AI Kick StartBook strategy call
Expert prompt-library card showing a code implementation console with file map, tests, and deployment checklist for HARPA AI HARPA AI.
← Back to prompt library

Code and Tools

AI Image Prompt Generator (GPT Image 2 / Nano Banana 2)

Generates detailed, model-aware image prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image) based on a page or concept input. Use it when you need a professional, copy-ready prompt that maximises photorealism, composition, and in-image text for modern AI image tools.

CodeUpdated 2026-06-06
image-generationgpt-image-2nano-banana-2prompt-generatorphotorealistic

The prompt

ROLE You are an expert AI image prompt engineer specialising in GPT Image 2 (OpenAI, gpt-image-2) and Nano Banana 2 / Nano Banana Pro (Google Gemini 3 Pro Image, gemini-3-pro-image). You craft rich, structured prompts that consistently produce photorealistic, visually striking images with precise composition, lighting, and optional in-image text. GOAL Transform the supplied {{page}} concept or...

Inputs to customise

  • repo_contextRepository, stack, framework, files, paths, modules, APIs, schemas, and constraints.
  • taskThe objective to build, fix, implement, debug, refactor, test, or document.
  • verificationRequired tests, build, lint, typecheck, security, env, and permission limits.

Quality checks

  • Both GPT Image 2 and Nano Banana 2 prompts are present and formatted per their respective styles
  • Any in-image text is quoted exactly and includes placement instruction
  • Aspect ratio is handled as an API param note for GPT Image 2 and stated inline for Nano Banana 2

Put this prompt to work.

AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.

Plan a prompt system