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

日本の手描き漫画と写真の比較ポスター

Japanese Hand-Drawn Manga Photo Comparison Poster

「日本の手描き漫画と写真の比較ポスター」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。

日本の手描き漫画と写真の比較ポスター — AI image creation
日本の手描き漫画と写真の比較ポスター

プロンプト

中国語プロンプト

将绑定到 identity_reference(ref-10a-v1)的唯一整幅照片作为原照和唯一输入。图中是一位成年女性。制作一张完整的竖版3:4对比海报,上下水平等分,无边框、无间隙。 上半部分:严格按提供内容原样呈现原照,不编辑、不重新着色、不重绘、不添加文字。保留女性身份、面部、居中姿势、比例、棕发、黑色细肩带服装、青蓝环境、光线和构图。保持照片比例;如需适配上半区,只裁去边缘青蓝背景,绝不裁切女性。 下半部分:将同一位可辨认的女性重绘为日式手绘漫画海报,采用极简有限色彩丝网印刷美学。保留可辨识特征、姿势、比例及其与原场景的关系;除指定排版文字外,不添加原照片中不存在的内容。插画置于下半区垂直居中略偏上,下方留出充足空间。 艺术风格:使用细腻、略不规则的墨黑轮廓(#02030B)、简化形状、干净的不透明色块和极简硬边阴影。插画仅限暖红(#E9444B)、柔和灰蓝(#5296BD)与米白纸色(#ECEDE5),红色为主、蓝色为辅。避免写实纹理、密集排线、3D效果和过度细节。 版式与文字:所有文字均须位于下半区,清晰可读且不被裁切。在下半区顶部附近用黑色手写体加入小型主体说明“静谧肖像”;在女性旁边加入简短黑色手写注释“平静目光”。使用为这两个字段设定的、符合照片内容的默认值;只有用户提供合适替代内容时才更换。插画下方以醒目的手刻印刷体分两行显示主标题:“Jen”使用暖红,“Style”使用灰蓝。每个标题变量只呈现一次;除非用户提供替代内容,否则保留已设默认值。 输出完整海报,不加额外边框、水印、虚构场景元素或装饰性杂乱。

英語プロンプト

Use the single attached full photo bound to identity_reference (ref-10a-v1) as the sole original photograph. It shows one adult woman. Create one complete vertical 3:4 comparison poster, divided into two equal horizontal halves with no border or gap. TOP HALF: show the original photo exactly as supplied, without editing, recoloring, redrawing or adding text. Preserve the woman's identity, face, centered pose, proportions, brown hair, black thin-strap clothing, teal-blue environment, lighting and composition. Keep the photo's proportions; crop only peripheral teal background if needed to fit the top half, never crop the woman. BOTTOM HALF: redraw the same recognizable woman as a Japanese hand-drawn comic poster with minimalist limited-color screen-print aesthetics. Preserve her recognizable features, pose, proportions and relationship to the original scene; add no content absent from the photo except the specified typography. Position the illustration in the upper-middle of this half, leaving generous negative space below. ART STYLE: use delicate, slightly irregular ink-black outlines (#02030B), simplified shapes, clean opaque color blocks and minimal hard-edged shadows. Restrict the illustration to warm red (#E9444B), muted gray-blue (#5296BD) and off-white paper (#ECEDE5), with red dominant over blue. Avoid photorealistic textures, dense hatching, 3D effects and excessive detail. LAYOUT AND TEXT: keep all text inside the lower half, fully legible and uncropped. Near the top of the lower half, add a small black handwritten subject caption using “Quiet portrait”. Beside the woman, add a short black handwritten annotation using “Still gaze”. Use the photo-grounded defaults supplied for these two fields; replace them only with photo-appropriate user-provided alternatives. Below the illustration, set the bold hand-carved print-style main title on two lines: “Jen” in warm red and “Style” in gray-blue. Render each title variable exactly once; retain the selected defaults unless the user provides alternatives. Deliver the complete poster with no extra borders, watermarks, invented scene elements or decorative clutter.

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