Next (#107)

* Allow passing the onnxruntime to install.py

* Fix CI

* Disallow none execution providers in the UI

* Use CV2 to detect fps

* Respect trim on videos with audio

* Respect trim on videos with audio (finally)

* Implement caching to speed up preview and webcam

* Define webcam UI and webcam performance

* Remove layout from components

* Add primary buttons

* Extract benchmark and webcam settings

* Introduce compact UI settings

* Caching for IO and **** prediction

* Caching for IO and **** prediction

* Introduce face analyser caching

* Fix some typing

* Improve setup for benchmark

* Clear image cache via post process

* Fix settings in UI, Simplify restore_audio() using shortest

* Select resolution and fps via webcam ui

* Introduce read_static_image() to stop caching temp images

* Use DirectShow under Windows

* Multi-threading for webcam

* Fix typing

* Refactor frame processor

* Refactor webcam processing

* Avoid warnings due capture.isOpened()

* Resume downloads (#110)

* Introduce resumable downloads

* Fix CURL commands

* Break execution_settings into pieces

* Cosmetic changes on cv2 webcam

* Update Gradio

* Move face cache to own file

* Uniform namings for threading

* Fix sorting of get_temp_frame_paths(), extend get_temp_frames_pattern()

* Minor changes from the review

* Looks stable to tme

* Update the disclaimer

* Update the disclaimer

* Update the disclaimer

facefusion/uis/typing.py

@@ -14,8 +14,13 @@ ComponentName = Literal\
 	'face_analyser_direction_dropdown',
 	'face_analyser_age_dropdown',
 	'face_analyser_gender_dropdown',
-	'frame_processors_checkbox_group'
+	'frame_processors_checkbox_group',
+	'benchmark_runs_checkbox_group',
+	'benchmark_cycles_slider',
+	'webcam_mode_radio',
+	'webcam_resolution_dropdown',
+	'webcam_fps_slider'
 ]
 WebcamMode = Literal[ 'inline', 'stream_udp', 'stream_v4l2' ]
-StreamMode = Literal['udp', 'v4l2']
+StreamMode = Literal[ 'udp', 'v4l2' ]
 Update = Dict[Any, Any]