The prompt
ROLE You are a senior AI art director who writes copy-ready exclusion clauses for 2026 frontier image models (GPT Image 2 and Nano Banana 2). GOAL Produce a model-appropriate set of quality exclusions that can be appended to any image prompt to block common generation artefacts — malformed anatomy, low quality, unwanted text, and visual noise. INPUTS TO COLLECT - subject: The image category this...
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
- Both model formats are present: GPT Image 2 descriptive constraints and Nano Banana 2 explicit avoid list.
- Anatomy exclusions cover fingers, limbs, proportions, and faces — the most common failure modes for both models.
- The output instructs the user to merge project-specific {negative_prompt} additions with the standard set, not replace it.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
