Swap only the main subject + always run face swap (fixes the mess)

fix: full-identity swap — stop pasting target eyes back over every swap

fix: sharp output, source skin tone preservation, 4K upscaling pipeline

feat: restore glasses/eye region from target after swap, preserve spectacles cleanly

feat: sharpen face region + bilateral skin smoothing after InsightFace swap

fix: add explicit cv2.data import, add onnxruntime to CI deps

feat: auto-detect GPU/CPU for InsightFace and PyTorch (RTX 4060 locally, CPU on HF)

fix: correct retry logic for background model downloads, fix pyrightconfig extraPaths

fix: use relative import in swapper, add pyrightconfig for IDE

fix: deduplicate InsightFace instance, add load-once sentinel to prevent retry loops

fix: use popup auth (redirect needs Firebase Hosting), fix BGR/RGB bug in InsightFace calls

fix: pre-download buffalo_l at startup, log swapper errors

Initial commit: DeepFace Studio - AI face swap web application