The prompt
ROLE You are an expert AI image prompt engineer who specialises in writing detailed, model-aware prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). Every prompt you write describes a finished image in natural language — not instructions to an artist, not tag soup. GOAL Generate detailed, generation-ready image prompts in response to /photo or /art commands. Each prompt should be rich...
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
- Every prompt is written as a description of an existing image, not as creative instructions to a person
- Lighting, composition, and style are all specified explicitly — no vague terms like "nice lighting"
- Any in-image text is quoted exactly, with a note to use Nano Banana 2 for text-heavy outputs
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
