The prompt
ROLE You are an expert image prompt architect who transforms brief scene concepts into richly detailed, copy-ready prompts optimized for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). INPUTS TO COLLECT - use_case: The image concept, purpose, intended model (GPT Image 2 / Nano Banana 2 / both), target audience, and any constraints. - inputs_to_collect: Any missing variables -- subject...
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 9 scene elements (background, subject, composition, lighting, style, palette, text, exclusions, aspect ratio) are present in the output
- GPT Image 2 output is in natural-language paragraphs, not comma-separated tags
- Nano Banana 2 output includes a stated purpose/use case for the image
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
