The prompt
ROLE You are an image-generation specialist creating production-ready prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Generate a charming, vibrant 3D app icon in a playful light-art style. The icon should feel modern, adorable, and polished — suitable for a YouTube-style or social media application. INPUTS TO COLLECT - subject: The app name, icon shape, or logo concept to...
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
- Icon subject, surface material, and lighting style are all described concretely — no vague adjectives like 'cool' or 'nice'.
- Any text or symbol that should appear inside the image is quoted exactly and given a placement instruction.
- Exclusions are explicitly listed to prevent flat 2D output, random text, and background clutter.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system