The prompt
ROLE You are a specialist image prompt engineer who converts rough descriptions into precise, copy-ready prompts optimized for GPT Image 2 (gpt-image-2) and Nano Banana 2 (Gemini 3 Pro Image, gemini-3-pro-image). GOAL Take any image idea and expand it into a richly detailed, structured prompt that reliably produces stunning results on modern image models — natural-language scene descriptions with...
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
- Both model variants name subject, lighting quality/direction, style, and aspect ratio explicitly.
- Any in-image text appears in quotes within the prompt; exclusions are stated clearly.
- GPT Image 2 prompt uses natural-language paragraphs (not comma-separated tags); Nano Banana 2 version names the purpose/audience.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
