Best PromptsYouTube Thumbnail
A Nano Banana Pro thumbnail formula: bold layout, exaggerated expression, high-contrast color, and 4 words of text legible at 200px.
A YouTube thumbnail, 16:9. Layout: [PICK ONE: a person's face large on the left third, object of the video on the right / extreme close-up face centered, text in the top band / person pointing at the object, text beside it]. Composition is bold and simple, readable in half a second at small size. The person: [ATTACH YOUR PHOTO AND ADD: "use the person from the attached photo, keeping their face and features exactly recognizable"] with an exaggerated [EXPRESSION: shocked, mouth open, eyebrows raised / delighted grin / skeptical squint], lit brightly from the front with a subtle rim light separating them from the background. The object/scene: [THE VIDEO'S SUBJECT, e.g. "a stack of glowing gold coins" / "the laptop with the exact app visible"], slightly oversized, vivid. Text: "[3-4 WORDS MAX]" in a heavy bold sans-serif with a thick [white/black] outline and slight drop shadow, filling [top band / right third], perfectly legible even at 200 pixels wide. Colors: high-contrast [PALETTE, e.g. "saturated red and yellow against a deep blue background"], background simple with a soft radial glow behind the main subject: the face and text pop above everything else.
How to use
Thumbnails with expressive faces and under-5-word text measurably lift click-through, and Nano Banana Pro is the model to use because its text rendering stays legible at small sizes. Judge the result at actual size: zoom out until it's phone-width, and if the text or expression doesn't read instantly, simplify. Fix misspelled text with a follow-up edit ('same image, fix the text to say X') instead of regenerating.
More image prompts
[Attach the reference image, then use this prompt:] Analyze this image and write me a prompt that would reproduce its look with a different subject. First, describe what you actually see, in these terms: - **Subject and composition**: what is in frame, where it sits, how much of the frame it fills, the crop and aspect ratio, the eye lev
Reverse Engineer an Image Prompt
Turn any reference image into a reusable prompt by naming its subject, lighting, lens, palette, and the one detail that carries the look.
Build me a reusable image style kit for [BRAND]. Brand personality in three words: [e.g. "warm, precise, unfussy"] Who it speaks to: [AUDIENCE] Brand colors: [HEX VALUES, or "you propose"] References I like: [DESCRIBE THEM, OR ATTACH THEM] What we must never look like: [THE COMPETITOR OR AESTHETIC TO AVOID] Where these images go: [WEBSIT
Brand Image Style Kit
Define one reusable visual formula so every image you generate looks like it came from the same brand, across subjects and use cases.
Create a t-shirt design. Concept: [THE IDEA, JOKE, PHRASE, OR IMAGE] Exact text, if any: [TYPE IT EXACTLY, WITH THE CAPITALIZATION YOU WANT] Audience and where they would wear it: [WHO BUYS THIS] Style: [bold vintage / minimal line art / retro 70s sunset / hand-drawn / heavy blackwork / kawaii] Shirt color it prints on: [DARK / LIGHT / B
Print on Demand Apparel
Generate t-shirt and merch artwork built for printing: flat color, clean edges, transparent background, and a mockup that sells it.