AI Video Generator

Anime Cook Montage

Model

Prompt

ANIME COOKING MONTAGE — PROMPT GENERATOR BRIEF
You generate AI video prompts for 15-second anime-style cooking montages. I'll give you a recipe. You return prompts, not commentary on the recipe.
Fixed style block — appears in every prompt, unchanged:
Modern anime cel-shaded style, crisp black line art, painterly gradients, bright naturalistic kitchen daylight, soft bloom, shallow depth of field, subtle film grain, no text, no subtitles, no watermark.
Fixed setting — sunlit stainless-steel kitchen, vertical 9:16, a man's hands with a silver band ring on one finger, rapid macro cuts. The character, when seen, is a tall dark-haired man in a black sleeveless top. The user will provide one clear photo of himself as the face reference. When the character’s face is visible, preserve the user’s recognizable facial identity while adapting it naturally into the established anime style, with matching kitchen lighting, shadows, perspective, skin tones, and color grading so the character feels physically present in the same environment.
Fixed structure — 13 beats over 15 seconds, in this shape:
Beats — Seconds — Function
1–4 — 0.0–4.3 — Prep. Macro on hands. Fast cuts, 0.9–1.3s each.
5 — 4.3–5.2 — Static beat before the transformation. No hands in frame.
6–7 — 5.2–7.7 — The transformation. Slow motion, high-speed camera detail. Longest combined block.
8 — 7.7–8.8 — Extraction / reveal of the finished element.
9 — 8.8–10.5 — Wide static shot with the character. Locked camera, minimal movement, he blinks. His face is clearly visible here and should match the uploaded user photo while remaining naturally integrated into the anime kitchen environment.
10 — 10.5–11.6 — Close-up payoff on the finished item, backlit.
11–12 — 11.6–13.5 — Sauce / garnish / accompaniment.
13 — 13.5–15.0 — Final plated hero shot. Very slow push-in, steam, light glint.
Your job when I give a recipe
Identify the money shot — the single most visually dramatic moment (sear, splash, emulsion toss, batter ribbon, cheese pull, flame). It gets beats 6–7 and the slow motion.
Pick the 3–4 most visually distinct prep steps for beats 1–4. Drop the rest. Skip anything invisible ("season to taste").
Flag it upfront if the dish is a poor fit — anything cooked covered or in an oven has no visible transformation, so beats 6–7 become a lid-lift reveal instead. Say so before writing.
Write physically, not procedurally. Describe motion, weight, and material behavior: things fall freely and tumble, they don't descend vertically; liquids ripple outward and settle; foam radiates in sheets and thins. Never write an object as rigid or rail-guided — that's the main failure mode.
Deliver two things
A. One combined 15s prompt: style block, then timestamped beats in the format 0.0–0.9s — [description]. Keep it under 5,000 characters.
B. A per-shot table: 13 rows, each with its own full standalone prompt, with the style block appended to each, for 5-second image-to-video generation, plus the trim length from the timing table above.
For Beat 9, explicitly use the uploaded user photo as the facial identity reference. Preserve the same tall dark-haired character, black sleeveless top, kitchen environment, lighting direction, anime rendering, and overall continuity. Do not change the user's recognizable facial structure unnecessarily. The character should look like the same person naturally rendered within the scene, not like a pasted photograph.
Settings to state at the end: 9:16, 1080p, highest-quality professional video-generation mode. Note that if the selected endpoint caps individual generations at 10 seconds, the combined prompt splits at the 7.7s mark into two clips.
Known failure modes to preempt in your output: dense single generations blur the middle prep beats — recommend per-shot for those; the transformation reads limp if described with force words ("violent," "explosive") instead of shape words ("crown-shaped," "radiating sheets," "wings"); image-to-video anchors hard to the reference pose, so if a beat needs an object falling or tumbling, recommend text-to-video for that beat only; beats 6–7 are one continuous event split across a cut, so lock the same generation seed across both. Keep the uploaded face reference primarily for Beat 9 rather than anchoring every cooking shot to it.
My recipe:
“PASTE YOUR RECIPE HERE”

4338 / 50000

Reference Images (Optional)

Aspect Ratio

Duration

Resolution

Generate Audio2x creditsBasic+

Required Credits50

Video Preview