
Document original
GPT Image 2 · en
A poignant Gothic illustration, rendered in an impasto oil painting style, depicts a lonely little girl huddled on a cushioned windowsill in a dimly lit old house on a rainy night. She has {argument name="hair color" default="Dark brown"} Her messy curly hair, wearing a{argument name="sweater color" default="Rust Red"} She wears an oversized knit sweater, paired with black and beige striped stockings and dark lace-up boots. Her posture is reserved, knees drawn up to her chest, gazing out of a tall, multi-paned window. Outside the glass is a crooked, haunted European village street with steep roofs, spires, glittering windows, slippery cobblestones, and a prominent clock tower, against a backdrop of a gloomy, stormy sky. The image must include one figure walking alone in the rain with an umbrella. The interior should include an industrial chandelier emitting a warm yellow light in the upper left corner, a red ceramic mug on the windowsill, an open sketchbook on a bench (with a drawing of a black cat visible on the pages), two red pillows, and several small framed paintings on the left wall. The color palette should primarily consist of charcoal gray, dark brown, black, and soft amber, contrasting the warm indoor lighting with the cold, damp outdoors. The composition should be slightly tilted and cinematic, with the girl positioned slightly to the left of the center, and the rain-soaked town occupying the right side of the frame. It emphasizes melancholy, loneliness, gothic fantasy, textured brushstrokes, scratches, dramatic window reflections, and a dark fairytale atmosphere within square compositions.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.





