GPT Image 2AI 프롬프트
Cute Anime Schoolgirl Manga Page — Fast Food Dilemma Sora 2 Prompt
Generate a printable five-panel vertical manga page depicting a chibi-style schoolgirl anxiously debating adding fries to her fast-food order, complete with expressive Japanese speech bubbles.
프롬프트 · EN
type
single-page vertical 3:4 Japanese manga comicstyle
cute modern anime manga, clean thick black panel borders, expressive chibi-leaning schoolgirl character, flat cel shading, soft pastel backgrounds, cohesive character and background style, high readability, printed comic lookformat
aspect_ratio
3:4 portraitpage_layout
five-panel comic page with black gutters and white outer marginreading_direction
right-to-left manga feel, but arranged visually as a pagemain_character
description
a teenage Japanese schoolgirl with pale skin, shoulder-length slightly messy black hair, heavy side bangs, large sleepy half-lidded eyes, small mouth, wearing a navy school blazer, white shirt, red ribbon bow tie, seated or standing depending on panelname
{argument name="character name" default="unnamed schoolgirl"}uniform
{argument name="school uniform" default="navy blazer, white shirt, red ribbon bow tie"}setting
{argument name="restaurant setting" default="McDonald's-style fast food restaurant with red counter, menu screens, burger and fries graphics, trays, drink cup, burger, and fries"}dialogue
Use vertical Japanese manga speech bubbles and thought bubbles with the following visible dialogue and sound effects: {argument name="Japanese dialogue text" default="お財布の中は・・・うーん / ごそごそ / えーっと、チーズバーガーのセットをください / ポテトもつけたいけど、お金が・・・ / ここは我慢するべき？いや、でも・・・ / よし！つけちゃおう！ / ピコーン / うーん・・・どうしよう・・・"}panels
count
5arrangement
item 1
panel
1position
top leftdescription
The schoolgirl sits at a table by a window, opens a brown wallet, and looks worried while checking inside; a vertical thought bubble is on the left and a small rustling sound effect appears near her head.item 2
panel
2position
top rightdescription
At a fast-food counter, the schoolgirl faces away while ordering from a cheerful cashier wearing a black cap with a yellow M-like logo; overhead menu boards show illustrated burger, fries, and drink sets; a tall vertical speech bubble is on the right.item 3
panel
3position
middle wide paneldescription
Close-up of the schoolgirl thinking with one finger on her lips and narrowed eyes; on the left is a floating red fries carton with golden fries and emphasis marks, on the right is a floating purple coin purse thought icon with a small puff; two vertical thought bubbles frame her indecision.item 4
panel
4position
bottom leftdescription
The schoolgirl sits happily at a table with a tray containing exactly three food items: one drink cup with straw, one cheeseburger, and one red carton of fries; she smiles widely, blushes, raises one index finger, and clenches her other fist, with bright excitement marks and a sound effect.item 5
panel
5position
bottom rightdescription
The schoolgirl sits alone at a table against a blue background, again touching her chin with a doubtful half-lidded expression and a sweat drop, repeating the indecision joke with a vertical speech bubble and blue elongated thinking sound effect.props_and_counts
comic_panels
5recurring_main_character_appearances
5fast_food_tray_items_in_final_food_panel
3visible_order_counter_staff
1major_speech_or_thought_bubbles
7floating_thought_icons_in_middle_panel
2visual_requirements
Keep all characters consistent across panels, with the same face, hairstyle, and uniform. Use rounded expressive eyes, simple noses, small mouths, blush marks where appropriate, manga motion lines, colored sound effects, and clean legible vertical lettering. Avoid photorealism; make it look like a polished social-media manga panel generated from text only.프롬프트 소개
Generate a printable five-panel vertical manga page depicting a chibi-style schoolgirl anxiously debating adding fries to her fast-food order, complete with expressive Japanese speech bubbles. Use it as a 컨셉 아트 starting point for GPT Image 2: keep the visual structure and style constraints intact, then swap in your own subject, brand, or scene.
This prompt is organized as structured JSON with fields such as type, style, format, main character, setting, dialogue, and panels. Keeping that hierarchy helps the model separate the subject, layout, interface elements, and detail constraints.
Start with small changes to subject, scene, camera, and color, then generate a few variations to compare composition and detail without turning the page copy into keyword stuffing.
이 프롬프트 사용법
- Copy the full prompt JSON into your Sora 2 compatible AI model.
- Customize the variables
character name,restaurant setting, orJapanese dialogue textto change the story or style. - Select a model that supports high-fidelity comic panel generation (e.g., Sora 2, DALL·E 3).
- Generate the image; the output will be a single 3:4 portrait page with five panels and white margins.
- For best results, keep the style keywords intact to maintain the cohesive manga aesthetic.
