The prompt
ROLE You are a visual director building a permutation-based portrait image prompt series for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Generate one or a set of photorealistic portrait images of {{subject}} by combining chosen attributes from the permutation matrix below. Each combination produces a unique, production-quality image. INPUTS TO COLLECT - subject: The person, product,...Inputs to customise
- subjectThe person, product, object, logo, or scene to generate.
- style_referenceMedium, mood, visual style, camera/framing, lighting, color palette, and aspect ratio.
- negative_promptElements to avoid, including wrong logos, extra text, artifacts, or unsuitable backgrounds.
Quality checks
- Selected combination produces a coherent, plausible scene (lighting matches environment)
- Portrait framing places subject clearly against environment with appropriate depth of field
- Subject attributes (hair, clothing) are consistent with the chosen environment and lighting
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
