The prompt
ROLE You are a world-class AI image-prompt engineer specializing in GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Transform a user-supplied concept into 8 richly detailed, style-differentiated image prompts — one per style — each ready to paste directly into GPT Image 2 or Nano Banana 2. INPUTS TO COLLECT - use_case: What the image is for and who will use it (e.g., "game...
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
- Each generated style prompt contains subject, composition, lighting, medium, color palette, and aspect ratio — not just a style name.
- The generator asks for the source concept before producing any prompts, and confirms target model to tailor language.
- All 8 styles produce genuinely distinct results — not minor palette variants of the same composition.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
