IP
生成
黑暗奇幻廢墟漫畫頁面預覽圖
主參考影像

黑暗奇幻廢墟漫畫頁

一張電影風格的四格動漫漫畫頁面,描繪了兩位奇幻劍士在致命的機械遺跡中穿行,非常適合用於故事插圖、網絡漫畫場景或輕小說宣傳藝術。

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。
試試這個提示

Free 1K preview

Generate one preview image instantly, no sign-up required.

3050/4000
Continue on Dovoo

提示詞

可直接複製的提示

{
  "type": "dark fantasy manga page",
  "style": "cinematic anime, highly detailed, dramatic lighting, gritty ruins, polished digital painting with manga panel layout",
  "setting": {
    "location": "ancient mechanical ruin corridor inside a labyrinth",
    "mood": "tense but intimate, two survivors growing closer after escaping a trap passage",
    "palette": "black, rust, charcoal, ember orange, dim gold"
  },
  "characters": [
    {
      "role": "male swordsman",
      "appearance": "young man, slim build, short black hair, long black coat with belts and straps, dark undersuit, sword on back, serious expression"
    },
    {
      "role": "female swordswoman",
      "appearance": "young woman, slim build, very long chestnut-orange hair, white and silver fantasy battle dress with armor accents, thigh-high boots, rapier at hip, alert expression"
    }
  ],
  "layout": {
    "sections": [
      {
        "title": "top panoramic panel",
        "position": "top",
        "count": 1,
        "labels": [
          "two small full-body figures standing before a colossal ruined archway filled with giant exposed gears, chains, rubble, and glowing lava cracks in the floor"
        ]
      },
      {
        "title": "middle left dialogue panel",
        "position": "middle-left",
        "count": 1,
        "labels": [
          "close three-quarter view of both characters leaning over an old map on a stone surface, male in front pointing, female behind him, one white speech bubble with Chinese text"
        ]
      },
      {
        "title": "middle right map panel",
        "position": "middle-right",
        "count": 1,
        "labels": [
          "aged parchment dungeon map with 6 skull markers, one red circled location, armored gloved finger pointing at the circled area, one white speech bubble with Chinese text"
        ]
      },
      {
        "title": "bottom full-width panel",
        "position": "bottom",
        "count": 1,
        "labels": [
          "full-body shot of the two characters walking side by side through a massive doorway in the mechanical ruins, embers glowing around their feet, one rectangular Chinese caption box near the bottom"
        ]
      }
    ],
    "panel_count": 4
  },
  "text": {
    "speech_bubbles_count": 2,
    "caption_boxes_count": 1,
    "visible_text_language": "Chinese",
    "speech_bubbles": [
      "The restricted area is in the central corridor. There are six floor traps, pressure-sensitive. The moment you step on one, magma will erupt from the side walls simultaneously.",
      "Is this... a floor collapse zone?"
    ],
    "caption_boxes": [
      "Only one person can pass at a time."
    ]
  },
  "composition": "vertical manga page, wide establishing panel on top, two split middle panels, one wide bottom panel, strong black gutters between panels",
  "effects": "embers, faint smoke, scorched textures, metallic decay, cracked stone, warm backlight from deep corridor",
  "quality": "ultra-detailed, sharp focus, epic scale, atmospheric depth"
}

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. 1. Copy the prompt and preserve its structure for the first test.
  2. 2. Replace the subject, context, and publishing channel.
  3. 3. Change one camera, lighting, or style variable per iteration.
  4. 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。

6

重用和來源註釋

預覽案例後,請謹慎使用此提示。

  1. 1.複製提示或直接在 Dovoo 中使用生成按鈕開啟提示。
  2. 2.根據您的實際使用情況調整變數、寬高比和參考影像。
  3. 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。
黑暗幻想廢墟漫畫頁面(GPT 圖 2) | Image Prompt Gallery