Specialised, not general
Purpose-built for live de-aging — an open lane the broad AR-filter SDKs don't lead on.
Vercila is the neural core behind FaceReady: it eases the signs of age on a live face, frame by frame, entirely on the user's own device — on Windows and macOS. We license it as an embeddable SDK, with a native C-ABI and no cloud step in the pipeline.
Most face-effects SDKs are built for mobile AR decoration — masks, makeup try-on, novelty filters. Vercila is built for a narrower, harder job: making a real person look rested and naturally younger on a live feed, without turning them into someone else.
Purpose-built for live de-aging — an open lane the broad AR-filter SDKs don't lead on.
Ships on Windows and macOS today, where the mobile-led competitors are weakest or absent.
Inference runs locally. There's no cloud processing step anywhere in the pipeline.
A residual approach keeps the subject's real skin and features — none of the plastic look of full-face regeneration.
A native C-ABI drops the engine into a host app or a virtual-camera pipeline, with no managed-runtime dependency.
Vercila already ships in a paid consumer product. The SDK is that proven engine, not a lab demo.
Vercila takes a video frame containing a face and returns the same frame with the signs of age eased back — under-eye shadow, the lines a lens over-sharpens, the flatness that reads as tired — while leaving features, expression and real skin texture intact. It computes a small correction and applies only that, so the result tracks motion exactly, because it is the original frame minus the camera's harshness.
De-age is the lead capability. The same engine exposes relight and warmth as independent parameters — use de-age alone, or combine them in one pass over the frame.
Because inference runs on the user's machine, there's no server in the loop: nothing is uploaded, nothing is transmitted, nothing is retained. For any vendor shipping a face-processing capability into regulated, enterprise or privacy-sensitive environments, that removes a whole category of data-handling and compliance exposure. Even the broad face-AR leaders run their core engines on-device; "cloud," where it shows up in this market, is effect delivery, not processing. Vercila has no cloud-inference path by design.
Get the technical overview, or start an evaluation — an engine build for Windows and macOS, C-ABI integration docs, and a direct technical contact.