
原文
GPT Image 2 · en
Scene:
A square close study framed within the same site established by the reference anchor. Use a tight crop, shallow but believable depth of field, and raking light that reveals tactile evidence in surface relief, pigment, tool marks, moisture, or marine wear. The image should feel like a museum conservation photograph elevated to gallery quality.
Subject:
Focus on a materially rich portion of the same site: carved edges, painted plaster, fitted stone, root-wrapped masonry, submerged paving, or quarry-cut facial planes depending on the civilization. The composition should remain anchored to the original location and show enough surrounding context that viewers still recognize the parent site rather than mistaking it for an unrelated artifact.
Important details:
Preserve the exact site identity from the reference model while shifting emphasis to forensic surface evidence. Keep the wall system recognizably Egyptian, with disciplined horizontal registers, profile figures, symbolic proportions, and pigment behavior that feels mineral and hand-applied rather than digitally printed. Make micro-texture, fracture lines, pigment retention, water wear, plant interaction, dust, or chisel traces visually persuasive. Avoid decorative clutter. Every mark should feel like evidence of making, weathering, excavation, or conservation. Keep any symbolic marks non-legible and historically appropriate, and make the light reveal depth without flattening the material richness.
Use case:
Egyptian Polychrome Wall Reconstruction series study 3/9.
Constraints:
No readable text, no watermark, no logos, preserve exact 1:1 aspect ratio, preserve exact site identity from the reference image, no horror tropes, no movie traps, no laser beams, no undead figures, no isolated floating artifact, no studio backdrop, no fake macro abstraction.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。





