ImageSocial graphicsIntermediateGenerates an image

Stat callout graphic with exact numbers

A one-number graphic for social or decks, with the figure and source line supplied by you so the model never invents data.

For: Performance marketers, Creative strategists, E-commerce marketers · Works with: OpenAI GPT Image, Google Gemini image generation (Nano Banana), Ideogram, Any image generator

Your prompt

Design a 1:1 stat graphic. Render this text exactly, nothing more: Big number: "42%" Label under it: "of our trial users upgraded within 30 days" Source line in small type at the bottom: "Source: internal data, Q2 2026, n=1,200" Layout: the big number dominates the centre, the label sits directly below, the source line is small and unobtrusive at the bottom edge with a safe margin. Style: minimal editorial poster; warm off-white (#F6F1E7) background, ink black (#111111) number, charcoal grey (#444444) label. Constraints: do not add any other numbers, percentages, charts or text; no logos; do not alter the figures.

Customize

The fields start with example values so you can see how the prompt works. Everything stays in your browser.

Graphic shape.

A figure YOU have verified.

Plain-language meaning.

Where the number comes from. Required for credibility.

Visual direction.

Background.

Number colour.

Label colour.

Example of what to expect

Illustrative only. It describes the kind of result this prompt aims for; real output varies by tool, model and run.

A square off-white graphic with '42%' in huge black type, the label beneath it, and a small source line at the bottom.

Expected format: One image; verify each character, especially digits and the percent sign.

How to use it

  1. Only use numbers you can source and defend.
  2. Compare every digit against your source after generation.
  3. Keep the source line; unsourced statistics erode trust.

Limitations

  • Models sometimes alter digits or add stray text; verify every character.
  • Never use the model to generate statistics; this prompt only formats numbers you supply.

Platform notes

OpenAI GPT Image

Official docs read · checked 2026-10-11

Aspect ratio is set with the size parameter, not in prose. Use medium or high quality for text and fine detail. Quote the literal text and describe typography as constraints; OpenAI and Google both document this pattern. Always proofread the result.

General notes on OpenAI GPT Image
  • OpenAI's guide covers gpt-image-2 (recommended), gpt-image-1.5, gpt-image-1 and gpt-image-1-mini.
  • Aspect ratio is set through the size parameter, not in prose. Quality is low, medium or high; medium or high is advised for small or dense text.
  • Put literal text in quotation marks, and when editing say what must stay unchanged.

Google Gemini image generation (Nano Banana)

Official docs read · checked 2026-10-11

Quote the literal text and describe typography as constraints; OpenAI and Google both document this pattern. Always proofread the result.

General notes on Google Gemini image generation (Nano Banana)
  • Google's docs list several Nano Banana models (2.1, 2 Lite, 2, Pro) and recommend 2.1 for new projects as of the verification date.
  • Supported aspect ratios include 1:1, 4:5, 9:16, 16:9 and 21:9; sizes 1K, 2K and 4K. Up to 14 reference images per request.
  • All generated images carry a SynthID watermark.

Ideogram

Not verified: third-party guidance only · checked 2026-10-11

Third-party guidance only; verify.

General notes on Ideogram
  • Known for text-in-image work. Third-party guides advise quoting the text and describing font style and layout. We could not find Ideogram's own prompting guide, so treat this as unverified.

Any image generator

Official docs read · checked 2026-10-11
General notes on Any image generator
  • Written as natural-language descriptions that the verified image models accept. Syntax for aspect ratio, quality and negative prompts differs by tool, so set those in your tool's own controls.

Source, license and attribution

Origin
Original by MarketerTools
Publisher
MarketerTools
License
Original work by MarketerTools, free to copy and use. Informed by the linked documentation; no third-party text is reproduced.
Platform assumptions checked
2026-10-11

Documentation and references behind this prompt

These informed the structure and the platform notes. A reference is not a license, and no third-party prompt text is copied here.

Spotted an attribution error, or are you a source owner with a request? Use the chat button at the bottom right and quote prompt ID img-022. We will correct or remove it.

Related prompts

  • ImageIntermediateGenerates an image

    LinkedIn carousel cover slide

    A bold, scannable cover for a document carousel: one headline, one visual idea, a swipe cue, and consistent colours you can reuse on every slide.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · Ideogram +1

  • ImageAdvancedGenerates an image

    Stat-led infographic from data you supply

    A multi-panel infographic where every number and label comes from you, laid out by the model; it never invents data.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · Any image generator

  • ImageIntermediateGenerates an image

    Event or webinar announcement graphic

    An announcement graphic with a clear information hierarchy for date, time and title, using exact text you provide.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · Ideogram +1

  • ImageIntermediateGenerates an image

    Podcast or series cover art

    Square cover art that stays legible as a tiny thumbnail in podcast apps and social feeds, with a short exact title.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · Ideogram +1