New
3.4.0
- Introduce single pass frame processing
- Process inference on multiple execution devices
- Add side by side preview modes along with preview resolutions
- Introduce
--expression-restorer-areasargument - Revamp webcam experience and performance
- Reintroduce the
yunetface detector - Add
--voice-extractor-modelargument - Migrate ArcFace converter to CrossFace models
- Balance source and target using the
--face-swapper-weightargument - Introduce
--benchmark-modeto select between warm and cold caches - Introduce many for the
--face-occluder-modelargument - Replace output resolution with relative output scale
- Add
libx264rgbto avoid color shifts due to RGB to YUV conversion - Add support for the
wmvvideo format - Experimental support for
MIGraphXexecution provider - Log model information in debug mode
- Remove
--execution-queue-countargument - Remove score and classifier items from the face debugger
- Fix crash on headless-run when passing invalid output path
- Fix demographic filters for mutated faces