Lazy rhythmic dance, deep brown wavy hair AI Image Prompt
Reference image is AI-generated, use the face; change hairstyle to deep brown wavy long hair, fluffy and lazy, air bangs; wear the clothes from image 2 (image 2 is also AI-generated). Camera follows the girl dancing 'Jia Tong Yao', lazy and rhythmic dance, smooth throughout. Actions include: swaying hips left and right, hands gently rotate near face, gentle chest sway, small shoulder shakes with arm circles, climax with cat paw hand gestures outward, left and right shoulder bumps, point to face and hip, hip rotation with butt bounce, left and right hip thrusts as ending. Background music is 'Dao Ma Dao Ma (DJ FUNK Version)', perfectly matched with the beat; camera pushes and pulls with the beat; long hair flows with movements. Background: ultra HD 8K, realistic photography, iPhone real-shot texture. Modern minimalist indoor empty scene, main subject is a light wood-framed interior door with matte cream flat panel, silver metal handle on the left, walls same color as door, no decorations, no clutter, no people. Soft even lighting, diffuse natural light, clean and transparent, no distortion, no artifacts, realistic details. 9:16 vertical composition, suitable for women's clothing e-commerce background. Soft indoor lighting illuminates full body. Also the scene is inside a bedroom with a soft spotlight from above lighting the girl, overall soft light and strong atmosphere. Exclude: blur, low resolution, noise, watermark, text, logo, distortion, deformation, malformed facial features, stiff movements, shaking, aspect ratio distortion. Original aspect ratio.
Content: Subject uses face from AI reference image, modified hairstyle and clothes; detailed dance actions (Jia Tong Yao step-by-step); scene is modern minimalist interior with door; realistic photography style 8K; 9:16 vertical composition; soft even lighting, diffuse natural light; creamy color palette; matte door material; camera push/pull with beat; original aspect ratio; relies on reference images.
Pros: Detailed synchronization of actions with music beats; clear and unified scene and lighting design.
Cons: Excessive step-by-step action description may increase generation length/difficulty; reliance on multiple reference images may compromise consistency.
Reference image: Obvious reference-image dependency (face from image 1, clothes from image 2)
Source materials are collected from publicly accessible web pages. Contact us if a rights issue needs review. Copyright & Privacy