Best PromptsInfographic From Your Data
Generate a finished infographic with accurate text in Nano Banana Pro: sectioned layout, quoted labels, chart types that render clean, and a fact-check pass.
A clean [VERTICAL 4:5 / HORIZONTAL 16:9] infographic titled "[EXACT TITLE IN QUOTES]". The data/content (everything the graphic states comes from here): """ [YOUR 3-5 FACTS, STATS, OR STEPS, exact numbers and labels, e.g. "Step 1: Soak beans 8 hours / 62% of users quit in week 1 / Q1: $1.2M"] """ Layout: [PICK ONE, numbered vertical flow, steps 1-[N] top to bottom, each with an icon / a central diagram of [THE SUBJECT] with labeled callouts around it / a dashboard grid: one big headline stat, supporting bar chart, three small KPI tiles]. Each section: a short header in quotes exactly as written above, the number rendered large, and a [flat minimal / hand-drawn / isometric] icon beside it. Charts only where the data calls for them: bar charts for comparisons, a donut for a single share, big numerals for KPIs, no chart junk, no fake 3D. Style: [AESTHETIC, e.g. "modern editorial, generous white space" / "warm hand-illustrated, paper texture"]. Palette: [2-4 COLORS OR HEX CODES] on a [LIGHT/DARK] background. All text in a clean legible sans-serif with strong contrast: every label readable at phone size. Keep total text under ~80 words. Render every quoted string letter-perfect. [NO-DATA VARIANT: let the model supply the content, then verify it: "A detailed infographic explaining [TOPIC, e.g. 'how espresso extraction works' / 'the water cycle'], with labeled stages, arrows showing flow, and one key number per stage."]
How to use
Legible in-image text at this density is specifically a Nano Banana Pro strength. Quote every string you need rendered exactly, keep total text well under 100 words, and prefer bars/donuts/big numerals, which render far cleaner than scatter plots or fine gridlines. The non-negotiable step: proofread every number and label against your source before publishing, especially in the no-data variant where the model supplies facts; text accuracy is high, not perfect. Fix typos with a follow-up edit ('same image, change X to Y'), not a fresh roll.
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.