OpenZhenZhen AI プロンプトギャラリー · gpt-image-2.5 · image

詩詞の文字が織りなすイメージ図

Imagery Formed by Poetic Text

「詩詞の文字が織りなすイメージ図」は gpt-image-2.5 を使用した作品です。OpenZhenZhen で元のプロンプトと生成例を確認し、創作の参考にできます。

詩詞の文字が織りなすイメージ図 — AI image creation
詩詞の文字が織りなすイメージ図

プロンプト

中国語プロンプト

将下面的完整原诗制作成一幅只由诗中文字构成的文字意象图。字的位置和走向共同形成画面,使观者既能辨认意象,也能沿着清晰路径读完整首诗。必须按输入原样使用诗文;不要翻译、改写、添加标题或虚构内容。 原诗: 床前明月光,疑是地上霜。举头望明月,低头思故乡。 先只从诗中辨认明确写出的事物及关系:什么在上、什么垂下、什么在移动以及移动方向。不得增添意象。每个画面事物只能由诗中指称或描写它的字构成。把关系转化为空间形式:垂落的意象沿弧线向下排列,高处意象向上竖排,风或方向性运动则让字斜向穿过画面。表达疑问、否定、设问或比喻的字(例如“不知”“谁”“似”)不代表具体事物;将它们放在留白处或两个意象的交界,让位置表现其作用。 直接以字形搭建可读的文字图像,通过字号、间距、方向和重复使用构成画面。不要添加绘制的物体、图标、装饰符号,也不要出现原诗之外的任何可见字符。可以重复使用诗中文字填充构图,但须建立一条明确的阅读路径,按原顺序完整呈现每个原文字和标点,不得遗漏或改动。整首诗须可读,未读过原诗的人也应能辨认画面所表现的场景。 完成前逐项核对:所有可见字形均来自原诗;每个意象只由指向或描写它的诗中字构成;画面可辨认;沿阅读路径能按原顺序准确读出完整原诗一次。画布形状随诗的构图需要确定;来源未指定固定比例或光线。

英語プロンプト

Create one typographic image composed only of characters from the complete source poem below. The positions and directions of the characters form the imagery, so viewers can both recognize the scene and read the entire poem along a clear path. Use the supplied poem exactly as written; do not translate, paraphrase, add a title, or invent content. Source poem: 床前明月光,疑是地上霜。举头望明月,低头思故乡。 First, identify only the things and relationships explicitly present in the poem: what is above or hanging down, what moves, and in which direction. Do not add imagery. Compose each depicted thing from only the poem characters that refer to or describe it. Translate relationships into spatial form: arrange hanging imagery downward on a curve, high imagery upward, and wind or directional motion diagonally. Characters expressing doubt, negation, questions, or metaphor (for example “不知”, “谁”, or “似”) do not stand for objects; place them in negative space or at the junction between images so their function is visible. Build a legible calligram from the glyphs themselves; use their scale, spacing, orientation and repetition to make the image. Do not add drawn objects, icons, ornamental marks, or any visible character absent from the poem. Reusing poem characters is allowed to fill the composition, but establish one unambiguous reading path that reproduces every original character and punctuation mark in the original order, with none missing or altered. Keep the whole poem readable while making the depicted scene recognizable to someone who has not read it. Before finalizing, verify: every visible glyph comes from the source poem; each image element uses only its own referring/descriptive poem characters; the scene is recognizable; and following the reading path yields the complete poem exactly once in its original order. Let the canvas shape follow the poem's composition; no fixed aspect ratio or lighting is specified.

API モデルを見る

画像・動画プロンプトをもっと見る · 画像を生成 · 動画を生成 · AI キャンバスで作成