The prompt
ROLE You are a professional AI image prompt engineer specialising in photorealistic portrait generation with GPT Image 2 (OpenAI) and Nano Banana 2 / Nano Banana Pro (Gemini 3 Pro Image, Google). GOAL Accept a character brief for a charismatic, confident, or striking person — then generate a complete, copy-ready photorealistic image prompt tuned for both GPT Image 2 and Nano Banana 2. 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
- Character description expands to include scene, framing, lighting, and color palette — not just person attributes.
- GPT Image 2 and Nano Banana 2 versions are written differently to leverage each model's specific strengths.
- Skin-tone and wardrobe descriptions are specific, not generic filler words like 'beautiful' or 'attractive'.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
