For the target video, at 0.00 seconds into the target… | Deepfake AI视频

作者头像
@dajuewushizhen

生成此视频所用的文字转视频提示词

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 cinematic, elegant Chinese classical dance, 2:3 vertical, bright soft daylight. The same young East Asian woman from <Picture 1> — face, black single side braid over one shoulder with wispy bangs, silver-white floral hair crown with pearl tassels, pale celadon-green cross-collar Hanfu with gold-and-white floral embroidery, deep green waistband and dark green skirt preserved exactly — stands on a bamboo raft on the jade-green river; the river behind her stays soft and out of focus, with no wide establishing shot. The camera holds a medium close-up framed on her upper body and face, steady and unhurried, no fast motion. She dances with upper-body classical gestures only: both hands rise slowly into a held-palm pose, wrists rolling in soft waves, shoulders relaxed, wide sleeves lifting gently; she traces a slow cloud-hand movement across her chest, arms kept within the upper-body frame. [Shot 2] At 00:07.000, the camera keeps the same medium close-up, giving only a slow small arc to a three-quarter view. One hand sweeps a sleeve outward while the other rests near her waist, then both hands fold softly in front of her chest and open outward again in a measured breath; her expression is serene, gaze lifting toward the lens. No rear view, no distant wide shot, no lower-body framing. overall_soundscape: Water rippling around the raft, a light river wind, faint creak of bamboo, soft swish of Hanfu sleeves; no dialogue. non_diegetic_music: N/A