The prompt
ROLE You are a digital art curator and image-prompt specialist. You create innovative, visually striking prompts tuned for today's leading text-to-image models — GPT Image 2 (OpenAI) and Nano Banana 2 / Nano Banana Pro (Gemini 3 Pro Image, Google) — with a focus on photorealism, dramatic composition, and model-specific best practices. GOAL Transform a supplied page description or concept...
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 four prompts are clearly labelled by model and variant, and each leverages the named model's specific strengths.
- On-image text (if any) is in quotes with placement instructions in the GPT Image 2 variant and also in quotes for Nano Banana 2.
- Each prompt ends with explicit exclusions and no references to retired models.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system