Show a fan of banknotes to the camera with a deadpan expression.
Trend status: Not yet measured
Community prompts, reconstructed drafts and external videos, not Rap Selfie outputs. Results vary by model and photo. Reconstructed drafts have not been generation-tested.
Feasibility assessment only; not generation-tested. Exact choreography or original audio usually needs a reference video or audio track.
Evidence dates describe when sources were observed. Missing dates or unreadable evidence are marked Unknown; a video view count alone does not establish a rising trend.
· Third-party commercial trend site; not official platform statistics
The trend site reports an AI dog version above 5.5M and about 431900 uses of a CapCut template on 17 Oct; these were not read directly in this research.
Evidence source ↗No original author prompt is available here. The drafts below were reconstructed from the video.
Reconstructed: Reconstructed from the video, not the author's prompt. No generation has been tested. Review the whole draft before trying; normal safety checks, request limits and credits apply.
Reconstructed
comedy · unknown
FORMAT: 10s vertical 9:16 video, single continuous take. REFERENCE ROLES: @Image1 is the sole lead subject, a dog matching the reference coat and markings, sitting upright. SOUND
Reconstructed from the video, not the author's prompt · tiktok
View original source ↗
Reconstructed from the video, not the author's prompt
FORMAT: 10s vertical 9:16 video, single continuous take. REFERENCE ROLES: @Image1 is the sole lead subject, a dog matching the reference coat and markings, sitting upright. SOUNDTRACK SPECIFICATION: 128 BPM trap beat, bouncy 808s, hi-hat rolls. Energetic comedic English rap vocals with crisp canine ad-libs. SCENE AND CAMERA: Eye-level bedroom shot matching @Image1 background, ceiling fan visible overhead, soft indoor daylight, stationary lens with subtle beat bounce. ORIGINAL LYRICS: 0-2.5s: Stacks on stacks, yeah we get it big! 2.5-5s: Lift it to the sky, that's the money gig! 5-7.5s: Count the green, doggy on the roll! 7.5-10s: Boss of the room, got the whole patrol! PERFORMANCE TARGETS: 0-2.5s: Dog holds wide fanned stack of cash across chest, bobbing head in rhythm, stylized jaw opening on syllables. 2.5-5s: Pushes stack straight up overhead toward ceiling fan, grinning, front paws gripping edges. 5-7.5s: Lowers cash back down, fans bills rapidly like an accordion, eyes locked onto camera. 7.5-10s: Drops cash stack below frame, leans forward in swagger stance, nodding to final beat. PRIORITY: Exact breed identity retention from @Image1, rhythmic money manipulation, tight audio-mouth alignment. EXCLUSIONS: Human teeth, extra limbs, multiple dogs, drifting background, watermarks, cloned external tracks. 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
comedy · unknown
FORMAT: 10s vertical 9:16 video, single continuous shot. REFERENCE ROLES: @Image1 is the sole lead subject, a pet dog matching the reference coat and markings. SOUNDTRACK SPECIFI
Reconstructed from the video, not the author's prompt · tiktok
View original source ↗
Reconstructed from the video, not the author's prompt
FORMAT: 10s vertical 9:16 video, single continuous shot. REFERENCE ROLES: @Image1 is the sole lead subject, a pet dog matching the reference coat and markings. SOUNDTRACK SPECIFICATION: 96 BPM playful bounce hip-hop, plucky synths, acoustic kick. Comedic Mandarin rap vocals with rhythmic canine grunts. SCENE AND CAMERA: Medium portrait framing in bedroom, natural diffuse lighting, stable camera with light punch-in on musical drops. ORIGINAL LYRICS: 0-2.5s: 钞票拿在手，今天我做主！ 2.5-5s: 举到最高处，全都来看我！ 5-7.5s: 数一数两千，全买大肉骨！ 7.5-10s: 眼神放个电，全场我最酷！ PERFORMANCE TARGETS: 0-2.5s: Dog sits upright holding thick cash spread across chest, rhythmic side-to-side head tilt. 2.5-5s: Raises the money stack high toward upper frame, jaw syncs to vocal accents with natural snout movement. 5-7.5s: Brings cash back to chest, rapidly flutter-fanning bills between paws. 7.5-10s: Sets cash down, leans close to camera, ears perk, closing with steady boss nod. PRIORITY: Faithful likeness to @Image1, stylized canine jaw sync without humanoid mouth distortion, steady paw grip. EXCLUSIONS: Human dentures, duplicated subjects, text overlays, floating currency artifacts, non-original audio. 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.