Generating images of a specific garment or product being worn by a model without a physical photoshoot. Used in fashion e-commerce to show items on-body across looks, scenes and variants.
Virtual try-on takes a product reference — typically a flat-lay or packshot of the garment — and generates images of a persona wearing it, preserving the item's cut, color and key details while the model, pose and scene are synthetic. It is a specialized relative of image-to-image generation: the garment anchors, the generation dresses.
The e-commerce case is straightforward economics: on-body imagery converts better than flat-lays, but a traditional on-model shoot has to be booked, shot and retouched per season and per variant. Generated try-on imagery refreshes a catalog — new colorways, new scenes, seasonal restyling — without another shoot. The fashion e-commerce use case shows the workflow around a consistent brand persona.
Honest limits: generated try-on is illustrative styling, not a fit or sizing tool — it shows how a garment looks in context, not how size M drapes on a specific body. Fine details are the failure mode to review for: intricate patterns, small logos and text on fabric can render approximately, so check hero shots at full size before publishing.
Related terms
Generating a new image using an existing image as input alongside a text prompt. The input image anchors composition, pose or subject while the prompt steers what changes.
A UGC ad format in which the persona holds, uses or presents the product on camera. The framing pairs a human face with visible proof of use — a staple of social product advertising.