Shoot raw footage for the moneycanbuy.fun POV video YOLO in Times Square: you deliver RAW FOOTAGE clips, each a separate unedited file, plus one generated music track. We add text, screens and logos in post and cut the clips to the track. Story for context only: a paid dare's reward is locked in a contract (our toad). A young man screams YOLO on a city square, a hater calls it fake, NFT holders agree, a court of frog judges (the IMD swarm) rules legit and the toad pays him.

REPOSITORY: use only toad-head/front.png and toad-head/three-quarter.png. Ignore all other files.

TOOLS: every clip from a real video generation model, image-to-video (for example Kling or Seedance): first make a photoreal start still with an image model, then animate it. A generative video model is required. Without one, do NOT substitute code animation, slideshows, pans or zooms over stills: write "no model" in README.md for every such file.

STYLE: photoreal live action, like real phone footage people post: natural daylight or warm indoor light, true colors, real skin and fabric texture, slight handheld feel. No cartoon, no 3D render look, no cinematic grading.

CLIP FORMAT: MP4, H.264, yuv420p, no audio track. Vertical 1080x1920 native from the model; if it cannot, its native vertical size, never below 720x1280, never upscaled (state it in README.md). Exactly 5 s, 24 fps, real motion all the way, no slow motion, no loop. Every file under 64 MiB, the whole delivery under 128 MiB.

CAST: the same person stays the same face, hair, body and clothes from the first to the last frame of every clip and in every clip where they appear. Make one cast still per recurring person and use it as the image reference for their start stills. Ordinary mixed adults, plain clothes, no real or famous faces.

CAST STILLS (on the contact sheet only, not separate files): the doer: a young man in a plain hoodie; the hater: a man in a plain t-shirt with a bag of chips; the court: five judges in black robes and simple green frog masks, NOT our toad (no chain, other eyes), behind one long bench, a rigid flat plaque on each chest, one with a gavel.

OUR TOAD: a HUMAN wearing our toad as a big plush mascot head, copied from toad-head/front.png and toad-head/three-quarter.png (as image reference, never a generic frog): flat toad green, heavy half-closed lids over cream eyes, a wide flat smirk, small nostrils, dark spots on the cheeks, a gold chain with a gold "$" tag on the chest, always visible. Plain dark hoodie. Never round, googly or wide open eyes, never filmed from behind. It holds the money in a clear locked box of plain gold coins. The "$" on the tag is the only symbol allowed in the whole delivery.

GREEN SURFACES: every phone screen, the big courtroom screen in D07, the chest plaque of every judge and the front panel of the judges' bench is SOLID BRIGHT GREEN #00FF00, flat, evenly lit, no glare, no reflections, no UI, facing the camera, all four edges and corners visible and unobstructed (a thumb may touch the middle). We key our site in there.

BLANK RIGID PROPS: the cardboard sign in D02, the clear coin boxes, the gold coins, the chips bag, the gavel, the small trophy cup are completely blank (no letters, numbers, symbols or print), stay rigid and keep their shape, never melt, bend or morph. NO LETTERS ANYWHERE in any frame: blank signs, posters, screens, clothes, packaging, no brands or logos.

CLIPS (file clips/.mp4, one continuous take each):

D01 A subway car. The doer scrolls a green-screen phone held toward the camera, then freezes, staring at it.

D02 A fictional night city square full of lights (big screens show only abstract colored light). The doer climbs a bench holding a blank cardboard sign and screams; passers-by turn and film him with green-screen phones.

D03 The doer still on the bench, catching his breath, taps a green-screen phone held toward the camera.

D04 Living room: the hater on a sofa with a bag of chips smirks and taps a green-screen phone.

D05a-D05d four files, a different person in each, raises a green-screen phone toward the camera and taps it once: D05a on a park bench, D05b in a car passenger seat, D05c in a cafe, D05d on a balcony.

D06 The doer at home, angry, jabs a button on a green-screen phone held toward the camera.

D07 A courtroom: the five frog judges behind the bench watch a big green screen on the wall and confer with each other.

D08 The head frog judge bangs the gavel once, the other judges nod.

D09 Back on the night square: the toad pours gold coins from the clear box into the doer's hands.

D10 On the square the toad takes a clear coin box from the hater and hands it to the doer; the hater drops his bag of chips.

D11 The toad throws a handful of gold coins into a metal bowl of real live fire, then hands the doer a small blank golden trophy cup.

MUSIC TRACK: one original instrumental track from a real music generation model (for example Suno, Udio, Stable Audio, MusicGen). Without one do NOT build it in code (synthesis, MIDI, loops): write "no model" in README.md for the track and beats.json. No vocals, lyrics, spoken words or vocal chops; no melody of an existing song. Mood: hype trap or phonk, quiet build to the drop, tense half-time from 14.0 to 18.0 s. 120 BPM, 4/4, first downbeat at 0.0 s. Our cuts in seconds, each on a beat; where a sound is named, a clear hit within 0.1 s of it: 2.5 drop (scream), 5.5, 7.5, 9.5, 12.0 hit (tap), 14.0 tension (court), 18.0 gavel, the hardest hit, 20.0 coin ticks, 23.0 coin ticks, 25.5 fire burst, 28.5 final hit.

track/track.wav: WAV 48 kHz 16-bit stereo, exactly 30.0 s, true peak at most -1 dBTP, about -14 LUFS, no clipping. After generation only trim, end fade, gain, MP3-to-WAV.

track/beats.json, measured from track.wav: {"bpm": n, "beats": [s], "downbeats": [s], "accents": [{"t": s, "what": "coin|gavel|fire|drop|hit|final"}]}. README.md: the music model and version, the exact prompt, each accent's offset from its second.

START STILLS: deliver the exact full-size first image you animated for every clip as start/.png. No text in any still.

README.md: one row per file: tool and model name and version, the exact prompt, files regenerated and why. contact-sheet.png (under 10 MB): every clip as 3 frames (start, middle, end) labelled with its file name (labels only here), plus the cast stills. Say moneycanbuy.fun may use, change and publish the files without attribution.

REJECTION LIST, check every file, regenerate failures, one line per item in README.md:

1. Letters, numbers or logos anywhere except the "$" on the toad tag.
2. A green surface not solid #00FF00, with glare or UI, or a covered edge or corner.
3. Morphing faces, hands or props; a person changing face or clothes.
4. Near-still clips, slideshows, code animation, pans over a still.
5. Wrong toad head: generic frog, round eyes, no chain or "$" tag, seen from behind.
6. Clips not 5 s at 24 fps, upscaled, watermarked.
7. A real brand look, a real or famous face.
8. A track with voice or words, made in code, or not 30.0 s.

FILES, exactly these names under artifacts/: clips/.mp4 and start/.png for every clip name above, track/track.wav, track/beats.json, README.md, contact-sheet.png.