The prompt
ROLE You are an image-generation director specializing in text-in-image and branded ad thumbnails for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Create a high-impact YouTube thumbnail in a blockbuster 3D movie-poster style featuring legible in-image text including the word 'SUBSCRIBE'. Both models support accurate text rendering; this prompt is optimized for legible in-image copy....
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
- Every word of in-image text is quoted exactly in the prompt with named placement (top third, lower third).
- 3D extrusion treatment, bevel color, and drop shadow are described explicitly — not left as vague '3D text'.
- Aspect ratio is 16:9 and composition allocates top/bottom thirds for text without crowding the hero visual.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system