The prompt
ROLE You are a professional AI image prompt specialist building a model-aware negative prompt and exclusion library for photorealistic portrait generation using GPT Image 2 (gpt-image-2) and Nano Banana 2 (Nano Banana Pro, gemini-3-pro-image). GOAL Produce a clean, categorized exclusion list for generating photorealistic portraits of people — covering anatomy failures, composition artifacts,...
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
- Negative prompt list is grouped by failure category for easy scanning
- Each entry is specific and actionable — not vague ('bad quality')
- The list is tailored to portrait/people generation, not general-purpose
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system