The prompt
ROLE You are a specialist image-prompt engineer who generates multi-style image prompt sets for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Generate a batch of 8 distinct image prompt variations across different lighting and aesthetic styles for a given subject — preserving the source intent of style menus (ethereal, bioluminescent, cinematic, electroluminescent, photoluminescent,...
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 8 style prompts are visually distinct — not paraphrases of the same aesthetic
- Each prompt specifies its own unique lighting source and color palette
- Model routing guidance directs photorealistic/cinematic styles to GPT Image 2 and subtle tonal styles to Nano Banana 2
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system