Next (#384)

* feat/yoloface (#334) * added yolov8 to face_detector (#323) * added yolov8 to face_detector * added yolov8 to face_detector * Initial cleanup and renaming * Update README * refactored detect_with_yoloface (#329) * refactored detect_with_yoloface * apply review * Change order again * Restore working code * modified code (#330) * refactored detect_with_yoloface * apply review * use temp_frame in detect_with_yoloface * reorder * modified * reorder models * Tiny cleanup --------- Co-authored-by: tamoharu <133945583+tamoharu@users.noreply.github.com> * include audio file functions (#336) * Add testing for audio handlers * Change order * Fix naming * Use correct typing in choices * Update help message for arguments, Notation based wording approach (#347) * Update help message for arguments, Notation based wording approach * Fix installer * Audio functions (#345) * Update ffmpeg.py * Create audio.py * Update ffmpeg.py * Update audio.py * Update audio.py * Update typing.py * Update ffmpeg.py * Update audio.py * Rename Frame to VisionFrame (#346) * Minor tidy up * Introduce audio testing * Add more todo for testing * Add more todo for testing * Fix indent * Enable venv on the fly * Enable venv on the fly * Revert venv on the fly * Revert venv on the fly * Force Gradio to shut up * Force Gradio to shut up * Clear temp before processing * Reduce terminal output * include audio file functions * Enforce output resolution on merge video * Minor cleanups * Add age and gender to face debugger items (#353) * Add age and gender to face debugger items * Rename like suggested in the code review * Fix the output framerate vs. time * Lip Sync (#356) * Cli implementation of wav2lip * - create get_first_item() - remove non gan wav2lip model - implement video memory strategy - implement get_reference_frame() - implement process_image() - rearrange crop_mask_list - implement test_cli * Simplify testing * Rename to lip syncer * Fix testing * Fix testing * Minor cleanup * Cuda 12 installer (#362) * Make cuda nightly (12) the default * Better keep legacy cuda just in case * Use CUDA and ROCM versions * Remove MacOS options from installer (CoreML include in default package) * Add lip-syncer support to source component * Add lip-syncer support to source component * Fix the check in the source component * Add target image check * Introduce more helpers to suite the lip-syncer needs * Downgrade onnxruntime as of buggy 1.17.0 release * Revert "Downgrade onnxruntime as of buggy 1.17.0 release" This reverts commit f4a7ae6824fed87f0be50906bbc7e2d61d00617b. * More testing and add todos * Fix the frame processor API to at least not throw errors * Introduce dict based frame processor inputs (#364) * Introduce dict based frame processor inputs * Forgot to adjust webcam * create path payloads (#365) * create index payload to paths for process_frames * rename to payload_paths * This code now is poetry * Fix the terminal output * Make lip-syncer work in the preview * Remove face debugger test for now * Reoder reference_faces, Fix testing * Use inswapper_128 on buggy onnxruntime 1.17.0 * Undo inswapper_128_fp16 duo broken onnxruntime 1.17.0 * Undo inswapper_128_fp16 duo broken onnxruntime 1.17.0 * Fix lip_syncer occluder & region mask issue * Fix preview once in case there was no output video fps * fix lip_syncer custom fps * remove unused import * Add 68 landmark functions (#367) * Add 68 landmark model * Add landmark to face object * Re-arrange and modify typing * Rename function * Rearrange * Rearrange * ignore type * ignore type * change type * ignore * name * Some cleanup * Some cleanup * Opps, I broke something * Feat/face analyser refactoring (#369) * Restructure face analyser and start TDD * YoloFace and Yunet testing are passing * Remove offset from yoloface detection * Cleanup code * Tiny fix * Fix get_many_faces() * Tiny fix (again) * Use 320x320 fallback for retinaface * Fix merging mashup * Upload wave2lip model * Upload 2dfan2 model and rename internal to face_predictor * Downgrade onnxruntime for most cases * Update for the face debugger to render landmark 68 * Try to make detect_face_landmark_68() and detect_gender_age() more uniform * Enable retinaface testing for 320x320 * Make detect_face_landmark_68() and detect_gender_age() as uniform as … (#370) * Make detect_face_landmark_68() and detect_gender_age() as uniform as possible * Revert landmark scale and translation * Make box-mask for lip-syncer adjustable * Add create_bbox_from_landmark() * Remove currently unused code * Feat/uniface (#375) * add uniface (#373) * Finalize UniFace implementation --------- Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com> * My approach how todo it * edit * edit * replace vertical blur with gaussian * remove region mask * Rebase against next and restore method * Minor improvements * Minor improvements * rename & add forehead padding * Adjust and host uniface model * Use 2dfan4 model * Rename to face landmarker * Feat/replace bbox with bounding box (#380) * Add landmark 68 to 5 convertion * Add landmark 68 to 5 convertion * Keep 5, 5/68 and 68 landmarks * Replace kps with landmark * Replace bbox with bounding box * Reshape face_landmark5_list different * Make yoloface the default * Move convert_face_landmark_68_to_5 to face_helper * Minor spacing issue * Dynamic detector sizes according to model (#382) * Dynamic detector sizes according to model * Dynamic detector sizes according to model * Undo false commited files * Add lib syncer model to the UI * fix halo (#383) * Bump to 2.3.0 * Update README and wording * Update README and wording * Fix spacing * Apply _vision suffix * Apply _vision suffix * Apply _vision suffix * Apply _vision suffix * Apply _vision suffix * Apply _vision suffix * Apply _vision suffix, Move mouth mask to face_masker.py * Apply _vision suffix * Apply _vision suffix * increase forehead padding --------- Co-authored-by: tamoharu <133945583+tamoharu@users.noreply.github.com> Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
2024-02-14 14:08:29 +01:00
parent 122da0545b
commit c77493ff9a
66 changed files with 1893 additions and 884 deletions
--- a/facefusion/uis/components/about.py
+++ b/facefusion/uis/components/about.py
@@ -17,7 +17,7 @@ def render() -> None:
 		link = metadata.get('url')
 	)
 	DONATE_BUTTON = gradio.Button(
-		value = wording.get('donate_button_label'),
+		value = wording.get('uis.donate_button'),
 		link = 'https://donate.facefusion.io',
 		size = 'sm'
 	)
--- a/facefusion/uis/components/benchmark.py
+++ b/facefusion/uis/components/benchmark.py
@@ -36,7 +36,7 @@ def render() -> None:
 	global BENCHMARK_CLEAR_BUTTON

 	BENCHMARK_RESULTS_DATAFRAME = gradio.Dataframe(
-		label = wording.get('benchmark_results_dataframe_label'),
+		label = wording.get('uis.benchmark_results_dataframe'),
 		headers =
 		[
 			'target_path',
@@ -57,12 +57,12 @@ def render() -> None:
 		]
 	)
 	BENCHMARK_START_BUTTON = gradio.Button(
-		value = wording.get('start_button_label'),
+		value = wording.get('uis.start_button'),
 		variant = 'primary',
 		size = 'sm'
 	)
 	BENCHMARK_CLEAR_BUTTON = gradio.Button(
-		value = wording.get('clear_button_label'),
+		value = wording.get('uis.clear_button'),
 		size = 'sm'
 	)

--- a/facefusion/uis/components/benchmark_options.py
+++ b/facefusion/uis/components/benchmark_options.py
@@ -14,12 +14,12 @@ def render() -> None:
 	global BENCHMARK_CYCLES_SLIDER

 	BENCHMARK_RUNS_CHECKBOX_GROUP = gradio.CheckboxGroup(
-		label = wording.get('benchmark_runs_checkbox_group_label'),
+		label = wording.get('uis.benchmark_runs_checkbox_group'),
 		value = list(BENCHMARKS.keys()),
 		choices = list(BENCHMARKS.keys())
 	)
 	BENCHMARK_CYCLES_SLIDER = gradio.Slider(
-		label = wording.get('benchmark_cycles_slider_label'),
+		label = wording.get('uis.benchmark_cycles_slider'),
 		value = 5,
 		step = 1,
 		minimum = 1,
--- a/facefusion/uis/components/common_options.py
+++ b/facefusion/uis/components/common_options.py
@@ -19,7 +19,7 @@ def render() -> None:
 	if facefusion.globals.skip_download:
 		value.append('skip-download')
 	COMMON_OPTIONS_CHECKBOX_GROUP = gradio.Checkboxgroup(
-		label = wording.get('common_options_checkbox_group_label'),
+		label = wording.get('uis.common_options_checkbox_group'),
 		choices = uis_choices.common_options,
 		value = value
 	)
--- a/facefusion/uis/components/execution.py
+++ b/facefusion/uis/components/execution.py
@@ -15,7 +15,7 @@ def render() -> None:
 	global EXECUTION_PROVIDERS_CHECKBOX_GROUP

 	EXECUTION_PROVIDERS_CHECKBOX_GROUP = gradio.CheckboxGroup(
-		label = wording.get('execution_providers_checkbox_group_label'),
+		label = wording.get('uis.execution_providers_checkbox_group'),
 		choices = encode_execution_providers(onnxruntime.get_available_providers()),
 		value = encode_execution_providers(facefusion.globals.execution_providers)
 	)
--- a/facefusion/uis/components/execution_queue_count.py
+++ b/facefusion/uis/components/execution_queue_count.py
@@ -12,7 +12,7 @@ def render() -> None:
 	global EXECUTION_QUEUE_COUNT_SLIDER

 	EXECUTION_QUEUE_COUNT_SLIDER = gradio.Slider(
-		label = wording.get('execution_queue_count_slider_label'),
+		label = wording.get('uis.execution_queue_count_slider'),
 		value = facefusion.globals.execution_queue_count,
 		step = facefusion.choices.execution_queue_count_range[1] - facefusion.choices.execution_queue_count_range[0],
 		minimum = facefusion.choices.execution_queue_count_range[0],
--- a/facefusion/uis/components/execution_thread_count.py
+++ b/facefusion/uis/components/execution_thread_count.py
@@ -12,7 +12,7 @@ def render() -> None:
 	global EXECUTION_THREAD_COUNT_SLIDER

 	EXECUTION_THREAD_COUNT_SLIDER = gradio.Slider(
-		label = wording.get('execution_thread_count_slider_label'),
+		label = wording.get('uis.execution_thread_count_slider'),
 		value = facefusion.globals.execution_thread_count,
 		step = facefusion.choices.execution_thread_count_range[1] - facefusion.choices.execution_thread_count_range[0],
 		minimum = facefusion.choices.execution_thread_count_range[0],
--- a/facefusion/uis/components/face_analyser.py
+++ b/facefusion/uis/components/face_analyser.py
@@ -1,4 +1,4 @@
-from typing import Optional
+from typing import Optional, Dict, Any

 import gradio

@@ -24,34 +24,37 @@ def render() -> None:
 	global FACE_DETECTOR_SCORE_SLIDER
 	global FACE_DETECTOR_MODEL_DROPDOWN

+	face_detector_size_dropdown_args : Dict[str, Any] =\
+	{
+		'label': wording.get('uis.face_detector_size_dropdown'),
+		'value': facefusion.globals.face_detector_size
+	}
+	if facefusion.globals.face_detector_size in facefusion.choices.face_detector_set[facefusion.globals.face_detector_model]:
+		face_detector_size_dropdown_args['choices'] = facefusion.choices.face_detector_set[facefusion.globals.face_detector_model]
 	with gradio.Row():
 		FACE_ANALYSER_ORDER_DROPDOWN = gradio.Dropdown(
-			label = wording.get('face_analyser_order_dropdown_label'),
+			label = wording.get('uis.face_analyser_order_dropdown'),
 			choices = facefusion.choices.face_analyser_orders,
 			value = facefusion.globals.face_analyser_order
 		)
 		FACE_ANALYSER_AGE_DROPDOWN = gradio.Dropdown(
-			label = wording.get('face_analyser_age_dropdown_label'),
+			label = wording.get('uis.face_analyser_age_dropdown'),
 			choices = [ 'none' ] + facefusion.choices.face_analyser_ages,
 			value = facefusion.globals.face_analyser_age or 'none'
 		)
 		FACE_ANALYSER_GENDER_DROPDOWN = gradio.Dropdown(
-			label = wording.get('face_analyser_gender_dropdown_label'),
+			label = wording.get('uis.face_analyser_gender_dropdown'),
 			choices = [ 'none' ] + facefusion.choices.face_analyser_genders,
 			value = facefusion.globals.face_analyser_gender or 'none'
 		)
 	FACE_DETECTOR_MODEL_DROPDOWN = gradio.Dropdown(
-		label = wording.get('face_detector_model_dropdown_label'),
-		choices = facefusion.choices.face_detector_models,
+		label = wording.get('uis.face_detector_model_dropdown'),
+		choices = facefusion.choices.face_detector_set.keys(),
 		value = facefusion.globals.face_detector_model
 	)
-	FACE_DETECTOR_SIZE_DROPDOWN = gradio.Dropdown(
-		label = wording.get('face_detector_size_dropdown_label'),
-		choices = facefusion.choices.face_detector_sizes,
-		value = facefusion.globals.face_detector_size
-	)
+	FACE_DETECTOR_SIZE_DROPDOWN = gradio.Dropdown(**face_detector_size_dropdown_args)
 	FACE_DETECTOR_SCORE_SLIDER = gradio.Slider(
-		label = wording.get('face_detector_score_slider_label'),
+		label = wording.get('uis.face_detector_score_slider'),
 		value = facefusion.globals.face_detector_score,
 		step = facefusion.choices.face_detector_score_range[1] - facefusion.choices.face_detector_score_range[0],
 		minimum = facefusion.choices.face_detector_score_range[0],
@@ -69,7 +72,7 @@ def listen() -> None:
 	FACE_ANALYSER_ORDER_DROPDOWN.change(update_face_analyser_order, inputs = FACE_ANALYSER_ORDER_DROPDOWN)
 	FACE_ANALYSER_AGE_DROPDOWN.change(update_face_analyser_age, inputs = FACE_ANALYSER_AGE_DROPDOWN)
 	FACE_ANALYSER_GENDER_DROPDOWN.change(update_face_analyser_gender, inputs = FACE_ANALYSER_GENDER_DROPDOWN)
-	FACE_DETECTOR_MODEL_DROPDOWN.change(update_face_detector_model, inputs = FACE_DETECTOR_MODEL_DROPDOWN)
+	FACE_DETECTOR_MODEL_DROPDOWN.change(update_face_detector_model, inputs = FACE_DETECTOR_MODEL_DROPDOWN, outputs = FACE_DETECTOR_SIZE_DROPDOWN)
 	FACE_DETECTOR_SIZE_DROPDOWN.change(update_face_detector_size, inputs = FACE_DETECTOR_SIZE_DROPDOWN)
 	FACE_DETECTOR_SCORE_SLIDER.change(update_face_detector_score, inputs = FACE_DETECTOR_SCORE_SLIDER)

@@ -86,8 +89,11 @@ def update_face_analyser_gender(face_analyser_gender : FaceAnalyserGender) -> No
 	facefusion.globals.face_analyser_gender = face_analyser_gender if face_analyser_gender != 'none' else None


-def update_face_detector_model(face_detector_model : FaceDetectorModel) -> None:
+def update_face_detector_model(face_detector_model : FaceDetectorModel) -> gradio.Dropdown:
 	facefusion.globals.face_detector_model = face_detector_model
+	if facefusion.globals.face_detector_size in facefusion.choices.face_detector_set[face_detector_model]:
+		return gradio.Dropdown(value = '640x640', choices = facefusion.choices.face_detector_set[face_detector_model])
+	return gradio.Dropdown(value = '640x640', choices = [ '640x640' ])


 def update_face_detector_size(face_detector_size : str) -> None:
--- a/facefusion/uis/components/face_masker.py
+++ b/facefusion/uis/components/face_masker.py
@@ -32,13 +32,13 @@ def render() -> None:
 	has_box_mask = 'box' in facefusion.globals.face_mask_types
 	has_region_mask = 'region' in facefusion.globals.face_mask_types
 	FACE_MASK_TYPES_CHECKBOX_GROUP = gradio.CheckboxGroup(
-		label = wording.get('face_mask_types_checkbox_group_label'),
+		label = wording.get('uis.face_mask_types_checkbox_group'),
 		choices = facefusion.choices.face_mask_types,
 		value = facefusion.globals.face_mask_types
 	)
 	with gradio.Group(visible = has_box_mask) as FACE_MASK_BOX_GROUP:
 		FACE_MASK_BLUR_SLIDER = gradio.Slider(
-			label = wording.get('face_mask_blur_slider_label'),
+			label = wording.get('uis.face_mask_blur_slider'),
 			step = facefusion.choices.face_mask_blur_range[1] - facefusion.choices.face_mask_blur_range[0],
 			minimum = facefusion.choices.face_mask_blur_range[0],
 			maximum = facefusion.choices.face_mask_blur_range[-1],
@@ -46,14 +46,14 @@ def render() -> None:
 		)
 		with gradio.Row():
 			FACE_MASK_PADDING_TOP_SLIDER = gradio.Slider(
-				label = wording.get('face_mask_padding_top_slider_label'),
+				label = wording.get('uis.face_mask_padding_top_slider'),
 				step = facefusion.choices.face_mask_padding_range[1] - facefusion.choices.face_mask_padding_range[0],
 				minimum = facefusion.choices.face_mask_padding_range[0],
 				maximum = facefusion.choices.face_mask_padding_range[-1],
 				value = facefusion.globals.face_mask_padding[0]
 			)
 			FACE_MASK_PADDING_RIGHT_SLIDER = gradio.Slider(
-				label = wording.get('face_mask_padding_right_slider_label'),
+				label = wording.get('uis.face_mask_padding_right_slider'),
 				step = facefusion.choices.face_mask_padding_range[1] - facefusion.choices.face_mask_padding_range[0],
 				minimum = facefusion.choices.face_mask_padding_range[0],
 				maximum = facefusion.choices.face_mask_padding_range[-1],
@@ -61,14 +61,14 @@ def render() -> None:
 			)
 		with gradio.Row():
 			FACE_MASK_PADDING_BOTTOM_SLIDER = gradio.Slider(
-				label = wording.get('face_mask_padding_bottom_slider_label'),
+				label = wording.get('uis.face_mask_padding_bottom_slider'),
 				step = facefusion.choices.face_mask_padding_range[1] - facefusion.choices.face_mask_padding_range[0],
 				minimum = facefusion.choices.face_mask_padding_range[0],
 				maximum = facefusion.choices.face_mask_padding_range[-1],
 				value = facefusion.globals.face_mask_padding[2]
 			)
 			FACE_MASK_PADDING_LEFT_SLIDER = gradio.Slider(
-				label = wording.get('face_mask_padding_left_slider_label'),
+				label = wording.get('uis.face_mask_padding_left_slider'),
 				step = facefusion.choices.face_mask_padding_range[1] - facefusion.choices.face_mask_padding_range[0],
 				minimum = facefusion.choices.face_mask_padding_range[0],
 				maximum = facefusion.choices.face_mask_padding_range[-1],
@@ -76,7 +76,7 @@ def render() -> None:
 			)
 	with gradio.Row():
 		FACE_MASK_REGION_CHECKBOX_GROUP = gradio.CheckboxGroup(
-			label = wording.get('face_mask_region_checkbox_group_label'),
+			label = wording.get('uis.face_mask_region_checkbox_group'),
 			choices = facefusion.choices.face_mask_regions,
 			value = facefusion.globals.face_mask_regions,
 			visible = has_region_mask
--- a/facefusion/uis/components/face_selector.py
+++ b/facefusion/uis/components/face_selector.py
@@ -9,7 +9,7 @@ from facefusion.face_store import clear_static_faces, clear_reference_faces
 from facefusion.vision import get_video_frame, read_static_image, normalize_frame_color
 from facefusion.filesystem import is_image, is_video
 from facefusion.face_analyser import get_many_faces
-from facefusion.typing import Frame, FaceSelectorMode
+from facefusion.typing import VisionFrame, FaceSelectorMode
 from facefusion.uis.core import get_ui_component, register_ui_component
 from facefusion.uis.typing import ComponentName

@@ -25,7 +25,7 @@ def render() -> None:

 	reference_face_gallery_args: Dict[str, Any] =\
 	{
-		'label': wording.get('reference_face_gallery_label'),
+		'label': wording.get('uis.reference_face_gallery'),
 		'object_fit': 'cover',
 		'columns': 8,
 		'allow_preview': False,
@@ -38,13 +38,13 @@ def render() -> None:
 		reference_frame = get_video_frame(facefusion.globals.target_path, facefusion.globals.reference_frame_number)
 		reference_face_gallery_args['value'] = extract_gallery_frames(reference_frame)
 	FACE_SELECTOR_MODE_DROPDOWN = gradio.Dropdown(
-		label = wording.get('face_selector_mode_dropdown_label'),
+		label = wording.get('uis.face_selector_mode_dropdown'),
 		choices = facefusion.choices.face_selector_modes,
 		value = facefusion.globals.face_selector_mode
 	)
 	REFERENCE_FACE_POSITION_GALLERY = gradio.Gallery(**reference_face_gallery_args)
 	REFERENCE_FACE_DISTANCE_SLIDER = gradio.Slider(
-		label = wording.get('reference_face_distance_slider_label'),
+		label = wording.get('uis.reference_face_distance_slider'),
 		value = facefusion.globals.reference_face_distance,
 		step = facefusion.choices.reference_face_distance_range[1] - facefusion.choices.reference_face_distance_range[0],
 		minimum = facefusion.choices.reference_face_distance_range[0],
@@ -135,30 +135,31 @@ def clear_and_update_reference_position_gallery() -> gradio.Gallery:


 def update_reference_position_gallery() -> gradio.Gallery:
-	gallery_frames = []
+	gallery_vision_frames = []
 	if is_image(facefusion.globals.target_path):
-		reference_frame = read_static_image(facefusion.globals.target_path)
-		gallery_frames = extract_gallery_frames(reference_frame)
+		temp_vision_frame = read_static_image(facefusion.globals.target_path)
+		gallery_vision_frames = extract_gallery_frames(temp_vision_frame)
 	if is_video(facefusion.globals.target_path):
-		reference_frame = get_video_frame(facefusion.globals.target_path, facefusion.globals.reference_frame_number)
-		gallery_frames = extract_gallery_frames(reference_frame)
-	if gallery_frames:
-		return gradio.Gallery(value = gallery_frames)
+		temp_vision_frame = get_video_frame(facefusion.globals.target_path, facefusion.globals.reference_frame_number)
+		gallery_vision_frames = extract_gallery_frames(temp_vision_frame)
+	if gallery_vision_frames:
+		return gradio.Gallery(value = gallery_vision_frames)
 	return gradio.Gallery(value = None)


-def extract_gallery_frames(reference_frame : Frame) -> List[Frame]:
-	crop_frames = []
-	faces = get_many_faces(reference_frame)
+def extract_gallery_frames(temp_vision_frame : VisionFrame) -> List[VisionFrame]:
+	gallery_vision_frames = []
+	faces = get_many_faces(temp_vision_frame)
+
 	for face in faces:
-		start_x, start_y, end_x, end_y = map(int, face.bbox)
+		start_x, start_y, end_x, end_y = map(int, face.bounding_box)
 		padding_x = int((end_x - start_x) * 0.25)
 		padding_y = int((end_y - start_y) * 0.25)
 		start_x = max(0, start_x - padding_x)
 		start_y = max(0, start_y - padding_y)
 		end_x = max(0, end_x + padding_x)
 		end_y = max(0, end_y + padding_y)
-		crop_frame = reference_frame[start_y:end_y, start_x:end_x]
-		crop_frame = normalize_frame_color(crop_frame)
-		crop_frames.append(crop_frame)
-	return crop_frames
+		crop_vision_frame = temp_vision_frame[start_y:end_y, start_x:end_x]
+		crop_vision_frame = normalize_frame_color(crop_vision_frame)
+		gallery_vision_frames.append(crop_vision_frame)
+	return gallery_vision_frames
--- a/facefusion/uis/components/frame_processors.py
+++ b/facefusion/uis/components/frame_processors.py
@@ -14,7 +14,7 @@ def render() -> None:
 	global FRAME_PROCESSORS_CHECKBOX_GROUP

 	FRAME_PROCESSORS_CHECKBOX_GROUP = gradio.CheckboxGroup(
-		label = wording.get('frame_processors_checkbox_group_label'),
+		label = wording.get('uis.frame_processors_checkbox_group'),
 		choices = sort_frame_processors(facefusion.globals.frame_processors),
 		value = facefusion.globals.frame_processors
 	)
--- a/facefusion/uis/components/frame_processors_options.py
+++ b/facefusion/uis/components/frame_processors_options.py
@@ -5,84 +5,120 @@ import facefusion.globals
 from facefusion import wording
 from facefusion.processors.frame.core import load_frame_processor_module
 from facefusion.processors.frame import globals as frame_processors_globals, choices as frame_processors_choices
-from facefusion.processors.frame.typings import FaceSwapperModel, FaceEnhancerModel, FrameEnhancerModel, FaceDebuggerItem
+from facefusion.processors.frame.typings import FaceDebuggerItem, FaceEnhancerModel, FaceSwapperModel, FrameEnhancerModel, LipSyncerModel
 from facefusion.uis.core import get_ui_component, register_ui_component

-FACE_SWAPPER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
+FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
 FACE_ENHANCER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
 FACE_ENHANCER_BLEND_SLIDER : Optional[gradio.Slider] = None
+FACE_SWAPPER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
 FRAME_ENHANCER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
 FRAME_ENHANCER_BLEND_SLIDER : Optional[gradio.Slider] = None
-FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
+LIP_SYNCER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None


 def render() -> None:
-	global FACE_SWAPPER_MODEL_DROPDOWN
+	global FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP
 	global FACE_ENHANCER_MODEL_DROPDOWN
 	global FACE_ENHANCER_BLEND_SLIDER
+	global FACE_SWAPPER_MODEL_DROPDOWN
 	global FRAME_ENHANCER_MODEL_DROPDOWN
 	global FRAME_ENHANCER_BLEND_SLIDER
-	global FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP
+	global LIP_SYNCER_MODEL_DROPDOWN

-	FACE_SWAPPER_MODEL_DROPDOWN = gradio.Dropdown(
-		label = wording.get('face_swapper_model_dropdown_label'),
-		choices = frame_processors_choices.face_swapper_models,
-		value = frame_processors_globals.face_swapper_model,
-		visible = 'face_swapper' in facefusion.globals.frame_processors
+	FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP = gradio.CheckboxGroup(
+		label = wording.get('uis.face_debugger_items_checkbox_group'),
+		choices = frame_processors_choices.face_debugger_items,
+		value = frame_processors_globals.face_debugger_items,
+		visible = 'face_debugger' in facefusion.globals.frame_processors
 	)
 	FACE_ENHANCER_MODEL_DROPDOWN = gradio.Dropdown(
-		label = wording.get('face_enhancer_model_dropdown_label'),
+		label = wording.get('uis.face_enhancer_model_dropdown'),
 		choices = frame_processors_choices.face_enhancer_models,
 		value = frame_processors_globals.face_enhancer_model,
 		visible = 'face_enhancer' in facefusion.globals.frame_processors
 	)
 	FACE_ENHANCER_BLEND_SLIDER = gradio.Slider(
-		label = wording.get('face_enhancer_blend_slider_label'),
+		label = wording.get('uis.face_enhancer_blend_slider'),
 		value = frame_processors_globals.face_enhancer_blend,
 		step = frame_processors_choices.face_enhancer_blend_range[1] - frame_processors_choices.face_enhancer_blend_range[0],
 		minimum = frame_processors_choices.face_enhancer_blend_range[0],
 		maximum = frame_processors_choices.face_enhancer_blend_range[-1],
 		visible = 'face_enhancer' in facefusion.globals.frame_processors
 	)
+	FACE_SWAPPER_MODEL_DROPDOWN = gradio.Dropdown(
+		label = wording.get('uis.face_swapper_model_dropdown'),
+		choices = frame_processors_choices.face_swapper_models,
+		value = frame_processors_globals.face_swapper_model,
+		visible = 'face_swapper' in facefusion.globals.frame_processors
+	)
 	FRAME_ENHANCER_MODEL_DROPDOWN = gradio.Dropdown(
-		label = wording.get('frame_enhancer_model_dropdown_label'),
+		label = wording.get('uis.frame_enhancer_model_dropdown'),
 		choices = frame_processors_choices.frame_enhancer_models,
 		value = frame_processors_globals.frame_enhancer_model,
 		visible = 'frame_enhancer' in facefusion.globals.frame_processors
 	)
 	FRAME_ENHANCER_BLEND_SLIDER = gradio.Slider(
-		label = wording.get('frame_enhancer_blend_slider_label'),
+		label = wording.get('uis.frame_enhancer_blend_slider'),
 		value = frame_processors_globals.frame_enhancer_blend,
 		step = frame_processors_choices.frame_enhancer_blend_range[1] - frame_processors_choices.frame_enhancer_blend_range[0],
 		minimum = frame_processors_choices.frame_enhancer_blend_range[0],
 		maximum = frame_processors_choices.frame_enhancer_blend_range[-1],
 		visible = 'frame_enhancer' in facefusion.globals.frame_processors
 	)
-	FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP = gradio.CheckboxGroup(
-		label = wording.get('face_debugger_items_checkbox_group_label'),
-		choices = frame_processors_choices.face_debugger_items,
-		value = frame_processors_globals.face_debugger_items,
-		visible = 'face_debugger' in facefusion.globals.frame_processors
+	LIP_SYNCER_MODEL_DROPDOWN = gradio.Dropdown(
+		label = wording.get('uis.lip_syncer_model_dropdown'),
+		choices = frame_processors_choices.lip_syncer_models,
+		value = frame_processors_globals.lip_syncer_model,
+		visible = 'lip_syncer' in facefusion.globals.frame_processors
 	)
-
-	register_ui_component('face_swapper_model_dropdown', FACE_SWAPPER_MODEL_DROPDOWN)
+	register_ui_component('face_debugger_items_checkbox_group', FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP)
 	register_ui_component('face_enhancer_model_dropdown', FACE_ENHANCER_MODEL_DROPDOWN)
 	register_ui_component('face_enhancer_blend_slider', FACE_ENHANCER_BLEND_SLIDER)
+	register_ui_component('face_swapper_model_dropdown', FACE_SWAPPER_MODEL_DROPDOWN)
 	register_ui_component('frame_enhancer_model_dropdown', FRAME_ENHANCER_MODEL_DROPDOWN)
 	register_ui_component('frame_enhancer_blend_slider', FRAME_ENHANCER_BLEND_SLIDER)
-	register_ui_component('face_debugger_items_checkbox_group', FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP)
+	register_ui_component('lip_syncer_model_dropdown', LIP_SYNCER_MODEL_DROPDOWN)


 def listen() -> None:
-	FACE_SWAPPER_MODEL_DROPDOWN.change(update_face_swapper_model, inputs = FACE_SWAPPER_MODEL_DROPDOWN, outputs = FACE_SWAPPER_MODEL_DROPDOWN)
+	FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP.change(update_face_debugger_items, inputs = FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP)
 	FACE_ENHANCER_MODEL_DROPDOWN.change(update_face_enhancer_model, inputs = FACE_ENHANCER_MODEL_DROPDOWN, outputs = FACE_ENHANCER_MODEL_DROPDOWN)
 	FACE_ENHANCER_BLEND_SLIDER.change(update_face_enhancer_blend, inputs = FACE_ENHANCER_BLEND_SLIDER)
+	FACE_SWAPPER_MODEL_DROPDOWN.change(update_face_swapper_model, inputs = FACE_SWAPPER_MODEL_DROPDOWN, outputs = FACE_SWAPPER_MODEL_DROPDOWN)
 	FRAME_ENHANCER_MODEL_DROPDOWN.change(update_frame_enhancer_model, inputs = FRAME_ENHANCER_MODEL_DROPDOWN, outputs = FRAME_ENHANCER_MODEL_DROPDOWN)
 	FRAME_ENHANCER_BLEND_SLIDER.change(update_frame_enhancer_blend, inputs = FRAME_ENHANCER_BLEND_SLIDER)
-	FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP.change(update_face_debugger_items, inputs = FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP)
+	LIP_SYNCER_MODEL_DROPDOWN.change(update_lip_syncer_model, inputs = LIP_SYNCER_MODEL_DROPDOWN, outputs = LIP_SYNCER_MODEL_DROPDOWN)
 	frame_processors_checkbox_group = get_ui_component('frame_processors_checkbox_group')
 	if frame_processors_checkbox_group:
-		frame_processors_checkbox_group.change(toggle_face_swapper_model, inputs = frame_processors_checkbox_group, outputs = [ FACE_SWAPPER_MODEL_DROPDOWN, FACE_ENHANCER_MODEL_DROPDOWN, FACE_ENHANCER_BLEND_SLIDER, FRAME_ENHANCER_MODEL_DROPDOWN, FRAME_ENHANCER_BLEND_SLIDER, FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP ])
+		frame_processors_checkbox_group.change(update_frame_processors, inputs = frame_processors_checkbox_group, outputs = [ FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP, FACE_ENHANCER_MODEL_DROPDOWN, FACE_ENHANCER_BLEND_SLIDER, FACE_SWAPPER_MODEL_DROPDOWN, FRAME_ENHANCER_MODEL_DROPDOWN, FRAME_ENHANCER_BLEND_SLIDER, LIP_SYNCER_MODEL_DROPDOWN ])
+
+
+def update_frame_processors(frame_processors : List[str]) -> Tuple[gradio.CheckboxGroup, gradio.Dropdown, gradio.Slider, gradio.Dropdown, gradio.Dropdown, gradio.Slider, gradio.Dropdown]:
+	has_face_debugger = 'face_debugger' in frame_processors
+	has_face_enhancer = 'face_enhancer' in frame_processors
+	has_face_swapper = 'face_swapper' in frame_processors
+	has_frame_enhancer = 'frame_enhancer' in frame_processors
+	has_lip_syncer = 'lip_syncer' in frame_processors
+	return gradio.CheckboxGroup(visible = has_face_debugger), gradio.Dropdown(visible = has_face_enhancer), gradio.Slider(visible = has_face_enhancer), gradio.Dropdown(visible = has_face_swapper), gradio.Dropdown(visible = has_frame_enhancer), gradio.Slider(visible = has_frame_enhancer), gradio.Dropdown(visible = has_lip_syncer)
+
+
+def update_face_debugger_items(face_debugger_items : List[FaceDebuggerItem]) -> None:
+	frame_processors_globals.face_debugger_items = face_debugger_items
+
+
+def update_face_enhancer_model(face_enhancer_model : FaceEnhancerModel) -> gradio.Dropdown:
+	frame_processors_globals.face_enhancer_model = face_enhancer_model
+	face_enhancer_module = load_frame_processor_module('face_enhancer')
+	face_enhancer_module.clear_frame_processor()
+	face_enhancer_module.set_options('model', face_enhancer_module.MODELS[face_enhancer_model])
+	if face_enhancer_module.pre_check():
+		return gradio.Dropdown(value = face_enhancer_model)
+	return gradio.Dropdown()
+
+
+def update_face_enhancer_blend(face_enhancer_blend : int) -> None:
+	frame_processors_globals.face_enhancer_blend = face_enhancer_blend


 def update_face_swapper_model(face_swapper_model : FaceSwapperModel) -> gradio.Dropdown:
@@ -93,26 +129,14 @@ def update_face_swapper_model(face_swapper_model : FaceSwapperModel) -> gradio.D
 		facefusion.globals.face_recognizer_model = 'arcface_inswapper'
 	if face_swapper_model == 'simswap_256' or face_swapper_model == 'simswap_512_unofficial':
 		facefusion.globals.face_recognizer_model = 'arcface_simswap'
+	if face_swapper_model == 'uniface_256':
+		facefusion.globals.face_recognizer_model = 'arcface_uniface'
 	face_swapper_module = load_frame_processor_module('face_swapper')
 	face_swapper_module.clear_frame_processor()
 	face_swapper_module.set_options('model', face_swapper_module.MODELS[face_swapper_model])
-	if not face_swapper_module.pre_check():
-		return gradio.Dropdown()
-	return gradio.Dropdown(value = face_swapper_model)
-
-
-def update_face_enhancer_model(face_enhancer_model : FaceEnhancerModel) -> gradio.Dropdown:
-	frame_processors_globals.face_enhancer_model = face_enhancer_model
-	face_enhancer_module = load_frame_processor_module('face_enhancer')
-	face_enhancer_module.clear_frame_processor()
-	face_enhancer_module.set_options('model', face_enhancer_module.MODELS[face_enhancer_model])
-	if not face_enhancer_module.pre_check():
-		return gradio.Dropdown()
-	return gradio.Dropdown(value = face_enhancer_model)
-
-
-def update_face_enhancer_blend(face_enhancer_blend : int) -> None:
-	frame_processors_globals.face_enhancer_blend = face_enhancer_blend
+	if face_swapper_module.pre_check():
+		return gradio.Dropdown(value = face_swapper_model)
+	return gradio.Dropdown()


 def update_frame_enhancer_model(frame_enhancer_model : FrameEnhancerModel) -> gradio.Dropdown:
@@ -120,22 +144,20 @@ def update_frame_enhancer_model(frame_enhancer_model : FrameEnhancerModel) -> gr
 	frame_enhancer_module = load_frame_processor_module('frame_enhancer')
 	frame_enhancer_module.clear_frame_processor()
 	frame_enhancer_module.set_options('model', frame_enhancer_module.MODELS[frame_enhancer_model])
-	if not frame_enhancer_module.pre_check():
-		return gradio.Dropdown()
-	return gradio.Dropdown(value = frame_enhancer_model)
+	if frame_enhancer_module.pre_check():
+		return gradio.Dropdown(value = frame_enhancer_model)
+	return gradio.Dropdown()


 def update_frame_enhancer_blend(frame_enhancer_blend : int) -> None:
 	frame_processors_globals.frame_enhancer_blend = frame_enhancer_blend


-def update_face_debugger_items(face_debugger_items : List[FaceDebuggerItem]) -> None:
-	frame_processors_globals.face_debugger_items = face_debugger_items
-
-
-def toggle_face_swapper_model(frame_processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Dropdown, gradio.Slider, gradio.Dropdown, gradio.Slider, gradio.CheckboxGroup]:
-	has_face_swapper = 'face_swapper' in frame_processors
-	has_face_enhancer = 'face_enhancer' in frame_processors
-	has_frame_enhancer = 'frame_enhancer' in frame_processors
-	has_face_debugger = 'face_debugger' in frame_processors
-	return gradio.Dropdown(visible = has_face_swapper), gradio.Dropdown(visible = has_face_enhancer), gradio.Slider(visible = has_face_enhancer), gradio.Dropdown(visible = has_frame_enhancer), gradio.Slider(visible = has_frame_enhancer), gradio.CheckboxGroup(visible = has_face_debugger)
+def update_lip_syncer_model(lip_syncer_model : LipSyncerModel) -> gradio.Dropdown:
+	frame_processors_globals.lip_syncer_model = lip_syncer_model
+	lip_syncer_module = load_frame_processor_module('lip_syncer')
+	lip_syncer_module.clear_frame_processor()
+	lip_syncer_module.set_options('model', lip_syncer_module.MODELS[lip_syncer_model])
+	if lip_syncer_module.pre_check():
+		return gradio.Dropdown(value = lip_syncer_model)
+	return gradio.Dropdown()
--- a/facefusion/uis/components/memory.py
+++ b/facefusion/uis/components/memory.py
@@ -15,12 +15,12 @@ def render() -> None:
 	global SYSTEM_MEMORY_LIMIT_SLIDER

 	VIDEO_MEMORY_STRATEGY = gradio.Dropdown(
-		label = wording.get('video_memory_strategy_dropdown_label'),
+		label = wording.get('uis.video_memory_strategy_dropdown'),
 		choices = facefusion.choices.video_memory_strategies,
 		value = facefusion.globals.video_memory_strategy
 	)
 	SYSTEM_MEMORY_LIMIT_SLIDER = gradio.Slider(
-		label = wording.get('system_memory_limit_slider_label'),
+		label = wording.get('uis.system_memory_limit_slider'),
 		step =facefusion.choices.system_memory_limit_range[1] - facefusion.choices.system_memory_limit_range[0],
 		minimum = facefusion.choices.system_memory_limit_range[0],
 		maximum = facefusion.choices.system_memory_limit_range[-1],
--- a/facefusion/uis/components/output.py
+++ b/facefusion/uis/components/output.py
@@ -22,19 +22,19 @@ def render() -> None:
 	global OUTPUT_CLEAR_BUTTON

 	OUTPUT_IMAGE = gradio.Image(
-		label = wording.get('output_image_or_video_label'),
+		label = wording.get('uis.output_image_or_video'),
 		visible = False
 	)
 	OUTPUT_VIDEO = gradio.Video(
-		label = wording.get('output_image_or_video_label')
+		label = wording.get('uis.output_image_or_video')
 	)
 	OUTPUT_START_BUTTON = gradio.Button(
-		value = wording.get('start_button_label'),
+		value = wording.get('uis.start_button'),
 		variant = 'primary',
 		size = 'sm'
 	)
 	OUTPUT_CLEAR_BUTTON = gradio.Button(
-		value = wording.get('clear_button_label'),
+		value = wording.get('uis.clear_button'),
 		size = 'sm'
 	)

--- a/facefusion/uis/components/output_options.py
+++ b/facefusion/uis/components/output_options.py
@@ -30,12 +30,12 @@ def render() -> None:
 	global OUTPUT_VIDEO_FPS_SLIDER

 	OUTPUT_PATH_TEXTBOX = gradio.Textbox(
-		label = wording.get('output_path_textbox_label'),
+		label = wording.get('uis.output_path_textbox'),
 		value = facefusion.globals.output_path or tempfile.gettempdir(),
 		max_lines = 1
 	)
 	OUTPUT_IMAGE_QUALITY_SLIDER = gradio.Slider(
-		label = wording.get('output_image_quality_slider_label'),
+		label = wording.get('uis.output_image_quality_slider'),
 		value = facefusion.globals.output_image_quality,
 		step = facefusion.choices.output_image_quality_range[1] - facefusion.choices.output_image_quality_range[0],
 		minimum = facefusion.choices.output_image_quality_range[0],
@@ -43,19 +43,19 @@ def render() -> None:
 		visible = is_image(facefusion.globals.target_path)
 	)
 	OUTPUT_VIDEO_ENCODER_DROPDOWN = gradio.Dropdown(
-		label = wording.get('output_video_encoder_dropdown_label'),
+		label = wording.get('uis.output_video_encoder_dropdown'),
 		choices = facefusion.choices.output_video_encoders,
 		value = facefusion.globals.output_video_encoder,
 		visible = is_video(facefusion.globals.target_path)
 	)
 	OUTPUT_VIDEO_PRESET_DROPDOWN = gradio.Dropdown(
-		label = wording.get('output_video_preset_dropdown_label'),
+		label = wording.get('uis.output_video_preset_dropdown'),
 		choices = facefusion.choices.output_video_presets,
 		value = facefusion.globals.output_video_preset,
 		visible = is_video(facefusion.globals.target_path)
 	)
 	OUTPUT_VIDEO_QUALITY_SLIDER = gradio.Slider(
-		label = wording.get('output_video_quality_slider_label'),
+		label = wording.get('uis.output_video_quality_slider'),
 		value = facefusion.globals.output_video_quality,
 		step = facefusion.choices.output_video_quality_range[1] - facefusion.choices.output_video_quality_range[0],
 		minimum = facefusion.choices.output_video_quality_range[0],
@@ -63,13 +63,13 @@ def render() -> None:
 		visible = is_video(facefusion.globals.target_path)
 	)
 	OUTPUT_VIDEO_RESOLUTION_DROPDOWN = gradio.Dropdown(
-		label = wording.get('output_video_resolution_dropdown_label'),
+		label = wording.get('uis.output_video_resolution_dropdown'),
 		choices = create_video_resolutions(facefusion.globals.target_path),
 		value = facefusion.globals.output_video_resolution,
 		visible = is_video(facefusion.globals.target_path)
 	)
 	OUTPUT_VIDEO_FPS_SLIDER = gradio.Slider(
-		label = wording.get('output_video_fps_slider_label'),
+		label = wording.get('uis.output_video_fps_slider'),
 		value = facefusion.globals.output_video_fps,
 		step = 0.01,
 		minimum = 1,
@@ -77,6 +77,7 @@ def render() -> None:
 		visible = is_video(facefusion.globals.target_path)
 	)
 	register_ui_component('output_path_textbox', OUTPUT_PATH_TEXTBOX)
+	register_ui_component('output_video_fps_slider', OUTPUT_VIDEO_FPS_SLIDER)


 def listen() -> None:
@@ -89,7 +90,6 @@ def listen() -> None:
 	OUTPUT_VIDEO_FPS_SLIDER.change(update_output_video_fps, inputs = OUTPUT_VIDEO_FPS_SLIDER)
 	multi_component_names : List[ComponentName] =\
 	[
-		'source_image',
 		'target_image',
 		'target_video'
 	]
--- a/facefusion/uis/components/preview.py
+++ b/facefusion/uis/components/preview.py
@@ -5,12 +5,14 @@ import gradio

 import facefusion.globals
 from facefusion import wording, logger
+from facefusion.audio import get_audio_frame
+from facefusion.common_helper import get_first
 from facefusion.core import conditional_append_reference_faces
-from facefusion.face_store import clear_static_faces, get_reference_faces, clear_reference_faces
-from facefusion.typing import Frame, Face, FaceSet
-from facefusion.vision import get_video_frame, count_video_frame_total, normalize_frame_color, resize_frame_resolution, read_static_image, read_static_images
-from facefusion.filesystem import is_image, is_video
 from facefusion.face_analyser import get_average_face, clear_face_analyser
+from facefusion.face_store import clear_static_faces, get_reference_faces, clear_reference_faces
+from facefusion.typing import Face, FaceSet, AudioFrame, VisionFrame
+from facefusion.vision import get_video_frame, count_video_frame_total, normalize_frame_color, resize_frame_resolution, read_static_image, read_static_images
+from facefusion.filesystem import is_image, is_video, filter_audio_paths
 from facefusion.content_analyser import analyse_frame
 from facefusion.processors.frame.core import load_frame_processor_module
 from facefusion.uis.typing import ComponentName
@@ -26,29 +28,34 @@ def render() -> None:

 	preview_image_args: Dict[str, Any] =\
 	{
-		'label': wording.get('preview_image_label'),
+		'label': wording.get('uis.preview_image'),
 		'interactive': False
 	}
 	preview_frame_slider_args: Dict[str, Any] =\
 	{
-		'label': wording.get('preview_frame_slider_label'),
+		'label': wording.get('uis.preview_frame_slider'),
 		'step': 1,
 		'minimum': 0,
 		'maximum': 100,
 		'visible': False
 	}
 	conditional_append_reference_faces()
+	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
 	source_frames = read_static_images(facefusion.globals.source_paths)
 	source_face = get_average_face(source_frames)
-	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
+	source_audio_path = get_first(filter_audio_paths(facefusion.globals.source_paths))
+	if source_audio_path and facefusion.globals.output_video_fps:
+		source_audio_frame = get_audio_frame(source_audio_path, facefusion.globals.output_video_fps, facefusion.globals.reference_frame_number)
+	else:
+		source_audio_frame = None
 	if is_image(facefusion.globals.target_path):
-		target_frame = read_static_image(facefusion.globals.target_path)
-		preview_frame = process_preview_frame(source_face, reference_faces, target_frame)
-		preview_image_args['value'] = normalize_frame_color(preview_frame)
+		target_vision_frame = read_static_image(facefusion.globals.target_path)
+		preview_vision_frame = process_preview_frame(reference_faces, source_face, source_audio_frame, target_vision_frame)
+		preview_image_args['value'] = normalize_frame_color(preview_vision_frame)
 	if is_video(facefusion.globals.target_path):
-		temp_frame = get_video_frame(facefusion.globals.target_path, facefusion.globals.reference_frame_number)
-		preview_frame = process_preview_frame(source_face, reference_faces, temp_frame)
-		preview_image_args['value'] = normalize_frame_color(preview_frame)
+		temp_vision_frame = get_video_frame(facefusion.globals.target_path, facefusion.globals.reference_frame_number)
+		preview_vision_frame = process_preview_frame(reference_faces, source_face, source_audio_frame, temp_vision_frame)
+		preview_image_args['value'] = normalize_frame_color(preview_vision_frame)
 		preview_image_args['visible'] = True
 		preview_frame_slider_args['value'] = facefusion.globals.reference_frame_number
 		preview_frame_slider_args['maximum'] = count_video_frame_total(facefusion.globals.target_path)
@@ -60,8 +67,12 @@ def render() -> None:

 def listen() -> None:
 	PREVIEW_FRAME_SLIDER.release(update_preview_image, inputs = PREVIEW_FRAME_SLIDER, outputs = PREVIEW_IMAGE)
+	reference_face_position_gallery = get_ui_component('reference_face_position_gallery')
+	if reference_face_position_gallery:
+		reference_face_position_gallery.select(update_preview_image, inputs = PREVIEW_FRAME_SLIDER, outputs = PREVIEW_IMAGE)
 	multi_one_component_names : List[ComponentName] =\
 	[
+		'source_audio',
 		'source_image',
 		'target_image',
 		'target_video'
@@ -81,17 +92,6 @@ def listen() -> None:
 		if component:
 			for method in [ 'upload', 'change', 'clear' ]:
 				getattr(component, method)(update_preview_frame_slider, outputs = PREVIEW_FRAME_SLIDER)
-	select_component_names : List[ComponentName] =\
-	[
-		'reference_face_position_gallery',
-		'face_analyser_order_dropdown',
-		'face_analyser_age_dropdown',
-		'face_analyser_gender_dropdown'
-	]
-	for component_name in select_component_names:
-		component = get_ui_component(component_name)
-		if component:
-			component.select(update_preview_image, inputs = PREVIEW_FRAME_SLIDER, outputs = PREVIEW_IMAGE)
 	change_one_component_names : List[ComponentName] =\
 	[
 		'face_debugger_items_checkbox_group',
@@ -105,7 +105,11 @@ def listen() -> None:
 		'face_mask_padding_bottom_slider',
 		'face_mask_padding_left_slider',
 		'face_mask_padding_right_slider',
-		'face_mask_region_checkbox_group'
+		'face_mask_region_checkbox_group',
+		'face_analyser_order_dropdown',
+		'face_analyser_age_dropdown',
+		'face_analyser_gender_dropdown',
+		'output_video_fps_slider'
 	]
 	for component_name in change_one_component_names:
 		component = get_ui_component(component_name)
@@ -117,6 +121,7 @@ def listen() -> None:
 		'face_enhancer_model_dropdown',
 		'face_swapper_model_dropdown',
 		'frame_enhancer_model_dropdown',
+		'lip_syncer_model_dropdown',
 		'face_detector_model_dropdown',
 		'face_detector_size_dropdown',
 		'face_detector_score_slider'
@@ -143,19 +148,25 @@ def update_preview_image(frame_number : int = 0) -> gradio.Image:
 			sleep(0.5)
 		logger.enable()
 	conditional_append_reference_faces()
+	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
 	source_frames = read_static_images(facefusion.globals.source_paths)
 	source_face = get_average_face(source_frames)
-	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
+	source_audio_path = get_first(filter_audio_paths(facefusion.globals.source_paths))
+	if source_audio_path and facefusion.globals.output_video_fps:
+		source_audio_frame = get_audio_frame(source_audio_path, facefusion.globals.output_video_fps, facefusion.globals.reference_frame_number)
+	else:
+		source_audio_frame = None
+
 	if is_image(facefusion.globals.target_path):
-		target_frame = read_static_image(facefusion.globals.target_path)
-		preview_frame = process_preview_frame(source_face, reference_faces, target_frame)
-		preview_frame = normalize_frame_color(preview_frame)
-		return gradio.Image(value = preview_frame)
+		target_vision_frame = read_static_image(facefusion.globals.target_path)
+		preview_vision_frame = process_preview_frame(reference_faces, source_face, source_audio_frame, target_vision_frame)
+		preview_vision_frame = normalize_frame_color(preview_vision_frame)
+		return gradio.Image(value = preview_vision_frame)
 	if is_video(facefusion.globals.target_path):
-		temp_frame = get_video_frame(facefusion.globals.target_path, frame_number)
-		preview_frame = process_preview_frame(source_face, reference_faces, temp_frame)
-		preview_frame = normalize_frame_color(preview_frame)
-		return gradio.Image(value = preview_frame)
+		temp_vision_frame = get_video_frame(facefusion.globals.target_path, frame_number)
+		preview_vision_frame = process_preview_frame(reference_faces, source_face, source_audio_frame, temp_vision_frame)
+		preview_vision_frame = normalize_frame_color(preview_vision_frame)
+		return gradio.Image(value = preview_vision_frame)
 	return gradio.Image(value = None)


@@ -166,18 +177,20 @@ def update_preview_frame_slider() -> gradio.Slider:
 	return gradio.Slider(value = None, maximum = None, visible = False)


-def process_preview_frame(source_face : Face, reference_faces : FaceSet, temp_frame : Frame) -> Frame:
-	temp_frame = resize_frame_resolution(temp_frame, 640, 640)
-	if analyse_frame(temp_frame):
-		return cv2.GaussianBlur(temp_frame, (99, 99), 0)
+def process_preview_frame(reference_faces : FaceSet, source_face : Face, source_audio_frame : AudioFrame, target_vision_frame : VisionFrame) -> VisionFrame:
+	target_vision_frame = resize_frame_resolution(target_vision_frame, 640, 640)
+	if analyse_frame(target_vision_frame):
+		return cv2.GaussianBlur(target_vision_frame, (99, 99), 0)
 	for frame_processor in facefusion.globals.frame_processors:
 		frame_processor_module = load_frame_processor_module(frame_processor)
 		logger.disable()
 		if frame_processor_module.pre_process('preview'):
 			logger.enable()
-			temp_frame = frame_processor_module.process_frame(
-				source_face,
-				reference_faces,
-				temp_frame
-			)
-	return temp_frame
+			target_vision_frame = frame_processor_module.process_frame(
+			{
+				'reference_faces': reference_faces,
+				'source_face': source_face,
+				'source_audio_frame': source_audio_frame,
+				'target_vision_frame': target_vision_frame
+			})
+	return target_vision_frame
--- a/facefusion/uis/components/source.py
+++ b/facefusion/uis/components/source.py
@@ -1,49 +1,67 @@
-from typing import Optional, List
+from typing import Optional, List, Tuple
 import gradio

 import facefusion.globals
 from facefusion import wording
 from facefusion.uis.typing import File
-from facefusion.filesystem import are_images
+from facefusion.common_helper import get_first
+from facefusion.filesystem import has_audio, has_image, filter_audio_paths, filter_image_paths
 from facefusion.uis.core import register_ui_component

 SOURCE_FILE : Optional[gradio.File] = None
+SOURCE_AUDIO : Optional[gradio.Audio] = None
 SOURCE_IMAGE : Optional[gradio.Image] = None


 def render() -> None:
 	global SOURCE_FILE
+	global SOURCE_AUDIO
 	global SOURCE_IMAGE

-	are_source_images = are_images(facefusion.globals.source_paths)
+	has_source_audio = has_audio(facefusion.globals.source_paths)
+	has_source_image = has_image(facefusion.globals.source_paths)
 	SOURCE_FILE = gradio.File(
 		file_count = 'multiple',
 		file_types =
 		[
+			'.mp3',
+			'.wav',
 			'.png',
 			'.jpg',
 			'.webp'
 		],
-		label = wording.get('source_file_label'),
-		value = facefusion.globals.source_paths if are_source_images else None
+		label = wording.get('uis.source_file'),
+		value = facefusion.globals.source_paths if has_source_audio or has_source_image else None
 	)
 	source_file_names = [ source_file_value['name'] for source_file_value in SOURCE_FILE.value ] if SOURCE_FILE.value else None
-	SOURCE_IMAGE = gradio.Image(
-		value = source_file_names[0] if are_source_images else None,
-		visible = are_source_images,
+	source_audio_path = get_first(filter_audio_paths(source_file_names))
+	source_image_path = get_first(filter_image_paths(source_file_names))
+	SOURCE_AUDIO = gradio.Audio(
+		value = source_audio_path if has_source_audio else None,
+		visible = has_source_audio,
 		show_label = False
 	)
+	SOURCE_IMAGE = gradio.Image(
+		value = source_image_path if has_source_image else None,
+		visible = has_source_image,
+		show_label = False
+	)
+	register_ui_component('source_audio', SOURCE_AUDIO)
 	register_ui_component('source_image', SOURCE_IMAGE)


 def listen() -> None:
-	SOURCE_FILE.change(update, inputs = SOURCE_FILE, outputs = SOURCE_IMAGE)
+	SOURCE_FILE.change(update, inputs = SOURCE_FILE, outputs = [ SOURCE_AUDIO, SOURCE_IMAGE ])


-def update(files : List[File]) -> gradio.Image:
+def update(files : List[File]) -> Tuple[gradio.Audio, gradio.Image]:
 	file_names = [ file.name for file in files ] if files else None
-	if are_images(file_names):
+	has_source_audio = has_audio(file_names)
+	has_source_image = has_image(file_names)
+	if has_source_audio or has_source_image:
+		source_audio_path = get_first(filter_audio_paths(file_names))
+		source_image_path = get_first(filter_image_paths(file_names))
 		facefusion.globals.source_paths = file_names
-		return gradio.Image(value = file_names[0], visible = True)
+		return gradio.Audio(value = source_audio_path, visible = has_source_audio), gradio.Image(value = source_image_path, visible = has_source_image)
 	facefusion.globals.source_paths = None
-	return gradio.Image(value = None, visible = False)
+	return gradio.Audio(value = None, visible = False), gradio.Image(value = None, visible = False)
--- a/facefusion/uis/components/target.py
+++ b/facefusion/uis/components/target.py
@@ -21,7 +21,7 @@ def render() -> None:
 	is_target_image = is_image(facefusion.globals.target_path)
 	is_target_video = is_video(facefusion.globals.target_path)
 	TARGET_FILE = gradio.File(
-		label = wording.get('target_file_label'),
+		label = wording.get('uis.target_file'),
 		file_count = 'single',
 		file_types =
 		[
--- a/facefusion/uis/components/temp_frame.py
+++ b/facefusion/uis/components/temp_frame.py
@@ -17,13 +17,13 @@ def render() -> None:
 	global TEMP_FRAME_QUALITY_SLIDER

 	TEMP_FRAME_FORMAT_DROPDOWN = gradio.Dropdown(
-		label = wording.get('temp_frame_format_dropdown_label'),
+		label = wording.get('uis.temp_frame_format_dropdown'),
 		choices = facefusion.choices.temp_frame_formats,
 		value = facefusion.globals.temp_frame_format,
 		visible = is_video(facefusion.globals.target_path)
 	)
 	TEMP_FRAME_QUALITY_SLIDER = gradio.Slider(
-		label = wording.get('temp_frame_quality_slider_label'),
+		label = wording.get('uis.temp_frame_quality_slider'),
 		value = facefusion.globals.temp_frame_quality,
 		step = facefusion.choices.temp_frame_quality_range[1] - facefusion.choices.temp_frame_quality_range[0],
 		minimum = facefusion.choices.temp_frame_quality_range[0],
--- a/facefusion/uis/components/trim_frame.py
+++ b/facefusion/uis/components/trim_frame.py
@@ -17,7 +17,7 @@ def render() -> None:

 	trim_frame_start_slider_args : Dict[str, Any] =\
 	{
-		'label': wording.get('trim_frame_start_slider_label'),
+		'label': wording.get('uis.trim_frame_start_slider'),
 		'step': 1,
 		'minimum': 0,
 		'maximum': 100,
@@ -25,7 +25,7 @@ def render() -> None:
 	}
 	trim_frame_end_slider_args : Dict[str, Any] =\
 	{
-		'label': wording.get('trim_frame_end_slider_label'),
+		'label': wording.get('uis.trim_frame_end_slider'),
 		'step': 1,
 		'minimum': 0,
 		'maximum': 100,
--- a/facefusion/uis/components/webcam.py
+++ b/facefusion/uis/components/webcam.py
@@ -12,7 +12,7 @@ from tqdm import tqdm
 import facefusion.globals
 from facefusion import logger, wording
 from facefusion.content_analyser import analyse_stream
-from facefusion.typing import Frame, Face, Fps
+from facefusion.typing import VisionFrame, Face, Fps
 from facefusion.face_analyser import get_average_face
 from facefusion.processors.frame.core import get_frame_processors_modules, load_frame_processor_module
 from facefusion.ffmpeg import open_ffmpeg
@@ -53,15 +53,15 @@ def render() -> None:
 	global WEBCAM_STOP_BUTTON

 	WEBCAM_IMAGE = gradio.Image(
-		label = wording.get('webcam_image_label')
+		label = wording.get('uis.webcam_image')
 	)
 	WEBCAM_START_BUTTON = gradio.Button(
-		value = wording.get('start_button_label'),
+		value = wording.get('uis.start_button'),
 		variant = 'primary',
 		size = 'sm'
 	)
 	WEBCAM_STOP_BUTTON = gradio.Button(
-		value = wording.get('stop_button_label'),
+		value = wording.get('uis.stop_button'),
 		size = 'sm'
 	)

@@ -80,6 +80,7 @@ def listen() -> None:
 		'face_swapper_model_dropdown',
 		'face_enhancer_model_dropdown',
 		'frame_enhancer_model_dropdown',
+		'lip_syncer_model_dropdown',
 		'source_image'
 	]
 	for component_name in change_two_component_names:
@@ -88,7 +89,7 @@ def listen() -> None:
 			component.change(update, cancels = start_event)


-def start(webcam_mode : WebcamMode, webcam_resolution : str, webcam_fps : Fps) -> Generator[Frame, None, None]:
+def start(webcam_mode : WebcamMode, webcam_resolution : str, webcam_fps : Fps) -> Generator[VisionFrame, None, None]:
 	facefusion.globals.face_selector_mode = 'one'
 	facefusion.globals.face_analyser_order = 'large-small'
 	source_frames = read_static_images(facefusion.globals.source_paths)
@@ -114,11 +115,11 @@ def start(webcam_mode : WebcamMode, webcam_resolution : str, webcam_fps : Fps) -
 				yield None


-def multi_process_capture(source_face : Face, webcam_capture : cv2.VideoCapture, webcam_fps : Fps) -> Generator[Frame, None, None]:
+def multi_process_capture(source_face : Face, webcam_capture : cv2.VideoCapture, webcam_fps : Fps) -> Generator[VisionFrame, None, None]:
 	with tqdm(desc = wording.get('processing'), unit = 'frame', ascii = ' =', disable = facefusion.globals.log_level in [ 'warn', 'error' ]) as progress:
 		with ThreadPoolExecutor(max_workers = facefusion.globals.execution_thread_count) as executor:
 			futures = []
-			deque_capture_frames : Deque[Frame] = deque()
+			deque_capture_frames : Deque[VisionFrame] = deque()
 			while webcam_capture and webcam_capture.isOpened():
 				_, capture_frame = webcam_capture.read()
 				if analyse_stream(capture_frame, webcam_fps):
@@ -148,17 +149,19 @@ def stop() -> gradio.Image:
 	return gradio.Image(value = None)


-def process_stream_frame(source_face : Face, temp_frame : Frame) -> Frame:
+def process_stream_frame(source_face : Face, target_vision_frame : VisionFrame) -> VisionFrame:
 	for frame_processor_module in get_frame_processors_modules(facefusion.globals.frame_processors):
 		logger.disable()
 		if frame_processor_module.pre_process('stream'):
 			logger.enable()
-			temp_frame = frame_processor_module.process_frame(
-				source_face,
-				None,
-				temp_frame
-			)
-	return temp_frame
+			target_vision_frame = frame_processor_module.process_frame(
+			{
+				'source_face': source_face,
+				'reference_faces': None,
+				'source_audio_frame': None,
+				'target_vision_frame': target_vision_frame
+			})
+	return target_vision_frame


 def open_stream(stream_mode : StreamMode, stream_resolution : str, stream_fps : Fps) -> subprocess.Popen[bytes]:
--- a/facefusion/uis/components/webcam_options.py
+++ b/facefusion/uis/components/webcam_options.py
@@ -16,17 +16,17 @@ def render() -> None:
 	global WEBCAM_FPS_SLIDER

 	WEBCAM_MODE_RADIO = gradio.Radio(
-		label = wording.get('webcam_mode_radio_label'),
+		label = wording.get('uis.webcam_mode_radio'),
 		choices = uis_choices.webcam_modes,
 		value = 'inline'
 	)
 	WEBCAM_RESOLUTION_DROPDOWN = gradio.Dropdown(
-		label = wording.get('webcam_resolution_dropdown'),
+		label = wording.get('uis.webcam_resolution_dropdown'),
 		choices = uis_choices.webcam_resolutions,
 		value = uis_choices.webcam_resolutions[0]
 	)
 	WEBCAM_FPS_SLIDER = gradio.Slider(
-		label = wording.get('webcam_fps_slider'),
+		label = wording.get('uis.webcam_fps_slider'),
 		value = 25,
 		step = 1,
 		minimum = 1,