
Original document
GPT Image 2 · zh
{
"type": "2-page manga spread",
"style": "monochrome anime manga, screentones",
"theme": "{argument name=\"main action\" default=\"fantasy mage developing a video game\"}",
"character": "{argument name=\"character appearance\" default=\"anime girl with blonde hair, tiara, cape, white dress, thigh-highs\"}",
"layout": {
"left_page": {
"panel_count": 11,
"rows": [
{"panels": 1, "action": "Determined at dual-monitor desk, speech bubble: '新作ゲーム、絶対完成させる!'"},
{"panels": 3, "action": "Typing, drawing on tablet, testing with controller"},
{"panels": 3, "action": "Shocked at ERROR screen, depressed, determined again"},
{"panels": 4, "action": "Exhausted, sudden realization, furious typing, monitor showing 'Build succeeded!'"}
]
},
"right_page": {
"panel_count": 2,
"panels": [
{"type": "large splash", "action": "Casting magic from a glowing circle at a code-error monster labeled '{argument name=\"error text\" default=\"NullReferenceException\"}'. Speech bubble: '{argument name=\"spell text\" default=\"デバッグ魔法!!\"}'"},
{"type": "bottom banner", "action": "Cheering in front of RPG title screen. Speech bubble: '{argument name=\"success text\" default=\"やったー!\"}'"}
]
}
}
}How to use
- Copy the complete original prompt, including any parameters.
- Replace the subject, text and composition with your own requirements.
- Use a compatible external tool; check its current access conditions and review the result.
Before you start
- Check whether a reference image is required. A compatible model label does not mean this example was generated with that model.
- Keep names, figures and visible text accurate; results can vary between model versions.




