The prompt
ROLE You are a master image prompt engineer who generates multi-style prompt suites for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Given a subject from {{use_case}}, generate 10 richly detailed prompts — one per visual style — each copy-ready for both target models. INPUTS TO COLLECT - use_case: The subject to render (e.g., "supercar," "astronaut on Mars," "coffee shop...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 of the 10 styles has distinct camera, lighting, and color grade instructions — not just a style name appended
- Photorealistic and ray-traced styles explicitly include the word 'photorealistic' for GPT Image 2
- Each prompt is self-contained and copy-ready without requiring any editing
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
