Why we're different

One sharp differentiator stated plainly: what sets this brand apart from the way things were done before.

When to use it

Positioning campaigns and crowded categories. It is a good test of whether you actually have a differentiator, because the format gives you nowhere to hide.

The thing to get right

One difference, not three. A list of differentiators is a benefits grid; this format only works when a single claim carries the whole ad.

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: why_different, which is what you name when you ask for it by hand or from an agent.

Can I list three differentiators?

Then you have built a benefits grid. This format only works when a single claim carries the whole ad, and choosing which claim that is happens to be the useful exercise. Run the others as separate ads and let the results decide.

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.

• Social proof wall: a logos and big-numbers social-proof ad, a wall of trust signals (counts, ratings, outlet and partner logos)
• Product spotlight: a dramatic, premium single-product spotlight with the hero lit in a pool of light against dark
• Press clipping screenshot: a real-looking press/article clipping or headline screenshot framed as the ad hero
• Highlighted-text hook: a bold sentence with the key phrase highlighted in marker style, so the hook IS the design
• Customer story: a narrative before-and-after customer journey ad, a real person's transformation told with their photo and a short story
• Unexpected twist: a setup and subverted-expectation twist, where the headline flips what you assumed, paired with a reveal

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. GPT Image 2.5 is the default pick. The image models page compares the rest, including FLUX.2 [pro], Ideogram V4 and Qwen-Image.

Hermoso plans and renders a why we're different 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.