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

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] Naturalistic live action with controlled contrast, warm sunset light, and measured framing. A steady medium close-up shows the woman standing in the desert landscape at sunset, holding the moss-covered rock with the visible word "MOSS" beside her face. The sandy terrain, distant hills, and low sun remain softly visible behind her. The camera remains static, with no cut, no zoom, and no pan. She keeps her gaze directed into the camera with a calm, confident expression. Her expression gradually shifts into a subtle smirk that slowly widens over the course of the shot. While continuing to hold the rock up near her face, she lifts her free hand and points upward at the rock in a clear, simple gesture, as if drawing attention to it. She maintains steady eye contact with the camera while holding the pointing gesture. She finishes with the slightly widened smirk, still pointing at the rock and holding a stable pose. overall_soundscape: Soft desert ambience with faint open-air breeze and quiet natural outdoor room tone. Subtle clothing and hand-movement rustle accompany the pointing gesture. No speech. non_diegetic_music: N/A