Halloween character parade — English R2

Video reference

Draft title: Halloween character parade — English R2

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 performer. Maintain exact facial features, hair, and attire.
SOUNDTRACK SPECIFICATION: 105 BPM 4/4 spooky hip-hop bounce with rolling 808s, toy piano melodies, and punchy rap vocals.
SCENE AND CAMERA: Halloween street parade illuminated by warm lanterns and floating streamers. Medium shot tracking dancer moving forward.
ORIGINAL LYRICS:
0.5-2.5s: "Lanterns high, step into the night,"
2.8-5.0s: "Spooky treats popping left and right!"
5.3-7.5s: "Spin around, make the magic glow,"
7.8-9.8s: "Put your hands up, steal the show!"
PERFORMANCE TARGETS:
0.0-2.5s: Rhythmic side-step groove while lip-syncing line 1, pointing playfully toward the lanterns.
2.5-5.0s: Skip forward with high-knee bounce, gesturing rhythmically to both sides matching line 2.
5.0-7.5s: Graceful twirl with arms sweeping outward, stopping square to camera with glowing trail effects under shoes.
7.5-10.0s: Emphatic punch-step forward, thrusting both hands toward the sky on beat 4 with purple flare effects.
PRIORITY: Precise lip-sync timing, crisp syllable alignment ahead of beat, stable identity.
EXCLUSIONS: No drifting identity, no extra fingers/limbs, no subtitle text, no audio cloning.

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