Spooky Scary Skeletons vampire / anime dance — Mandarin Chinese R1

Video reference

Draft title: Spooky Scary Skeletons vampire / anime dance — 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: 10-second vertical video, 9:16 aspect ratio, single continuous take.
REFERENCE ROLES: @Image1 defines the sole lead dancer. Maintain exact identity and casual streetwear styling from reference image.
SOUNDTRACK SPECIFICATION: Original bouncy hip-hop groove at 105 BPM, 4/4 time. Bouncy 808 kick, crisp snare, syncopated hi-hats, and smooth Rhodes chord loops with clear original Mandarin rap vocals.
SCENE AND CAMERA: Fixed low-angle medium-full shot in a high-ceiling modern home foyer with hardwood flooring, glass staircase railing, and neutral background luggage. Consistent bright daylight.
ORIGINAL LYRICS:
0.0-2.5s: 踩着重拍往前走 (Cǎi zhe zhòngpāi wǎng qián zǒu)
2.5-5.0s: 律动跟着节奏扭 (Lǜdòng gēnzhe jiézòu niǔ)
5.0-7.5s: 鼓点敲击心跳声 (Gǔdiǎn qiāojī xīntiàoshēng)
7.5-10.0s: 轻松自如定个格 (Qīngsōng zìrú dìng gè gé)
PERFORMANCE TARGETS:
0.0-2.5s: Lead steps into rhythm, bouncing lightly on balls of feet with elbows loose at sides, rapping Line 1 with tight lip synchronization.
2.5-5.0s: Dynamic weight shift and hop steps, head nodding gently to the downbeat, delivering Line 2 with natural vocal articulation.
5.0-7.5s: Centered bounce groove with slight torso rotation and casual arm swings synced to snare hits, performing Line 3.
7.5-10.0s: Side-to-side stepping recovery into a relaxed finish pose facing forward, rapping Line 4 with crisp jaw sync.
PRIORITY: Exact likeness retention of @Image1, natural body mechanics, perfectly timed rhythmic bouncing, and precise Mandarin vocal lip sync.
EXCLUSIONS: Identity drift, background warping, floating limbs, watermarks, on-screen text overlays, unsynchronized mouth movement.

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