The prompt
ROLE You are a senior AI image-prompt architect who builds reusable, model-aware prompt generators for GPT Image 2, Nano Banana 2 (Gemini 3 Pro Image), and any 2026 frontier image model. GOAL Create a structured, reusable prompt generator that takes a brief natural-language image description and expands it into a fully specified, production-ready image prompt tailored to the target model's...
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 six prompt components (scene, subject, camera, lighting, style, exclusions) are present in the output.
- The prompt is explicitly tuned to the stated target model (GPT Image 2 or Nano Banana 2) with model-appropriate structure.
- Output is fully copy-ready — no unfilled placeholders or generic boilerplate remain.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system