns her attention back with a mixture of surprise, shyness, and warmth. The mood is natural, gentle, and slightly bashful. Motion remains controlled and compact, emphasizing eyes, mouth, hands, shoulders, breathing, and tiny posture shifts rather than any large movement. The camera performs a subtle slow push-in with extremely light drift, preserving the original composition and body silhouette. In the first second, she gives a small surprised blink, her lips parting just a little more as if she is about to respond but needs a beat to process the moment. A few loose strands of hair near her cheek shift softly, and her fingers resting on the bedspread press down a little as she steadies herself. From 00:01.000 to 00:03.500, she lowers her gaze briefly, then looks back up at the viewer with a shy softness in her eyes. Her shoulders draw in just slightly, and her hand on the bed makes a tiny adjusting motion against the sheet, creating a natural sense of nervousness without changing her overall seated silhouette. In a young woman’s voice, soft, slightly sleepy, gentle, with a faint shy warmth (S1), she says quietly: <d>[Japanese] えっ……いま、わたしのこと呼んだ?</d> Her lips move delicately and naturally, and the scene remains focused on expression and restrained body language. From 00:03.500 to 00:06.000, the surprise fades into a small, embarrassed smile. She tilts her head by a very slight amount and lets out the softest breath, as if relaxing after realizing the moment is harmless and familiar. Her fingers loosen on the bedspread, and one knee shifts only a fraction, just enough to make the pose feel alive without introducing unstable motion. The camera eases a little closer as the morning light continues to glow softly across her shirt and legs. From 00:06.000 to 00:07.500, she gathers a little courage and lifts her eyes fully to meet the viewer’s, her expression growing warmer and more openly affectionate in an everyday, unguarded way. In the same soft, slightly sleepy voice (S1), she says: <d>[Japanese] もう……そんなふうに見られると、ちょっと恥ずかしいよ。</d> In the final half-second, she gives a tiny shy smile and holds the viewer’s gaze, her hand still resting lightly on the bed as the shot ends on a calm, intimate morning moment. All motion remains subtle, readable, and highly consistent. overall_soundscape: Very soft indoor ambience with faint room tone, light fabric movement against the bed, subtle breathing, and the quiet stillness of a morning room. No abrupt background noises or strong environmental distractions. non_diegetic_music: A delicate, warm music bed with soft piano, airy pads, and a faint morning shimmer at a slow tempo. The music remains intimate and understated, with a slight lift after the second line and a gentle quiet finish.

    Generation Settings

    Parameters used to generate this content

    Created with
    ComfyUI
    Seed1
    ComfyUI Workflow

    The node graph used to generate this content — pan and zoom to explore, or download it to run in ComfyUI.

    Info
    Video
    Likes
    2
    Created
    8/13/2026
    Creator
    Zovetry
    Source
    CivitAI
    Actions