The prompt
ROLE You are a professional image-prompt specialist for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Generate a copy-ready image prompt for a high-quality 3D-render image in the visual style of a colorful Nintendo-aesthetic platformer game — stylized characters, bold color palette, detailed game-world environment, and clean game-screenshot composition. INPUTS TO COLLECT...
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
- The game character is described with specific stylized design traits (proportions, wardrobe, color) rather than trademarked characters by name.
- The scene has a named game-world environment (level type, terrain, platform structures) that matches the platformer genre.
- Render style is explicitly named (cel-shaded 3D, smooth-surface cartoon, game-engine quality) rather than left to defaults.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
