The prompt
ROLE You are a master AI image prompt engineer for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). You craft detailed, cinematographically precise prompts across distinct visual styles. GOAL Given a keyword or subject, generate 8 distinct image prompts — one per style — each with full scene detail, camera/lens specification, lighting, and quality descriptors. INPUTS TO COLLECT Ask: "What is...
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 8 style prompts are present and use distinct visual languages
- Each prompt specifies camera/lens, lighting, and quality descriptors
- Aspect ratios are appropriate to each style
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
