The Shlabu / Artlist method remade: Midjourney 90s character still → GPT Image character sheet → location stills → Seedance 2.5 with timed dialogue moments. Build short cinematic NYC friend-cam micro films, not cartoon storyboards.
Open Midjourney (or your image model) and ask for one mid-1990s 35mm film still of your subject. Name the city, season, outfit fabrics, jewelry, and the candid mid-stride glance. Keep it photographic: pores, flyaways, fine grain, lifted blacks. This still is the face and wardrobe lock for everything after. Do not start in Seedance.
02
02Step 2
Build the character reference sheet
Pass that still into GPT Image (or Nano Banana Pro) and ask for a CHARACTER REFERENCE SHEET: full-height panels plus macro swatches, same face and outfit in every panel, warm grey studio, no smoothing. The sheet is what Seedance uses as the identity ref, so identity holds when the camera moves and the accent flips.
03
03Step 3
Lock the location stills
Generate empty or near-empty location stills next: NYC diner booth, Village sidewalk, night street. Period props only, no phones. Soft cloudy daylight or warm pendants, Kodak 35mm grade. Keep one clean diner still as the location ref. Your remake used a teal vinyl booth, Formica, chrome napkin holder, neon OPEN in the window.
In Seedance 2.5, wire the character sheet + location still as reference images. Write a REFERENCE MAP (which image is face vs place), then a GLOBAL SETUP (year, light, handheld friend-cam, length), then MOMENT blocks with clocks: lean-in line, accent shift, tiny giggle, shrug. Optional accent audio ref. One continuous take, live sync dialogue, no music, no cuts. Paste the master prompt below and swap your phrase.
05
05Step 5
Grade, cut, and post the craft
Pull a 1–2s grade pass if needed (warm lift, fine grain), keep the friend-cam shake, and post a still from the method under the clip so people see the craft. Proof from the remake: a 7s diner friend-cam where she says a pizza line in thick old Brooklyn, giggles once, then shrugs "it's all in the prompt." That is the video people will make: short cinematic 90s NYC micro-films with dialogue and natural acting.
Seedance 2.5 master prompt (swap the phrase, keep the clocks)
GLOBAL SETUP Year: mid 1990s, NYC diner. No modern devices. Light: soft diffused window light frame left, warm pendants. Format: single continuous take, 7 seconds, no cuts. Handheld friend-cam across the booth, seated eye level, gentle shake/drift entire time. Framing: medium shot from tabletop up, subject frame-left, diner soft-focus right. Performance: natural, relaxed, eyes on lens. Voice: young adult, natural; only the quoted signature phrase shifts accent. Audio: live sync dialogue, room tone, cutlery murmur, no music.
MOMENT 1 (0.0–2.0s): Lean in. Neutral American: "She can say, slice of pizza," MOMENT 2 (2.0–4.6s): Same breath: "or make it..." then thick old Brooklyn: "Lemme get a slahce a PEET-za". Drawn-out vowels, sing-song. Playful head tilt + loose hand flick. MOMENT 3 (4.6–5.0s): Tiny soft giggle at her own accent, breathy, eyes crinkle, head dips. MOMENT 4 (5.0–7.0s): Neutral again, still smiling: "it's all in the prompt." Small open-palm shrug on "prompt", settles into slight smirk, clip ends mid-drift.
NEGATIVES No wrong gender voice. Accent only on the signature phrase. One tiny giggle. No cuts, no music, no text, no phones, no hard sun.
Want this running for you?
Build it step by step inside AI Creative OS, with me in the thread.
