Social media ad

The general-purpose feed ad: a rendered image with a headline, a supporting line and a call to action composited on top. It is the catch-all the app reaches for when the brief is simply "make me an ad".

When to use it

The right starting point for almost any static test. When you do not yet know whether your audience responds to proof, price or a promise, this is the format flexible enough to carry any of them.

The thing to get right

All three lines of copy are composited by the app after the picture is rendered, so they come out pixel-exact. Model-painted headlines warp letters and invent words, which is why no format here asks the image model to spell.

The format at a glance

• Output — a still image ad.
• Structure — a single frame, with the copy composited on top.
• Family — Image ads.
• Recipe id — social_ad, which is what you name when you ask for it by hand or from an agent.

Who writes the headline?

You do, and the app typesets it after the picture is rendered. All three lines come out pixel-exact, which is why no format in this catalog asks the image model to spell: model-painted headlines warp letters and invent words that were never in the brief.

Related formats

Static, direct-response creative for the feed: the headline, the offer, the proof, the comparison. Every word on these is composited by the app after the picture is rendered, so the copy comes out exactly as written.

• Bold graphic poster — a striking typographic poster / bold graphic ad
• Customer story — a narrative before→after customer journey ad — a real person's transformation told with their photo + a short story
• Infographic — a static infographic / data-driven visual
• Press clipping screenshot — a real-looking press/article clipping or headline screenshot framed as the ad hero
• Before / after — a before-and-after transformation visual
• Social proof wall — a logos + big-numbers social-proof ad — a wall of trust signals (counts, ratings, outlet/partner logos)

The full catalog is on the creative recipes index.

Models that render it

This format is rendered by an image model, with the copy composited on top afterwards. Nano Banana Pro is the default pick. The image models page compares the rest, including Nano Banana 2, GPT Image and FLUX1.1 Pro.

Hermoso plans and renders a social media ad from your brand rather than from a prompt you write, composites every on-screen word after the render so the copy comes out exact, and exposes the same format to an AI agent over MCP. How Hermoso renders a format covers all three.