Releases: C0untFloyd/roop-unleashed
v4.3.1
v4.2.8
Bugfix: Starting roop-unleashed without NVIDIA gpu but cuda option enabled
Bugfix: Target Faces couldn't be moved left/right
Bugfix: Enhancement and upscaling working again in virtual cam
Corrupt videos caught when adding to target files, displaying warning msg
Source Files Component cleared after face detection to release temp files
Added masking and mouth restore options to virtual cam
v4.2.3
Hotfix for gradio pydantic issue with fastapi
Upgraded to Gradio 4.43 hoping it will fix remaining issues
Added new action when no face detected -> use last swapped
Specified image format for image controls - opening new tabs on preview images possible again!
Hardcoded image output format for livecam to jpeg - might be faster than previous webp
Chain events to be only executed if previous was a success
v4.2.0
Added ability to move input & target faces order
New CLI Arguments override settings
Small UI changes to faceswapping tab
Added mask option and code for restoration of original mouth area
Updated gradio to v4.42.0
Added CLI Arguments --server_share and --cuda_device_id
Added webp image support
v4.1.1
Bugfix: Post-processing after swapping
v4.1.0
- Added much desired subsample upscaling up to 512 pixels, known from Rope and Face Fusion
- Upgraded to latest Gradio
v4.0.0
Bugfix: Unnecessary init every frame in live-cam
Bugfix: Installer downloading insightface package each run
Added xseg masking to live-cam
Added realesrganx2 to frame processors
Upgraded some requirements
Added subtypes and different model support to frame processors
Allow frame processors to change resolutions of videos
Different OpenCV Cap for MacOS Virtual Cam
Added complete frame processing to extras tab
Colorize, upscale and misc filters added
Added new models to the assets from v3.9.0
https://github.com/C0untFloyd/roop-unleashed/releases/tag/v3.9.0
v3.9.0
Bugfix: Face detection bounding box corrupt values at weird angles
Rewrote mask previewing to work with every model
Switching mask engines toggles text interactivity
Clearing target files, resets face selection dropdown
Massive rewrite of swapping architecture, needed for xseg implementation
Added DFL Xseg Support for partial face occlusion
Face masking only runs when there is a face detected
Removed unnecessary toggle checkbox for text masking
Added ability to do multiple swap passes
v3.6.7
Upgraded to Gradio 4.26.0 - fixed some minor UI Bugs like collapsing masking
Windows installer installs from pre-compiled insightface, no need for Visual Studio anymore
Facesets can be created from video frames
v3.6.6 - all hail to the easter bunny
Upgraded to gradio 1.24.0 which might have lesser browser bugs but may introduce some funky new ones
Added UTF-8 image reading support