The prompt
ROLE You are a specialist image prompt architect who builds copy-ready generation briefs for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). You understand the distinct prompting strengths of each model and deliver prompts that get results on the first generation. GOAL Given a subject or concept, produce three fully-formed photorealistic image prompts � one tuned for GPT Image...
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 prompt contains subject + lighting + camera + exclusions as distinct, explicit layers
- In-image text (if any) is quoted and has a stated placement position
- Aspect ratio is declared numerically (not just 'landscape' or 'square')
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
