Halloween character parade — Mandarin Chinese R1

Video reference

Draft title: Halloween character parade — Mandarin Chinese R1

Watch external video ↗ · Playback is available at the source.

Reconstructed prompt

Reconstructed from the video, not the author's prompt. This draft has not been generation-tested. Results vary by model and photo.

FORMAT: 9:16 vertical video, 10 seconds, single continuous take.
REFERENCE ROLES: @Image1 is the sole lead dancer. Maintain costume, hair, and visual identity precisely. If non-human, use stylized jaw motion without human teeth.
SOUNDTRACK SPECIFICATION: 124 BPM 4/4 upbeat electro-swing rap track with brass stabs, bouncy synth bass, festive chimes, and crisp Mandarin rap vocals performed by @Image1. Performer's lips and jaw are precisely synchronized with every spoken syllable.
SCENE AND CAMERA: Night festival street decorated with glowing jack-o'-lanterns, hanging lanterns, and falling confetti. Full-body medium-wide shot smoothly tracking with the dancer's steps.
ORIGINAL LYRICS:
0.0-2.5s: 夜幕降临狂欢起
2.5-5.0s: 南瓜灯下踏节拍
5.0-7.5s: 旋转跳跃踩星火
7.5-10.0s: 魔法点亮这一刻
PERFORMANCE TARGETS:
0.0-2.5s: Front-facing gentle bounce, hands clasped lightly near chest, sway left to right on the downbeat while delivering opening rap line.
2.5-5.0s: Turn slightly stage-right, executing three rhythmic skipping steps forward, kicking lightly on beats 1 and 3 while rapping second line.
5.0-7.5s: Open arms outward to the sides, spin 180 degrees back to face camera with light ground sparkles underfoot while delivering third line.
7.5-10.0s: Step forward into a medium close-up, pump both fists playfully, then raise both hands overhead as magical starburst sparkles emit on the final hit, rapping final line with an energetic expression.
PRIORITY: Flawless identity lock to @Image1, tight lip sync matching Mandarin lyrics, smooth anime-style physics, fluid leg motion.
EXCLUSIONS: Identity morphing, extra limbs, out-of-sync mouth movement, text, watermarks.

INPUT AND AUDIO BOUNDARY: @Image1 is the sole uploaded photo; no other image, audio or video reference. Preserve the uploaded person/pet identity, hair or fur markings and body proportions, or the reference object’s geometry and materials; do not copy another performer’s identifying appearance. Generic supporting figures are distinct. All BPM, instrumentation and lyrics are newly authored targets, not measurements or quotations of the source. Generate original audio, never clone source music, melody or a named voice. Lips match the generated vocal exactly, never precede it; during instrumental sections the mouth stays relaxed. If the input is a pet use stylized jaw articulation only, never human lips or human teeth. No recognizable copyrighted character appearance, text, logos or watermarks. Do not change the input subject’s gender or age. No generation has been tested.

Copy prompt