GPT Image 2AI-Prompt
Gothic Witch in Ruined Cathedral — Sora 2 Prompt
Generate a cinematic dark fantasy image of a Victorian gothic witch casting spells in a ruined cathedral — ideal for book covers and concept art.
PROMPT · EN
一个位于巨大废弃大教堂内的暗黑哥特奇幻场景，采用垂直全身构图。画面正中央站着一位神秘的女巫，身着优雅的维多利亚风格黑色礼服，配有合身的束腰胸衣、精致的银色刺绣、透明蕾丝袖、从手臂垂下的长蕾丝饰片、黑色手套以及长拖尾裙摆。她的头发梳成整洁的深色盘发，戴着精致的发饰，并佩戴着考究的珠宝。她一手拿着一本打开的法术书，另一只手以优雅的姿态抬起进行施法。周围环绕着低垂的薄雾和缭绕的烟雾。大教堂内部宏大且破败，拥有高耸的尖拱、肋架拱顶、开裂的石质地面、两侧破碎的墓穴或祭坛，粗壮扭曲的树根在地面蔓延并缠绕着石质结构。在两侧的高处对称放置 2 座大型石像鬼雕像，左右各一，俯瞰着整个场景。在前景和中景散布许多带有温暖橙色火焰的黑色蜡烛，营造出仪式感。背景中，高大的彩色玻璃窗透出冷蓝色的日光，形成戏剧性的耶稣光，与烛光形成鲜明对比。整体氛围阴森、神秘、具有电影感、庄严且细节丰富，呈现出逼真的质感、深邃的阴影、体积光、大气雾霾、深蓝灰色调以及极致细节的哥特式建筑。
Über diesen Prompt
Generate a cinematic dark fantasy image of a Victorian gothic witch casting spells in a ruined cathedral — ideal for book covers and concept art. Use it as a Konzeptkunst starting point for GPT Image 2: keep the visual structure and style constraints intact, then swap in your own subject, brand, or scene.
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.
So verwendest du diesen Prompt
- Copy the prompt from the text area above.
- Paste into an AI image generator (Midjourney, Stable Diffusion, DALL·E 3) or video model (Sora).
- Adjust settings like aspect ratio (e.g., 2:3 portrait) or style strength.
- Generate and refine as needed.
