Skill · Image

Ad & Social Image Set

Plan ad and social image variants around one test variable, with a shared lock block, safe areas per format and a pre-flight check, so the results tell you something.

Paid

Version 3Updated 15 Oct 2026

When to use

  • A campaign needs several image variants and the user will compare their results.
  • One approved visual has to be adapted for feed, story and banner placements.
  • An organic social series should look like one campaign.

When not to use

  • A single hero image: editorial-product-photo-style or gpt-image-product-shots fit better.
  • Regulated categories (health outcomes, finance returns, before/after results). The skill flags the risk but can't judge the platform's ad policy; the user checks it.
  • Text-led designs where the lettering is the concept: plan those with text-in-image-layout.

Example

User: Cold-brew coffee concentrate sold online; audience: people working from home, 25-40; question: product on a desk or product in a hand? Placements: 4:5 feed and 9:16 stories. Nano Banana 2.1 with a product photo.

Output (excerpt):

  • Test line: "We change how the bottle is shown (on the desk vs in a hand pouring); the desk, light and palette stay fixed; the winner is the variant with the higher click-through after the budget you set."
  • Lock block (start): "Image 1 is the exact product: a 500 ml clear glass bottle of dark coffee concentrate with a kraft-paper label… Soft morning window light from the left, warm white desk, palette #F4EDE4, #3B2A20 and #7FA37A…"
File nameVariable valueRatioModelPrompt (start)
coldbrew_hold-desk_4x5_v1Bottle standing on the desk4:5Nano Banana 2.1"[lock block] The bottle stands on the desk next to an open laptop…"
coldbrew_hold-hand_9x16_v1A hand pouring from the bottle into a glass of ice9:16Nano Banana 2.1"[lock block] A hand pours from the bottle into a tall glass of ice, both in the middle third of the tall frame…"

Illustrative example written by Meevra to show the format; actual output will differ.

What is inside

The full skill has these sections. The ones marked “in the pack” come with the download.

  • When to use on this page
  • When not to use on this page
  • Inputs to ask for in the pack
  • Workflow in the pack
  • Output format in the pack
  • Example on this page
  • Model notes (Oct 2026) in the pack
  • Troubleshooting in the pack

Get Ad & Social Image Set

The full skill is a SKILL.md folder you install once and reuse: the workflow, the checklist and the answer format written out, with notes for each model. It comes in the Image pack (4 prompts · 4 skills · 1 free), with a QUICKSTART, setup notes in every item and 12 months of updates.

Or check out via Payhip

What is in the pack

All-Access 39 € vs 7 packs × 12 € = 84 € · less than buying 4 or more packs one by one

Stuck? Email support@meevra.com — we'll help you set it up.

See the pack

  • PromptPaid

    FLUX.2 Product Series Consistency

    Plan a 6-12 image FLUX.2 product series that looks like one shoot: reference plan, frozen product sentence, locked style block, shot list and a two-image drift check before you generate the rest.

    Image
    • FLUX
  • PromptPaid

    Image Edit Brief

    Turn a messy list of image changes into ordered one-change edit passes, each with a keep-the-rest prompt, the details most at risk and a check, plus a stop rule before the image degrades.

    Image
    • Nano Banana
    • GPT-Image
    • Midjourney
    • FLUX
  • PromptFree

    Image Style: Editorial Product Photography

    A reusable dark-and-gold style block for premium product shots that keeps light, scale and camera height identical across a whole series.

    Image
    • Midjourney
    • FLUX
    • Nano Banana
    • GPT-Image
  • PromptPaid

    Text-in-Image Layout

    Get posters, thumbnails and social cards whose text actually renders: copy cut to fit, a layout spec, a model-ready prompt, a blank fallback and a proofreading list.

    Image
    • Nano Banana
    • GPT-Image
    • Midjourney
    • FLUX
  • SkillPaid

    GPT-Image Product Shot Set

    Build a five-shot listing set from your real product photos with GPT-Image 2.5, with a fidelity lock and a side-by-side check so the product stays the one buyers receive.

    Image
    • GPT-Image
  • SkillPaid

    Midjourney Style Lock

    Turn a few reference images into a calibrated Midjourney V8.2 style card: one suffix, one style sentence and a drift check the whole team reuses.

    Image
    • Midjourney