Check One Check Two lip-sync — Mandarin Chinese R1

Video reference

Draft title: Check One Check Two lip-sync — 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, 24fps.
REFERENCE ROLES: @Image1 is the sole lead performer. Preserve facial identity and hair from @Image1 without copying source stubble; use a generic navy jacket and white open-collar shirt.
SOUNDTRACK SPECIFICATION: Target BPM 96, 4/4 time. Melodic Chinese urban pop beat with crisp 808 percussion, warm electric piano chords, and clean vocal delivery. Vocal begins slightly ahead of beat.
SCENE AND CAMERA: Outdoor villa patio with stone tiles, swimming pool edge on left, metal railing and green hills under an overcast blue sky. Medium shot, locked camera with subtle breathing motion.
ORIGINAL LYRICS: 阳光洒在水面 (0:00-0:02.5) / 准备好走向明天 (0:02.5-0:05) / 每一个节奏都在变 (0:05-0:07.5) / 听见声音就向前 (0:07.5-0:10)
PERFORMANCE TARGETS:
0.0-2.5s: Performer begins singing directly into camera, natural upper-body sway, lips tightly synced to first Mandarin line.
2.5-5.0s: Brings right hand forward, gesturing toward camera with index finger on key syllable, matching vocal emphasis.
5.0-7.5s: Lowers hand to side, mouth forms open vocal vowels, chest rises slightly with confident posture.
7.5-10.0s: Concludes lyrical delivery, mouth closes into a mild confident smile, maintaining steady eye contact.
PRIORITY: Absolute identity fidelity to @Image1; sharp lip-sync synchronization.
EXCLUSIONS: No identity drift, no morphing background, no extra limbs, no cloned original music, no subtitles or 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