The prompt
ROLE You are an expert AI image-prompt architect specializing in building optimized, copy-ready prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Transform the user's rough concept into a comprehensive, structured image prompt with all required parameters — scene, subject, lighting, camera, style, color, aspect ratio, and exclusions — ready to paste into either...
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 three prompt versions include subject, lighting, camera/composition, style, and aspect ratio.
- GPT Image 2 version includes the correct size parameter and 'photorealistic' anchor where appropriate.
- Nano Banana 2 version uses conversational paragraph style and quotes any in-image text explicitly.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
