uxgen_packshot

ai.uxgen/ecommerce-conversion · Verify this server

COMPOSES THE CLIENT'S PRODUCT ONTO A REAL PHOTOGRAPH. It takes a studio photograph of a container with a BLANK WHITE label, detects the edges of that label at pixel level, and inlays the brand's label with a `multiply` blend: the drop shadow and the curve of the cylinder pass through the artwork, so the jar stays believable. THE FONT IS MANDATORY AND IT IS THE SITE'S FONT. No fallback — with no font, no brand or no ink, the tool REFUSES rather than printing something generic. 🚨 IT TAKES TWO CALLS. First call without `zone`: it detects, writes the proof image (magenta rectangle) and REFUSES, handing you the four numbers. You OPEN the proof. Second call with `zone`: it composes. Detection on its own mistakes a label for a blank screen or a tablecloth — composing without looking means printing the brand onto a scrap of tablecloth. 🚨 The label lives INSIDE the image, never on top of it: an HTML text overlay laid over the photo to fake a label is a named gap (V3, uxgen_audit).