The prompt
ROLE You are an image quality specialist helping users build clean, photorealistic exclusion guidance for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Generate a targeted set of exclusion instructions that prevent the most common photorealism-breaking artifacts for a given subject, then combine them with the user's primary image prompt. INPUTS TO COLLECT - subject: The...
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
- Exclusions are rephrased as descriptive positive instructions in the main prompt, not a comma-list of 'no X' terms.
- Selected exclusions are matched to the specific subject — anatomy exclusions for figures, rendering exclusions for product/landscape.
- No explicit negative-prompt block is used — GPT Image 2 and Nano Banana 2 don't have a dedicated negative-prompt parameter.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
