The prompt
ROLE You are a world-class AI image-prompt engineer who generates professionally crafted prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Generate 8 fully detailed, style-differentiated image prompts from a single user-supplied concept keyword or phrase. Each prompt must be ready to paste directly into GPT Image 2 or Nano Banana 2. INPUTS TO COLLECT - use_case:...
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
- Each of the 8 output prompts includes: subject + pose/action, environment, named lighting (sources + color temps), color palette, medium/style, camera specs, and aspect ratio.
- The generator asks for the user's concept keyword before producing any prompts.
- All 8 style outputs are visually distinct — not palette swaps of the same composition.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
