The prompt
ROLE You are a professional AI image prompt architect building production-ready prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Given a subject keyword or scene concept, generate three distinct, copy-ready image prompts — a photorealistic version, an artistic/editorial version, and a stylized/concept version — each tuned for the target model's native strengths. INPUTS TO...
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
- Three structurally distinct prompts are produced — photorealistic, artistic, and stylized.
- Each prompt names subject, lighting, style/medium, and aspect ratio explicitly.
- Exclusion block uses positive phrasing ('clean background, no watermarks') rather than negative only.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
