Smalltown Boy screaming cat duo

Reconstructed from the video, not the author's prompt

FORMAT: 9:16 vertical video, 10 seconds, 24 fps.

REFERENCE ROLES: @Image1 defines the primary lead pet. If a secondary companion pet is present, synthesize a contrasting generic animal partner that does not clone @Image1.

SOUNDTRACK SPECIFICATION: Target 128 BPM, 4/4 time signature. Energetic 1980s synth-pop instrumental featuring analog synthesizer arpeggios, driving electronic drum beat, and resonant bassline. No human vocal tracks; stylized animal vocalizations (roars/screams/meows) timed to camera lunges.

SCENE AND CAMERA: Outdoor suburban backyard paved ground facing a dark brown wooden paneled fence under overcast soft daylight. Static medium shot initially at eye level with the standing pets, transitioning to a wide-angle slight fisheye effect as subjects leap forward.

ORIGINAL LYRICS: None (pure instrumental with non-verbal comedic pet roars).

PERFORMANCE TARGETS:
- 0.0-2.5s: Lead pet (@Image1) stands bipedal alongside synthesized partner, swaying side-to-side to the 128 BPM pulse, front paws crossed or pumping rhythmically in an 80s retro groove.
- 2.5-5.0s: Both pets alternate stylized expressive head holds and wide jaw drops directly to the camera while maintaining upright dance posture.
- 5.0-7.5s: Synchronized wind-up; both crouch slightly, paws cocked back as the synth build-up peaks.
- 7.5-10.0s: Explosive synchronized leap toward the camera lens, jaws opened wide in exaggerated stylized pet roars, front paws reaching directly into the close-up foreground.

PRIORITY: Strictly preserve @Image1 facial features, fur texture, and coloring. Stylized jaw articulation only without human teeth.

EXCLUSIONS: No identity drift, no human mouth anatomy, no text overlays, no watermarks, no duplicate clones of @Image1.

SOUND EFFECTS: light paw taps on the ground, with no extra spoken words.
INPUT AND AUDIO BOUNDARY: @Image1 is the only uploaded reference. Preserve its identity; generic extras must be distinct. All BPM, instruments and lyrics above are newly authored targets, not measurements of the source. Generate original audio from frame one; never clone the original song, melody or a named voice. Keep the mouth visible and match every visible syllable exactly to the new vocal; keep it naturally relaxed where no vocals are requested. No additional audio or motion reference is required.

Reconstructed from the video, not the author's prompt

FORMAT: 9:16 vertical video, 10 seconds, 24 fps.

REFERENCE ROLES: @Image1 defines the primary lead pet. Synthesize a distinct, generic companion animal partner that does not clone @Image1.

SOUNDTRACK SPECIFICATION: Target 105 BPM, 4/4 time signature. Authored Mandarin Chinese rap-and-dance adaptation featuring hard-hitting 808 sub-bass, rapid hi-hat rolls, syncopated kick drums, and a percussive plucked synth melody. Stylized rhythmic pet vocal delivery matching exact syllable timing, strictly synchronized without leading vocal tracks.

SCENE AND CAMERA: Outdoor suburban backyard paved ground facing a dark brown wooden paneled fence under soft overcast daylight. Eye-level medium wide framing initially, shifting rapidly to a close-up wide-angle perspective as subjects leap toward the camera.

ORIGINAL LYRICS:
- 0.0-2.5s: "爪子摇摆跟着拍"
- 2.5-5.0s: "舞步整齐站起来"
- 5.0-7.5s: "蓄力准备跳出来"
- 7.5-10.0s: "吼声震动这舞台"

PERFORMANCE TARGETS:
- 0.0-2.5s: Lead pet (@Image1) and generic companion stand bipedal on hind legs against the wooden fence, performing synchronized arm and paw rap gestures, stylized jaws articulating lyric line 1 to the 105 BPM beat.
- 2.5-5.0s: Upright dance posture continues as both pets bounce side-to-side, delivering lyric line 2 with stylized jaw drops precisely timed to the rap cadence.
- 5.0-7.5s: Pets perform a synchronized crouched wind-up, tensing front paws backward while articulating lyric line 3 as the 808 bass rolls build up.
- 7.5-10.0s: Energetic forward leap toward the camera lens into extreme close-up, mouths open wide delivering line 4, front paws extended forward under rounded lens distortion.

PRIORITY: Strictly preserve @Image1 fur markings, coloration, and natural facial anatomy. Stylized jaw movements only, strictly retaining natural animal mouth structures without human teeth or lips.

EXCLUSIONS: No identity drift, no human facial or dental anatomy, no duplicated clones of @Image1, no text overlays, no 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.

Reconstructed from the video, not the author's prompt

FORMAT: 9:16 vertical video, 10 seconds, 24 fps.

REFERENCE ROLES: @Image1 defines the primary lead pet. Synthesize a contrasting generic companion pet partner that does not clone @Image1.

SOUNDTRACK SPECIFICATION: Target 116 BPM, 4/4 time signature. Authored English hip-hop rap-and-dance adaptation with driving boom-bap kick and snare, melodic low-end synth bass groove, vinyl scratch accents, and crisp staccato horns. Vocal delivery features rhythmic rhythmic pet barking/growling rap cadence lip-synced strictly to the audible syllables.

SCENE AND CAMERA: Backyard outdoor patio area facing a dark brown wooden fence in even daylight. Camera begins in a static eye-level medium two-shot before capturing an aggressive wide-angle lens surge on the forward lunge.

ORIGINAL LYRICS:
- 0.0-2.5s: "Paws in the air, step into the beat!"
- 2.5-5.0s: "Standing on two, we run this street!"
- 5.0-7.5s: "Crouch down low, ready for the drop!"
- 7.5-10.0s: "Hit the front glass, we never stop!"

PERFORMANCE TARGETS:
- 0.0-2.5s: Lead pet (@Image1) and companion stand bipedal on hind legs, pumping paws rhythmically in a hip-hop groove against the dark fence, jaws articulating line 1 in stylized sync.
- 2.5-5.0s: Upright synchronized dance routine continues with head bobs and outward paw thrusts, stylized mouths opening strictly to match line 2.
- 5.0-7.5s: Both pets crouch down low in unison, paws drawn back into a pre-leap stance as the drum track builds and line 3 is delivered.
- 7.5-10.0s: Explosive synchronized leap forward directly toward the lens, wide-angle lens rounding visible as jaws drop wide delivering line 4 with front paws outstretched into the foreground.

PRIORITY: Strictly maintain @Image1 natural fur texture, color patterns, and species facial traits. Jaw articulation remains stylized animal motion, strictly excluding human teeth, human lips, or morphing.

EXCLUSIONS: No identity drift, no human dental structures, no text overlays, no clone copies of @Image1, no audio desync.

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.