Hotfix memory leak (#1213)

* fix potential memory leak

* siwtch to queue

* fix lint

* spacing

* cosmetics

.github/workflows/ci.yml

@@ -43,7 +43,7 @@ jobs:
   - name: Checkout
     uses: actions/checkout@v4
   - name: Set up FFmpeg
-    uses: FedericoCarboni/setup-ffmpeg@v3
+    uses: AnimMouse/setup-ffmpeg@v1
   - name: Set up Python 3.12
     uses: actions/setup-python@v5
     with:

facefusion.ini

@@ -1,7 +1,3 @@
-[workflow]
-workflow_mode =
-workflow_strategy =
-
 [paths]
 temp_path =
 jobs_path =
@@ -72,6 +68,10 @@ output_video_quality =
 output_video_scale =
 output_video_fps =
 
+[workflow]
+workflow_mode =
+workflow_strategy =
+
 [processors]
 processors =
 age_modifier_model =

facefusion/args.py

@@ -9,8 +9,6 @@ from facefusion.vision import detect_video_fps
 
 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('command', args.get('command'))
-	apply_state_item('workflow_mode', args.get('workflow_mode'))
-	apply_state_item('workflow_strategy', args.get('workflow_strategy'))
 	apply_state_item('temp_path', args.get('temp_path'))
 	apply_state_item('jobs_path', args.get('jobs_path'))
 	apply_state_item('source_paths', args.get('source_paths'))
@@ -63,6 +61,8 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 		output_video_fps = normalize_fps(args.get('output_video_fps')) or detect_video_fps(args.get('target_path'))
 		apply_state_item('output_video_fps', output_video_fps)
 
+	apply_state_item('workflow_mode', args.get('workflow_mode'))
+	apply_state_item('workflow_strategy', args.get('workflow_strategy'))
 	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
 	apply_state_item('processors', args.get('processors'))
 

facefusion/content_analyser.py

@@ -9,7 +9,7 @@ from facefusion.download import conditional_download_hashes, conditional_downloa
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
 from facefusion.types import Detection, DownloadScope, DownloadSet, Fps, InferencePool, ModelSet, VisionFrame
-from facefusion.vision import detect_video_fps, fit_contain_frame, read_image
+from facefusion.vision import detect_video_fps, fit_contain_frame, is_vision_frame, read_image
 
 STREAM_COUNTER = 0
 
@@ -172,7 +172,7 @@ def analyse_video(video_path : str, trim_frame_start : int, trim_frame_end : int
 			vision_frame = video_manager.read_video_frame(video_reader)
 
 			if frame_number % int(video_fps) == 0:
-				if numpy.any(vision_frame):
+				if is_vision_frame(vision_frame):
 					total += 1
 
 					if analyse_frame(vision_frame):

facefusion/core.py

@@ -100,7 +100,7 @@ def pre_check() -> bool:
 def common_pre_check() -> bool:
 	content_analyser_content = inspect.getsource(content_analyser).encode()
 
-	return hash_helper.create_hash(content_analyser_content) == '0922c180'
+	return hash_helper.create_hash(content_analyser_content) == '3c6ce25e'
 
 
 def processors_pre_check() -> bool:
@@ -315,16 +315,19 @@ def conditional_process() -> ErrorCode:
 	if state_manager.get_item('workflow_mode') == 'auto':
 		state_manager.set_item('workflow_mode', detect_workflow_mode())
 
-	for processor_module in get_processors_modules(state_manager.get_item('processors')):
+	if state_manager.get_item('workflow_mode') == detect_workflow_mode():
-		if not processor_module.pre_process('output'):
+		for processor_module in get_processors_modules(state_manager.get_item('processors')):
-			return 2
+			if not processor_module.pre_process('output'):
+				return 2
 
-	if state_manager.get_item('workflow_mode') == 'image-to-image':
+		if state_manager.get_item('workflow_mode') == 'image-to-image':
-		return image_to_image.process(start_time)
+			return image_to_image.process(start_time)
-	if state_manager.get_item('workflow_mode') == 'image-to-video':
+		if state_manager.get_item('workflow_mode') == 'image-to-video':
-		return image_to_video.process(start_time)
+			return image_to_video.process(start_time)
 
-	return 0
+		return 0
+
+	return 2
 
 
 def detect_workflow_mode() -> WorkflowMode:

facefusion/face_creator.py

@@ -10,6 +10,7 @@ from facefusion.face_helper import apply_nms, average_points, convert_to_face_la
 from facefusion.face_landmarker import detect_face_landmark, estimate_face_landmark_68_5
 from facefusion.face_recognizer import calculate_face_embedding
 from facefusion.types import BoundingBox, Face, FaceLandmark5, FaceLandmarkSet, FaceScoreSet, Score, VisionFrame
+from facefusion.vision import is_vision_frame
 
 
 def create_faces(vision_frame : VisionFrame, bounding_boxes : List[BoundingBox], face_scores : List[Score], face_landmarks_5 : List[FaceLandmark5]) -> List[Face]:
@@ -73,7 +74,7 @@ def get_many_faces(vision_frames : List[VisionFrame]) -> List[Face]:
 	many_faces : List[Face] = []
 
 	for vision_frame in vision_frames:
-		if numpy.any(vision_frame):
+		if is_vision_frame(vision_frame):
 			all_bounding_boxes = []
 			all_face_scores = []
 			all_face_landmarks_5 = []

facefusion/face_store.py

@@ -1,17 +1,16 @@
 import threading
 from typing import List, Optional
 
-import numpy
-
 from facefusion.hash_helper import create_hash
 from facefusion.types import Face, FaceStore, VisionFrame
+from facefusion.vision import is_vision_frame
 
 FACE_STORE : FaceStore = {}
 
 
 def get_faces(vision_frame : VisionFrame) -> Optional[List[Face]]:
-	if numpy.any(vision_frame):
+	if is_vision_frame(vision_frame):
-		vision_hash = create_hash(vision_frame.data)
+		vision_hash = create_hash(vision_frame.tobytes())
 
 		if FACE_STORE.get(vision_hash):
 			return FACE_STORE.get(vision_hash).get('faces')
@@ -20,8 +19,8 @@ def get_faces(vision_frame : VisionFrame) -> Optional[List[Face]]:
 
 
 def set_faces(vision_frame : VisionFrame, faces : List[Face]) -> None:
-	if numpy.any(vision_frame):
+	if is_vision_frame(vision_frame):
-		vision_hash = create_hash(vision_frame.data)
+		vision_hash = create_hash(vision_frame.tobytes())
 		FACE_STORE.setdefault(vision_hash,
 		{
 			'lock': threading.Lock()
@@ -29,8 +28,8 @@ def set_faces(vision_frame : VisionFrame, faces : List[Face]) -> None:
 
 
 def resolve_lock(vision_frame : VisionFrame) -> threading.Lock:
-	if numpy.any(vision_frame):
+	if is_vision_frame(vision_frame):
-		vision_hash = create_hash(vision_frame.data)
+		vision_hash = create_hash(vision_frame.tobytes())
 		return FACE_STORE.setdefault(vision_hash,
 		{
 			'lock': threading.Lock()

facefusion/ffmpeg.py

@@ -66,7 +66,7 @@ def run_ffmpeg(commands : List[Command]) -> subprocess.Popen[bytes]:
 
 def open_ffmpeg(commands : List[Command]) -> subprocess.Popen[bytes]:
 	commands = ffmpeg_builder.run(commands)
-	return subprocess.Popen(commands, stdin = subprocess.PIPE, stdout = subprocess.PIPE, pipesize = 1024 * 1024)
+	return subprocess.Popen(commands, stdin = subprocess.PIPE, stderr = subprocess.DEVNULL, stdout = subprocess.PIPE)
 
 
 def create_video_reader(video_path : str, frame_number : int, video_metadata : VideoReaderMetadata) -> subprocess.Popen[bytes]:

facefusion/installer.py

@@ -28,8 +28,8 @@ if is_windows():
 	ONNXRUNTIME_SET['directml'] = ('onnxruntime-directml', '1.24.4')
 	ONNXRUNTIME_SET['qnn'] = ('onnxruntime-qnn', '1.24.4')
 if is_linux():
-	ONNXRUNTIME_SET['migraphx'] = ('onnxruntime-migraphx', '1.25.0')
+	ONNXRUNTIME_SET['migraphx'] = ('onnxruntime-migraphx', '1.26.0')
-	ONNXRUNTIME_SET['rocm'] = ('onnxruntime-rocm', '1.22.2.post1')
+	ONNXRUNTIME_SET['rocm'] = ('onnxruntime-rocm', '1.22.2.post3')
 
 
 def cli() -> None:

facefusion/locales.py

@@ -98,8 +98,6 @@ LOCALES : Locales =\
 		{
 			'install_dependency': 'choose the variant of {dependency} to install',
 			'skip_conda': 'skip the conda environment check',
-			'workflow_mode': 'choose the workflow mode',
-			'workflow_strategy': 'choose the workflow strategy',
 			'config_path': 'choose the config file to override defaults',
 			'temp_path': 'specify the directory for the temporary resources',
 			'jobs_path': 'specify the directory to store jobs',
@@ -136,7 +134,7 @@ LOCALES : Locales =\
 			'voice_extractor_model': 'choose the model responsible for extracting the voices',
 			'trim_frame_start': 'specify the starting frame of the target video',
 			'trim_frame_end': 'specify the ending frame of the target video',
-			'temp_frame_format': 'specify the temporary resources format',
+			'temp_frame_format': 'specify the temporary frame format',
 			'temp_pixel_format': 'specify the temporary pixel format',
 			'target_frame_amount': 'specify the amount of target frames forwarded to the processor',
 			'output_image_quality': 'specify the image quality which translates to the image compression',
@@ -149,6 +147,8 @@ LOCALES : Locales =\
 			'output_video_quality': 'specify the video quality which translates to the video compression',
 			'output_video_scale': 'specify the video scale based on the target video',
 			'output_video_fps': 'specify the video fps based on the target video',
+			'workflow_mode': 'detect or enforce the workflow mode',
+			'workflow_strategy': 'process the temporary frames in memory or on disk',
 			'processors': 'load a single or multiple processors (choices: {choices}, ...)',
 			'background-remover-model': 'choose the model responsible for removing the background',
 			'background-remover-color': 'apply red, green blue and alpha values of the background',
@@ -204,7 +204,6 @@ LOCALES : Locales =\
 			'clear_button': 'CLEAR',
 			'download_providers_checkbox_group': 'DOWNLOAD PROVIDERS',
 			'execution_providers_checkbox_group': 'EXECUTION PROVIDERS',
-			'workflow_mode_dropdown': 'WORKFLOW MODE',
 			'workflow_strategy_dropdown': 'WORKFLOW STRATEGY',
 			'execution_thread_count_slider': 'EXECUTION THREAD COUNT',
 			'face_detector_angles_checkbox_group': 'FACE DETECTOR ANGLES',

facefusion/metadata.py

@@ -4,7 +4,7 @@ METADATA =\
 {
 	'name': 'FaceFusion',
 	'description': 'Industry leading face manipulation platform',
-	'version': 'NEXT',
+	'version': '3.8.0',
 	'license': 'OpenRAIL-AS',
 	'author': 'Henry Ruhs',
 	'url': 'https://facefusion.io'

facefusion/processors/modules/frame_enhancer/types.py

@@ -9,4 +9,4 @@ FrameEnhancerInputs = TypedDict('FrameEnhancerInputs',
 	'temp_vision_mask' : Mask
 })
 
-FrameEnhancerModel = Literal['clear_reality_x4', 'face_dat_x4', 'lsdir_x4', 'nomos8k_sc_x4', 'real_esrgan_x2', 'real_esrgan_x2_fp16', 'real_esrgan_x4', 'real_esrgan_x4_fp16', 'real_esrgan_x8', 'real_esrgan_x8_fp16', 'real_hatgan_x4', 'real_web_photo_x4', 'realistic_rescaler_x4', 'remacri_x4', 'siax_x4', 'span_kendata_x4', 'swin2_sr_x4', 'tghq_face_x8', 'ultra_sharp_x4', 'ultra_sharp_2_x4']
+FrameEnhancerModel = Literal['clear_reality_x4', 'face_dat_x4', 'nomos8k_sc_x4', 'real_esrgan_x2', 'real_esrgan_x2_fp16', 'real_esrgan_x4', 'real_esrgan_x4_fp16', 'real_esrgan_x8', 'real_esrgan_x8_fp16', 'real_hatgan_x4', 'real_web_photo_x4', 'realistic_rescaler_x4', 'remacri_x4', 'siax_x4', 'span_kendata_x4', 'swin2_sr_x4', 'tghq_face_x8', 'ultra_sharp_x4', 'ultra_sharp_2_x4']

facefusion/program.py

@@ -21,15 +21,6 @@ def create_help_formatter_large(prog : str) -> HelpFormatter:
 	return HelpFormatter(prog, max_help_position = 300)
 
 
-def create_workflow_program() -> ArgumentParser:
-	program = ArgumentParser(add_help = False)
-	group_workflow = program.add_argument_group('workflow')
-	group_workflow.add_argument('--workflow-mode', help = translator.get('help.workflow_mode'), default = config.get_str_value('workflow', 'workflow_mode', 'auto'), choices = facefusion.choices.workflow_modes)
-	group_workflow.add_argument('--workflow-strategy', help = translator.get('help.workflow_strategy'), default = config.get_str_value('workflow', 'workflow_strategy', 'stream'), choices = facefusion.choices.workflow_strategies)
-	job_store.register_step_keys([ 'workflow_mode', 'workflow_strategy' ])
-	return program
-
-
 def create_config_path_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_paths = program.add_argument_group('paths')
@@ -209,6 +200,15 @@ def create_output_creation_program() -> ArgumentParser:
 	return program
 
 
+def create_workflow_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_workflow = program.add_argument_group('workflow')
+	group_workflow.add_argument('--workflow-mode', help = translator.get('help.workflow_mode'), default = config.get_str_value('workflow', 'workflow_mode', 'auto'), choices = facefusion.choices.workflow_modes)
+	group_workflow.add_argument('--workflow-strategy', help = translator.get('help.workflow_strategy'), default = config.get_str_value('workflow', 'workflow_strategy', 'memory'), choices = facefusion.choices.workflow_strategies)
+	job_store.register_step_keys([ 'workflow_mode', 'workflow_strategy' ])
+	return program
+
+
 def create_processors_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
@@ -309,7 +309,7 @@ def create_step_index_program() -> ArgumentParser:
 
 
 def collect_step_program() -> ArgumentParser:
-	return ArgumentParser(parents = [ create_workflow_program(), create_face_detector_program(), create_face_landmarker_program(), create_face_selector_program(), create_face_tracker_program(), create_face_masker_program(), create_voice_extractor_program(), create_frame_extraction_program(), create_frame_distribution_program(), create_output_creation_program(), create_processors_program() ], add_help = False)
+	return ArgumentParser(parents = [ create_face_detector_program(), create_face_landmarker_program(), create_face_selector_program(), create_face_tracker_program(), create_face_masker_program(), create_voice_extractor_program(), create_frame_extraction_program(), create_frame_distribution_program(), create_output_creation_program(), create_workflow_program(), create_processors_program() ], add_help = False)
 
 
 def collect_job_program() -> ArgumentParser:

facefusion/streamer.py

@@ -5,7 +5,6 @@ from concurrent.futures import ThreadPoolExecutor
 from typing import Deque, Iterator, List
 
 import cv2
-import numpy
 from tqdm import tqdm
 
 from facefusion import ffmpeg_builder, logger, state_manager, translator
@@ -15,7 +14,7 @@ from facefusion.ffmpeg import open_ffmpeg
 from facefusion.filesystem import is_directory
 from facefusion.processors.core import get_processors_modules
 from facefusion.types import Fps, StreamMode, VisionFrame
-from facefusion.vision import extract_vision_mask, read_static_images
+from facefusion.vision import extract_vision_mask, is_vision_frame, read_static_images
 
 
 def multi_process_capture(camera_capture : cv2.VideoCapture, camera_fps : Fps) -> Iterator[VisionFrame]:
@@ -31,7 +30,7 @@ def multi_process_capture(camera_capture : cv2.VideoCapture, camera_fps : Fps) -
 				if analyse_stream(capture_vision_frame, camera_fps):
 					camera_capture.release()
 
-				if numpy.any(capture_vision_frame):
+				if is_vision_frame(capture_vision_frame):
 					future = executor.submit(process_stream_frame, source_vision_frames, capture_vision_frame)
 					futures.append(future)
 

facefusion/types.py

@@ -65,7 +65,7 @@ Locales : TypeAlias = Dict[Language, Dict[str, Any]]
 LocalePoolSet : TypeAlias = Dict[str, Locales]
 
 WorkflowMode = Literal['auto', 'image-to-image', 'image-to-video']
-WorkflowStrategy = Literal['disk', 'stream']
+WorkflowStrategy = Literal['disk', 'memory']
 
 CameraCaptureSet : TypeAlias = Dict[str, cv2.VideoCapture]
 CameraPoolSet = TypedDict('CameraPoolSet',
@@ -322,8 +322,6 @@ JobSet : TypeAlias = Dict[str, Job]
 StateKey = Literal\
 [
 	'command',
-	'workflow_mode',
-	'workflow_strategy',
 	'config_path',
 	'temp_path',
 	'jobs_path',
@@ -378,6 +376,8 @@ StateKey = Literal\
 	'output_video_quality',
 	'output_video_scale',
 	'output_video_fps',
+	'workflow_mode',
+	'workflow_strategy',
 	'processors',
 	'open_browser',
 	'ui_layouts',
@@ -395,8 +395,6 @@ StateKey = Literal\
 State = TypedDict('State',
 {
 	'command' : str,
-	'workflow_mode' : WorkflowMode,
-	'workflow_strategy' : WorkflowStrategy,
 	'config_path' : str,
 	'temp_path' : str,
 	'jobs_path' : str,
@@ -451,6 +449,8 @@ State = TypedDict('State',
 	'output_video_quality' : int,
 	'output_video_scale' : Scale,
 	'output_video_fps' : float,
+	'workflow_mode' : WorkflowMode,
+	'workflow_strategy' : WorkflowStrategy,
 	'processors' : List[str],
 	'open_browser' : bool,
 	'ui_layouts' : List[str],

facefusion/uis/components/preview.py

@@ -18,7 +18,7 @@ from facefusion.types import AudioFrame, Face, Mask, VisionFrame
 from facefusion.uis import choices as uis_choices
 from facefusion.uis.core import get_ui_component, get_ui_components, register_ui_component
 from facefusion.uis.types import ComponentOptions, PreviewMode
-from facefusion.vision import detect_frame_orientation, extract_vision_mask, fit_cover_frame, merge_vision_mask, obscure_frame, read_static_image, read_static_images, read_video_frame, restrict_frame, select_video_frames, unpack_resolution
+from facefusion.vision import detect_frame_orientation, extract_vision_mask, fit_cover_frame, is_vision_frame, merge_vision_mask, obscure_frame, read_static_image, read_static_images, read_video_frame, restrict_frame, select_video_frames, unpack_resolution
 
 PREVIEW_IMAGE : Optional[gradio.Image] = None
 
@@ -277,7 +277,7 @@ def create_face_by_face(reference_vision_frame : VisionFrame, source_vision_fram
 		target_crop_vision_frame = extract_crop_frame(target_vision_frame, target_face)
 		output_crop_vision_frame = extract_crop_frame(temp_vision_frame, target_face)
 
-		if numpy.any(target_crop_vision_frame) and numpy.any(output_crop_vision_frame):
+		if is_vision_frame(target_crop_vision_frame) and is_vision_frame(output_crop_vision_frame):
 			target_crop_dimension = min(target_crop_vision_frame.shape[:2])
 			target_crop_vision_frame = fit_cover_frame(target_crop_vision_frame, (target_crop_dimension, target_crop_dimension))
 			output_crop_vision_frame = fit_cover_frame(output_crop_vision_frame, (target_crop_dimension, target_crop_dimension))

facefusion/uis/components/workflow.py

@@ -4,21 +4,14 @@ import gradio
 
 import facefusion.choices
 from facefusion import state_manager, translator
-from facefusion.types import WorkflowMode, WorkflowStrategy
+from facefusion.types import WorkflowStrategy
 
-WORKFLOW_MODE_DROPDOWN : Optional[gradio.Dropdown] = None
 WORKFLOW_STRATEGY_DROPDOWN : Optional[gradio.Dropdown] = None
 
 
 def render() -> None:
-	global WORKFLOW_MODE_DROPDOWN
 	global WORKFLOW_STRATEGY_DROPDOWN
 
-	WORKFLOW_MODE_DROPDOWN = gradio.Dropdown(
-		label = translator.get('uis.workflow_mode_dropdown'),
-		choices = facefusion.choices.workflow_modes,
-		value = state_manager.get_item('workflow_mode')
-	)
 	WORKFLOW_STRATEGY_DROPDOWN = gradio.Dropdown(
 		label = translator.get('uis.workflow_strategy_dropdown'),
 		choices = facefusion.choices.workflow_strategies,
@@ -27,13 +20,8 @@ def render() -> None:
 
 
 def listen() -> None:
-	WORKFLOW_MODE_DROPDOWN.change(update_workflow_mode, inputs = WORKFLOW_MODE_DROPDOWN)
 	WORKFLOW_STRATEGY_DROPDOWN.change(update_workflow_strategy, inputs = WORKFLOW_STRATEGY_DROPDOWN)
 
 
-def update_workflow_mode(workflow_mode : WorkflowMode) -> None:
-	state_manager.set_item('workflow_mode', workflow_mode)
-
-
 def update_workflow_strategy(workflow_strategy : WorkflowStrategy) -> None:
 	state_manager.set_item('workflow_strategy', workflow_strategy)

facefusion/workflows/image_to_video.py

@@ -3,7 +3,7 @@ from functools import partial
 from facefusion import process_manager, state_manager
 from facefusion.types import ErrorCode
 from facefusion.workflows.core import clear, setup
-from facefusion.workflows.to_video import analyse_video, extract_frames, finalize_video, merge_frames, process_disk_frames, process_stream_frames, restore_audio
+from facefusion.workflows.to_video import analyse_video, extract_frames, finalize_video, merge_frames, process_disk_frames, process_memory_frames, restore_audio
 
 
 def process(start_time : float) -> ErrorCode:
@@ -22,8 +22,8 @@ def process(start_time : float) -> ErrorCode:
 			merge_frames
 		])
 
-	if state_manager.get_item('workflow_strategy') == 'stream':
+	if state_manager.get_item('workflow_strategy') == 'memory':
-		tasks.append(process_stream_frames)
+		tasks.append(process_memory_frames)
 
 	tasks.extend(
 	[

facefusion/workflows/to_video.py

@@ -1,5 +1,6 @@
-from concurrent.futures import ThreadPoolExecutor, as_completed
+from collections import deque
-from typing import Tuple
+from concurrent.futures import Future, ThreadPoolExecutor
+from typing import Deque
 
 import cv2
 import numpy
@@ -58,18 +59,23 @@ def process_disk_frames() -> ErrorCode:
 			read_static_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
 
 			with ThreadPoolExecutor(max_workers = state_manager.get_item('execution_thread_count')) as executor:
-				futures = []
+				futures : Deque[Future[bool]] = deque()
 
 				for frame_number, temp_frame_path in temp_frame_set.items():
 					future = executor.submit(process_disk_frame, temp_frame_path, frame_number)
 					futures.append(future)
 
-				for future in as_completed(futures):
+				while futures:
+					future = futures.popleft()
+
 					if is_process_stopping():
+
 						for pending_future in futures:
 							pending_future.cancel()
 
-					if not future.cancelled():
+						futures.clear()
+
+					else:
 						future.result()
 						progress.update()
 
@@ -84,7 +90,7 @@ def process_disk_frames() -> ErrorCode:
 	return 0
 
 
-def process_stream_frame(frame_number : int, temp_video_resolution : Resolution) -> Tuple[int, VisionFrame]:
+def process_memory_frame(frame_number : int, temp_video_resolution : Resolution) -> VisionFrame:
 	target_vision_frames = select_video_frames(state_manager.get_item('target_path'), frame_number, state_manager.get_item('target_frame_amount'))
 	target_vision_frame = get_middle(target_vision_frames)
 	temp_vision_frame = target_vision_frame.copy()
@@ -100,10 +106,10 @@ def process_stream_frame(frame_number : int, temp_video_resolution : Resolution)
 	if state_manager.get_item('temp_pixel_format') == 'bgr24':
 		temp_vision_frame = temp_vision_frame[:, :, :3]
 
-	return frame_number, numpy.ascontiguousarray(temp_vision_frame)
+	return numpy.ascontiguousarray(temp_vision_frame)
 
 
-def process_stream_frames() -> ErrorCode:
+def process_memory_frames() -> ErrorCode:
 	trim_frame_start, trim_frame_end = restrict_trim_frame(state_manager.get_item('target_path'), state_manager.get_item('trim_frame_start'), state_manager.get_item('trim_frame_end'))
 	output_video_resolution = scale_resolution(detect_video_resolution(state_manager.get_item('target_path')), state_manager.get_item('output_video_scale'))
 	temp_video_resolution = restrict_video_resolution(state_manager.get_item('target_path'), output_video_resolution)
@@ -119,20 +125,24 @@ def process_stream_frames() -> ErrorCode:
 			read_static_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
 
 			with ThreadPoolExecutor(max_workers = state_manager.get_item('execution_thread_count')) as executor:
-				futures = []
+				futures : Deque[Future[VisionFrame]] = deque()
 
 				for frame_number in temp_frame_range:
-					future = executor.submit(process_stream_frame, frame_number, temp_video_resolution)
+					future = executor.submit(process_memory_frame, frame_number, temp_video_resolution)
 					futures.append(future)
 
-				for future in futures:
+				while futures:
+					future = futures.popleft()
+
 					if is_process_stopping():
+
 						for pending_future in futures:
 							pending_future.cancel()
 
-					if not future.cancelled():
+						futures.clear()
-						_, temp_vision_frame = future.result()
+
-						video_manager.write_video_frame(video_writer, temp_vision_frame)
+					else:
+						video_manager.write_video_frame(video_writer, future.result())
 						progress.update()
 
 		if not video_manager.close_video_writer(video_writer):

requirements.txt

@@ -1,8 +1,8 @@
 gradio-rangeslider==0.0.8
 gradio==5.50.0
-numpy==2.2.1
+numpy==2.4.6
-onnx==1.21.0
+onnx==1.22.0
 onnxruntime==1.26.0
-opencv-python==4.13.0.92
+opencv-python-headless==5.0.0.93
-tqdm==4.67.3
+tqdm==4.70.0
-scipy==1.17.1
+scipy==1.18.0

tests/test_video_manager.py

@@ -50,34 +50,35 @@ def test_get_reader() -> None:
 	assert video_metadata.get('resolution') == (426, 226)
 	assert video_metadata.get('fps') == 25.0
 	assert video_metadata.get('frame_total') == 270
+
 	assert get_reader(get_test_example_file('target-240p-25fps.mp4'), 'read_video_frame') is video_reader
 	assert not get_reader(get_test_example_file('target-240p-25fps.mp4'), 'select_video_frames').get('id') == video_reader.get('id')
 
 
 def test_conditional_seek_video_reader() -> None:
 	video_reader = get_reader(get_test_example_file('target-240p-25fps.mp4'), 'read_video_frame')
-	sequential_frames = {}
+	video_frames = {}
 
 	for frame_number in range(30):
-		sequential_frames[frame_number] = read_video_frame(video_reader)
+		video_frames[frame_number] = read_video_frame(video_reader)
 
 	for frame_number in [ 5, 17, 29 ]:
 		conditional_seek_video_reader(video_reader, frame_number)
 
-		assert numpy.array_equal(read_video_frame(video_reader), sequential_frames.get(frame_number)) is True
+		assert numpy.array_equal(read_video_frame(video_reader), video_frames.get(frame_number)) is True
 
 
 def test_seek_video_reader() -> None:
 	video_reader = get_reader(get_test_example_file('target-240p-25fps.mp4'), 'read_video_frame')
-	sequential_frames = {}
+	video_frames = {}
 
 	for frame_number in range(30):
-		sequential_frames[frame_number] = read_video_frame(video_reader)
+		video_frames[frame_number] = read_video_frame(video_reader)
 
 	for frame_number in [ 5, 17, 29 ]:
 		seek_video_reader(video_reader, frame_number)
 
-		assert numpy.array_equal(read_video_frame(video_reader), sequential_frames.get(frame_number)) is True
+		assert numpy.array_equal(read_video_frame(video_reader), video_frames.get(frame_number)) is True
 
 
 def test_drain_video_reader() -> None:
@@ -133,6 +134,7 @@ def test_collect_video_frames() -> None:
 
 def test_close_video_reader() -> None:
 	video_reader = get_reader(get_test_example_file('target-240p-25fps.mp4'), 'select_video_frames')
+
 	read_video_frames(video_reader, 0, 4)
 	close_video_reader(video_reader)
 
@@ -176,6 +178,7 @@ def test_close_video_writer() -> None:
 	create_temp_directory(target_path)
 	video_reader = get_reader(target_path, 'read_video_frame')
 	video_writer = get_writer(target_path, 30.0, (426, 226), (426, 226), 30.0)
+
 	write_video_frame(video_writer, read_video_frame(video_reader))
 
 	assert close_video_writer(video_writer) is True
@@ -186,6 +189,7 @@ def test_clear_video_pool() -> None:
 	create_temp_directory(target_path)
 	video_reader = get_reader(target_path, 'select_video_frames')
 	video_writer = get_writer(target_path, 25.0, (426, 226), (426, 226), 25.0)
+
 	read_video_frames(video_reader, 0, 4)
 	write_video_frame(video_writer, read_video_frame(video_reader))
 	clear_video_pool()