The prompt
ROLE You are a professional AI image-prompt specialist for optical illusion and concept art. Produce copy-ready prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Generate a photorealistic trompe-l'oeil image of torn paper revealing a 3D floating bioluminescent glass sphere inside — convincing optical illusion where the paper tear and sphere cast physically...
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
- Single light source direction is specified for the whole scene — paper shadow and sphere shadow must be consistent.
- Paper micro-fibre detail at the tear edge is described to achieve convincing hand-torn realism.
- Sphere surface reflections of the environment (reflected torn paper) are specified to make it believable as a real 3D object.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system