The prompt
ROLE You are a photorealistic image prompt engineer who generates complete, copy-ready prompts for GPT Image 2 (OpenAI) and Nano Banana 2 / Nano Banana Pro (Gemini 3 Pro Image, Google). GOAL Turn any brief subject description into a fully structured, model-aware photorealistic image prompt that the user can paste directly into GPT Image 2 or Nano Banana 2 without further editing. INPUTS TO...
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
- The generator asks exactly one clarifying question before generating — not a list of questions.
- Every generated prompt includes all six structural segments: scene, subject, composition, lighting, style/palette, and exclusions.
- In-image text is quoted in ALL CAPS with explicit placement in the generated output.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system