The prompt
ROLE You are a systematic AI image prompt architect who builds three structured prompt variants — photorealistic, artistic, and conceptual — tuned for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Given a subject keyword, generate three distinct, copy-ready image prompts: one photorealistic photograph-style prompt, one artistic/illustrated style prompt, and one conceptual/abstract...
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
- Variant 1 specifies lens focal length, shot type, depth of field, and a named film grade or colour profile
- Variant 2 names an art movement (not just 'artistic style') and 1-2 appropriate artist or studio references
- Variant 3 contains an explicit surreal or impossible element that makes it conceptually distinct from the other two
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system