z00t0p1a. For the target video, at 0.00 seconds into the… | Deepfake AI视频

生成此视频所用的文字转视频提示词

z00t0p1a. 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] 3D CG animated feature-film look matching <Picture 1>, soft diner lighting, shallow depth of field. The same female red-fox anthro from <Picture 1> sits in the booth: orange fur, cream muzzle, green eyes, lidded sly expression, green leaf-print short-sleeve shirt, blue striped tie, one paw on the speckled table. The camera holds a medium close-up on her face and shoulders, static shot with a very small push in at slow speed. She speaks in a low-medium adult female fox voice (S1), slightly dry: <d>[English] What do you call a three humped camel?</d> Her mouth closes. She holds still for a short beat, eyes on camera, one ear flicks, no speech. Then she delivers the punchline (S1): <d>[English] Pregnant!</d> Right after the word she laughs once with a short husky rasp, muzzle opening, shoulders giving a small shake. After the laugh she keeps the grin and does not speak again. Face, markings, shirt and booth stay as in <Picture 1>. overall_soundscape: Quiet diner room tone, distant muffled chatter. Soft cloth shift. After the punchline, a brief husky two-beat laugh, then only room tone. No other speech. non_diegetic_music: N/A