Document original
GPT Image 2 · en
Create a cinematic photorealistic nighttime street scene in rainy Tokyo, horizontal 16:9 composition. A solitary {argument name="subject" default="young woman"} stands slightly right of center outside a brightly lit convenience store, holding a transparent plastic umbrella above her head and a white takeaway coffee cup near her mouth. She wears an oversized light beige rain jacket over a long dark skirt, with damp dark hair and a calm, introspective posture; keep the face softly blurred and indistinct. The store windows glow warm yellow and reveal shelves of products, with visible Japanese-style signage including a “24 OPEN” sign and a staff recruitment notice. The wet asphalt street stretches into the background on the left, reflecting red traffic lights, neon shop signs, and car headlights; include one taxi-like car at the far left foreground, a red traffic signal high left, narrow urban buildings, poles, and deep perspective bokeh. Add heavy rain, water droplets on the lens, umbrella highlights, puddles, reflections, and moody steam-like atmosphere. Visual style: ultra-realistic street photography, cinematic film still, shallow depth of field, warm store light contrasting with cool dark rain, high dynamic range, 35mm lens feel, subtle grain, natural imperfections, no posed fashion look, no readable branding beyond generic convenience-store signs. Use {argument name="location" default="Tokyo side street"}, {argument name="weather" default="heavy rain at night"}, {argument name="main clothing" default="oversized light beige rain jacket"}, and {argument name="mood" default="quiet melancholy and urban solitude"}.Mode d’emploi
- Copiez le prompt original complet, paramètres compris.
- Adaptez le sujet, le texte et la composition à vos besoins.
- Utilisez un outil externe compatible ; vérifiez l’accès et le résultat.
Avant de commencer
- Vérifiez si une image de référence est nécessaire. La compatibilité ne prouve pas le modèle utilisé pour cet exemple.
- Vérifiez noms, chiffres et textes ; les versions du modèle peuvent produire des résultats différents.
