ImageLaunch and hero visualsIntermediateGenerates an image

Consistent icon or spot-illustration set

A style-locked prompt for generating several matching icons or spot illustrations, changing only the concept each time.

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

Your prompt

Create a single icon-style illustration of a shield with a checkmark representing data security on a plain off-white background. Style lock (identical for every icon in the set): rounded line icon, 3px uniform stroke, rounded caps, one flat fill accent, no outlines other than the stroke. Size and framing: square 1:1, the icon centred and filling about 70% of the canvas with equal margin on all sides. Colour: only these colours: deep indigo stroke (#2B2F7A) and a mint (#7ED9B5) fill accent. Detail level: simple, readable at 64 pixels; no text, no gradients unless specified in the style lock, no shadows outside the icon. Constraints: one object only, no background elements, no frame.

Customize

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

Change this for each icon.

The style description to reuse verbatim for the whole set.

Plain background.

The full palette.

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 centred indigo-line shield icon with a mint checkmark on an off-white background, matching a uniform stroke style.

Expected format: One icon per generation; repeat with a new CONCEPT, keeping all other text identical.

How to use it

  1. Paste the style lock unchanged for every icon.
  2. Generate a trial set of three to check consistency before producing more.
  3. Vectorise or redraw final icons for production use.

Limitations

  • Consistency across generations is imperfect; expect drift and curate.
  • Not a substitute for a designed icon system; raster output only.

Platform notes

OpenAI GPT Image

Official docs read · checked 2026-10-11

OpenAI recommends a consistent, skimmable template for production prompts. Aspect ratio is set with the size parameter, not in prose. Use medium or high quality for text and fine detail.

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

Gemini supports multi-turn editing and reference images, which help keep a set consistent.

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.

FLUX (Black Forest Labs)

Official docs read · checked 2026-10-11
General notes on FLUX (Black Forest Labs)
  • BFL's official guidance for FLUX.2: no negative prompts (describe what you want), write sentences rather than keyword lists, specify lighting, quote text to render, and pair colour names with hex codes.

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-030. We will correct or remove it.

Related prompts

  • ImageIntermediateGenerates an image

    Abstract SaaS hero illustration

    A non-photographic, brand-colour illustration for software pages where a screenshot would be unreadable or unavailable.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · FLUX (Black Forest Labs) +1

  • ImageIntermediateGenerates an image

    Reusable brand style-anchor prompt block

    A paste-in style block that keeps a team's AI images visually consistent across scenes and campaigns.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · FLUX (Black Forest Labs) +1

  • ImageIntermediateGenerates an image

    Product launch teaser visual

    A teaser that hints at a product without fully revealing it, to build anticipation before launch.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · FLUX (Black Forest Labs) +2

  • ImageIntermediateGenerates an image

    Landing-page hero image with copy space

    A wide hero visual designed around the headline and CTA zones of a landing page, including how it should crop on mobile.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · FLUX (Black Forest Labs) +2