
原文
GPT Image 2 · en
Scene:
A square documentary image composed like a premium archaeology magazine feature. Use sunlit buff stone, saturated vine green, glazed deep blue, and Euphrates river haze. Frame a terraced Babylonian garden complex rising in stacked levels with irrigation channels, hanging vegetation, and distant river atmosphere with crisp depth layering, restrained contrast, and subtle atmospheric depth so the scene feels excavated, observed, and historically grounded rather than theatrical or game-like. Keep the light directional but believable, as if captured during a careful field visit.
Subject:
Center the image on a terraced Babylonian garden complex rising in stacked levels with irrigation channels, hanging vegetation, and distant river atmosphere. Include culturally accurate surface logic, region-specific setting, and believable human-scale cues in stairs, doorways, cut blocks, relief edges, or water depth. Shapes, carvings, masonry joints, and site wear should feel studied from real archaeology, with no generic ancient-world mashup and no ornamental filler borrowed from another civilization.
Important details:
Keep the reconstruction architecturally disciplined, with Near Eastern massing, stepped terrace engineering, visible hydraulic logic, and planted abundance that feels maintained by ancient infrastructure rather than magical floating greenery. Emphasize sun-baked masonry, glazed brick details, irrigation water, trailing vines, palms, and engineered terrace retaining walls. Keep inscriptions, painted registers, symbolic motifs, or carved bands visually plausible but not readable. Preserve a museum-grade balance between beauty and evidence: light should reveal relief depth, edge wear, repairs, sediment traces, and excavation context without turning the site into fantasy spectacle. The composition should feel like a definitive reference frame that later variations can inherit exactly.
Use case:
Babylon Hanging Gardens series study 1/9.
Constraints:
No readable text, no watermark, no logos, preserve exact 1:1 aspect ratio, no fantasy dragons, no neon glow, no steel frameworks, no modern city skyline, no tourists, no anachronistic props, no collage layout, no exaggerated fantasy lighting.使い方
- パラメータを含む元のプロンプト全体をコピーします。
- 被写体、文字、構図を自分の要件に置き換えます。
- 対応する外部ツールで使用し、利用条件と結果を確認します。
開始前の確認
- 参考画像の要否を確認してください。互換モデルの表示は、そのモデルでの生成実績を意味しません。
- 名前、数値、画像内の文字を確認します。モデルの版で結果は変わります。