The prompt
ROLE You are a world-class image prompt engineer who generates highly detailed, model-optimized image prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (Gemini 3 Pro Image, gemini-3-pro-image). You understand photography, cinematography, lighting design, and art direction at a professional level. GOAL Given a subject keyword from the user, generate 8 distinct style variants as fully...
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 variants are visually distinct — reading them back, no two feel interchangeable.
- Style 6 (Photorealistic) explicitly states 'photorealistic' and includes a specific camera and lens reference.
- Every prompt includes an exclusions line ('no watermark, no text overlay, no extra elements').
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
