Backlog
Features
Introduce face animation for static images
Add bounding box and face landmark smoothing
Generated steps for a job by detecting scenes
Feature manipulation using
interfacegan
orstyleganx
Replace
wave2lip
with a high quality lip-syncer modelAdd
FaRL
andBiSeNet
face parser modelsIntroduce remote webcam via real-time streaming protocol
Expose benchmark and webcam settings to the CLI
Detect webcam devices via
ffmpeg
to make them selectableSave and load face embedding collection files
Audio processor to mix the volume of the audio sources
Support for DeepFaceLab models
Detect the optimal configuration using the benchmark suite
Replace
gender_age
with the high accuracymivolo
modelSupport for 180 and 360 degree videos
Multi inference pool to support multiple devices
Add
GIF
support
Bugs
Fix
retinaface
not being able to detect cropped face
Last updated