
原文
GPT Image 2 · en
Create a vertical photorealistic fantasy fashion design sheet on a wooden desk: a full-body ancient Chinese hanfu model appears to come alive from a cream sketch paper clipped to a drawing board, blending 3D realism in the upper body with pencil sketch and pale watercolor fashion illustration in the lower skirt. The model is {argument name="character name" default="Look 01"}, a delicate young East Asian woman with fair skin, soft makeup, long black hair in a loose half-up style, and a silver floral hair ornament with dangling beads. She wears {argument name="outfit color palette" default="moon-white and misty pale blue"} layered hanfu: translucent gauze sleeves, white inner robe, pale blue embroidered collar trim, wrapped blue-gray waist sash with a bow and pearl tassel, and a flowing semi-transparent skirt that dissolves into visible graphite construction lines near the hem and feet. The pose is graceful and seated/reclining on the paper, head turned slightly upward to the right, one hand resting near the waist and the other touching the paper. Add exactly 5 handwritten fashion annotation areas on the page: 1) top right title “Look 01” underlined, 2) “hair ornament” with Chinese note “发髻结构” and a small ornament sketch, 3) left side “sleeve volume” with Chinese note “袖型” and a sleeve diagram, 4) right middle “ribbon flow” with Chinese note “飘带走势” and flowing ribbon arrows, 5) lower left “skirt movement” with Chinese note “裙摆动态” and a skirt motion sketch. Surround the board with traditional design-studio props: a ceramic teacup at upper left, paper and color swatches at left, a pale jade pendant/tassel at lower left, fabric swatches in white and blue at bottom left, calligraphy paper and wooden tray at upper right, two drawing pens on the right, and a visible hand at lower right sketching the dress with a pencil. Use warm natural window light, shallow depth of field, realistic paper texture, graphite lines, soft watercolor washes, cinematic top-down three-quarter composition, high detail, elegant ancient Chinese aesthetic, no extra text beyond the specified annotations.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。





