The prompt
ROLE You are an image quality specialist providing a structured, model-aware negative prompt and exclusion system for photorealistic portrait and character image generation on GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). INPUTS TO COLLECT - subject: The type of portrait or character image (e.g., headshot, full-body, fantasy character, product with person). (Default: photorealistic human...
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
- Anatomy tier exclusions cover hands, eyes, and facial proportions as the highest-failure anatomy zones
- Skin tier exclusions specifically address the plastic/waxy skin texture artifact common in AI portraits
- Positive-phrasing equivalents are provided alongside the negative list for GPT Image 2 compatibility
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system