
日落拳擊館漫畫頁
一幅電影感十足的漫畫畫面,描繪了一位孤獨的女學生在黃昏時分發現了一家拳擊館,非常適合用來創作戲劇性的多格故事場景。
這是一個動漫與遊戲的GPT Image 2範例。請使用下方可直接使用的提示資訊產生類似的視覺素材,並在重複使用前查看Awesome GPT Image 2 Prompts署名和商業用途授權資訊。
需要完整的提示符號集?請使用 動漫與遊戲 主題中心提供更多相關範例,或打開 GPT Image 2 提示庫 有關完整範例索引、可重複使用結構和來源歸屬的資訊。
Free 1K preview
Generate one preview image instantly, no sign-up required.
3708/4000
提示詞
可直接複製的提示
{
"type": "manga page",
"format": "single black-bordered comic page with 5 panels",
"style": "cinematic seinen manga, highly detailed painterly anime realism, moody urban atmosphere, warm dusk lighting, soft filmic shadows, subtle grain, dramatic perspective, Japanese signage and dialogue",
"reading_direction": "right to left visual flow",
"setting": {
"time": "sunset into early evening",
"place": "an old Japanese shopping street with narrow road, aging storefronts, hanging signs, power lines, bicycles, vending machines, and shuttered shops",
"mood": "nostalgic, tense, introspective, the feeling of finding a place to belong"
},
"character": {
"primary": "{argument name=\"角色名称\" default=\"high school girl\"}",
"appearance": "slim teenage schoolgirl with straight dark shoulder-length hair and bangs, pale skin, serious expression",
"outfit": {
"count": 4,
"items": [
"dark school blazer",
"white shirt with ribbon tie",
"dark plaid pleated skirt",
"black knee socks and brown loafers"
]
},
"accessory": "dark shoulder bag"
},
"layout": {
"sections": [
{
"title": "top wide panel",
"position": "full width top",
"count": 1,
"labels": [
"girl standing alone in the middle of a long street at sunset, centered composition, vertical narration text above her: どこにいても、居場所がない気がした。"
]
},
{
"title": "middle left panel",
"position": "left middle",
"count": 1,
"labels": [
"close-up of her loafers and knee socks on wet pavement with a tiny motion mark"
]
},
{
"title": "middle right panel",
"position": "right middle wide",
"count": 1,
"labels": [
"old boxing gym with half-open shutter glowing warmly inside, several people training in the ring and near punching bags, large sound effects パンッ and パパンッ, vertical narration text on the right: その音に、足が止まった。"
]
},
{
"title": "bottom left panel",
"position": "left bottom",
"count": 1,
"labels": [
"view from behind a sweaty short-haired young man in a sleeveless black shirt looking toward the entrance, the girl standing in the doorway, speech balloon: ……やるのか?"
]
},
{
"title": "bottom right panel",
"position": "right bottom",
"count": 1,
"labels": [
"over-the-shoulder shot from behind the girl as she touches the window frame and watches a teenage boxer training inside the gym"
]
}
],
"panel_gutters": "clean white gutters of consistent width",
"border": "thin black outer border"
},
"environment_details": {
"street_sign_count": 5,
"visible_signs": [
"Nakamura Pharmacy",
"Yamashita",
"肉の鈴木",
"大場ボクシングジム",
"タバコ"
],
"gym_details": {
"count": 5,
"items": [
"boxing ring",
"trainees sparring",
"hanging heavy bags",
"fluorescent ceiling lights",
"wall sign reading 努力は裏切らない"
]
}
},
"color_palette": {
"count": 5,
"colors": [
"amber sunset sky",
"warm orange indoor light",
"muted blue-gray shadows",
"weathered brown wood and concrete",
"deep navy school uniform"
]
},
"camera": "top panel uses a long centered street perspective; other panels alternate between detail close-up, exterior medium-wide, and intimate over-the-shoulder shots",
"quality": "ultra-detailed illustration, expressive lighting, readable Japanese manga text, emotionally grounded storytelling"
}提示變數
提示符號中可編輯的參數佔位符及其預設值。
多變的
角色名称
預設
high school girl
Best for
- - 動漫與遊戲 visual exploration
- - Image generation and reference-image edits
- - Reusable briefs that keep source attribution visible
Change these parts
- - Subject, product, character, or scene
- - Aspect ratio, camera, lighting, and background
- - Brand, text, color, and output constraints
Recommended model and settings
- - Model: gpt-image-2
- - Input mode: 文生圖
- - Aspect ratio: source
- - Commercial status: review original source
How to use this prompt
- 1. Copy the prompt and preserve its structure for the first test.
- 2. Replace the subject, context, and publishing channel.
- 3. Change one camera, lighting, or style variable per iteration.
- 4. Inspect the output, source, text, and rights before reuse.
Limitations, source, and reuse cautions
- - Generated output is an editable draft, not factual, legal, or rights evidence.
- - Review the linked source, people, brands, logos, text, and third-party media before commercial use.
內容來自Awesome GPT Image 2 Prompts 。必須註明出處。商業用途狀態為allowed ;付費使用前請查看來源版權資訊。
此類案例更多
按類別、輸入模式相容性、品質和低風險進行優先排序。
重用和來源註釋
預覽案例後,請謹慎使用此提示。
- 1.複製提示或直接在 Dovoo 中使用生成按鈕開啟提示。
- 2.根據您的實際使用情況調整變數、寬高比和參考影像。
- 3.發布或付費使用前,請確認版權、署名要求以及品牌或肖像權風險。





