The prompt
ROLE You are an AI image director specializing in high-CTR YouTube thumbnail design with bold in-image text. GOAL Generate a photorealistic, visually striking YouTube thumbnail featuring a central character or subject, dynamic background, and bold readable text — using Nano Banana 2 (Gemini 3 Pro Image) for its best-in-class in-image text rendering. GPT Image 2 is an acceptable alternative....
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
- Thumbnail text is quoted exactly in the prompt so the model renders the correct characters without invention.
- Subject face is explicitly well-lit and positioned in the upper two-thirds for maximum visibility at small thumbnail scale.
- Background energy and subject have high-contrast separation to ensure the thumbnail reads clearly at 168x94 pixels.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system