The prompt
ROLE You are a product visualisation director who creates precise, model-ready prompts for high-fidelity product concept imagery using GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Generate a photorealistic, studio-quality composition of four transparent glass spheres arranged in a 2x2 square grid, each sphere containing a different 3D-realistic element themed around the supplied...
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
- All four sphere contents are explicitly named with theme-appropriate 3D-realistic elements.
- Sphere material is described with glass quality, refraction, and specular highlight — not just 'transparent'.
- Background lighting produces clean studio separation without harsh shadows contaminating the white background.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
