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, the woman shown in <Picture 1> — late 30s to early 50s, short asymmetrical bob in deep burgundy and fiery auburn with reddish-orange highlights, water droplets clinging to the tips, black V-neck top with a slight leathery sheen, rain-soaked skin — stands in a rainy urban street at night, bokeh streetlights in warm yellow and cool blue blurred behind her. She is drenched, her expression hard and resolute. The camera holds a medium close-up in a slight profile angle as she slowly turns her head upward, tilting her chin toward the dark sky. Rain strikes her face directly — droplets landing on her forehead, cheeks, and closed lips, streams trickling down along her jawline and neck. Her brow furrows deeper, her jaw tightens, her eyes narrow against the downpour, and the muscles in her neck cord with visible tension. The angry, dripping-wet woman with a raw, commanding voice (S1) suddenly shouts upward at the sky: <d>[English] I want to speak to your manager.</d> Her whole body stiffens with the force of the yell, water shaking from her hair with the movement. The camera pushes in with small amplitude at slow speed toward her face as the echo of her shout fades into the rain. overall_soundscape: Steady heavy rain falls on pavement and skin, with individual droplets audibly striking fabric and flesh. A sharp intake of breath precedes the shout, and wet hair whips faintly as she tilts her head back. Distant traffic hiss and tyre spray linger underneath throughout. non_diegetic_music: A low, sustained cello drone at slow tempo builds faintly in volume as she tilts her head upward, then cuts abruptly the moment she shouts.
Parameters used to generate this content
The node graph used to generate this content — pan and zoom to explore, or download it to run in ComfyUI.
AI models used to generate this content