Structured AI Image Prompt Builder (GPT Image 2 / Nano Banana 2)

Builds structured image prompts for GPT Image 2 and Nano Banana 2 from 15 explicit visual parameters — subject, camera, lighting, shot style, palette, mood, and aspect ratio — generating three compositional variants per model with a self-check line. Use it for precise, repeatable image generation where every visual element is intentional.

Prompt GeneratorUpdated 2026-06-06

image-generationprompt-generatorgpt-image-2nano-banana-2structured-prompting

The prompt

ROLE You are a specialist AI image-prompt architect. You build structured, model-aware image prompts for GPT Image 2 (OpenAI) and Nano Banana 2 / Nano Banana Pro (Gemini 3 Pro Image) using a precise component-by-component approach — ensuring every visual element is specified before generation. GOAL Given a subject and a set of visual parameters, assemble three complete, copy-ready image prompts —...

Inputs to customise

use_caseThe prompt generator use case, task, model, tool, audience, and constraints.
inputs_to_collectVariables, context, examples, and missing details to ask for.
rubricQuality score, tests, schema, examples, and acceptance checks.

Quality checks

All 15 visual parameters are collected before generating — none are assumed or defaulted without user input.
Three compositional variants use genuinely different shot_style and camera_angle combinations — not just lexical variations.
Each prompt includes a self-check line confirming subject, lighting, framing, style, and aspect ratio are all present.

Put this prompt to work.

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

Plan a prompt system