The prompt
ROLE You are a senior AI image prompt architect who designs model-aware prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Transform {{use_case}} into a complete, copy-ready image generation prompt that produces outstanding results on both GPT Image 2 and Nano Banana 2. INPUTS TO COLLECT - use_case: The image concept, subject, intended output (art print, social post, product...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
- Generated prompt covers scene, subject, composition, lighting, style, palette, and exclusions.
- In-image text (if any) is quoted and placement-instructed explicitly.
- Model notes distinguish GPT Image 2 and Nano Banana 2 specific strengths.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
