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] Live-action, high-detail realistic style, soft even studio lighting that makes the skin appear extremely fair, luminous and glowing like porcelain. A beautiful young East Asian woman with the exact same face, extremely pale glowing skin, elegant traditional Chinese double-bun hairstyle with ornate golden hair accessories, red bead tassels and earrings as in <Picture 1>. She wears the same black strapless embroidered dress with vibrant colorful floral patterns (large peonies and intricate embroidery). Plain light white background. She stands centered in medium shot (waist-up to upper body). She smiles sweetly and playfully at the camera, forms a heart shape with both hands in front of her chest, holds the pose briefly, then gently lowers her hands, waves one hand, makes light graceful pointing and dance-like upper-body movements with soft shoulder and arm gestures, and returns to another heart gesture while maintaining charming eye contact and elegant expression. Smooth natural motion, slight fabric movement on the dress, hair ornaments sway subtly. Static camera with very slight gentle push-in, one continuous shot. overall_soundscape: Soft clean room tone, subtle fabric rustle from the dress, gentle soft breathing and light movement sounds. No dialogue. non_diegetic_music: Light elegant traditional Chinese-inspired soft instrumental music with gentle pipa or guzheng tones, soft and romantic, low volume, ending cleanly.