チャットGPT
ダークドリーム — ワインジョーゼット
チャットGPT 向けに書かれました。結果と参照写真のサポートはモデルによって異なる場合があります。
このプロンプトを使う前に
リストされているツール: チャットGPT。完全な説明: 1,424 文字。 2 にはサンプル画像が提供されています。
This prompt mentions reference images. Read its instructions for the required number of photos and identity constraints. We have not independently tested this prompt. Tool labels and supplied images are not a guarantee of compatibility or output quality.
プロンプト全文
Create an ultra-photorealistic 9:16 vertical portrait using the uploaded photograph as the EXACT identity reference. Preserve her exact facial identity, natural skin tone, facial proportions, and recognizable features.
Dress her in a deep wine-red georgette saree with a subtle black-and-gold woven border and a fitted wine blouse. Add antique-gold jhumkas, a thin gold necklace, and minimal makeup. Hair loosely tied with a few natural strands around her face.
Place her inside a dimly lit traditional Indian room with dark wooden architecture, a single warm lamp glowing behind her, and soft shadows surrounding the scene. She stands near the doorway, slightly turning her body while looking calmly toward the camera.
Use a deliberately dreamy photographic treatment: noticeable soft-focus filter, gentle overall blur, slight movement blur around the saree and hair, subtle lens diffusion, warm amber highlights, deep muted shadows, low-contrast cinematic color grading, fine visible film grain, faint halation around the lamp, very subtle reddish-brown color cast and a soft vignette.
The result must still look like a real contemporary photograph—beautifully imperfect, slightly hazy, cinematic and tactile—not a perfectly sharp AI render.
No 80s/90s fashion, no period recreation, no excessive glow, no fake skin, no extreme blur hiding the face, no fantasy costume, no distorted hands, no facial changes, no text.プロンプト全体をコピーし、必要に応じて独自の参考写真を使用してください。
このプロンプトで提供されるサンプル画像。このプロンプトは当社のサイトではテストされていません。
