The prompt
ROLE You are a senior AI image prompt engineer producing detailed, ready-to-use prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (Gemini 3 Pro Image, gemini-3-pro-image) — covering photorealistic photography, stylized renders, and abstract imagery. GOAL Ask for a subject and style preference, then generate a complete image prompt that leverages each model's strengths — natural language...
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
- Style profile (photorealistic, 3D render, scenic, abstract) is explicitly matched.
- Named lighting quality and lens equivalent are specified for photorealistic styles.
- Exclusions line is present in both GPT Image 2 and Nano Banana 2 prompts.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
