Green-screen reaction

The creator is composited over a full-bleed on-screen element — a review, an article, a competitor page, a product screenshot — which they point at and react to.

When to use it

The fastest way to make a claim someone else made into your ad. Ideal for press mentions, five-star reviews, a viral comment, or a competitor's own pricing page.

The thing to get right

The thing behind the creator has to be legible on a phone at speed. If a viewer has to squint at the screenshot, the format has spent its hook on something they never read.

The format at a glance

• Output — a video ad.
• Structure — 4 beats, each one a separately planned shot.
• Family — Creator & UGC video.
• Recipe id — green_screen, which is what you name when you ask for it by hand or from an agent.

What can go behind the creator?

A review, an article, a competitor page, a product screenshot. The constraint is legibility on a phone at speed, so crop to the sentence that matters rather than compositing a whole page the viewer will never read.

Related formats

Formats built around a person on camera — the talking-head, the unboxing, the try-on, the demo. These are the highest-volume paid-social formats on TikTok, Reels and Shorts, and the ones where realism matters more than polish.

• UGC talking-head — a real creator reviewing/recommending the product straight to camera (TikTok/Reels)
• Transformation — a before→after video transformation — space, skin, hair or outfit — with the reveal as the payoff beat
• UGC unboxing — a creator excitedly opening/unpacking the product
• Podcast clip — a viral podcast-clip ad — two people at a mic'd table mid-conversation, one telling the product story as an authentic sit-down excerpt, captions-forward
• UGC tutorial / demo — a creator demonstrating how the product works, step by step
• Product review — an authentic, balanced to-camera review of the product — honest reviewer energy, not a hard pitch

The full catalog is on the creative recipes index.

Models that render it

This format is rendered by a video model. The plan picks one unless you name it, and Seedance 2.5 is the default pick. You can ask for another by name, such as Gemini Omni 1.1, Gemini Omni or Veo 3.1. All three render native sound, so a voice comes out of the same take as the picture. The video models page compares every option.

Hermoso plans and renders a green-screen reaction 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.