IP
生成
Premium poster split composition preview image
主要参照画像

Premium poster split composition

Creates a vertical poster divided into two halves: a realistic photo on top and a schematic line-art illustration on the bottom.

これはグラフィック&ポスター向けのGPT Image 2プロンプトケースです。以下のコピー可能なプロンプトを使用して同様のビジュアルを生成し、再利用する前にAwesome GPT Image 2 Prompts帰属表示と商用利用権を確認してください。

プロンプトセット全体が必要ですか? グラフィック&ポスター 関連する例をもっと見るにはトピックハブを開くか、 GPT Image 2 プロンプトカタログ 完全な例の索引、再利用可能な構造、および出典の明記については、こちらをご覧ください。
Upload image to generate

Free 1K preview

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

…

Free text preview doesn’t preserve reference-image consistency.

2863/4000
Continue on Dovoo

プロンプト

コピー準備完了プロンプト

Please create a separate, independently designed premium poster from each uploaded photo. Do not combine multiple photos into one composition; output one individual poster for each photo. Use a vertical 3:4 composition, with the upper and lower sections strictly divided 1:1, each occupying exactly 50% of the total height.

Upper Half:  
Preserve the original photograph, maintaining the subject’s identity, structure, pose, realistic texture, natural lighting, and original color atmosphere. Apply only subtle, sophisticated color grading to give it the visual quality of an art magazine, independent publication, or exhibition image. To adapt the image to the 3:4 format, the surrounding background may be naturally extended, but do not stretch, distort, or alter the subject.

Lower Half:  
Extract the most recognizable subject, silhouette, structure, pose, and narrative relationship from the photograph and reconstruct it in the style of Mid-century vernacular graphic illustration + schematic line drawing + two-color spot printing.

Do not completely trace or replicate the photograph. Instead, use diagrammatic abstraction to compress complex objects into a small number of clear geometric shapes, functional contours, and essential structural elements. The result should resemble an illustration from an old instruction manual, advertising card, technical label, or vernacular print: immediately recognizable, yet more direct, humorous, and symbolic than the realistic object itself.

Emphasize economy of line: if a structure can be explained with a single line, do not use unnecessary strokes. Use direct black pen outlines, rectangles, circles, diamonds, straight lines, and simple planes to describe the objects. People, animals, and objects may have slightly exaggerated proportions, while machines, buildings, and complex structures should be simplified into clear boxes, openings, panels, and silhouette relationships.

Use a flat, schematic diagrammatic perspective rather than realistic lighting or strictly accurate spatial depth. The visual language should exist somewhere between illustration and technical diagram, maintaining this distinctive character throughout the composition.

Reorganize the composition according to the most important narrative relationship in the original image. Maintain one clear primary subject, while using a small number of supporting objects, guide lines, directional relationships, or structural symbols to reinforce the story.

Pay close attention to visual hierarchy, geometric order, scale contrast, positive and negative space, and intentional whitespace. The image may feel slightly naïve, awkward, or handmade in a vernacular way, but it must never feel cluttered. Every visual element should appear to exist for the purpose of “explaining what is happening”, rather than simply serving as decoration.

Best for

  • - グラフィック&ポスター 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: 画像から画像
  • - 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.
Awesome GPT Image 2 Promptsからインポートされました。出典の明記が必要です。商用利用の可否はallowedです。有料利用の前に、出典元の権利をご確認ください。

このカテゴリーのその他の事例

カテゴリー、入力モードの互換性、品質、およびリスクの低さに基づいて優先順位付けされています。

6

再利用と出典に関する注記

ケースを事前に確認してから、このプロンプトを安全に使用してください。

  1. 1.プロンプトをコピーするか、生成ボタンを使ってDovooで直接開いてください。
  2. 2.ご自身の用途に合わせて、変数、アスペクト比、および参照画像を調整してください。
  3. 3.公開または有料利用の前に、情報源の権利、帰属表示の要件、およびブランドまたは肖像権に関するリスクを確認してください。
大人限定

検閲なしのプロンプト、チャット、生成機能が欲しいですか?

このサイトの内容はすべて職場でも閲覧可能です。フィルターなしのNSFW(職場閲覧注意)AIチャットや画像・動画生成をご希望の場合は、Stella AIをご利用ください。

Stella AIでは、フィルターなしのAIチャット、画像、動画生成が可能です。