Back To School Enrollment And Retail Kit — Parent Checkout Cart

Back To School Enrollment And Retail Kit — Parent Checkout Cart

Document original

GPT Image 2 · en

Scene:
Create a square retail image with bright aisle or checkout light, organized product stacks, and a polished family-shopping atmosphere. The frame should feel like a campaign image for school-season purchasing rather than a supermarket snapshot. Use cart geometry, shelf rhythm, and clear object hierarchy to communicate efficient preparation and family-oriented buying behavior.

Subject:
Show a cart with school supplies, tech accessories, storage items, lunch or apparel forms, and a few checkout cues that remain non-legible. People can be implied or partly present, but the purchasing structure should stay central. The subject should communicate bulk preparation, care, and efficient decision-making for the new term.

Important details:
Retail clarity matters most. Make cart metal, packaging forms, plastic, paper, and polished floor reflections all feel real. Keep the scene commercially neat and useful for retail, education, or parent-targeted promotions. Avoid discount-chaos energy; this is organized, capable preparation. Keep the frame precise enough for gallery, research, and campaign reuse, with believable materials and a strong thumbnail read.

Use case:
Back to School single study 7/9.

Constraints:
No readable text, no watermark, no logos, preserve exact 1:1 aspect ratio, no readable price labels, no store logos, no chaotic crowd, no mascot packaging, no messy bargain-bin feel, no readable receipts, no neon promo signs, no graduation décor.

Mode d’emploi

  1. Copiez le prompt original complet, paramètres compris.
  2. Adaptez le sujet, le texte et la composition à vos besoins.
  3. 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.