【検証】Seedance 2.5でAI Music Video制作！音声同期とモデル使い分けの極意│Pollo.ai

[Image 1 (Frontal extreme close-up)]

Ultra realistic close-up portrait of the same beautiful East Asian woman with long dark brown hair, wearing black leather crop top and arm sleeves, singing passionately, mouth slightly open forming the "ah" sound of "lost", soft emotional expression with gentle sad eyes, dramatic dusty urban city background at dusk, cinematic lighting, highly detailed face and lips, sharp focus on mouth, 8k, masterpiece

[Image 2 (high-angle shot)]

Same beautiful East Asian woman, long dark hair flowing, black leather outfit, slight low-angle close-up, head tilted softly, mouth forming the soft "uh" of "love", warm melancholic smile in the eyes, dusty city skyline behind, golden hour light mixed with dust particles, highly detailed lips and teeth, photorealistic, 8k

[Image 3 (Extreme close-up of the mouth) *Most critical shot for lip-sync verification.]

Extreme close-up of the same woman's mouth and lower face only, long dark hair strands visible, black leather collar, lips precisely forming the "come come" double "k" sound, teeth slightly showing, realistic moisture on lips, soft dust particles floating, dramatic side lighting, ultra detailed lips, tongue and teeth, photorealistic, 8k, focus only on mouth movement

[Image 4 (Reaching out + face)]

Same beautiful East Asian woman reaching her right hand toward camera, black leather crop top and studded belt, long dark hair, face in close-up singing "dust", mouth forming sharp "s" sound with teeth visible, emotional intense gaze, dusty urban background with flying dust and city buildings, cinematic depth of field, highly detailed face and hand, photorealistic, 8k

[Image 5 (End frame)]

Same woman, slightly pulled back medium close-up, black leather outfit, long dark hair, soft final breath expression after singing, gentle closed-mouth smile with lingering emotion, large amount of dust swirling around her, city skyline at dusk, cinematic lighting, photorealistic, 8k, peaceful ending frame

Please combine the lyrics, the attached audio, and the five images in a balanced way to create a dynamic video that is perfect for a promotional clip.
[lyrics]
You're in love with the way I make you feel
'Cause I already lost the one that I love

Image (Frontal extreme close-up)
Ultra realistic close-up portrait of the same beautiful East Asian woman with long dark brown hair, wearing black leather crop top and arm sleeves, singing passionately, mouth slightly open forming the "ah" sound of "lost", soft emotional expression with gentle sad eyes, dramatic dusty urban city background at dusk, cinematic lighting, highly detailed face and lips, sharp focus on mouth, 8k, masterpiece

【動画の長さ13s│共通Prompt】
Please combine the lyrics, the attached audio, and the five images in a balanced way to create a dynamic video that is perfect for a promotional clip.
[lyrics]
You're in love with the way I make you feel
'Cause I already lost the one that I love
If you come come close I'll leave you in the dust
Image 1 (0:00–0:03: Frontal extreme close-up)
Ultra realistic close-up portrait of the same beautiful East Asian woman with long dark brown hair, wearing black leather crop top and arm sleeves, singing passionately, mouth slightly open forming the "ah" sound of "lost", soft emotional expression with gentle sad eyes, dramatic dusty urban city background at dusk, cinematic lighting, highly detailed face and lips, sharp focus on mouth, 8k, masterpiece
Image 2 (0:03–0:06, high-angle shot)
Same beautiful East Asian woman, long dark hair flowing, black leather outfit, slight low-angle close-up, head tilted softly, mouth forming the soft "uh" of "love", warm melancholic smile in the eyes, dusty city skyline behind, golden hour light mixed with dust particles, highly detailed lips and teeth, photorealistic, 8k
Image 3 (0:06–0:09: Extreme close-up of the mouth) *Most critical shot for lip-sync verification.
Extreme close-up of the same woman's mouth and lower face only, long dark hair strands visible, black leather collar, lips precisely forming the "come come" double "k" sound, teeth slightly showing, realistic moisture on lips, soft dust particles floating, dramatic side lighting, ultra detailed lips, tongue and teeth, photorealistic, 8k, focus only on mouth movement
Image 4 (0:09–0:12: Reaching out + face)
Same beautiful East Asian woman reaching her right hand toward camera, black leather crop top and studded belt, long dark hair, face in close-up singing "dust", mouth forming sharp "s" sound with teeth visible, emotional intense gaze, dusty urban background with flying dust and city buildings, cinematic depth of field, highly detailed face and hand, photorealistic, 8k
Image 5 (0:12–0:13 End frame)
Same woman, slightly pulled back medium close-up, black leather outfit, long dark hair, soft final breath expression after singing, gentle closed-mouth smile with lingering emotion, large amount of dust swirling around her, city skyline at dusk, cinematic lighting, photorealistic, 8k, peaceful ending frame