Face selector auto mode (#1137)

* introduce face selector auto mode

* introduce face selector auto mode

* introduce face selector auto mode

* correct way is to pass source_vision_frames

facefusion/choices.py

@@ -2,7 +2,7 @@ import logging
 from typing import List, Sequence, get_args
 
 from facefusion.common_helper import create_float_range, create_int_range
-from facefusion.types import Angle, AudioEncoder, AudioFormat, AudioTypeSet, BenchmarkMode, BenchmarkResolution, BenchmarkSet, DownloadProvider, DownloadProviderSet, DownloadScope, EncoderSet, ExecutionProvider, ExecutionProviderSet, FaceDetectorModel, FaceDetectorSet, FaceLandmarkerModel, FaceMaskArea, FaceMaskAreaSet, FaceMaskRegion, FaceMaskRegionSet, FaceMaskType, FaceOccluderModel, FaceParserModel, FaceSelectorMode, FaceSelectorOrder, Gender, ImageFormat, ImageTypeSet, JobStatus, LogLevel, LogLevelSet, Race, Score, TempFrameFormat, UiWorkflow, VideoEncoder, VideoFormat, VideoMemoryStrategy, VideoPreset, VideoTypeSet, VoiceExtractorModel
+from facefusion.types import Angle, AudioEncoder, AudioFormat, AudioTypeSet, BenchmarkMode, BenchmarkResolution, BenchmarkSet, DownloadProvider, DownloadProviderSet, DownloadScope, EncoderSet, ExecutionProvider, ExecutionProviderSet, FaceDetectorModel, FaceDetectorSet, FaceLandmarkerModel, FaceMaskArea, FaceMaskAreaSet, FaceMaskRegion, FaceMaskRegionSet, FaceMaskType, FaceOccluderModel, FaceParserModel, FaceSelectorGender, FaceSelectorMode, FaceSelectorOrder, FaceSelectorRace, Gender, ImageFormat, ImageTypeSet, JobStatus, LogLevel, LogLevelSet, Race, Score, TempFrameFormat, UiWorkflow, VideoEncoder, VideoFormat, VideoMemoryStrategy, VideoPreset, VideoTypeSet, VoiceExtractorModel
 
 face_detector_set : FaceDetectorSet =\
 {
@@ -16,8 +16,10 @@ face_detector_models : List[FaceDetectorModel] = list(get_args(FaceDetectorModel
 face_landmarker_models : List[FaceLandmarkerModel] = list(get_args(FaceLandmarkerModel))
 face_selector_modes : List[FaceSelectorMode] = list(get_args(FaceSelectorMode))
 face_selector_orders : List[FaceSelectorOrder] = list(get_args(FaceSelectorOrder))
-face_selector_genders : List[Gender] = list(get_args(Gender))
-face_selector_races : List[Race] = list(get_args(Race))
+genders : List[Gender] = list(get_args(Gender))
+races : List[Race] = list(get_args(Race))
+face_selector_genders : List[FaceSelectorGender] = list(get_args(FaceSelectorGender))
+face_selector_races : List[FaceSelectorRace] = list(get_args(FaceSelectorRace))
 face_occluder_models : List[FaceOccluderModel] = list(get_args(FaceOccluderModel))
 face_parser_models : List[FaceParserModel] = list(get_args(FaceParserModel))
 face_mask_types : List[FaceMaskType] = list(get_args(FaceMaskType))

facefusion/face_selector.py

@@ -2,26 +2,33 @@ from typing import List
 
 import numpy
 
+import facefusion.choices
 from facefusion import state_manager
+from facefusion.common_helper import get_first
 from facefusion.face_analyser import get_many_faces, get_one_face
 from facefusion.types import Face, FaceSelectorOrder, Gender, Race, Score, VisionFrame
 
 
-def select_faces(reference_vision_frame : VisionFrame, target_vision_frame : VisionFrame) -> List[Face]:
+def select_faces(reference_vision_frame : VisionFrame, source_vision_frames : List[VisionFrame], target_vision_frame : VisionFrame) -> List[Face]:
+	source_faces = []
 	target_faces = get_many_faces([ target_vision_frame ])
 
+	if state_manager.get_item('face_selector_gender') == 'auto' or state_manager.get_item('face_selector_race') == 'auto':
+		source_faces = get_many_faces(source_vision_frames)
+
 	if state_manager.get_item('face_selector_mode') == 'many':
-		return sort_and_filter_faces(target_faces)
+		return sort_and_filter_faces(source_faces, target_faces)
 
 	if state_manager.get_item('face_selector_mode') == 'one':
-		target_face = get_one_face(sort_and_filter_faces(target_faces))
+		target_face = get_one_face(sort_and_filter_faces(source_faces, target_faces))
 		if target_face:
 			return [ target_face ]
 
 	if state_manager.get_item('face_selector_mode') == 'reference':
 		reference_faces = get_many_faces([ reference_vision_frame ])
-		reference_faces = sort_and_filter_faces(reference_faces)
+		reference_faces = sort_and_filter_faces(source_faces, reference_faces)
 		reference_face = get_one_face(reference_faces, state_manager.get_item('reference_face_position'))
+
 		if reference_face:
 			match_faces = find_match_faces([ reference_face ], target_faces, state_manager.get_item('reference_face_distance'))
 			return match_faces
@@ -53,17 +60,33 @@ def calculate_face_distance(face : Face, reference_face : Face) -> float:
 	return 0
 
 
-def sort_and_filter_faces(faces : List[Face]) -> List[Face]:
-	if faces:
+def sort_and_filter_faces(source_faces : List[Face], target_faces : List[Face]) -> List[Face]:
+	if target_faces:
 		if state_manager.get_item('face_selector_order'):
-			faces = sort_faces_by_order(faces, state_manager.get_item('face_selector_order'))
-		if state_manager.get_item('face_selector_gender'):
-			faces = filter_faces_by_gender(faces, state_manager.get_item('face_selector_gender'))
-		if state_manager.get_item('face_selector_race'):
-			faces = filter_faces_by_race(faces, state_manager.get_item('face_selector_race'))
+			target_faces = sort_faces_by_order(target_faces, state_manager.get_item('face_selector_order'))
+
+		face_selector_gender = state_manager.get_item('face_selector_gender')
+		face_selector_race = state_manager.get_item('face_selector_race')
+
+		if source_faces and face_selector_gender == 'auto' or face_selector_race == 'auto':
+			source_face = get_first(sort_faces_by_order(source_faces, 'large-small'))
+
+			if source_face:
+				if face_selector_gender == 'auto':
+					face_selector_gender = source_face.gender
+				if face_selector_race == 'auto':
+					face_selector_race = source_face.race
+
+		if face_selector_gender in facefusion.choices.genders:
+			target_faces = filter_faces_by_gender(target_faces, face_selector_gender)
+
+		if face_selector_race in facefusion.choices.races:
+			target_faces = filter_faces_by_race(target_faces, face_selector_race)
+
 		if state_manager.get_item('face_selector_age_start') or state_manager.get_item('face_selector_age_end'):
-			faces = filter_faces_by_age(faces, state_manager.get_item('face_selector_age_start'), state_manager.get_item('face_selector_age_end'))
-	return faces
+			target_faces = filter_faces_by_age(target_faces, state_manager.get_item('face_selector_age_start'), state_manager.get_item('face_selector_age_end'))
+
+	return target_faces
 
 
 def sort_faces_by_order(faces : List[Face], order : FaceSelectorOrder) -> List[Face]:

facefusion/processors/modules/age_modifier/core.py

@@ -276,10 +276,11 @@ def normalize_extend_frame(extend_vision_frame : VisionFrame) -> VisionFrame:
 
 def process_frame(inputs : AgeModifierInputs) -> ProcessorOutputs:
 	reference_vision_frame = inputs.get('reference_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
 	target_vision_frame = inputs.get('target_vision_frame')
 	temp_vision_frame = inputs.get('temp_vision_frame')
 	temp_vision_mask = inputs.get('temp_vision_mask')
-	target_faces = select_faces(reference_vision_frame, target_vision_frame)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frame)
 
 	if target_faces:
 		for target_face in target_faces:

facefusion/processors/modules/age_modifier/types.py

@@ -1,4 +1,4 @@
-from typing import Any, Literal, TypeAlias, TypedDict
+from typing import Any, List, Literal, TypeAlias, TypedDict
 
 from numpy.typing import NDArray
 
@@ -7,6 +7,7 @@ from facefusion.types import Mask, VisionFrame
 AgeModifierInputs = TypedDict('AgeModifierInputs',
 {
 	'reference_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
 	'target_vision_frame' : VisionFrame,
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask

facefusion/processors/modules/deep_swapper/core.py

@@ -411,10 +411,11 @@ def prepare_crop_mask(crop_source_mask : Mask, crop_target_mask : Mask) -> Mask:
 
 def process_frame(inputs : DeepSwapperInputs) -> ProcessorOutputs:
 	reference_vision_frame = inputs.get('reference_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
 	target_vision_frame = inputs.get('target_vision_frame')
 	temp_vision_frame = inputs.get('temp_vision_frame')
 	temp_vision_mask = inputs.get('temp_vision_mask')
-	target_faces = select_faces(reference_vision_frame, target_vision_frame)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frame)
 
 	if target_faces:
 		for target_face in target_faces:

facefusion/processors/modules/deep_swapper/types.py

@@ -1,4 +1,4 @@
-from typing import Any, TypeAlias, TypedDict
+from typing import Any, List, TypeAlias, TypedDict
 
 from numpy.typing import NDArray
 
@@ -7,6 +7,7 @@ from facefusion.types import Mask, VisionFrame
 DeepSwapperInputs = TypedDict('DeepSwapperInputs',
 {
 	'reference_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
 	'target_vision_frame' : VisionFrame,
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask

facefusion/processors/modules/expression_restorer/core.py

@@ -257,10 +257,11 @@ def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
 
 def process_frame(inputs : ExpressionRestorerInputs) -> ProcessorOutputs:
 	reference_vision_frame = inputs.get('reference_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
 	target_vision_frame = inputs.get('target_vision_frame')
 	temp_vision_frame = inputs.get('temp_vision_frame')
 	temp_vision_mask = inputs.get('temp_vision_mask')
-	target_faces = select_faces(reference_vision_frame, target_vision_frame)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frame)
 
 	if target_faces:
 		for target_face in target_faces:

facefusion/processors/modules/face_debugger/core.py

@@ -232,10 +232,11 @@ def calculate_scale(temp_vision_frame : VisionFrame) -> int:
 
 def process_frame(inputs : FaceDebuggerInputs) -> ProcessorOutputs:
 	reference_vision_frame = inputs.get('reference_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
 	target_vision_frame = inputs.get('target_vision_frame')
 	temp_vision_frame = inputs.get('temp_vision_frame')
 	temp_vision_mask = inputs.get('temp_vision_mask')
-	target_faces = select_faces(reference_vision_frame, target_vision_frame)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frame)
 
 	if target_faces:
 		for target_face in target_faces:

facefusion/processors/modules/face_debugger/types.py

@@ -1,10 +1,11 @@
-from typing import Literal, TypedDict
+from typing import List, Literal, TypedDict
 
 from facefusion.types import Mask, VisionFrame
 
 FaceDebuggerInputs = TypedDict('FaceDebuggerInputs',
 {
 	'reference_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
 	'target_vision_frame' : VisionFrame,
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask

facefusion/processors/modules/face_editor/core.py

@@ -486,10 +486,11 @@ def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
 
 def process_frame(inputs : FaceEditorInputs) -> ProcessorOutputs:
 	reference_vision_frame = inputs.get('reference_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
 	target_vision_frame = inputs.get('target_vision_frame')
 	temp_vision_frame = inputs.get('temp_vision_frame')
 	temp_vision_mask = inputs.get('temp_vision_mask')
-	target_faces = select_faces(reference_vision_frame, target_vision_frame)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frame)
 
 	if target_faces:
 		for target_face in target_faces:

facefusion/processors/modules/face_editor/types.py

@@ -1,10 +1,11 @@
-from typing import Literal, TypedDict
+from typing import List, Literal, TypedDict
 
 from facefusion.types import Mask, VisionFrame
 
 FaceEditorInputs = TypedDict('FaceEditorInputs',
 {
 	'reference_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
 	'target_vision_frame' : VisionFrame,
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask

facefusion/processors/modules/face_enhancer/core.py

@@ -413,10 +413,11 @@ def blend_paste_frame(temp_vision_frame : VisionFrame, paste_vision_frame : Visi
 
 def process_frame(inputs : FaceEnhancerInputs) -> ProcessorOutputs:
 	reference_vision_frame = inputs.get('reference_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
 	target_vision_frame = inputs.get('target_vision_frame')
 	temp_vision_frame = inputs.get('temp_vision_frame')
 	temp_vision_mask = inputs.get('temp_vision_mask')
-	target_faces = select_faces(reference_vision_frame, target_vision_frame)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frame)
 
 	if target_faces:
 		for target_face in target_faces:

facefusion/processors/modules/face_enhancer/types.py

@@ -1,4 +1,4 @@
-from typing import Any, Literal, TypeAlias, TypedDict
+from typing import Any, List, Literal, TypeAlias, TypedDict
 
 from numpy.typing import NDArray
 
@@ -7,6 +7,7 @@ from facefusion.types import Mask, VisionFrame
 FaceEnhancerInputs = TypedDict('FaceEnhancerInputs',
 {
 	'reference_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
 	'target_vision_frame' : VisionFrame,
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask

facefusion/processors/modules/face_swapper/core.py

@@ -775,7 +775,7 @@ def process_frame(inputs : FaceSwapperInputs) -> ProcessorOutputs:
 	temp_vision_frame = inputs.get('temp_vision_frame')
 	temp_vision_mask = inputs.get('temp_vision_mask')
 	source_face = extract_source_face(source_vision_frames)
-	target_faces = select_faces(reference_vision_frame, target_vision_frame)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frame)
 
 	if source_face and target_faces:
 		for target_face in target_faces:

facefusion/processors/modules/lip_syncer/core.py

@@ -282,11 +282,12 @@ def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
 
 def process_frame(inputs : LipSyncerInputs) -> ProcessorOutputs:
 	reference_vision_frame = inputs.get('reference_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
 	source_voice_frame = inputs.get('source_voice_frame')
 	target_vision_frame = inputs.get('target_vision_frame')
 	temp_vision_frame = inputs.get('temp_vision_frame')
 	temp_vision_mask = inputs.get('temp_vision_mask')
-	target_faces = select_faces(reference_vision_frame, target_vision_frame)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frame)
 
 	if target_faces:
 		for target_face in target_faces:

facefusion/processors/modules/lip_syncer/types.py

@@ -1,4 +1,4 @@
-from typing import Any, Literal, TypeAlias, TypedDict
+from typing import Any, List, Literal, TypeAlias, TypedDict
 
 from numpy.typing import NDArray
 
@@ -7,6 +7,7 @@ from facefusion.types import AudioFrame, Mask, VisionFrame
 LipSyncerInputs = TypedDict('LipSyncerInputs',
 {
 	'reference_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
 	'source_voice_frame' : AudioFrame,
 	'target_vision_frame' : VisionFrame,
 	'temp_vision_frame' : VisionFrame,

facefusion/types.py

@@ -29,9 +29,14 @@ FaceScoreSet = TypedDict('FaceScoreSet',
 	'landmarker' : Score
 })
 Embedding : TypeAlias = NDArray[numpy.float64]
-Gender = Literal['female', 'male']
+
 Age : TypeAlias = range
+Gender = Literal['female', 'male']
 Race = Literal['white', 'black', 'latino', 'asian', 'indian', 'arabic']
+
+FaceSelectorGender = Literal['auto', 'female', 'male']
+FaceSelectorRace = Literal['auto', 'white', 'black', 'latino', 'asian', 'indian', 'arabic']
+
 Face = namedtuple('Face',
 [
 	'bounding_box',
@@ -40,8 +45,8 @@ Face = namedtuple('Face',
 	'angle',
 	'embedding',
 	'embedding_norm',
-	'gender',
 	'age',
+	'gender',
 	'race'
 ])
 Language = Literal['en']
@@ -346,8 +351,8 @@ State = TypedDict('State',
 	'face_landmarker_score' : Score,
 	'face_selector_mode' : FaceSelectorMode,
 	'face_selector_order' : FaceSelectorOrder,
-	'face_selector_race' : Race,
-	'face_selector_gender' : Gender,
+	'face_selector_race' : FaceSelectorRace,
+	'face_selector_gender' : FaceSelectorGender,
 	'face_selector_age_start' : int,
 	'face_selector_age_end' : int,
 	'reference_face_position' : int,

facefusion/uis/components/face_selector.py

@@ -9,12 +9,12 @@ from facefusion import state_manager, translator
 from facefusion.common_helper import calculate_float_step, calculate_int_step
 from facefusion.face_analyser import get_many_faces
 from facefusion.face_selector import sort_and_filter_faces
-from facefusion.filesystem import is_image, is_video
-from facefusion.types import FaceSelectorMode, FaceSelectorOrder, Gender, Race, VisionFrame
+from facefusion.filesystem import filter_image_paths, is_image, is_video
+from facefusion.types import FaceSelectorGender, FaceSelectorMode, FaceSelectorOrder, FaceSelectorRace, VisionFrame
 from facefusion.uis.core import get_ui_component, get_ui_components, register_ui_component
 from facefusion.uis.types import ComponentOptions
 from facefusion.uis.ui_helper import convert_str_none
-from facefusion.vision import fit_cover_frame, read_static_image, read_video_frame
+from facefusion.vision import fit_cover_frame, read_static_image, read_static_images, read_video_frame
 
 FACE_SELECTOR_MODE_DROPDOWN : Optional[gradio.Dropdown] = None
 FACE_SELECTOR_ORDER_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -42,12 +42,14 @@ def render() -> None:
 		'elem_classes': 'box-face-selector',
 		'visible': 'reference' in state_manager.get_item('face_selector_mode')
 	}
+	source_vision_frames = read_static_images(filter_image_paths(state_manager.get_item('source_paths')))
+
 	if is_image(state_manager.get_item('target_path')):
 		target_vision_frame = read_static_image(state_manager.get_item('target_path'))
-		reference_face_gallery_options['value'] = extract_gallery_frames(target_vision_frame)
+		reference_face_gallery_options['value'] = extract_gallery_frames(source_vision_frames, target_vision_frame)
 	if is_video(state_manager.get_item('target_path')):
 		target_vision_frame = read_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
-		reference_face_gallery_options['value'] = extract_gallery_frames(target_vision_frame)
+		reference_face_gallery_options['value'] = extract_gallery_frames(source_vision_frames, target_vision_frame)
 	FACE_SELECTOR_MODE_DROPDOWN = gradio.Dropdown(
 		label = translator.get('uis.face_selector_mode_dropdown'),
 		choices = facefusion.choices.face_selector_modes,
@@ -154,12 +156,12 @@ def update_face_selector_order(face_analyser_order : FaceSelectorOrder) -> gradi
 	return update_reference_position_gallery()
 
 
-def update_face_selector_gender(face_selector_gender : Gender) -> gradio.Gallery:
+def update_face_selector_gender(face_selector_gender : FaceSelectorGender) -> gradio.Gallery:
 	state_manager.set_item('face_selector_gender', convert_str_none(face_selector_gender))
 	return update_reference_position_gallery()
 
 
-def update_face_selector_race(face_selector_race : Race) -> gradio.Gallery:
+def update_face_selector_race(face_selector_race : FaceSelectorRace) -> gradio.Gallery:
 	state_manager.set_item('face_selector_race', convert_str_none(face_selector_race))
 	return update_reference_position_gallery()
 
@@ -197,24 +199,27 @@ def clear_and_update_reference_position_gallery() -> gradio.Gallery:
 
 def update_reference_position_gallery(frame_number : int = 0) -> gradio.Gallery:
 	gallery_vision_frames = []
+	source_vision_frames = read_static_images(filter_image_paths(state_manager.get_item('source_paths')))
+
 	if is_image(state_manager.get_item('target_path')):
 		target_vision_frame = read_static_image(state_manager.get_item('target_path'))
-		gallery_vision_frames = extract_gallery_frames(target_vision_frame)
+		gallery_vision_frames = extract_gallery_frames(source_vision_frames, target_vision_frame)
 	if is_video(state_manager.get_item('target_path')):
 		target_vision_frame = read_video_frame(state_manager.get_item('target_path'), frame_number)
-		gallery_vision_frames = extract_gallery_frames(target_vision_frame)
+		gallery_vision_frames = extract_gallery_frames(source_vision_frames, target_vision_frame)
 	if gallery_vision_frames:
 		return gradio.Gallery(value = gallery_vision_frames)
 	return gradio.Gallery(value = None)
 
 
-def extract_gallery_frames(target_vision_frame : VisionFrame) -> List[VisionFrame]:
+def extract_gallery_frames(source_vision_frames : List[VisionFrame], target_vision_frame : VisionFrame) -> List[VisionFrame]:
 	gallery_vision_frames = []
-	faces = get_many_faces([ target_vision_frame ])
-	faces = sort_and_filter_faces(faces)
+	source_faces = get_many_faces(source_vision_frames)
+	target_faces = get_many_faces([ target_vision_frame ])
+	target_faces = sort_and_filter_faces(source_faces, target_faces)
 
-	for face in faces:
-		start_x, start_y, end_x, end_y = map(int, face.bounding_box)
+	for target_face in target_faces:
+		start_x, start_y, end_x, end_y = map(int, target_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)
@@ -225,4 +230,5 @@ def extract_gallery_frames(target_vision_frame : VisionFrame) -> List[VisionFram
 		crop_vision_frame = fit_cover_frame(crop_vision_frame, (128, 128))
 		crop_vision_frame = cv2.cvtColor(crop_vision_frame, cv2.COLOR_BGR2RGB)
 		gallery_vision_frames.append(crop_vision_frame)
+
 	return gallery_vision_frames

facefusion/uis/components/preview.py

@@ -231,7 +231,7 @@ def process_preview_frame(reference_vision_frame : VisionFrame, source_vision_fr
 			return numpy.hstack((temp_vision_frame, temp_vision_frame))
 
 		if preview_mode == 'face-by-face':
-			target_crop_vision_frame, output_crop_vision_frame = create_face_by_face(reference_vision_frame, target_vision_frame[:, :, :3], temp_vision_frame[:, :, :3])
+			target_crop_vision_frame, output_crop_vision_frame = create_face_by_face(reference_vision_frame, source_vision_frames, target_vision_frame[:, :, :3], temp_vision_frame[:, :, :3])
 			target_crop_vision_frame = obscure_frame(target_crop_vision_frame)
 			output_crop_vision_frame = obscure_frame(output_crop_vision_frame)
 			return numpy.hstack((target_crop_vision_frame, output_crop_vision_frame))
@@ -261,14 +261,14 @@ def process_preview_frame(reference_vision_frame : VisionFrame, source_vision_fr
 		return numpy.hstack((target_vision_frame, temp_vision_frame))
 
 	if preview_mode == 'face-by-face':
-		target_crop_vision_frame, output_crop_vision_frame = create_face_by_face(reference_vision_frame, target_vision_frame, temp_vision_frame)
+		target_crop_vision_frame, output_crop_vision_frame = create_face_by_face(reference_vision_frame, source_vision_frames, target_vision_frame, temp_vision_frame)
 		return numpy.hstack((target_crop_vision_frame, output_crop_vision_frame))
 
 	return temp_vision_frame
 
 
-def create_face_by_face(reference_vision_frame : VisionFrame, target_vision_frame : VisionFrame, temp_vision_frame : VisionFrame) -> Tuple[VisionFrame, VisionFrame]:
-	target_faces = select_faces(reference_vision_frame[:, :, :3], target_vision_frame[:, :, :3])
+def create_face_by_face(reference_vision_frame : VisionFrame, source_vision_frames : List[VisionFrame], target_vision_frame : VisionFrame, temp_vision_frame : VisionFrame) -> Tuple[VisionFrame, VisionFrame]:
+	target_faces = select_faces(reference_vision_frame[:, :, :3], source_vision_frames, target_vision_frame[:, :, :3])
 	target_face = get_one_face(target_faces)
 
 	if target_face: