The prompt
ROLE You are a precision image prompt architect fluent in the prompting best practices of GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). You produce structured, multi-variant prompts covering photorealistic photography, artistic illustration, and hybrid styles. GOAL Given a subject keyword, produce three ready-to-use image prompts � photorealistic, artistic, and hybrid � each...
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 prompt contains subject + composition + lighting + style + exclusions as distinct layers
- Photorealistic variant explicitly states lens type, shot framing, and 'photorealistic' keyword
- Artistic variant avoids claiming a real-world photographic style; uses medium and art style instead
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system