黑暗奇幻世界观构建项目
一个电影感网格演示板，展示了一致的中世纪弓箭手角色、雪景地点以及用于世界观构建或图像生成展示的道具。
gpt-image-2 · 3D 渲染 · 产品 · 信息图 / 教育视觉图 · 游戏素材 · 电影 / 电影剧照 · 角色 · 风景 / 自然
中文提示词
目标：创建一个黑暗电影感的演示项目，用于世界观构建 / 图像生成工作流，展示如何通过逐张图像构建一致的奇幻角色、地点和道具。 画布：4:3 宽屏构图，深黑色背景，圆角矩形卡片以整洁的网格排列，间距柔和，带有微妙的阴影，呈现出低调的高级 UI 感。 布局：使用 6 张可见卡片。卡片 1 是左上角的长条文本卡。卡片 2 是右上角的大型宽幅角色卡。卡片 3 和 4 是中间两张中等尺寸的横向地点卡。卡片 5 和 6 是左下和中下方的两张小型道具卡，如果画布构图允许，右下角可部分露出/裁剪第三张角色卡。每张图像卡左上角都有一个深色小标签。 文本内容：在左上角的文本卡中，顶部包含小间距的大写文本“ONE WORLD”。下半部分包含标题“Built image by image”以及正文“A character, her locations, and the props she carries — generated separately, holding one look.”。使用简洁的现代无衬线字体，标题为白色，正文为柔和的灰色。 可见标签图像卡：5 张完全可见的带标签图像卡加 1 张文本卡。标签如下：2 张标签为“Character”，2 张标签为“Location”，以及 2 张标签为“Prop”（如果包含右下角裁剪部分）；否则保持主要可见集为 1 张 Character、2 张 Location 和 2 张 Prop。不要添加额外标签。 主体细节：主角为 {argument name="character description" default="一位皮肤白皙、金发编辫的中世纪年轻女弓箭手，表情严肃，身披羊毛斗篷，背着皮质箭袋"}。将她置于雪覆盖的石制城堡庭院中，手持长木弓，采用冷蓝灰色调灯光，具有浅景深的电影感。地点展示 {argument name="world setting" default="一个冷酷的北欧中世纪冬季世界"}：一个是冰封的港口，维京风格长船被困在冰中，伴有火光、山脉和积雪；另一个是设防的雪地军营，有帐篷、木栅栏、瞭望塔、升起的炊烟和风暴云。道具展示 2 个特写物品：一个带有苍白符文和碎骨标记的旧皮袋或护腕，以及一排置于雪地中、背景模糊的鹿角或角质碎片。 视觉风格：照片级真实感的黑暗奇幻电影风格，去饱和的蓝灰色冬季色调，飘落的雪花，逼真的纹理，高细节，情绪化的自然光，所有卡片保持一致的中世纪服装和材质。圆角卡片，优雅的间距，无鲜艳色彩。 约束：保持界面极简且具有编辑感，如同高级 AI 图像生成案例研究。保留确切的标题和正文内容。避免使用徽标、水印、图表、动漫风格、现代物品或额外的 UI 杂乱元素。
原始提示词
Goal: Create a dark cinematic presentation board for a worldbuilding / image-generation workflow, showing how a consistent fantasy character, locations, and props are built image by image. Canvas: Wide 4:3 composition on a nearly black background with rounded rectangular cards arranged in a clean grid, soft gaps, subtle shadows, and a muted premium UI feel. Layout: Use exactly 6 visible cards. Card 1 is a tall text card on the upper left. Card 2 is a large wide character card on the upper right. Cards 3 and 4 are two medium landscape location cards across the middle row. Cards 5 and 6 are two smaller prop cards along the lower left and lower center, with a third lower-right character card partially visible/cropped at the edge if the canvas framing allows. Each image card has a small dark pill label in the top-left corner. Text content: On the upper-left text card, include small spaced uppercase text “ONE WORLD” near the top. In the lower half, include the headline “Built image by image” and the body text “A character, her locations, and the props she carries — generated separately, holding one look.” Use clean modern sans-serif typography, white headline, muted gray body text. Visible labeled image cards: 5 fully visible labeled image cards plus 1 text card. The labels are: 2 cards labeled “Character,” 2 cards labeled “Location,” and 2 cards labeled “Prop” if the lower-right crop is included; otherwise keep the main visible set as 1 Character, 2 Location, and 2 Prop. Do not add extra labels. Subject details: The main character is {argument name="character description" default="a pale young blonde medieval archer girl with braided hair, serious expression, wool cloak and leather quiver of arrows"}. Place her in a snowy stone castle courtyard, holding a long wooden bow, with cold blue-gray lighting and shallow cinematic depth of field. The locations show {argument name="world setting" default="a grim Nordic medieval winter world"}: one frozen harbor with Viking-style longships trapped in ice, torchlight, mountains and snow; one fortified snowy military camp with tents, wooden palisades, watchtowers, smoke rising, and stormy clouds. The props show exactly 2 close-up items: a weathered leather pouch or wrist guard marked with pale runic symbols and small bones, and a row of antler or horn pieces in snow with blurred background. Visual style: Photorealistic cinematic dark fantasy, desaturated blue-gray winter palette, falling snow, realistic textures, high detail, moody natural lighting, consistent medieval wardrobe and materials across all cards. Rounded card corners, elegant spacing, no bright colors. Constraints: Keep the interface minimal and editorial, like a premium AI image-generation case study. Preserve the exact headline and body copy. Avoid logos, watermarks, charts, anime style, modern objects, or extra UI clutter.