add groups to capabilities

keep v4 style
merge master into v4 - post adjustments
2026-07-28 12:59:03 +02:00 · 2026-07-02 20:39:09 +02:00 · 2026-07-01 17:21:33 +02:00 · 2026-07-01 17:10:31 +02:00 · 2026-07-01 16:02:19 +02:00 · 2026-07-01 14:44:53 +02:00
233 changed files with 10386 additions and 6156 deletions
@@ -33,8 +33,11 @@ jobs:
    uses: actions/setup-python@v5
    with:
     python-version: '3.12'
-  - run: python install.py --onnxruntime default --skip-conda
+  - run: python install.py default --skip-conda
  - run: pip install pytest
+  - run: pip install pytest-mock
+  - run: pip install httpx
+  - run: pip install python-multipart
  - run: pytest
 report:
  needs: test
@@ -48,10 +51,13 @@ jobs:
    uses: actions/setup-python@v5
    with:
     python-version: '3.12'
-  - run: python install.py --onnxruntime default --skip-conda
+  - run: python install.py default --skip-conda
  - run: pip install coveralls
  - run: pip install pytest
  - run: pip install pytest-cov
+  - run: pip install pytest-mock
+  - run: pip install httpx
+  - run: pip install python-multipart
  - run: pytest tests --cov facefusion
  - run: coveralls --service github
    env:
@@ -4,4 +4,5 @@ __pycache__
 .caches
 .idea
 .jobs
+.libraries
 .vscode
@@ -8,12 +8,6 @@ FaceFusion
 ![License](https://img.shields.io/badge/license-OpenRAIL--AS-green)


-Preview
-------
-
-![Preview](https://raw.githubusercontent.com/facefusion/facefusion/master/.github/preview.png?sanitize=true)
-
-
 Installation
 ------------

@@ -34,10 +28,10 @@ options:

 commands:
    run                                           run the program
-    headless-run                                  run the program in headless mode
    batch-run                                     run the program in batch mode
    force-download                                force automate downloads and exit
    benchmark                                     benchmark the program
+    api                                           start the API server
    job-list                                      list jobs by status
    job-create                                    create a drafted job
    job-submit                                    submit a drafted job to become a queued job
@@ -1,3 +1,6 @@
+[workflow]
+workflow =
+
 [paths]
 temp_path =
 jobs_path =
@@ -32,6 +35,9 @@ reference_face_position =
 reference_face_distance =
 reference_frame_number =

+[face_tracker]
+face_tracker_score =
+
 [face_masker]
 face_occluder_model =
 face_parser_model =
@@ -48,7 +54,9 @@ voice_extractor_model =
 trim_frame_start =
 trim_frame_end =
 temp_frame_format =
-keep_temp =
+
+[frame_distribution]
+target_frame_amount =

 [output_creation]
 output_image_quality =
@@ -56,6 +64,7 @@ output_image_scale =
 output_audio_encoder =
 output_audio_quality =
 output_audio_volume =
+output_audio_fps =
 output_video_encoder =
 output_video_preset =
 output_video_quality =
@@ -104,11 +113,6 @@ frame_enhancer_blend =
 lip_syncer_model =
 lip_syncer_weight =

-[uis]
-open_browser =
-ui_layouts =
-ui_workflow =
-
 [download]
 download_providers =
 download_scope =
@@ -118,6 +122,11 @@ benchmark_mode =
 benchmark_resolutions =
 benchmark_cycle_count =

+[api]
+api_host =
+api_port =
+api_security_strategy =
+
 [execution]
 execution_device_ids =
 execution_providers =
@@ -125,7 +134,6 @@ execution_thread_count =

 [memory]
 video_memory_strategy =
-system_memory_limit =

 [misc]
 log_level =
@@ -0,0 +1,14 @@
+from typing import Optional
+
+from starlette.datastructures import Headers
+from starlette.types import Scope
+
+
+def get_sec_websocket_protocol(scope : Scope) -> Optional[str]:
+	protocol_header = Headers(scope = scope).get('Sec-WebSocket-Protocol')
+
+	if protocol_header:
+		protocol, _, _ = protocol_header.partition(',')
+		return protocol.strip()
+
+	return None
@@ -0,0 +1,91 @@
+import asyncio
+import os
+import uuid
+from typing import List, Optional
+
+from starlette.datastructures import UploadFile
+
+import facefusion.choices
+from facefusion import ffmpeg, process_manager, state_manager
+from facefusion.filesystem import create_directory, get_file_extension, get_file_format, is_audio, is_image, is_video
+from facefusion.types import ImageMetadata, MediaType
+from facefusion.vision import detect_image_resolution
+
+
+def extract_image_metadata(file_path : str) -> ImageMetadata:
+	metadata : ImageMetadata =\
+	{
+		'resolution': detect_image_resolution(file_path)
+	}
+	return metadata
+
+
+def detect_media_type_by_path(file_path : str) -> Optional[MediaType]:
+	if is_audio(file_path):
+		return 'audio'
+	if is_image(file_path):
+		return 'image'
+	if is_video(file_path):
+		return 'video'
+	return None
+
+
+def detect_media_type_by_format(file_format : str) -> Optional[MediaType]:
+	if file_format in facefusion.choices.audio_set:
+		return 'audio'
+	if file_format in facefusion.choices.image_set:
+		return 'image'
+	if file_format in facefusion.choices.video_set:
+		return 'video'
+	return None
+
+
+def validate_asset_files(upload_files : List[UploadFile]) -> bool:
+	available_encoder_set = ffmpeg.get_static_available_encoder_set()
+
+	for upload_file in upload_files:
+		file_format = get_file_format(upload_file.filename)
+		media_type = detect_media_type_by_format(file_format)
+
+		if media_type == 'audio' and facefusion.choices.audio_set.get(file_format) not in available_encoder_set.get('audio'): #type:ignore[call-overload]
+			return False
+
+		if media_type == 'image' and facefusion.choices.image_set.get(file_format) not in available_encoder_set.get('image'): #type:ignore[call-overload]
+			return False
+
+		if media_type == 'video' and facefusion.choices.video_set.get(file_format) not in available_encoder_set.get('video'): #type:ignore[call-overload]
+			return False
+
+	return True
+
+
+async def save_asset_files(upload_files : List[UploadFile]) -> List[str]:
+	asset_paths : List[str] = []
+	api_security_strategy = state_manager.get_item('api_security_strategy')
+
+	for upload_file in upload_files:
+		file_format = get_file_format(upload_file.filename)
+		file_extension = get_file_extension(upload_file.filename)
+		media_type = detect_media_type_by_format(file_format)
+		temp_path = state_manager.get_temp_path()
+
+		create_directory(temp_path)
+
+		asset_file_name = uuid.uuid4().hex
+		asset_path = os.path.join(temp_path, asset_file_name + file_extension)
+		file_content = await upload_file.read()
+
+		process_manager.start()
+
+		if media_type == 'audio' and await asyncio.to_thread(ffmpeg.sanitize_audio, file_content, asset_path, api_security_strategy):
+			asset_paths.append(asset_path)
+
+		if media_type == 'image' and await asyncio.to_thread(ffmpeg.sanitize_image, file_content, asset_path):
+			asset_paths.append(asset_path)
+
+		if media_type == 'video' and await asyncio.to_thread(ffmpeg.sanitize_video, file_content, asset_path, api_security_strategy):
+			asset_paths.append(asset_path)
+
+		process_manager.end()
+
+	return asset_paths
@@ -0,0 +1,92 @@
+import uuid
+from datetime import datetime, timedelta
+from typing import List, Optional, cast
+
+from facefusion.apis.asset_helper import detect_media_type_by_path, extract_image_metadata
+from facefusion.ffprobe import extract_audio_metadata, extract_video_metadata
+from facefusion.filesystem import get_file_format, get_file_name, get_file_size
+from facefusion.types import AssetId, AssetSet, AssetStore, AssetType, AudioAsset, AudioFormat, ImageAsset, ImageFormat, SessionId, VideoAsset, VideoFormat
+
+ASSET_STORE : AssetStore = {}
+
+
+def create_asset(session_id : SessionId, asset_type : AssetType, asset_path : str) -> Optional[AudioAsset | ImageAsset | VideoAsset]:
+	asset_id = str(uuid.uuid4())
+	asset_name = get_file_name(asset_path)
+	asset_format = get_file_format(asset_path)
+	asset_size = get_file_size(asset_path)
+	media_type = detect_media_type_by_path(asset_path)
+	created_at = datetime.now()
+	expires_at = created_at + timedelta(hours = 2)
+
+	if session_id not in ASSET_STORE:
+		ASSET_STORE[session_id] = {}
+
+	if media_type == 'audio':
+		ASSET_STORE[session_id][asset_id] = cast(AudioAsset,
+		{
+			'id': asset_id,
+			'created_at': created_at,
+			'expires_at': expires_at,
+			'type': asset_type,
+			'media': media_type,
+			'name': asset_name,
+			'format': cast(AudioFormat, asset_format),
+			'size': asset_size,
+			'path': asset_path,
+			'metadata': extract_audio_metadata(asset_path)
+		})
+
+	if media_type == 'image':
+		ASSET_STORE[session_id][asset_id] = cast(ImageAsset,
+		{
+			'id': asset_id,
+			'created_at': created_at,
+			'expires_at': expires_at,
+			'type': asset_type,
+			'media': media_type,
+			'name': asset_name,
+			'format': cast(ImageFormat, asset_format),
+			'size': asset_size,
+			'path': asset_path,
+			'metadata': extract_image_metadata(asset_path)
+		})
+
+	if media_type == 'video':
+		ASSET_STORE[session_id][asset_id] = cast(VideoAsset,
+		{
+			'id': asset_id,
+			'created_at': created_at,
+			'expires_at': expires_at,
+			'type': asset_type,
+			'media': media_type,
+			'name': asset_name,
+			'format': cast(VideoFormat, asset_format),
+			'size': asset_size,
+			'path': asset_path,
+			'metadata': extract_video_metadata(asset_path)
+		})
+
+	return ASSET_STORE[session_id].get(asset_id)
+
+
+def get_assets(session_id : SessionId) -> Optional[AssetSet]:
+	return ASSET_STORE.get(session_id)
+
+
+def get_asset(session_id : SessionId, asset_id : AssetId) -> Optional[AudioAsset | ImageAsset | VideoAsset]:
+	if session_id in ASSET_STORE:
+		return ASSET_STORE.get(session_id).get(asset_id)
+	return None
+
+
+def delete_assets(session_id : SessionId, asset_ids : List[AssetId]) -> None:
+	if session_id in ASSET_STORE:
+		for asset_id in asset_ids:
+			if asset_id in ASSET_STORE.get(session_id):
+				del ASSET_STORE[session_id][asset_id]
+	return None
+
+
+def clear() -> None:
+	ASSET_STORE.clear()
@@ -0,0 +1,58 @@
+from types import ModuleType
+from typing import List
+
+from starlette.applications import Starlette
+from starlette.middleware import Middleware
+from starlette.middleware.cors import CORSMiddleware
+from starlette.routing import Route, WebSocketRoute
+
+from facefusion.apis.endpoints.assets import delete_assets, get_asset, get_assets, upload_asset
+from facefusion.apis.endpoints.capabilities import get_capabilities
+from facefusion.apis.endpoints.metrics import get_metrics, websocket_metrics
+from facefusion.apis.endpoints.ping import websocket_ping
+from facefusion.apis.endpoints.session import create_session, destroy_session, get_session, refresh_session
+from facefusion.apis.endpoints.state import get_state, set_state
+from facefusion.apis.endpoints.stream import delete_stream, post_stream, websocket_stream
+from facefusion.apis.middlewares.session import create_session_guard
+from facefusion.libraries import aom as aom_module, datachannel as datachannel_module, opus as opus_module, vpx as vpx_module
+
+
+def get_common_modules() -> List[ModuleType]:
+	return [ aom_module, datachannel_module, opus_module, vpx_module ]
+
+
+def pre_check() -> bool:
+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
+
+	return True
+
+
+def create_api() -> Starlette:
+	session_guard = Middleware(create_session_guard)
+	routes =\
+		[
+			Route('/session', create_session, methods = [ 'POST' ]),
+			Route('/session', get_session, methods = [ 'GET' ], middleware = [ session_guard ]),
+			Route('/session', refresh_session, methods = [ 'PUT' ]),
+			Route('/session', destroy_session, methods = [ 'DELETE' ], middleware = [ session_guard ]),
+			Route('/state', get_state, methods = [ 'GET' ], middleware = [ session_guard ]),
+			Route('/state', set_state, methods = [ 'PUT' ], middleware = [ session_guard ]),
+			Route('/assets', get_assets, methods = [ 'GET' ], middleware = [ session_guard ]),
+			Route('/assets', upload_asset, methods = [ 'POST' ], middleware = [ session_guard ]),
+			Route('/assets/{asset_id}', get_asset, methods = [ 'GET' ], middleware = [ session_guard ]),
+			Route('/assets', delete_assets, methods = [ 'DELETE' ], middleware = [ session_guard ]),
+			Route('/capabilities', get_capabilities, methods = [ 'GET' ]),
+			Route('/metrics', get_metrics, methods = [ 'GET' ], middleware = [ session_guard ]),
+			Route('/stream', post_stream, methods = [ 'POST' ], middleware = [ session_guard ]),
+			Route('/stream', delete_stream, methods = [ 'DELETE' ], name = 'delete_stream', middleware = [ session_guard ]),
+			WebSocketRoute('/metrics', websocket_metrics, middleware = [ session_guard ]),
+			WebSocketRoute('/ping', websocket_ping, middleware = [ session_guard ]),
+			WebSocketRoute('/stream', websocket_stream, middleware = [ session_guard ])
+		]
+
+	api = Starlette(routes = routes)
+	api.add_middleware(CORSMiddleware, allow_origins = [ '*' ], allow_methods = [ '*' ], allow_headers = [ '*' ])
+
+	return api
@@ -0,0 +1,135 @@
+import os
+from typing import List
+
+from starlette.requests import Request
+from starlette.responses import FileResponse, JSONResponse, Response
+from starlette.status import HTTP_200_OK, HTTP_201_CREATED, HTTP_400_BAD_REQUEST, HTTP_404_NOT_FOUND, HTTP_415_UNSUPPORTED_MEDIA_TYPE
+
+from facefusion import session_context, session_manager
+from facefusion.apis import asset_store
+from facefusion.apis.asset_helper import save_asset_files, validate_asset_files
+from facefusion.apis.endpoints.session import extract_access_token
+from facefusion.filesystem import remove_file
+
+
+async def upload_asset(request : Request) -> Response:
+	access_token = extract_access_token(request.scope)
+	session_id = session_manager.find_session_id(access_token)
+	asset_type = request.query_params.get('type')
+
+	if session_id and asset_type in [ 'source', 'target' ]:
+		session_context.set_session_id(session_id)
+
+		form = await request.form()
+		upload_files = form.getlist('file')
+
+		if upload_files and validate_asset_files(upload_files):
+			asset_paths = await save_asset_files(upload_files)
+
+			if asset_paths:
+				asset_ids : List[str] = []
+
+				for asset_path in asset_paths:
+					asset = asset_store.create_asset(session_id, asset_type, asset_path)
+
+					if asset:
+						asset_id = asset.get('id')
+
+						if asset_id:
+							asset_ids.append(asset_id)
+
+				if asset_ids:
+					return JSONResponse(
+					{
+						'asset_ids': asset_ids
+					}, status_code = HTTP_201_CREATED)
+
+			return Response(status_code = HTTP_415_UNSUPPORTED_MEDIA_TYPE)
+
+	return Response(status_code = HTTP_400_BAD_REQUEST)
+
+
+async def get_assets(request : Request) -> Response:
+	access_token = extract_access_token(request.scope)
+	session_id = session_manager.find_session_id(access_token)
+
+	if session_id:
+		asset_set = asset_store.get_assets(session_id)
+		assets = []
+
+		if asset_set:
+			for asset in asset_set.values():
+				assets.append(
+				{
+					'id': asset.get('id'),
+					'created_at': asset.get('created_at').isoformat(),
+					'expires_at': asset.get('expires_at').isoformat(),
+					'type': asset.get('type'),
+					'media': asset.get('media'),
+					'name': asset.get('name'),
+					'format': asset.get('format'),
+					'size': asset.get('size'),
+					'metadata': asset.get('metadata')
+				})
+
+		return JSONResponse(
+		{
+			'assets': assets
+		}, status_code = HTTP_200_OK)
+
+	return Response(status_code = HTTP_400_BAD_REQUEST)
+
+
+async def get_asset(request : Request) -> Response:
+	access_token = extract_access_token(request.scope)
+	session_id = session_manager.find_session_id(access_token)
+	asset_id = request.path_params.get('asset_id')
+
+	if session_id and asset_id:
+		asset = asset_store.get_asset(session_id, asset_id)
+
+		if asset:
+			if request.query_params.get('action') == 'download':
+				asset_path = asset.get('path')
+
+				if os.path.exists(asset_path):
+					return FileResponse(asset_path, filename = asset.get('name'))
+
+			return JSONResponse(
+			{
+				'id': asset.get('id'),
+				'created_at': asset.get('created_at').isoformat(),
+				'expires_at': asset.get('expires_at').isoformat(),
+				'type': asset.get('type'),
+				'media': asset.get('media'),
+				'name': asset.get('name'),
+				'format': asset.get('format'),
+				'size': asset.get('size'),
+				'metadata': asset.get('metadata')
+			}, status_code = HTTP_200_OK)
+
+	return Response(status_code = HTTP_404_NOT_FOUND)
+
+
+async def delete_assets(request : Request) -> Response:
+	access_token = extract_access_token(request.scope)
+	session_id = session_manager.find_session_id(access_token)
+	body = await request.json()
+	asset_ids = body.get('asset_ids')
+
+	if session_id and asset_ids:
+		asset_set = asset_store.get_assets(session_id)
+
+		if asset_set:
+
+			for asset_id in asset_ids:
+				if asset_id in asset_set:
+					asset = asset_set.get(asset_id)
+
+					if asset:
+						remove_file(asset.get('path'))
+
+			asset_store.delete_assets(session_id, asset_ids)
+			return Response(status_code = HTTP_200_OK)
+
+	return Response(status_code = HTTP_404_NOT_FOUND)
@@ -0,0 +1,20 @@
+from starlette.requests import Request
+from starlette.responses import JSONResponse
+from starlette.status import HTTP_200_OK
+
+import facefusion.choices
+from facefusion import capability_store
+
+
+async def get_capabilities(request : Request) -> JSONResponse:
+	capabilities =\
+	{
+		'formats':
+		{
+			'audio': facefusion.choices.audio_formats,
+			'image': facefusion.choices.image_formats,
+			'video': facefusion.choices.video_formats
+		},
+		'arguments': capability_store.get_api_capability_group()
+	}
+	return JSONResponse(capabilities, status_code = HTTP_200_OK)
@@ -0,0 +1,32 @@
+import asyncio
+
+from starlette.requests import Request
+from starlette.responses import JSONResponse, Response
+from starlette.status import HTTP_404_NOT_FOUND
+from starlette.websockets import WebSocket
+
+from facefusion.apis.api_helper import get_sec_websocket_protocol
+from facefusion.system import get_metrics_set
+
+
+async def get_metrics(request : Request) -> Response:
+	metrics_set = get_metrics_set()
+
+	if metrics_set:
+		return JSONResponse(metrics_set)
+
+	return Response(status_code = HTTP_404_NOT_FOUND)
+
+
+async def websocket_metrics(websocket : WebSocket) -> None:
+	subprotocol = get_sec_websocket_protocol(websocket.scope)
+	await websocket.accept(subprotocol = subprotocol)
+
+	try:
+		while True:
+			metrics_set = get_metrics_set()
+			await websocket.send_json(metrics_set)
+			await asyncio.sleep(2)
+
+	except Exception:
+		pass
@@ -0,0 +1,16 @@
+from starlette.websockets import WebSocket
+
+from facefusion.apis.api_helper import get_sec_websocket_protocol
+
+
+async def websocket_ping(websocket : WebSocket) -> None:
+	subprotocol = get_sec_websocket_protocol(websocket.scope)
+
+	await websocket.accept(subprotocol = subprotocol)
+
+	try:
+		while True:
+			await websocket.receive()
+
+	except Exception:
+		pass
@@ -0,0 +1,75 @@
+import os
+import secrets
+
+from starlette.requests import Request
+from starlette.responses import JSONResponse
+from starlette.status import HTTP_200_OK, HTTP_201_CREATED, HTTP_401_UNAUTHORIZED
+
+from facefusion import session_context, session_manager, translator
+from facefusion.apis.session_helper import extract_access_token
+
+
+async def create_session(request : Request) -> JSONResponse:
+	body = await request.json()
+
+	if not body.get('api_key') or body.get('api_key') == os.getenv('FACEFUSION_API_KEY'):
+		session_id = secrets.token_urlsafe(16)
+		session = session_manager.create_session()
+		session_context.set_session_id(session_id)
+		session_manager.set_session(session_id, session)
+
+		return JSONResponse(
+		{
+			'access_token': session.get('access_token'),
+			'refresh_token': session.get('refresh_token')
+		}, status_code = HTTP_201_CREATED)
+
+	return JSONResponse(
+	{
+		'message': translator.get('something_went_wrong', 'facefusion.apis')
+	}, status_code = HTTP_401_UNAUTHORIZED)
+
+
+async def get_session(request : Request) -> JSONResponse:
+	access_token = extract_access_token(request.scope)
+	session_id = session_manager.find_session_id(access_token)
+	session = session_manager.get_session(session_id)
+
+	return JSONResponse(
+	{
+		'access_token': session.get('access_token'),
+		'refresh_token': session.get('refresh_token'),
+		'created_at': session.get('created_at').isoformat(),
+		'expires_at': session.get('expires_at').isoformat()
+	}, status_code = HTTP_200_OK)
+
+
+async def refresh_session(request : Request) -> JSONResponse:
+	body = await request.json()
+
+	for session_id, session in session_manager.SESSIONS.items():
+		if session.get('refresh_token') == body.get('refresh_token') and session_manager.validate_session(session_id):
+			__session__ = session_manager.create_session()
+			session_manager.set_session(session_id, __session__)
+
+			return JSONResponse(
+			{
+				'access_token': __session__.get('access_token'),
+				'refresh_token': __session__.get('refresh_token')
+			}, status_code = HTTP_200_OK)
+
+	return JSONResponse(
+	{
+		'message': translator.get('something_went_wrong', 'facefusion.apis')
+	}, status_code = HTTP_401_UNAUTHORIZED)
+
+
+async def destroy_session(request : Request) -> JSONResponse:
+	access_token = extract_access_token(request.scope)
+	session_id = session_manager.find_session_id(access_token)
+	session_manager.clear_session(session_id)
+
+	return JSONResponse(
+	{
+		'message': translator.get('ok', 'facefusion.apis')
+	}, status_code = HTTP_200_OK)
@@ -0,0 +1,93 @@
+from starlette.requests import Request
+from starlette.responses import JSONResponse
+from starlette.status import HTTP_200_OK, HTTP_400_BAD_REQUEST, HTTP_404_NOT_FOUND, HTTP_422_UNPROCESSABLE_CONTENT
+
+from facefusion import args_helper, capability_store, session_manager, state_manager, translator
+from facefusion.apis import asset_store
+from facefusion.apis.endpoints.session import extract_access_token
+
+
+async def get_state(request : Request) -> JSONResponse:
+	api_args = args_helper.extract_api_args(state_manager.get_state())
+	return JSONResponse(state_manager.collect_state(api_args), status_code = HTTP_200_OK)
+
+
+async def set_state(request : Request) -> JSONResponse:
+	__api_args__ = {}
+
+	action = request.query_params.get('action')
+	asset_type = request.query_params.get('type')
+
+	if action == 'select' and asset_type == 'source':
+		return await select_source(request)
+
+	if action == 'select' and asset_type == 'target':
+		return await select_target(request)
+
+	body = await request.json()
+	api_args = capability_store.get_api_arguments()
+
+	for key, value in body.items():
+		if key not in api_args:
+			return JSONResponse(
+			{
+				'message': translator.get('invalid_state_key', 'facefusion.apis')
+			}, status_code = HTTP_400_BAD_REQUEST)
+		__api_args__[key] = value
+
+	if __api_args__:
+
+		for key, value in __api_args__.items():
+			state_manager.set_item(key, value)
+
+		__api_args__ = args_helper.extract_api_args(state_manager.get_state())
+		return JSONResponse(state_manager.collect_state(__api_args__), status_code = HTTP_200_OK)
+
+	return JSONResponse({}, status_code = HTTP_422_UNPROCESSABLE_CONTENT)
+
+
+async def select_source(request : Request) -> JSONResponse:
+	body = await request.json()
+	asset_ids = body.get('asset_ids')
+	access_token = extract_access_token(request.scope)
+	session_id = session_manager.find_session_id(access_token)
+
+	if isinstance(asset_ids, list) and session_id:
+		source_paths = []
+
+		for asset_id in asset_ids:
+			asset = asset_store.get_asset(session_id, asset_id)
+
+			if asset:
+				source_paths.append(asset.get('path'))
+
+		state_manager.set_item('source_paths', source_paths)
+
+		__api_args__ = args_helper.extract_api_args(state_manager.get_state())
+		return JSONResponse(state_manager.collect_state(__api_args__), status_code = HTTP_200_OK)
+
+	return JSONResponse(
+	{
+		'message': translator.get('source_asset_not_found', 'facefusion.apis')
+	}, status_code = HTTP_404_NOT_FOUND)
+
+
+async def select_target(request : Request) -> JSONResponse:
+	body = await request.json()
+	asset_id = body.get('asset_id')
+	access_token = extract_access_token(request.scope)
+	session_id = session_manager.find_session_id(access_token)
+
+	if isinstance(asset_id, str) and session_id:
+		asset = asset_store.get_asset(session_id, asset_id)
+
+		if asset:
+			state_manager.set_item('target_path', asset.get('path'))
+
+			__api_args__ = args_helper.extract_api_args(state_manager.get_state())
+			return JSONResponse(state_manager.collect_state(__api_args__), status_code = HTTP_200_OK)
+
+	return JSONResponse(
+	{
+		'message': translator.get('target_asset_not_found', 'facefusion.apis')
+	}, status_code = HTTP_404_NOT_FOUND)
@@ -0,0 +1,52 @@
+from starlette.requests import Request
+from starlette.responses import Response
+from starlette.status import HTTP_200_OK, HTTP_201_CREATED, HTTP_404_NOT_FOUND
+from starlette.websockets import WebSocket, WebSocketState
+
+from facefusion import session_context, session_manager
+from facefusion.apis.api_helper import get_sec_websocket_protocol
+from facefusion.apis.session_helper import extract_access_token
+from facefusion.apis.stream_manager import destroy_stream, process_image, process_video
+
+
+async def websocket_stream(websocket : WebSocket) -> None:
+	subprotocol = get_sec_websocket_protocol(websocket.scope)
+	access_token = extract_access_token(websocket.scope)
+	session_id = session_manager.find_session_id(access_token)
+	session_context.set_session_id(session_id)
+
+	await websocket.accept(subprotocol = subprotocol)
+	await process_image(websocket)
+
+	if websocket.client_state == WebSocketState.CONNECTED:
+		await websocket.close()
+
+
+async def post_stream(request : Request) -> Response:
+	headers =\
+	{
+		'Location': request.url_for('delete_stream').path
+	}
+	content_type = request.headers.get('content-type')
+	access_token = extract_access_token(request.scope)
+	session_id = session_manager.find_session_id(access_token)
+	session_context.set_session_id(session_id)
+
+	if session_id and content_type == 'application/sdp':
+		sdp_offer = await request.body()
+		sdp_answer = process_video(session_id, sdp_offer.decode())
+
+		if sdp_answer:
+			return Response(sdp_answer, status_code = HTTP_201_CREATED, media_type = 'application/sdp', headers = headers)
+
+	return Response(status_code = HTTP_404_NOT_FOUND)
+
+
+async def delete_stream(request : Request) -> Response:
+	access_token = extract_access_token(request.scope)
+	session_id = session_manager.find_session_id(access_token)
+
+	if session_id and destroy_stream(session_id):
+		return Response(status_code = HTTP_200_OK)
+
+	return Response(status_code = HTTP_404_NOT_FOUND)
@@ -0,0 +1,15 @@
+from facefusion.types import Locales
+
+LOCALES : Locales =\
+{
+	'en':
+	{
+		'ok': 'ok',
+		'something_went_wrong': 'something went wrong',
+		'invalid_access_token': 'invalid access token',
+		'invalid_refresh_token': 'invalid refresh token',
+		'source_asset_not_found': 'source asset not found',
+		'target_asset_not_found': 'target asset not found',
+		'invalid_state_key': 'invalid state key'
+	}
+}
@@ -0,0 +1,34 @@
+from starlette.responses import JSONResponse
+from starlette.status import HTTP_401_UNAUTHORIZED, HTTP_426_UPGRADE_REQUIRED
+from starlette.types import ASGIApp, Receive, Scope, Send
+
+from facefusion import session_manager, translator
+from facefusion.apis.session_helper import extract_access_token
+
+
+def create_session_guard(app : ASGIApp) -> ASGIApp:
+	async def middleware(scope : Scope, receive : Receive, send : Send) -> None:
+		access_token = extract_access_token(scope)
+
+		if access_token:
+			session_id = session_manager.find_session_id(access_token)
+
+			if session_id:
+				if session_manager.validate_session(session_id):
+					return await app(scope, receive, send)
+
+				response = JSONResponse(
+				{
+					'message': translator.get('invalid_access_token', 'facefusion.apis')
+				}, status_code = HTTP_426_UPGRADE_REQUIRED)
+
+				return await response(scope, receive, send)
+
+		response = JSONResponse(
+		{
+			'message': translator.get('invalid_access_token', 'facefusion.apis')
+		}, status_code = HTTP_401_UNAUTHORIZED)
+
+		return await response(scope, receive, send)
+
+	return middleware
@@ -0,0 +1,29 @@
+from typing import Optional
+
+from starlette.datastructures import Headers
+from starlette.types import Scope
+
+from facefusion.apis.api_helper import get_sec_websocket_protocol
+from facefusion.types import Token
+
+
+def extract_access_token(scope : Scope) -> Optional[Token]:
+	if scope.get('type') == 'http':
+		auth_header = Headers(scope = scope).get('Authorization')
+
+		if auth_header:
+			auth_prefix, _, access_token = auth_header.partition(' ')
+
+			if auth_prefix.lower() == 'bearer' and access_token:
+				return access_token
+
+	if scope.get('type') == 'websocket':
+		subprotocol = get_sec_websocket_protocol(scope)
+
+		if subprotocol:
+			protocol_prefix, _, access_token = subprotocol.partition('.')
+
+			if protocol_prefix == 'access_token' and access_token:
+				return access_token
+
+	return None
@@ -0,0 +1,67 @@
+from functools import partial
+from queue import Queue
+from typing import Optional, Tuple
+
+import numpy
+
+from facefusion import rtc
+from facefusion.apis.stream_event import create_receive_event
+from facefusion.codecs import opus_decoder, opus_encoder
+from facefusion.types import AudioCodec, AudioFrame, Buffer, OpusDecoder, RtcPeer, RtcPeerAudio, Time
+
+
+def run_audio_encode_loop(rtc_peer : RtcPeer, audio_queue : Queue[Tuple[Time, AudioFrame]]) -> None:
+	audio_codec = rtc_peer.get('audio').get('codec')
+	temp_audio_time, temp_audio_frame = audio_queue.get()
+	audio_encoder = opus_encoder.create(48000, 2)
+
+	while numpy.any(temp_audio_frame):
+		audio_buffer = opus_encoder.encode(audio_encoder, temp_audio_frame.tobytes(), 2)
+
+		if audio_buffer:
+			audio_timestamp = rtc.convert_time_to_timestamp(audio_codec, temp_audio_time)
+			rtc.send_audio(rtc_peer, audio_buffer, audio_timestamp)
+
+		temp_audio_time, temp_audio_frame = audio_queue.get()
+
+	opus_encoder.destroy(audio_encoder)
+
+
+def receive_audio_frames(rtc_peer_audio : RtcPeerAudio, audio_queue : Queue[Tuple[Time, AudioFrame]]) -> None:
+	audio_track = rtc_peer_audio.get('receiver_track')
+	audio_codec = rtc_peer_audio.get('codec')
+	audio_decoder = create_audio_decoder(audio_codec)
+
+	audio_frame_handler = partial(handle_audio_frame, audio_codec, audio_decoder, audio_queue)
+	receive_event = create_receive_event(audio_track, audio_frame_handler)
+	receive_event.wait()
+
+	empty_audio_frame = numpy.empty(0)
+	audio_queue.put((0.0, empty_audio_frame))
+	destroy_audio_decoder(audio_codec, audio_decoder)
+
+
+def decode_audio_frame(audio_codec : AudioCodec, audio_decoder : OpusDecoder, input_buffer : Buffer) -> Optional[Buffer]:
+	if audio_codec == 'opus':
+		return opus_decoder.decode(audio_decoder, input_buffer, 2)
+	return None
+
+
+def create_audio_decoder(audio_codec : AudioCodec) -> Optional[OpusDecoder]:
+	if audio_codec == 'opus':
+		return opus_decoder.create(48000, 2)
+	return None
+
+
+def destroy_audio_decoder(audio_codec : AudioCodec, audio_decoder : OpusDecoder) -> None:
+	if audio_codec == 'opus':
+		opus_decoder.destroy(audio_decoder)
+
+
+def handle_audio_frame(audio_codec : AudioCodec, audio_decoder : OpusDecoder, audio_queue : Queue[Tuple[Time, AudioFrame]], audio_buffer : Buffer, audio_timestamp : int) -> None:
+	audio_frame = decode_audio_frame(audio_codec, audio_decoder, audio_buffer)
+
+	if audio_frame:
+		audio_frame = numpy.frombuffer(audio_frame, dtype = numpy.float32)
+		audio_time = rtc.convert_timestamp_to_time(audio_codec, audio_timestamp)
+		audio_queue.put((audio_time, audio_frame))
@@ -0,0 +1,30 @@
+import ctypes
+import threading
+from functools import partial
+
+from facefusion.libraries import datachannel as datachannel_module
+from facefusion.types import FrameHandler
+
+
+def create_receive_event(track : int, frame_handler : FrameHandler) -> threading.Event:
+	datachannel_library = datachannel_module.create_static_library()
+	receive_event = threading.Event()
+
+	frame_callback = ctypes.CFUNCTYPE(None, ctypes.c_int, ctypes.c_void_p, ctypes.c_int, ctypes.c_void_p, ctypes.c_void_p)(partial(dispatch_frame, frame_handler))
+	close_callback = ctypes.CFUNCTYPE(None, ctypes.c_int, ctypes.c_void_p)(partial(dispatch_event, receive_event))
+	datachannel_library.rtcSetFrameCallback(track, frame_callback)
+	datachannel_library.rtcSetClosedCallback(track, close_callback)
+	receive_event.frame_callback = frame_callback  # type: ignore[attr-defined]
+	receive_event.close_callback = close_callback  # type: ignore[attr-defined]
+
+	return receive_event
+
+
+def dispatch_frame(frame_handler : FrameHandler, track : int, data : ctypes.c_void_p, size : int, info : ctypes.c_void_p, pointer : ctypes.c_void_p) -> None:
+	frame_buffer = ctypes.string_at(data, size)
+	frame_timestamp = ctypes.cast(info, ctypes.POINTER(ctypes.c_uint32)).contents.value
+	frame_handler(frame_buffer, frame_timestamp)
+
+
+def dispatch_event(event : threading.Event, track : int, pointer : ctypes.c_void_p) -> None:
+	event.set()
@@ -0,0 +1,136 @@
+import ctypes
+import threading
+from collections.abc import AsyncIterator
+from concurrent.futures import Future, ThreadPoolExecutor
+from queue import Queue
+from typing import Optional, Tuple
+
+import cv2
+import numpy
+from starlette.websockets import WebSocket
+
+from facefusion import rtc, rtc_store, state_manager, streamer
+from facefusion.apis.stream_audio import receive_audio_frames, run_audio_encode_loop
+from facefusion.apis.stream_video import receive_video_frames, run_video_encode_loop
+from facefusion.libraries import datachannel as datachannel_module
+from facefusion.types import AudioCodec, AudioFrame, BufferPack, PeerConnection, RtcPeer, RtcPeerAudio, SdpAnswer, SdpOffer, SessionId, Time, VideoCodec, VisionFrame
+
+
+async def process_image(websocket : WebSocket) -> None:
+	capture_vision_frame = await anext(receive_vision_frames(websocket), None)
+
+	if numpy.any(capture_vision_frame):
+		output_vision_frame = streamer.process_stream_frame(capture_vision_frame)
+		is_success, output_frame_buffer = cv2.imencode('.jpg', output_vision_frame)
+
+		if is_success:
+			await websocket.send_bytes(output_frame_buffer.tobytes())
+
+
+async def receive_vision_frames(websocket : WebSocket) -> AsyncIterator[VisionFrame]:
+	websocket_event = await websocket.receive()
+
+	while websocket_event.get('type') == 'websocket.receive':
+		frame_buffer = websocket_event.get('bytes') or bytes()
+		vision_frame = cv2.imdecode(numpy.frombuffer(frame_buffer, numpy.uint8), cv2.IMREAD_COLOR)
+
+		if numpy.any(vision_frame):
+			yield vision_frame
+
+		websocket_event = await websocket.receive()
+
+
+def process_video(session_id : SessionId, sdp_offer : SdpOffer) -> Optional[SdpAnswer]:
+	video_codec : VideoCodec = 'vp8'
+
+	if rtc.get_payload_type(sdp_offer, 'vp9'):
+		video_codec = 'vp9'
+
+	if rtc.get_payload_type(sdp_offer, 'av1'):
+		video_codec = 'av1'
+
+	video_payload_type = rtc.get_payload_type(sdp_offer, video_codec)
+
+	if video_payload_type:
+		peer_connection : PeerConnection = rtc.create_peer_connection()
+		video_receiver_track = rtc.add_video_track(peer_connection, 'recvonly', video_codec, video_payload_type)
+		video_sender_track = rtc.add_video_track(peer_connection, 'sendonly', video_codec, video_payload_type)
+
+		sender_bitrate = ctypes.c_uint(0)
+		receiver_bitrate = ctypes.c_uint(8000)
+		rtc.wire_sender_bitrate(video_sender_track, sender_bitrate)
+
+		audio_codec : AudioCodec = 'opus'
+		audio_payload_type = rtc.get_payload_type(sdp_offer, audio_codec)
+
+		if audio_payload_type:
+			audio_receiver_track = rtc.add_audio_track(peer_connection, 'recvonly', audio_codec, audio_payload_type)
+			audio_sender_track = rtc.add_audio_track(peer_connection, 'sendonly', audio_codec, audio_payload_type)
+
+		rtc.set_remote_description(peer_connection, sdp_offer)
+		sdp_answer = rtc.create_sdp_answer(peer_connection)
+
+		if sdp_answer:
+			rtc_peer : RtcPeer =\
+			{
+				'peer_connection': peer_connection,
+				'video':
+				{
+					'sender_track': video_sender_track,
+					'receiver_track': video_receiver_track,
+					'codec': video_codec
+				},
+				'sender_bitrate': sender_bitrate,
+				'receiver_bitrate': receiver_bitrate
+			}
+
+			if audio_payload_type:
+				rtc_peer['audio'] = RtcPeerAudio(
+					sender_track = audio_sender_track,
+					receiver_track = audio_receiver_track,
+					codec = audio_codec
+				)
+
+			rtc_store.init_peers(session_id)
+			rtc_store.get_peers(session_id).append(rtc_peer)
+
+			threading.Thread(target = run_peer_loop, args = (session_id, rtc_peer), daemon = True).start()
+
+			return sdp_answer
+
+		datachannel_module.create_static_library().rtcDeletePeerConnection(peer_connection)
+
+	return None
+
+
+def run_peer_loop(session_id : SessionId, rtc_peer : RtcPeer) -> None:
+	execution_thread_count = state_manager.get_item('execution_thread_count')
+	video_queue : Queue[Tuple[Time, Future[BufferPack]]] = Queue(maxsize = execution_thread_count)
+	audio_queue : Queue[Tuple[Time, AudioFrame]] = Queue(maxsize = execution_thread_count * 10)
+	video_executor = ThreadPoolExecutor(max_workers = execution_thread_count)
+
+	video_receiver_thread = threading.Thread(target = receive_video_frames, args = (rtc_peer.get('video'), video_queue, video_executor), daemon = True)
+	video_encoder_thread = threading.Thread(target = run_video_encode_loop, args = (rtc_peer, video_queue), daemon = True)
+	video_receiver_thread.start()
+	video_encoder_thread.start()
+
+	if rtc_peer.get('audio'):
+		audio_receiver_thread = threading.Thread(target = receive_audio_frames, args = (rtc_peer.get('audio'), audio_queue), daemon = True)
+		audio_encoder_thread = threading.Thread(target = run_audio_encode_loop, args = (rtc_peer, audio_queue), daemon = True)
+		audio_receiver_thread.start()
+		audio_encoder_thread.start()
+		audio_receiver_thread.join()
+		audio_encoder_thread.join()
+
+	video_receiver_thread.join()
+	video_encoder_thread.join()
+	video_executor.shutdown(wait = True)
+	rtc_store.delete_peers(session_id)
+
+
+def destroy_stream(session_id : SessionId) -> bool:
+	if rtc_store.has_peers(session_id):
+		rtc_store.delete_peers(session_id)
+		return not rtc_store.has_peers(session_id)
+
+	return False
@@ -0,0 +1,174 @@
+from concurrent.futures import Future, ThreadPoolExecutor
+from functools import partial
+from queue import Queue
+from typing import Optional, Tuple
+
+import cv2
+import numpy
+
+from facefusion import rtc, streamer
+from facefusion.apis.stream_event import create_receive_event
+from facefusion.codecs import aom_decoder, aom_encoder, vpx_decoder, vpx_encoder
+from facefusion.types import AomDecoder, AomEncoder, BitRate, Buffer, BufferPack, Resolution, RtcPeer, RtcPeerVideo, Time, VideoCodec, VisionFrame, VpxDecoder, VpxEncoder
+
+
+def run_video_encode_loop(rtc_peer : RtcPeer, video_queue : Queue[Tuple[Time, Future[BufferPack]]]) -> None:
+	video_codec = rtc_peer.get('video').get('codec')
+	video_time, video_future = video_queue.get()
+	video_pack = video_future.result()
+	video_buffer = video_pack.get('buffer')
+	video_resolution = video_pack.get('resolution')
+
+	if video_buffer:
+		temp_resolution : Resolution = video_resolution
+		temp_bitrate : BitRate = 8000
+		video_encoder = create_video_encoder(video_codec, temp_resolution, temp_bitrate)
+		frame_index = 0
+
+		while video_buffer:
+			sender_bitrate = rtc_peer.get('sender_bitrate').value
+
+			if video_resolution[0] - temp_resolution[0] or video_resolution[1] - temp_resolution[1]:
+				temp_resolution = video_resolution
+				update_video_encoder_resolution(video_codec, video_encoder, temp_resolution)
+
+			if sender_bitrate > 0 and sender_bitrate - temp_bitrate:
+				temp_bitrate = sender_bitrate
+				update_video_encoder_bitrate(video_codec, video_encoder, temp_bitrate)
+
+			__video_buffer__ = encode_video_frame(video_codec, video_encoder, video_buffer, temp_resolution, frame_index)
+
+			if __video_buffer__:
+				video_timestamp = rtc.convert_time_to_timestamp(video_codec, video_time)
+				rtc.send_video(rtc_peer, __video_buffer__, video_timestamp)
+
+			receiver_bitrate = rtc_peer.get('receiver_bitrate').value
+			rtc.adapt_receiver_bitrate(rtc_peer, receiver_bitrate)
+			frame_index += 1
+
+			video_time, video_future = video_queue.get()
+			video_pack = video_future.result()
+			video_buffer = video_pack.get('buffer')
+			video_resolution = video_pack.get('resolution')
+
+		destroy_video_encoder(video_codec, video_encoder)
+		rtc.clear_bitrate(rtc_peer)
+
+
+def receive_video_frames(rtc_peer_video : RtcPeerVideo, video_queue : Queue[Tuple[Time, Future[BufferPack]]], video_executor : ThreadPoolExecutor) -> None:
+	video_track = rtc_peer_video.get('receiver_track')
+	video_codec = rtc_peer_video.get('codec')
+	video_decoder = create_video_decoder(video_codec)
+
+	video_frame_handler = partial(handle_video_frame, video_codec, video_decoder, video_queue, video_executor)
+	receive_event = create_receive_event(video_track, video_frame_handler)
+	receive_event.wait()
+
+	empty_future : Future[BufferPack] = Future()
+	empty_future.set_result(BufferPack(buffer = bytes(), resolution = (0, 0)))
+	video_queue.put((0.0, empty_future))
+	destroy_video_decoder(video_codec, video_decoder)
+
+
+def process_video_frame(input_vision_frame : VisionFrame) -> BufferPack:
+	output_vision_frame = streamer.process_stream_frame(input_vision_frame)
+	output_resolution : Resolution = (output_vision_frame.shape[1], output_vision_frame.shape[0])
+	output_buffer = cv2.cvtColor(output_vision_frame, cv2.COLOR_BGR2YUV_I420).tobytes()
+	return BufferPack(buffer = output_buffer, resolution = output_resolution)
+
+
+def decode_video_frame(video_codec : VideoCodec, video_decoder : VpxDecoder | AomDecoder, input_buffer : Buffer) -> Optional[VisionFrame]:
+	if video_codec == 'av1':
+		aom_pointer = aom_decoder.decode(video_decoder, input_buffer)
+
+		if aom_pointer:
+			return normalize_vision_frame(aom_pointer)
+
+	if video_codec in [ 'vp8', 'vp9' ]:
+		vpx_pointer = vpx_decoder.decode(video_decoder, input_buffer)
+
+		if vpx_pointer:
+			return normalize_vision_frame(vpx_pointer)
+
+	return None
+
+
+def encode_video_frame(video_codec : VideoCodec, video_encoder : VpxEncoder | AomEncoder, input_buffer : Buffer, frame_resolution : Resolution, frame_index : int) -> Buffer:
+	if video_codec == 'av1':
+		return aom_encoder.encode(video_encoder, input_buffer, frame_resolution, frame_index)
+
+	if video_codec in [ 'vp8', 'vp9' ]:
+		return vpx_encoder.encode(video_encoder, input_buffer, frame_resolution, frame_index)
+
+	return bytes()
+
+
+def normalize_vision_frame(frame_pointer : BufferPack) -> VisionFrame:
+	frame_width, frame_height = frame_pointer.get('resolution')
+	vision_frame = numpy.frombuffer(frame_pointer.get('buffer'), dtype = numpy.uint8).reshape((frame_height * 3 // 2, frame_width))
+	return cv2.cvtColor(vision_frame, cv2.COLOR_YUV2BGR_I420)
+
+
+def create_video_decoder(video_codec : VideoCodec) -> Optional[VpxDecoder | AomDecoder]:
+	if video_codec == 'av1':
+		return aom_decoder.create(8)
+
+	if video_codec in [ 'vp8', 'vp9' ]:
+		return vpx_decoder.create(video_codec, 8)
+
+	return None
+
+
+def create_video_encoder(video_codec : VideoCodec, frame_resolution : Resolution, bitrate : BitRate) -> Optional[VpxEncoder | AomEncoder]:
+	if video_codec == 'av1':
+		return aom_encoder.create(frame_resolution, bitrate, 8, 10)
+
+	if video_codec in [ 'vp8', 'vp9' ]:
+		return vpx_encoder.create(video_codec, frame_resolution, bitrate, 8, 10)
+
+	return None
+
+
+def destroy_video_decoder(video_codec : VideoCodec, video_decoder : VpxDecoder | AomDecoder) -> None:
+	if video_codec == 'av1':
+		aom_decoder.destroy(video_decoder)
+
+	if video_codec in [ 'vp8', 'vp9' ]:
+		vpx_decoder.destroy(video_decoder)
+
+
+def destroy_video_encoder(video_codec : VideoCodec, video_encoder : VpxEncoder | AomEncoder) -> None:
+	if video_codec == 'av1':
+		aom_encoder.destroy(video_encoder)
+
+	if video_codec in [ 'vp8', 'vp9' ]:
+		vpx_encoder.destroy(video_encoder)
+
+
+def update_video_encoder_resolution(video_codec : VideoCodec, video_encoder : VpxEncoder | AomEncoder, frame_resolution : Resolution) -> bool:
+	if video_codec == 'av1':
+		return aom_encoder.update_resolution(video_encoder, frame_resolution)
+
+	if video_codec in [ 'vp8', 'vp9' ]:
+		return vpx_encoder.update_resolution(video_encoder, frame_resolution)
+
+	return False
+
+
+def update_video_encoder_bitrate(video_codec : VideoCodec, video_encoder : VpxEncoder | AomEncoder, bitrate : BitRate) -> bool:
+	if video_codec == 'av1':
+		return aom_encoder.update_bitrate(video_encoder, bitrate)
+
+	if video_codec in [ 'vp8', 'vp9' ]:
+		return vpx_encoder.update_bitrate(video_encoder, bitrate)
+
+	return False
+
+
+def handle_video_frame(video_codec : VideoCodec, video_decoder : VpxDecoder | AomDecoder, video_queue : Queue[Tuple[Time, Future[BufferPack]]], video_executor : ThreadPoolExecutor, video_buffer : Buffer, video_timestamp : int) -> None:
+	vision_frame = decode_video_frame(video_codec, video_decoder, video_buffer)
+
+	if numpy.any(vision_frame) and video_queue.qsize() < video_queue.maxsize:
+		video_future = video_executor.submit(process_video_frame, vision_frame)
+		video_time = rtc.convert_timestamp_to_time(video_codec, video_timestamp)
+		video_queue.put((video_time, video_future))
@@ -5,12 +5,14 @@ from facefusion.types import AppContext


 def detect_app_context() -> AppContext:
+	jobs_path = os.path.join('facefusion', 'jobs')
+	apis_path = os.path.join('facefusion', 'apis')
 	frame = sys._getframe(1)

 	while frame:
-		if os.path.join('facefusion', 'jobs') in frame.f_code.co_filename:
+		if jobs_path in frame.f_code.co_filename:
 			return 'cli'
-		if os.path.join('facefusion', 'uis') in frame.f_code.co_filename:
-			return 'ui'
+		if apis_path in frame.f_code.co_filename:
+			return 'api'
 		frame = frame.f_back
 	return 'cli'
@@ -1,14 +1,17 @@
-from facefusion import state_manager
+from typing import Union
+
+from facefusion.capability_store import get_api_arguments, get_cli_arguments, get_sys_arguments
 from facefusion.filesystem import get_file_name, is_video, resolve_file_paths
-from facefusion.jobs import job_store
 from facefusion.normalizer import normalize_fps, normalize_space
 from facefusion.processors.core import get_processors_modules
-from facefusion.types import ApplyStateItem, Args
+from facefusion.processors.types import ProcessorState
+from facefusion.types import ApplyStateItem, Args, State
 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', args.get('workflow'))
 	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'))
@@ -33,6 +36,7 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('reference_face_position', args.get('reference_face_position'))
 	apply_state_item('reference_face_distance', args.get('reference_face_distance'))
 	apply_state_item('reference_frame_number', args.get('reference_frame_number'))
+	apply_state_item('face_tracker_score', args.get('face_tracker_score'))
 	apply_state_item('face_occluder_model', args.get('face_occluder_model'))
 	apply_state_item('face_parser_model', args.get('face_parser_model'))
 	apply_state_item('face_mask_types', args.get('face_mask_types'))
@@ -44,12 +48,13 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('trim_frame_start', args.get('trim_frame_start'))
 	apply_state_item('trim_frame_end', args.get('trim_frame_end'))
 	apply_state_item('temp_frame_format', args.get('temp_frame_format'))
-	apply_state_item('keep_temp', args.get('keep_temp'))
+	apply_state_item('target_frame_amount', args.get('target_frame_amount'))
 	apply_state_item('output_image_quality', args.get('output_image_quality'))
 	apply_state_item('output_image_scale', args.get('output_image_scale'))
 	apply_state_item('output_audio_encoder', args.get('output_audio_encoder'))
 	apply_state_item('output_audio_quality', args.get('output_audio_quality'))
 	apply_state_item('output_audio_volume', args.get('output_audio_volume'))
+	apply_state_item('output_audio_fps', normalize_fps(args.get('output_audio_fps')))
 	apply_state_item('output_video_encoder', args.get('output_video_encoder'))
 	apply_state_item('output_video_preset', args.get('output_video_preset'))
 	apply_state_item('output_video_quality', args.get('output_video_quality'))
@@ -65,9 +70,6 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	for processor_module in get_processors_modules(available_processors):
 		processor_module.apply_args(args, apply_state_item)

-	apply_state_item('open_browser', args.get('open_browser'))
-	apply_state_item('ui_layouts', args.get('ui_layouts'))
-	apply_state_item('ui_workflow', args.get('ui_workflow'))
 	apply_state_item('execution_device_ids', args.get('execution_device_ids'))
 	apply_state_item('execution_providers', args.get('execution_providers'))
 	apply_state_item('execution_thread_count', args.get('execution_thread_count'))
@@ -76,8 +78,10 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('benchmark_mode', args.get('benchmark_mode'))
 	apply_state_item('benchmark_resolutions', args.get('benchmark_resolutions'))
 	apply_state_item('benchmark_cycle_count', args.get('benchmark_cycle_count'))
+	apply_state_item('api_host', args.get('api_host'))
+	apply_state_item('api_port', args.get('api_port'))
+	apply_state_item('api_security_strategy', args.get('api_security_strategy'))
 	apply_state_item('video_memory_strategy', args.get('video_memory_strategy'))
-	apply_state_item('system_memory_limit', args.get('system_memory_limit'))
 	apply_state_item('log_level', args.get('log_level'))
 	apply_state_item('halt_on_error', args.get('halt_on_error'))
 	apply_state_item('job_id', args.get('job_id'))
@@ -85,33 +89,41 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('step_index', args.get('step_index'))


-def reduce_step_args(args : Args) -> Args:
+def extract_api_args(state : Union[State, ProcessorState]) -> Args:
+	api_args =\
+	{
+		key: state.get(key) for key in state if key in get_api_arguments()
+	}
+	return api_args
+
+
+def extract_cli_args(state : Union[State, ProcessorState]) -> Args:
+	cli_args =\
+	{
+		key: state.get(key) for key in state if key in get_cli_arguments()
+	}
+	return cli_args
+
+
+def extract_sys_args(state : Union[State, ProcessorState]) -> Args:
+	sys_args =\
+	{
+		key: state.get(key) for key in state if key in get_sys_arguments()
+	}
+	return sys_args
+
+
+def extract_step_args(state : Union[State, ProcessorState]) -> Args:
 	step_args =\
 	{
-		key: args[key] for key in args if key in job_store.get_step_keys()
+		key: state.get(key) for key in state if key in get_cli_arguments() and key not in get_sys_arguments()
 	}
 	return step_args


-def reduce_job_args(args : Args) -> Args:
-	job_args =\
-	{
-		key: args[key] for key in args if key in job_store.get_job_keys()
-	}
-	return job_args
-
-
-def collect_step_args() -> Args:
+def filter_step_args(args : Args) -> Args:
 	step_args =\
 	{
-		key: state_manager.get_item(key) for key in job_store.get_step_keys() #type:ignore[arg-type]
+		key: args.get(key) for key in args if key in get_cli_arguments() and key not in get_sys_arguments()
 	}
 	return step_args
-
-
-def collect_job_args() -> Args:
-	job_args =\
-	{
-		key: state_manager.get_item(key) for key in job_store.get_job_keys() #type:ignore[arg-type]
-	}
-	return job_args
@@ -1,5 +1,6 @@
+import math
 from functools import lru_cache
-from typing import Any, List, Optional
+from typing import Any, List, Optional, Tuple

 import numpy
 import scipy
@@ -7,7 +8,8 @@ from numpy.typing import NDArray

 from facefusion.ffmpeg import read_audio_buffer
 from facefusion.filesystem import is_audio
-from facefusion.types import Audio, AudioFrame, Fps, Mel, MelFilterBank, Spectrogram
+from facefusion.media_helper import restrict_trim_frame
+from facefusion.types import Audio, AudioFrame, Duration, Fps, Mel, MelFilterBank, Spectrogram
 from facefusion.voice_extractor import batch_extract_voice


@@ -141,3 +143,29 @@ def create_spectrogram(audio : Audio) -> Spectrogram:
 	spectrogram = scipy.signal.stft(audio, nperseg = mel_bin_total, nfft = mel_bin_total, noverlap = mel_bin_overlap)[2]
 	spectrogram = numpy.dot(mel_filter_bank, numpy.abs(spectrogram))
 	return spectrogram
+
+
+def count_audio_frame_total(audio_path : str, fps : Fps) -> int:
+	audio_duration = detect_audio_duration(audio_path)
+	if audio_duration > 0:
+		return math.ceil(audio_duration * fps)
+	return 0
+
+
+def detect_audio_duration(audio_path : str) -> Duration:
+	audio_sample_rate = 48000
+	audio_sample_size = 16
+	audio_channel_total = 2
+
+	if is_audio(audio_path):
+		audio_buffer = read_audio_buffer(audio_path, audio_sample_rate, audio_sample_size, audio_channel_total)
+		if audio_buffer:
+			audio = numpy.frombuffer(audio_buffer, dtype = numpy.int16).reshape(-1, audio_channel_total)
+			audio_duration = len(audio) / audio_sample_rate
+			return audio_duration
+	return 0
+
+
+def restrict_trim_audio_frame(audio_path : str, fps : Fps, trim_frame_start : Optional[int], trim_frame_end : Optional[int]) -> Tuple[int, int]:
+	audio_frame_total = count_audio_frame_total(audio_path, fps)
+	return restrict_trim_frame(audio_frame_total, trim_frame_start, trim_frame_end)
@@ -9,7 +9,7 @@ import facefusion.choices
 from facefusion import content_analyser, core, state_manager
 from facefusion.cli_helper import render_table
 from facefusion.download import conditional_download, resolve_download_url
-from facefusion.face_store import clear_static_faces
+from facefusion.face_store import clear_faces
 from facefusion.filesystem import get_file_extension
 from facefusion.types import BenchmarkCycleSet
 from facefusion.vision import count_video_frame_total, detect_video_fps
@@ -64,7 +64,7 @@ def cycle(cycle_count : int) -> BenchmarkCycleSet:
 		if state_manager.get_item('benchmark_mode') == 'cold':
 			content_analyser.analyse_image.cache_clear()
 			content_analyser.analyse_video.cache_clear()
-			clear_static_faces()
+			clear_faces()

 		start_time = perf_counter()
 		core.conditional_process()
@@ -0,0 +1,65 @@
+from argparse import Action
+from typing import Dict, List
+
+from facefusion.types import CapabilityGroup, CapabilitySet, CapabilityStore, Group, Scope
+
+CAPABILITY_STORE : CapabilityStore =\
+{
+	'api': {},
+	'cli': {},
+	'sys': {}
+}
+
+
+def get_api_capability_group() -> CapabilityGroup:
+	capability_group : CapabilityGroup = {}
+
+	for name, value in CAPABILITY_STORE.get('api').items():
+		for group in value.get('groups'):
+			capability_group.setdefault(group, {})[name] = value
+
+	return capability_group
+
+
+def get_api_capability_set() -> Dict[str, CapabilitySet]:
+	return CAPABILITY_STORE.get('api')
+
+
+def get_cli_capability_set() -> Dict[str, CapabilitySet]:
+	return CAPABILITY_STORE.get('cli')
+
+
+def get_sys_capability_set() -> Dict[str, CapabilitySet]:
+	return CAPABILITY_STORE.get('sys')
+
+
+def get_api_arguments() -> List[str]:
+	return list(get_api_capability_set().keys())
+
+
+def get_cli_arguments() -> List[str]:
+	return list(get_cli_capability_set().keys())
+
+
+def get_sys_arguments() -> List[str]:
+	return list(get_sys_capability_set().keys())
+
+
+def register_capability_set(actions : List[Action], scopes : List[Scope], groups : List[Group]) -> None:
+	for action in actions:
+		value : CapabilitySet =\
+		{
+			'default': action.default,
+			'groups': groups
+		}
+
+		if action.choices:
+			value['choices'] = list(action.choices)
+
+		for scope in scopes:
+			if scope == 'api':
+				CAPABILITY_STORE['api'][action.dest] = value
+			if scope == 'cli':
+				CAPABILITY_STORE['cli'][action.dest] = value
+			if scope == 'sys':
+				CAPABILITY_STORE['sys'][action.dest] = value
@@ -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, ApiSecurityStrategy, AudioEncoder, AudioFormat, AudioSet, BenchmarkMode, BenchmarkResolution, BenchmarkSet, DownloadProvider, DownloadProviderSet, DownloadScope, ExecutionProvider, ExecutionProviderSet, FaceDetectorModel, FaceDetectorSet, FaceLandmarkerModel, FaceMaskArea, FaceMaskAreaSet, FaceMaskRegion, FaceMaskRegionSet, FaceMaskType, FaceOccluderModel, FaceParserModel, FaceSelectorGender, FaceSelectorMode, FaceSelectorOrder, FaceSelectorRace, Gender, ImageEncoder, ImageFormat, ImageSet, JobStatus, LogLevel, LogLevelSet, Race, Score, TempFrameFormat, VideoEncoder, VideoFormat, VideoMemoryStrategy, VideoPreset, VideoSet, VoiceExtractorModel, WorkFlow

 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))
@@ -45,48 +47,46 @@ face_mask_regions : List[FaceMaskRegion] = list(get_args(FaceMaskRegion))

 voice_extractor_models : List[VoiceExtractorModel] = list(get_args(VoiceExtractorModel))

-audio_type_set : AudioTypeSet =\
+workflows : List[WorkFlow] = [ 'auto', 'audio-to-image:frames', 'audio-to-image:video', 'image-to-image', 'image-to-video', 'image-to-video:frames' ]
+
+audio_set : AudioSet =\
 {
-	'flac': 'audio/flac',
-	'm4a': 'audio/mp4',
-	'mp3': 'audio/mpeg',
-	'ogg': 'audio/ogg',
-	'opus': 'audio/opus',
-	'wav': 'audio/x-wav'
+	'flac': 'flac',
+	'm4a': 'aac',
+	'mp3': 'libmp3lame',
+	'ogg': 'flac',
+	'opus': 'libopus',
+	'wav': 'pcm_s16le'
 }
-image_type_set : ImageTypeSet =\
+image_set : ImageSet =\
 {
-	'bmp': 'image/bmp',
-	'jpeg': 'image/jpeg',
-	'png': 'image/png',
-	'tiff': 'image/tiff',
-	'webp': 'image/webp'
+	'bmp': 'bmp',
+	'jpeg': 'mjpeg',
+	'png': 'png',
+	'tiff': 'tiff',
+	'webp': 'libwebp'
 }
-video_type_set : VideoTypeSet =\
+video_set : VideoSet =\
 {
-	'avi': 'video/x-msvideo',
-	'm4v': 'video/mp4',
-	'mkv': 'video/x-matroska',
-	'mp4': 'video/mp4',
-	'mpeg': 'video/mpeg',
-	'mov': 'video/quicktime',
-	'mxf': 'application/mxf',
-	'webm': 'video/webm',
-	'wmv': 'video/x-ms-wmv'
+	'avi': 'mpeg4',
+	'm4v': 'libx264',
+	'mkv': 'libx264',
+	'mov': 'libx264',
+	'mp4': 'libx264',
+	'mpeg': 'mpeg1video',
+	'mxf': 'mpeg2video',
+	'webm': 'libvpx-vp9',
+	'wmv': 'msmpeg4'
 }
 audio_formats : List[AudioFormat] = list(get_args(AudioFormat))
 image_formats : List[ImageFormat] = list(get_args(ImageFormat))
 video_formats : List[VideoFormat] = list(get_args(VideoFormat))
 temp_frame_formats : List[TempFrameFormat] = list(get_args(TempFrameFormat))

-output_audio_encoders : List[AudioEncoder] = list(get_args(AudioEncoder))
-output_video_encoders : List[VideoEncoder] = list(get_args(VideoEncoder))
-output_encoder_set : EncoderSet =\
-{
-	'audio': output_audio_encoders,
-	'video': output_video_encoders
-}
-output_video_presets : List[VideoPreset] = list(get_args(VideoPreset))
+audio_encoders : List[AudioEncoder] = list(get_args(AudioEncoder))
+image_encoders : List[ImageEncoder] = list(get_args(ImageEncoder))
+video_encoders : List[VideoEncoder] = list(get_args(VideoEncoder))
+video_presets : List[VideoPreset] = list(get_args(VideoPreset))

 benchmark_modes : List[BenchmarkMode] = list(get_args(BenchmarkMode))
 benchmark_set : BenchmarkSet =\
@@ -138,6 +138,7 @@ download_providers : List[DownloadProvider] = list(get_args(DownloadProvider))
 download_scopes : List[DownloadScope] = list(get_args(DownloadScope))

 video_memory_strategies : List[VideoMemoryStrategy] = list(get_args(VideoMemoryStrategy))
+api_security_strategies : List[ApiSecurityStrategy] = list(get_args(ApiSecurityStrategy))

 log_level_set : LogLevelSet =\
 {
@@ -148,12 +149,10 @@ log_level_set : LogLevelSet =\
 }
 log_levels : List[LogLevel] = list(get_args(LogLevel))

-ui_workflows : List[UiWorkflow] = list(get_args(UiWorkflow))
 job_statuses : List[JobStatus] = list(get_args(JobStatus))

 benchmark_cycle_count_range : Sequence[int] = create_int_range(1, 10, 1)
 execution_thread_count_range : Sequence[int] = create_int_range(1, 32, 1)
-system_memory_limit_range : Sequence[int] = create_int_range(0, 128, 4)
 face_detector_margin_range : Sequence[int] = create_int_range(0, 100, 1)
 face_detector_angles : Sequence[Angle] = create_int_range(0, 270, 90)
 face_detector_score_range : Sequence[Score] = create_float_range(0.0, 1.0, 0.05)
@@ -162,6 +161,8 @@ face_mask_blur_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)
 face_mask_padding_range : Sequence[int] = create_int_range(0, 100, 1)
 face_selector_age_range : Sequence[int] = create_int_range(0, 100, 1)
 reference_face_distance_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)
+face_tracker_score_range : Sequence[Score] = create_float_range(0.0, 0.5, 0.05)
+target_frame_amount_range : Sequence[int] = create_int_range(0, 10, 1)
 output_image_quality_range : Sequence[int] = create_int_range(0, 100, 1)
 output_image_scale_range : Sequence[float] = create_float_range(0.25, 8.0, 0.25)
 output_audio_quality_range : Sequence[int] = create_int_range(0, 100, 1)
@@ -0,0 +1,70 @@
+import ctypes
+import struct
+from typing import Optional
+
+from facefusion.libraries import aom as aom_module
+from facefusion.types import AomDecoder, Buffer, BufferPack
+
+
+def create(thread_count : int) -> Optional[AomDecoder]:
+	aom_library = aom_module.create_static_library()
+
+	if aom_library:
+		aom_decoder = ctypes.create_string_buffer(128)
+		aom_codec = ctypes.c_void_p.in_dll(aom_library, 'aom_codec_av1_dx_algo')
+		config_buffer = ctypes.create_string_buffer(128)
+
+		struct.pack_into('I', config_buffer, 0, thread_count)
+		struct.pack_into('I', config_buffer, 12, 1)
+
+		if aom_library.aom_codec_dec_init_ver(aom_decoder, ctypes.byref(aom_codec), config_buffer, 0, 22) == 0:
+			return aom_decoder
+
+	return None
+
+
+def decode(aom_decoder : AomDecoder, input_buffer : Buffer) -> Optional[BufferPack]:
+	aom_library = aom_module.create_static_library()
+
+	if aom_library and input_buffer:
+		input_total = len(input_buffer)
+		temp_buffer = ctypes.create_string_buffer(input_buffer)
+
+		if aom_library.aom_codec_decode(aom_decoder, temp_buffer, input_total, None) == 0:
+			address = aom_library.aom_codec_get_frame(aom_decoder, ctypes.byref(ctypes.c_void_p(0)))
+
+			if address:
+				frame_width = ctypes.c_uint.from_address(address + 28).value & ~1
+				frame_height = ctypes.c_uint.from_address(address + 32).value & ~1
+
+				return BufferPack(
+					buffer = collect(address, frame_width, frame_height),
+					resolution = (frame_width, frame_height)
+				)
+
+	return None
+
+
+def collect(address : int, frame_width : int, frame_height : int) -> Buffer:
+	output_parts = []
+
+	for index in range(3):
+		plane_pointer = ctypes.c_void_p.from_address(address + 64 + index * 8).value
+		stride = ctypes.c_int.from_address(address + 88 + index * 4).value
+		plane_width = frame_width >> (index > 0)
+		plane_height = frame_height >> (index > 0)
+
+		if stride == plane_width:
+			output_parts.append(ctypes.string_at(plane_pointer, plane_width * plane_height))
+		else:
+			for row in range(plane_height):
+				output_parts.append(ctypes.string_at(plane_pointer + row * stride, plane_width))
+
+	return bytes().join(output_parts)
+
+
+def destroy(aom_decoder : AomDecoder) -> None:
+	aom_library = aom_module.create_static_library()
+
+	if aom_library:
+		aom_library.aom_codec_destroy(aom_decoder)
@@ -0,0 +1,94 @@
+import ctypes
+import struct
+from typing import Optional
+
+from facefusion.libraries import aom as aom_module
+from facefusion.types import AomEncoder, BitRate, Buffer, Resolution
+
+
+def create(frame_resolution : Resolution, bitrate : BitRate, thread_count : int, cpu_count : int) -> Optional[AomEncoder]:
+	aom_library = aom_module.create_static_library()
+
+	if aom_library:
+		aom_encoder = ctypes.create_string_buffer(1152)
+		aom_codec = ctypes.c_void_p.in_dll(aom_library, 'aom_codec_av1_cx_algo')
+
+		config_buffer = ctypes.create_string_buffer(1024)
+
+		if aom_library.aom_codec_enc_config_default(ctypes.byref(aom_codec), config_buffer, 1) == 0:
+			struct.pack_into('I', config_buffer, 4, thread_count)
+			struct.pack_into('I', config_buffer, 12, frame_resolution[0])
+			struct.pack_into('I', config_buffer, 16, frame_resolution[1])
+			struct.pack_into('I', config_buffer, 136, bitrate)
+			struct.pack_into('I', config_buffer, 192, 30)
+
+			if aom_library.aom_codec_enc_init_ver(aom_encoder, ctypes.byref(aom_codec), config_buffer, 0, 25) == 0:
+				aom_library.aom_codec_control(aom_encoder, 13, ctypes.c_int(cpu_count))
+				aom_library.aom_codec_control(aom_encoder, 75, ctypes.c_int(1))
+				aom_library.aom_codec_control(aom_encoder, 106, ctypes.c_int(0))
+				aom_library.aom_codec_control(aom_encoder, 122, ctypes.c_int(0))
+				aom_library.aom_codec_control(aom_encoder, 123, ctypes.c_int(0))
+				ctypes.memmove(ctypes.addressof(aom_encoder) + 128, config_buffer, 1024)
+				return aom_encoder
+
+	return None
+
+
+def encode(aom_encoder : AomEncoder, input_buffer : Buffer, frame_resolution : Resolution, frame_index : int) -> Buffer:
+	aom_library = aom_module.create_static_library()
+	output_buffer = bytes()
+
+	if aom_library:
+		temp_buffer = ctypes.create_string_buffer(256)
+		encode_buffer = ctypes.create_string_buffer(input_buffer)
+
+		if aom_library.aom_img_wrap(temp_buffer, 0x102, frame_resolution[0], frame_resolution[1], 1, encode_buffer) and aom_library.aom_codec_encode(aom_encoder, temp_buffer, frame_index, 1, 0, 1) == 0:
+			output_buffer = collect(aom_encoder)
+
+	return output_buffer
+
+
+def collect(aom_encoder : AomEncoder) -> Buffer:
+	aom_library = aom_module.create_static_library()
+	output_parts = []
+
+	packet_cursor = ctypes.c_void_p(0)
+	packet = aom_library.aom_codec_get_cx_data(aom_encoder, ctypes.byref(packet_cursor))
+
+	while packet:
+		if ctypes.c_int.from_address(packet).value == 0:
+			buffer_pointer = ctypes.c_void_p.from_address(packet + 8).value
+			buffer_size = ctypes.c_size_t.from_address(packet + 16).value
+			output_parts.append(ctypes.string_at(buffer_pointer, buffer_size))
+
+		packet = aom_library.aom_codec_get_cx_data(aom_encoder, ctypes.byref(packet_cursor))
+
+	return bytes().join(output_parts)
+
+
+def update_resolution(aom_encoder : AomEncoder, frame_resolution : Resolution) -> bool:
+	aom_library = aom_module.create_static_library()
+
+	if aom_library:
+		struct.pack_into('I', aom_encoder, 128 + 12, frame_resolution[0])
+		struct.pack_into('I', aom_encoder, 128 + 16, frame_resolution[1])
+		return aom_library.aom_codec_enc_config_set(aom_encoder, ctypes.cast(ctypes.addressof(aom_encoder) + 128, ctypes.c_void_p)) == 0
+
+	return False
+
+
+def update_bitrate(aom_encoder : AomEncoder, bitrate : BitRate) -> bool:
+	aom_library = aom_module.create_static_library()
+
+	if aom_library:
+		struct.pack_into('I', aom_encoder, 128 + 136, bitrate)
+		return aom_library.aom_codec_enc_config_set(aom_encoder, ctypes.cast(ctypes.addressof(aom_encoder) + 128, ctypes.c_void_p)) == 0
+
+	return False
+
+
+def destroy(aom_encoder : AomEncoder) -> None:
+	aom_library = aom_module.create_static_library()
+
+	if aom_library:
+		aom_library.aom_codec_destroy(aom_encoder)
@@ -0,0 +1,38 @@
+import ctypes
+from typing import Optional
+
+from facefusion.libraries import opus as opus_module
+from facefusion.types import Buffer, OpusDecoder
+
+
+def create(sample_rate : int, channel_total : int) -> Optional[OpusDecoder]:
+	opus_library = opus_module.create_static_library()
+
+	if opus_library:
+		return opus_library.opus_decoder_create(sample_rate, channel_total, ctypes.byref(ctypes.c_int(0)))
+
+	return None
+
+
+def decode(opus_decoder : OpusDecoder, input_buffer : Buffer, channel_total : int) -> Buffer:
+	opus_library = opus_module.create_static_library()
+	output_buffer = bytes()
+
+	if opus_library:
+		input_total = len(input_buffer)
+		sample_size = ctypes.sizeof(ctypes.c_float)
+		sample_total = opus_library.opus_decoder_get_nb_samples(opus_decoder, input_buffer, input_total)
+		sample_buffer = (ctypes.c_float * (sample_total * channel_total))()
+		output_total = opus_library.opus_decode_float(opus_decoder, input_buffer, input_total, sample_buffer, sample_total, 0)
+
+		if output_total:
+			output_buffer = ctypes.string_at(ctypes.addressof(sample_buffer), output_total * channel_total * sample_size)
+
+	return output_buffer
+
+
+def destroy(opus_decoder : OpusDecoder) -> None:
+	opus_library = opus_module.create_static_library()
+
+	if opus_library:
+		opus_library.opus_decoder_destroy(opus_decoder)
@@ -0,0 +1,38 @@
+import ctypes
+from typing import Optional
+
+from facefusion.libraries import opus as opus_module
+from facefusion.types import Buffer, OpusEncoder
+
+
+def create(sample_rate : int, channel_total : int) -> Optional[OpusEncoder]:
+	opus_library = opus_module.create_static_library()
+
+	if opus_library:
+		return opus_library.opus_encoder_create(sample_rate, channel_total, 2049, ctypes.byref(ctypes.c_int(0)))
+
+	return None
+
+
+def encode(opus_encoder : OpusEncoder, input_buffer : Buffer, channel_total : int) -> Buffer:
+	opus_library = opus_module.create_static_library()
+	output_buffer = bytes()
+
+	if opus_library:
+		sample_size = ctypes.sizeof(ctypes.c_float)
+		sample_total = len(input_buffer) // (sample_size * channel_total)
+		sample_buffer = (ctypes.c_float * (sample_total * channel_total)).from_buffer_copy(input_buffer)
+		temp_buffer = ctypes.create_string_buffer(2048)
+		output_total = opus_library.opus_encode_float(opus_encoder, sample_buffer, sample_total, temp_buffer, 2048)
+
+		if output_total:
+			output_buffer = temp_buffer.raw[:output_total]
+
+	return output_buffer
+
+
+def destroy(opus_encoder : OpusEncoder) -> None:
+	opus_library = opus_module.create_static_library()
+
+	if opus_library:
+		opus_library.opus_encoder_destroy(opus_encoder)
@@ -0,0 +1,74 @@
+import ctypes
+import struct
+from typing import Optional
+
+from facefusion.libraries import vpx as vpx_module
+from facefusion.types import Buffer, BufferPack, VpxDecoder, VxpVideoCodec
+
+
+def create(video_codec : VxpVideoCodec, thread_count : int) -> Optional[VpxDecoder]:
+	vpx_library = vpx_module.create_static_library()
+
+	if vpx_library:
+		vpx_decoder = ctypes.create_string_buffer(64)
+		vpx_algo = 'vpx_codec_vp8_dx_algo'
+
+		if video_codec == 'vp9':
+			vpx_algo = 'vpx_codec_vp9_dx_algo'
+
+		vpx_codec = ctypes.c_void_p.in_dll(vpx_library, vpx_algo)
+		config_buffer = ctypes.create_string_buffer(128)
+
+		struct.pack_into('I', config_buffer, 0, thread_count)
+
+		if vpx_library.vpx_codec_dec_init_ver(vpx_decoder, ctypes.byref(vpx_codec), config_buffer, 0, 12) == 0:
+			return vpx_decoder
+
+	return None
+
+
+def decode(vpx_decoder : VpxDecoder, input_buffer : Buffer) -> Optional[BufferPack]:
+	vpx_library = vpx_module.create_static_library()
+
+	if vpx_library and input_buffer:
+		input_total = len(input_buffer)
+		temp_buffer = ctypes.create_string_buffer(input_buffer)
+
+		if vpx_library.vpx_codec_decode(vpx_decoder, temp_buffer, input_total, None, 0) == 0:
+			address = vpx_library.vpx_codec_get_frame(vpx_decoder, ctypes.byref(ctypes.c_void_p(0)))
+
+			if address:
+				frame_width = ctypes.c_uint.from_address(address + 24).value & ~1
+				frame_height = ctypes.c_uint.from_address(address + 28).value & ~1
+
+				return BufferPack(
+					buffer = collect(address, frame_width, frame_height),
+					resolution = (frame_width, frame_height)
+				)
+
+	return None
+
+
+def collect(address : int, frame_width : int, frame_height : int) -> Buffer:
+	output_parts = []
+
+	for index in range(3):
+		plane_pointer = ctypes.c_void_p.from_address(address + 48 + index * 8).value
+		stride = ctypes.c_int.from_address(address + 80 + index * 4).value
+		plane_width = frame_width >> (index > 0)
+		plane_height = frame_height >> (index > 0)
+
+		if stride == plane_width:
+			output_parts.append(ctypes.string_at(plane_pointer, plane_width * plane_height))
+		else:
+			for row in range(plane_height):
+				output_parts.append(ctypes.string_at(plane_pointer + row * stride, plane_width))
+
+	return bytes().join(output_parts)
+
+
+def destroy(vpx_decoder : VpxDecoder) -> None:
+	vpx_library = vpx_module.create_static_library()
+
+	if vpx_library:
+		vpx_library.vpx_codec_destroy(vpx_decoder)
@@ -0,0 +1,104 @@
+import ctypes
+import struct
+from typing import Optional
+
+from facefusion.libraries import vpx as vpx_module
+from facefusion.types import BitRate, Buffer, Resolution, VpxEncoder, VxpVideoCodec
+
+
+def create(video_codec : VxpVideoCodec, frame_resolution : Resolution, bitrate : BitRate, thread_count : int, cpu_count : int) -> Optional[VpxEncoder]:
+	vpx_library = vpx_module.create_static_library()
+
+	if vpx_library:
+		vpx_encoder = ctypes.create_string_buffer(640)
+		vpx_algo = 'vpx_codec_vp8_cx_algo'
+
+		if video_codec == 'vp9':
+			vpx_algo = 'vpx_codec_vp9_cx_algo'
+
+		vpx_codec = ctypes.c_void_p.in_dll(vpx_library, vpx_algo)
+
+		config_buffer = ctypes.create_string_buffer(512)
+
+		if vpx_library.vpx_codec_enc_config_default(ctypes.byref(vpx_codec), config_buffer, 0) == 0:
+			struct.pack_into('I', config_buffer, 4, thread_count)
+			struct.pack_into('I', config_buffer, 12, frame_resolution[0])
+			struct.pack_into('I', config_buffer, 16, frame_resolution[1])
+			struct.pack_into('I', config_buffer, 28, 1)
+			struct.pack_into('I', config_buffer, 36, 0)
+			struct.pack_into('I', config_buffer, 44, 0)
+			struct.pack_into('I', config_buffer, 72, 0)
+			struct.pack_into('I', config_buffer, 112, bitrate)
+			struct.pack_into('I', config_buffer, 116, 2)
+			struct.pack_into('I', config_buffer, 120, 50)
+			struct.pack_into('I', config_buffer, 124, 50)
+			struct.pack_into('I', config_buffer, 128, 50)
+
+			if vpx_library.vpx_codec_enc_init_ver(vpx_encoder, ctypes.byref(vpx_codec), config_buffer, 0, 39) == 0:
+				vpx_library.vpx_codec_control_(vpx_encoder, 13, ctypes.c_int(cpu_count))
+				vpx_library.vpx_codec_control_(vpx_encoder, 12, ctypes.c_int(0))
+				vpx_library.vpx_codec_control_(vpx_encoder, 27, ctypes.c_int(10))
+				ctypes.memmove(ctypes.addressof(vpx_encoder) + 64, config_buffer, 512)
+				return vpx_encoder
+
+	return None
+
+
+def encode(vpx_encoder : VpxEncoder, input_buffer : Buffer, frame_resolution : Resolution, frame_index : int) -> Buffer:
+	vpx_library = vpx_module.create_static_library()
+	output_buffer = bytes()
+
+	if vpx_library:
+		temp_buffer = ctypes.create_string_buffer(256)
+		encode_buffer = ctypes.create_string_buffer(input_buffer)
+
+		if vpx_library.vpx_img_wrap(temp_buffer, 0x102, frame_resolution[0], frame_resolution[1], 1, encode_buffer) and vpx_library.vpx_codec_encode(vpx_encoder, temp_buffer, frame_index, 1, 0, 1) == 0:
+			output_buffer = collect(vpx_encoder)
+
+	return output_buffer
+
+
+def collect(vpx_encoder : VpxEncoder) -> Buffer:
+	vpx_library = vpx_module.create_static_library()
+	output_parts = []
+
+	packet_cursor = ctypes.c_void_p(0)
+	packet = vpx_library.vpx_codec_get_cx_data(vpx_encoder, ctypes.byref(packet_cursor))
+
+	while packet:
+		if ctypes.c_int.from_address(packet).value == 0:
+			buffer_pointer = ctypes.c_void_p.from_address(packet + 8).value
+			buffer_size = ctypes.c_size_t.from_address(packet + 16).value
+			output_parts.append(ctypes.string_at(buffer_pointer, buffer_size))
+
+		packet = vpx_library.vpx_codec_get_cx_data(vpx_encoder, ctypes.byref(packet_cursor))
+
+	return bytes().join(output_parts)
+
+
+def update_resolution(vpx_encoder : VpxEncoder, frame_resolution : Resolution) -> bool:
+	vpx_library = vpx_module.create_static_library()
+
+	if vpx_library:
+		struct.pack_into('I', vpx_encoder, 64 + 12, frame_resolution[0])
+		struct.pack_into('I', vpx_encoder, 64 + 16, frame_resolution[1])
+		return vpx_library.vpx_codec_enc_config_set(vpx_encoder, ctypes.cast(ctypes.addressof(vpx_encoder) + 64, ctypes.c_void_p)) == 0
+
+	return False
+
+
+def update_bitrate(vpx_encoder : VpxEncoder, bitrate : BitRate) -> bool:
+	vpx_library = vpx_module.create_static_library()
+
+	if vpx_library:
+		struct.pack_into('I', vpx_encoder, 64 + 112, bitrate)
+		return vpx_library.vpx_codec_enc_config_set(vpx_encoder, ctypes.cast(ctypes.addressof(vpx_encoder) + 64, ctypes.c_void_p)) == 0
+
+	return False
+
+
+def destroy(vpx_encoder : VpxEncoder) -> None:
+	vpx_library = vpx_module.create_static_library()
+
+	if vpx_library:
+		vpx_library.vpx_codec_destroy(vpx_encoder)
@@ -78,6 +78,12 @@ def get_first(__list__ : Any) -> Any:
 	return None


+def get_middle(__list__ : Any) -> Any:
+	if isinstance(__list__, Sequence) and __list__:
+		return __list__[len(__list__) // 2]
+	return None
+
+
 def get_last(__list__ : Any) -> Any:
 	if isinstance(__list__, Reversible):
 		return next(reversed(__list__), None)
@@ -1,29 +1,20 @@
 from configparser import ConfigParser
+from functools import lru_cache
 from typing import List, Optional

 from facefusion import state_manager
 from facefusion.common_helper import cast_bool, cast_float, cast_int

-CONFIG_PARSER = None

-
-def get_config_parser() -> ConfigParser:
-	global CONFIG_PARSER
-
-	if CONFIG_PARSER is None:
-		CONFIG_PARSER = ConfigParser()
-		CONFIG_PARSER.read(state_manager.get_item('config_path'), encoding = 'utf-8')
-	return CONFIG_PARSER
-
-
-def clear_config_parser() -> None:
-	global CONFIG_PARSER
-
-	CONFIG_PARSER = None
+@lru_cache
+def get_static_config_parser() -> ConfigParser:
+	config_parser = ConfigParser()
+	config_parser.read(state_manager.get_item('config_path'), encoding = 'utf-8')
+	return config_parser


 def get_str_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[str]:
-	config_parser = get_config_parser()
+	config_parser = get_static_config_parser()

 	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
 		return config_parser.get(section, option)
@@ -31,7 +22,7 @@ def get_str_value(section : str, option : str, fallback : Optional[str] = None)


 def get_int_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[int]:
-	config_parser = get_config_parser()
+	config_parser = get_static_config_parser()

 	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
 		return config_parser.getint(section, option)
@@ -39,7 +30,7 @@ def get_int_value(section : str, option : str, fallback : Optional[str] = None)


 def get_float_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[float]:
-	config_parser = get_config_parser()
+	config_parser = get_static_config_parser()

 	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
 		return config_parser.getfloat(section, option)
@@ -47,7 +38,7 @@ def get_float_value(section : str, option : str, fallback : Optional[str] = None


 def get_bool_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[bool]:
-	config_parser = get_config_parser()
+	config_parser = get_static_config_parser()

 	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
 		return config_parser.getboolean(section, option)
@@ -55,7 +46,7 @@ def get_bool_value(section : str, option : str, fallback : Optional[str] = None)


 def get_str_list(section : str, option : str, fallback : Optional[str] = None) -> Optional[List[str]]:
-	config_parser = get_config_parser()
+	config_parser = get_static_config_parser()

 	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
 		return config_parser.get(section, option).split()
@@ -65,7 +56,7 @@ def get_str_list(section : str, option : str, fallback : Optional[str] = None) -


 def get_int_list(section : str, option : str, fallback : Optional[str] = None) -> Optional[List[int]]:
-	config_parser = get_config_parser()
+	config_parser = get_static_config_parser()

 	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
 		return list(map(int, config_parser.get(section, option).split()))
@@ -1,16 +1,14 @@
 from functools import lru_cache
-from typing import List, Tuple
+from typing import Tuple

 import numpy
 from tqdm import tqdm

 from facefusion import inference_manager, state_manager, translator
-from facefusion.common_helper import is_macos
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.execution import has_execution_provider
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.types import Detection, DownloadScope, DownloadSet, ExecutionProvider, Fps, InferencePool, ModelSet, VisionFrame
+from facefusion.types import Detection, DownloadScope, DownloadSet, Fps, InferencePool, ModelSet, VisionFrame
 from facefusion.vision import detect_video_fps, fit_contain_frame, read_image, read_video_frame

 STREAM_COUNTER = 0
@@ -119,12 +117,6 @@ def clear_inference_pool() -> None:
 	inference_manager.clear_inference_pool(__name__, model_names)


-def resolve_execution_providers() -> List[ExecutionProvider]:
-	if is_macos() and has_execution_provider('coreml'):
-		return [ 'cpu' ]
-	return state_manager.get_item('execution_providers')
-
-
 def collect_model_downloads() -> Tuple[DownloadSet, DownloadSet]:
 	model_set = create_static_model_set('full')
 	model_hash_set = {}
@@ -175,10 +167,12 @@ def analyse_video(video_path : str, trim_frame_start : int, trim_frame_end : int
 		for frame_number in frame_range:
 			if frame_number % int(video_fps) == 0:
 				vision_frame = read_video_frame(video_path, frame_number)
-				total += 1

-				if analyse_frame(vision_frame):
-					counter += 1
+				if numpy.any(vision_frame):
+					total += 1
+
+					if analyse_frame(vision_frame):
+						counter += 1

 			if counter > 0 and total > 0:
 				rate = counter / total * 100
@@ -5,19 +5,22 @@ import signal
 import sys
 from time import time

-from facefusion import benchmarker, cli_helper, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, hash_helper, logger, state_manager, translator, voice_extractor
-from facefusion.args import apply_args, collect_job_args, reduce_job_args, reduce_step_args
+import uvicorn
+
+import facefusion.apis.core
+from facefusion import args_helper, benchmarker, cli_helper, content_analyser, hash_helper, logger, state_manager, translator
+from facefusion.args_helper import apply_args
 from facefusion.download import conditional_download_hashes, conditional_download_sources
 from facefusion.exit_helper import hard_exit, signal_exit
-from facefusion.filesystem import get_file_extension, get_file_name, is_image, is_video, resolve_file_paths, resolve_file_pattern
+from facefusion.filesystem import get_file_extension, has_audio, has_image, has_video
+from facefusion.filesystem import get_file_name, resolve_file_paths, resolve_file_pattern
 from facefusion.jobs import job_helper, job_manager, job_runner
 from facefusion.jobs.job_list import compose_job_list
-from facefusion.memory import limit_system_memory
 from facefusion.processors.core import get_processors_modules
 from facefusion.program import create_program
 from facefusion.program_helper import validate_args
-from facefusion.types import Args, ErrorCode
-from facefusion.workflows import image_to_image, image_to_video
+from facefusion.types import Args, ErrorCode, WorkFlow
+from facefusion.workflows import audio_to_image, audio_to_image_as_frames, image_to_image, image_to_video, image_to_video_as_frames


 def cli() -> None:
@@ -41,11 +44,6 @@ def cli() -> None:


 def route(args : Args) -> None:
-	system_memory_limit = state_manager.get_item('system_memory_limit')
-
-	if system_memory_limit and system_memory_limit > 0:
-		limit_system_memory(system_memory_limit)
-
 	if state_manager.get_item('command') == 'force-download':
 		error_code = force_download()
 		hard_exit(error_code)
@@ -55,37 +53,34 @@ def route(args : Args) -> None:
 			hard_exit(2)
 		benchmarker.render()

+	if state_manager.get_item('command') == 'api':
+		if not common_pre_check() or not processors_pre_check() or not facefusion.apis.core.pre_check():
+			hard_exit(2)
+
+		logger.info(translator.get('api_started').format(host = state_manager.get_item('api_host'), port = state_manager.get_item('api_port')), __name__)
+		uvicorn.run(facefusion.apis.core.create_api(), host = state_manager.get_item('api_host'), port = state_manager.get_item('api_port'))
+		hard_exit(1)
+
 	if state_manager.get_item('command') in [ 'job-list', 'job-create', 'job-submit', 'job-submit-all', 'job-delete', 'job-delete-all', 'job-add-step', 'job-remix-step', 'job-insert-step', 'job-remove-step' ]:
-		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
+		if not job_manager.init_jobs(state_manager.get_jobs_path()):
 			hard_exit(1)
 		error_code = route_job_manager(args)
 		hard_exit(error_code)

 	if state_manager.get_item('command') == 'run':
-		import facefusion.uis.core as ui
-
-		if not common_pre_check() or not processors_pre_check():
-			hard_exit(2)
-		for ui_layout in ui.get_ui_layouts_modules(state_manager.get_item('ui_layouts')):
-			if not ui_layout.pre_check():
-				hard_exit(2)
-		ui.init()
-		ui.launch()
-
-	if state_manager.get_item('command') == 'headless-run':
-		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
+		if not job_manager.init_jobs(state_manager.get_jobs_path()):
 			hard_exit(1)
 		error_code = process_headless(args)
 		hard_exit(error_code)

 	if state_manager.get_item('command') == 'batch-run':
-		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
+		if not job_manager.init_jobs(state_manager.get_jobs_path()):
 			hard_exit(1)
 		error_code = process_batch(args)
 		hard_exit(error_code)

 	if state_manager.get_item('command') in [ 'job-run', 'job-run-all', 'job-retry', 'job-retry-all' ]:
-		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
+		if not job_manager.init_jobs(state_manager.get_jobs_path()):
 			hard_exit(1)
 		error_code = route_job_runner()
 		hard_exit(error_code)
@@ -107,21 +102,9 @@ def pre_check() -> bool:


 def common_pre_check() -> bool:
-	common_modules =\
-	[
-		content_analyser,
-		face_classifier,
-		face_detector,
-		face_landmarker,
-		face_masker,
-		face_recognizer,
-		voice_extractor
-	]
-
 	content_analyser_content = inspect.getsource(content_analyser).encode()
-	content_analyser_hash = hash_helper.create_hash(content_analyser_content)

-	return all(module.pre_check() for module in common_modules) and content_analyser_hash == 'b14e7b92'
+	return hash_helper.create_hash(content_analyser_content) == '975d67d6'


 def processors_pre_check() -> bool:
@@ -132,22 +115,19 @@ def processors_pre_check() -> bool:


 def force_download() -> ErrorCode:
-	common_modules =\
-	[
-		content_analyser,
-		face_classifier,
-		face_detector,
-		face_landmarker,
-		face_masker,
-		face_recognizer,
-		voice_extractor
-	]
+	download_scope = state_manager.get_item('download_scope')
 	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
 	processor_modules = get_processors_modules(available_processors)
+	common_modules = []
+
+	for processor_module in processor_modules:
+		for common_module in processor_module.get_common_modules():
+			if common_module not in common_modules:
+				common_modules.append(common_module)

 	for module in common_modules + processor_modules:
 		if hasattr(module, 'create_static_model_set'):
-			for model in module.create_static_model_set(state_manager.get_item('download_scope')).values():
+			for model in module.create_static_model_set(download_scope).values():
 				model_hash_set = model.get('hashes')
 				model_source_set = model.get('sources')

@@ -203,7 +183,7 @@ def route_job_manager(args : Args) -> ErrorCode:
 		return 1

 	if state_manager.get_item('command') == 'job-add-step':
-		step_args = reduce_step_args(args)
+		step_args = args_helper.filter_step_args(args)

 		if job_manager.add_step(state_manager.get_item('job_id'), step_args):
 			logger.info(translator.get('job_step_added').format(job_id = state_manager.get_item('job_id')), __name__)
@@ -212,7 +192,7 @@ def route_job_manager(args : Args) -> ErrorCode:
 		return 1

 	if state_manager.get_item('command') == 'job-remix-step':
-		step_args = reduce_step_args(args)
+		step_args = args_helper.filter_step_args(args)

 		if job_manager.remix_step(state_manager.get_item('job_id'), state_manager.get_item('step_index'), step_args):
 			logger.info(translator.get('job_remix_step_added').format(job_id = state_manager.get_item('job_id'), step_index = state_manager.get_item('step_index')), __name__)
@@ -221,7 +201,7 @@ def route_job_manager(args : Args) -> ErrorCode:
 		return 1

 	if state_manager.get_item('command') == 'job-insert-step':
-		step_args = reduce_step_args(args)
+		step_args = args_helper.filter_step_args(args)

 		if job_manager.insert_step(state_manager.get_item('job_id'), state_manager.get_item('step_index'), step_args):
 			logger.info(translator.get('job_step_inserted').format(job_id = state_manager.get_item('job_id'), step_index = state_manager.get_item('step_index')), __name__)
@@ -275,7 +255,7 @@ def route_job_runner() -> ErrorCode:

 def process_headless(args : Args) -> ErrorCode:
 	job_id = job_helper.suggest_job_id('headless')
-	step_args = reduce_step_args(args)
+	step_args = args_helper.filter_step_args(args)

 	if job_manager.create_job(job_id) and job_manager.add_step(job_id, step_args) and job_manager.submit_job(job_id) and job_runner.run_job(job_id, process_step):
 		return 0
@@ -284,10 +264,9 @@ def process_headless(args : Args) -> ErrorCode:

 def process_batch(args : Args) -> ErrorCode:
 	job_id = job_helper.suggest_job_id('batch')
-	step_args = reduce_step_args(args)
-	job_args = reduce_job_args(args)
-	source_paths = resolve_file_pattern(job_args.get('source_pattern'))
-	target_paths = resolve_file_pattern(job_args.get('target_pattern'))
+	step_args = args_helper.filter_step_args(args)
+	source_paths = resolve_file_pattern(step_args.get('source_pattern'))
+	target_paths = resolve_file_pattern(step_args.get('target_pattern'))

 	if job_manager.create_job(job_id):
 		if source_paths and target_paths:
@@ -296,7 +275,7 @@ def process_batch(args : Args) -> ErrorCode:
 				step_args['target_path'] = target_path

 				try:
-					step_args['output_path'] = job_args.get('output_pattern').format(index = index, source_name = get_file_name(source_path), target_name = get_file_name(target_path), target_extension = get_file_extension(target_path))
+					step_args['output_path'] = step_args.get('output_pattern').format(index = index, source_name = get_file_name(source_path), target_name = get_file_name(target_path), target_extension = get_file_extension(target_path))
 				except KeyError:
 					return 1

@@ -310,7 +289,7 @@ def process_batch(args : Args) -> ErrorCode:
 				step_args['target_path'] = target_path

 				try:
-					step_args['output_path'] = job_args.get('output_pattern').format(index = index, target_name = get_file_name(target_path), target_extension = get_file_extension(target_path))
+					step_args['output_path'] = step_args.get('output_pattern').format(index = index, target_name = get_file_name(target_path), target_extension = get_file_extension(target_path))
 				except KeyError:
 					return 1

@@ -323,8 +302,10 @@ def process_batch(args : Args) -> ErrorCode:

 def process_step(job_id : str, step_index : int, step_args : Args) -> bool:
 	step_total = job_manager.count_step_total(job_id)
-	step_args.update(collect_job_args())
-	apply_args(step_args, state_manager.set_item)
+	cli_args = args_helper.extract_cli_args(state_manager.get_state())
+	args = cli_args.copy()
+	args.update(step_args)
+	apply_args(args, state_manager.set_item)

 	logger.info(translator.get('processing_step').format(step_current = step_index + 1, step_total = step_total), __name__)
 	if common_pre_check() and processors_pre_check():
@@ -336,15 +317,36 @@ def process_step(job_id : str, step_index : int, step_args : Args) -> bool:
 def conditional_process() -> ErrorCode:
 	start_time = time()

+	if state_manager.get_item('workflow') == 'auto':
+		state_manager.set_item('workflow', detect_workflow())
+
 	for processor_module in get_processors_modules(state_manager.get_item('processors')):
 		if not processor_module.pre_process('output'):
 			return 2

-	if is_image(state_manager.get_item('target_path')):
+	if state_manager.get_item('workflow') == 'audio-to-image:video':
+		return audio_to_image.process(start_time)
+	if state_manager.get_item('workflow') == 'audio-to-image:frames':
+		return audio_to_image_as_frames.process(start_time)
+	if state_manager.get_item('workflow') == 'image-to-image':
 		return image_to_image.process(start_time)
-	if is_video(state_manager.get_item('target_path')):
+	if state_manager.get_item('workflow') == 'image-to-video':
 		return image_to_video.process(start_time)
+	if state_manager.get_item('workflow') == 'image-to-video:frames':
+		return image_to_video_as_frames.process(start_time)

 	return 0


+def detect_workflow() -> WorkFlow:
+	if has_video([ state_manager.get_item('target_path') ]):
+		if get_file_extension(state_manager.get_item('output_path')):
+			return 'image-to-video'
+		return 'image-to-video:frames'
+
+	if has_audio(state_manager.get_item('source_paths')) and has_image([ state_manager.get_item('target_path') ]):
+		if get_file_extension(state_manager.get_item('output_path')):
+			return 'audio-to-image:video'
+		return 'audio-to-image:frames'
+
+	return 'image-to-image'
@@ -10,10 +10,10 @@ import facefusion.choices
 from facefusion import curl_builder, logger, process_manager, state_manager, translator
 from facefusion.filesystem import get_file_name, get_file_size, is_file, remove_file
 from facefusion.hash_helper import validate_hash
-from facefusion.types import Command, DownloadProvider, DownloadSet
+from facefusion.types import Buffer, Command, DownloadProvider, DownloadSet


-def open_curl(commands : List[Command]) -> subprocess.Popen[bytes]:
+def open_curl(commands : List[Command]) -> subprocess.Popen[Buffer]:
 	commands = curl_builder.run(commands)
 	return subprocess.Popen(commands, stdin = subprocess.PIPE, stdout = subprocess.PIPE)

@@ -1,15 +1,13 @@
 import os
-import shutil
-import subprocess
-import xml.etree.ElementTree as ElementTree
 from functools import lru_cache
-from typing import List, Optional
+from typing import List, Tuple

 import onnxruntime

 import facefusion.choices
 from facefusion.filesystem import create_directory, is_directory
-from facefusion.types import ExecutionDevice, ExecutionProvider, InferenceOptionSet, InferenceProvider, ValueAndUnit
+from facefusion.system import detect_graphic_devices
+from facefusion.types import ExecutionProvider, InferenceOptionSet, InferenceProvider

 onnxruntime.set_default_logger_severity(3)

@@ -39,7 +37,7 @@ def create_inference_providers(execution_device_id : int, execution_providers :
 			inference_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
 			{
 				'device_id': execution_device_id,
-				'cudnn_conv_algo_search': resolve_cudnn_conv_algo_search()
+				'cudnn_conv_algo_search': resolve_static_cudnn_conv_algo_search(tuple(execution_providers))
 			}))

 		if execution_provider == 'tensorrt':
@@ -112,13 +110,19 @@ def resolve_cache_path() -> str:
 	return os.path.join('.caches', onnxruntime.get_version_string())


-def resolve_cudnn_conv_algo_search() -> str:
-	execution_devices = detect_static_execution_devices()
-	product_names = ('GeForce GTX 1630', 'GeForce GTX 1650', 'GeForce GTX 1660')
+@lru_cache()
+def resolve_static_cudnn_conv_algo_search(execution_providers : Tuple[ExecutionProvider, ...]) -> str:
+	return resolve_cudnn_conv_algo_search(list(execution_providers))

-	for execution_device in execution_devices:
-		if execution_device.get('product').get('name').startswith(product_names):
-			return 'DEFAULT'
+
+def resolve_cudnn_conv_algo_search(execution_providers : List[ExecutionProvider]) -> str:
+	if has_execution_provider('cuda') or has_execution_provider('tensorrt'):
+		graphic_devices = detect_graphic_devices(execution_providers)
+		product_names = ('GeForce GTX 1630', 'GeForce GTX 1650', 'GeForce GTX 1660')
+
+		for graphic_device in graphic_devices:
+			if graphic_device.get('product').get('name').startswith(product_names):
+				return 'DEFAULT'

 	return 'EXHAUSTIVE'

@@ -127,68 +131,3 @@ def resolve_openvino_device_type(execution_device_id : int) -> str:
 	if execution_device_id == 0:
 		return 'GPU'
 	return 'GPU.' + str(execution_device_id)
-
-
-def run_nvidia_smi() -> subprocess.Popen[bytes]:
-	commands = [ shutil.which('nvidia-smi'), '--query', '--xml-format' ]
-	return subprocess.Popen(commands, stdout = subprocess.PIPE)
-
-
-@lru_cache()
-def detect_static_execution_devices() -> List[ExecutionDevice]:
-	return detect_execution_devices()
-
-
-def detect_execution_devices() -> List[ExecutionDevice]:
-	execution_devices : List[ExecutionDevice] = []
-
-	try:
-		output, _ = run_nvidia_smi().communicate()
-		root_element = ElementTree.fromstring(output)
-	except Exception:
-		root_element = ElementTree.Element('xml')
-
-	for gpu_element in root_element.findall('gpu'):
-		execution_devices.append(
-		{
-			'driver_version': root_element.findtext('driver_version'),
-			'framework':
-			{
-				'name': 'CUDA',
-				'version': root_element.findtext('cuda_version')
-			},
-			'product':
-			{
-				'vendor': 'NVIDIA',
-				'name': gpu_element.findtext('product_name').replace('NVIDIA', '').strip()
-			},
-			'video_memory':
-			{
-				'total': create_value_and_unit(gpu_element.findtext('fb_memory_usage/total')),
-				'free': create_value_and_unit(gpu_element.findtext('fb_memory_usage/free'))
-			},
-			'temperature':
-			{
-				'gpu': create_value_and_unit(gpu_element.findtext('temperature/gpu_temp')),
-				'memory': create_value_and_unit(gpu_element.findtext('temperature/memory_temp'))
-			},
-			'utilization':
-			{
-				'gpu': create_value_and_unit(gpu_element.findtext('utilization/gpu_util')),
-				'memory': create_value_and_unit(gpu_element.findtext('utilization/memory_util'))
-			}
-		})
-
-	return execution_devices
-
-
-def create_value_and_unit(text : str) -> Optional[ValueAndUnit]:
-	if ' ' in text:
-		value, unit = text.split()
-
-		return\
-		{
-			'value': int(value),
-			'unit': str(unit)
-		}
-	return None
@@ -28,7 +28,7 @@ def graceful_exit(error_code : ErrorCode) -> None:
 	while process_manager.is_processing():
 		sleep(0.5)

-	if state_manager.get_item('target_path'):
-		clear_temp_directory(state_manager.get_item('target_path'))
+	if state_manager.get_item('output_path'):
+		clear_temp_directory(state_manager.get_temp_path(), state_manager.get_item('output_path'))

 	hard_exit(error_code)
@@ -2,14 +2,13 @@ from typing import List, Optional

 import numpy

-from facefusion import state_manager
-from facefusion.common_helper import get_first
+from facefusion import face_store, state_manager
+from facefusion.common_helper import get_first, get_middle
 from facefusion.face_classifier import classify_face
 from facefusion.face_detector import detect_faces, detect_faces_by_angle
-from facefusion.face_helper import apply_nms, convert_to_face_landmark_5, estimate_face_angle, get_nms_threshold
+from facefusion.face_helper import apply_nms, average_points, convert_to_face_landmark_5, estimate_face_angle, get_nms_threshold
 from facefusion.face_landmarker import detect_face_landmark, estimate_face_landmark_68_5
 from facefusion.face_recognizer import calculate_face_embedding
-from facefusion.face_store import get_static_faces, set_static_faces
 from facefusion.types import BoundingBox, Face, FaceLandmark5, FaceLandmarkSet, FaceScoreSet, Score, VisionFrame


@@ -47,7 +46,9 @@ def create_faces(vision_frame : VisionFrame, bounding_boxes : List[BoundingBox],
 		}
 		face_embedding, face_embedding_norm = calculate_face_embedding(vision_frame, face_landmark_set.get('5/68'))
 		gender, age, race = classify_face(vision_frame, face_landmark_set.get('5/68'))
+
 		faces.append(Face(
+			origin = 'detect',
 			bounding_box = bounding_box,
 			score_set = face_score_set,
 			landmark_set = face_landmark_set,
@@ -68,7 +69,102 @@ def get_one_face(faces : List[Face], position : int = 0) -> Optional[Face]:
 	return None


-def get_average_face(faces : List[Face]) -> Optional[Face]:
+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):
+			all_bounding_boxes = []
+			all_face_scores = []
+			all_face_landmarks_5 = []
+
+			for face_detector_angle in state_manager.get_item('face_detector_angles'):
+				if face_detector_angle == 0:
+					bounding_boxes, face_scores, face_landmarks_5 = detect_faces(vision_frame)
+				else:
+					bounding_boxes, face_scores, face_landmarks_5 = detect_faces_by_angle(vision_frame, face_detector_angle)
+				all_bounding_boxes.extend(bounding_boxes)
+				all_face_scores.extend(face_scores)
+				all_face_landmarks_5.extend(face_landmarks_5)
+
+			if all_bounding_boxes and all_face_scores and all_face_landmarks_5 and state_manager.get_item('face_detector_score') > 0:
+				faces = create_faces(vision_frame, all_bounding_boxes, all_face_scores, all_face_landmarks_5)
+
+				if faces:
+					many_faces.extend(faces)
+
+	return many_faces
+
+
+def get_static_faces(vision_frames : List[VisionFrame]) -> List[Face]:
+	many_faces : List[Face] = []
+
+	for vision_frame in vision_frames:
+		faces = face_store.get_faces(vision_frame)
+
+		if not faces:
+			with face_store.resolve_lock(vision_frame):
+				faces = face_store.get_faces(vision_frame)
+
+				if not faces:
+					faces = get_many_faces([ vision_frame ])
+
+					if faces:
+						face_store.set_faces(vision_frame, faces)
+
+		many_faces.extend(faces)
+
+	return many_faces
+
+
+def refill_faces(faces : List[Optional[Face]]) -> List[Face]:
+	fill_faces = []
+	anchor_index_previous = -1
+
+	for index, face in enumerate(faces):
+		if face:
+			for gap_index in range(anchor_index_previous + 1, index):
+				average_factor = (gap_index - anchor_index_previous) / (index - anchor_index_previous)
+				average_face = average_face_geometry([faces[anchor_index_previous], face], average_factor)
+				fill_faces.append(average_face)
+
+			fill_faces.append(face)
+			anchor_index_previous = index
+
+	return fill_faces
+
+
+def average_face_geometry(faces : List[Face], average_factor : float) -> Face:
+	face_first = get_first(faces)
+	face_middle = get_middle(faces)
+	face_anchor = face_middle
+
+	if average_factor < 0.5:
+		face_anchor = face_first
+
+	landmark_set : FaceLandmarkSet =\
+	{
+		'5': average_points(face_first.landmark_set.get('5'), face_middle.landmark_set.get('5'), average_factor),
+		'5/68': average_points(face_first.landmark_set.get('5/68'), face_middle.landmark_set.get('5/68'), average_factor),
+		'68': average_points(face_first.landmark_set.get('68'), face_middle.landmark_set.get('68'), average_factor),
+		'68/5': average_points(face_first.landmark_set.get('68/5'), face_middle.landmark_set.get('68/5'), average_factor)
+	}
+
+	return Face(
+		origin = 'refill',
+		bounding_box = average_points(face_first.bounding_box, face_middle.bounding_box, average_factor),
+		score_set = face_anchor.score_set,
+		landmark_set = landmark_set,
+		angle = estimate_face_angle(landmark_set.get('68/5')),
+		embedding = face_anchor.embedding,
+		embedding_norm = face_anchor.embedding_norm,
+		gender = face_anchor.gender,
+		age = face_anchor.age,
+		race = face_anchor.race
+	)
+
+
+def average_face_identity(faces : List[Face]) -> Optional[Face]:
 	face_embeddings = []
 	face_embeddings_norm = []

@@ -80,6 +176,7 @@ def get_average_face(faces : List[Face]) -> Optional[Face]:
 			face_embeddings_norm.append(face.embedding_norm)

 		return Face(
+			origin = first_face.origin,
 			bounding_box = first_face.bounding_box,
 			score_set = first_face.score_set,
 			landmark_set = first_face.landmark_set,
@@ -93,37 +190,6 @@ def get_average_face(faces : List[Face]) -> Optional[Face]:
 	return None


-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):
-			static_faces = get_static_faces(vision_frame)
-			if static_faces:
-				many_faces.extend(static_faces)
-			else:
-				all_bounding_boxes = []
-				all_face_scores = []
-				all_face_landmarks_5 = []
-
-				for face_detector_angle in state_manager.get_item('face_detector_angles'):
-					if face_detector_angle == 0:
-						bounding_boxes, face_scores, face_landmarks_5 = detect_faces(vision_frame)
-					else:
-						bounding_boxes, face_scores, face_landmarks_5 = detect_faces_by_angle(vision_frame, face_detector_angle)
-					all_bounding_boxes.extend(bounding_boxes)
-					all_face_scores.extend(face_scores)
-					all_face_landmarks_5.extend(face_landmarks_5)
-
-				if all_bounding_boxes and all_face_scores and all_face_landmarks_5 and state_manager.get_item('face_detector_score') > 0:
-					faces = create_faces(vision_frame, all_bounding_boxes, all_face_scores, all_face_landmarks_5)
-
-					if faces:
-						many_faces.extend(faces)
-						set_static_faces(vision_frame, faces)
-	return many_faces
-
-
 def scale_face(target_face : Face, target_vision_frame : VisionFrame, temp_vision_frame : VisionFrame) -> Face:
 	scale_x = temp_vision_frame.shape[1] / target_vision_frame.shape[1]
 	scale_y = temp_vision_frame.shape[0] / target_vision_frame.shape[0]
@@ -228,7 +228,7 @@ def detect_with_retinaface(vision_frame : VisionFrame, face_detector_size : str)
 		if numpy.any(keep_indices):
 			stride_height = face_detector_height // feature_stride
 			stride_width = face_detector_width // feature_stride
-			anchors = create_static_anchors(feature_stride, anchor_total, stride_height, stride_width)
+			anchors = create_static_anchors(feature_stride, anchor_total, stride_width, stride_height)
 			bounding_boxes_raw = detection[index + feature_map_channel] * feature_stride
 			face_landmarks_5_raw = detection[index + feature_map_channel * 2] * feature_stride

@@ -273,7 +273,7 @@ def detect_with_scrfd(vision_frame : VisionFrame, face_detector_size : str) -> T
 		if numpy.any(keep_indices):
 			stride_height = face_detector_height // feature_stride
 			stride_width = face_detector_width // feature_stride
-			anchors = create_static_anchors(feature_stride, anchor_total, stride_height, stride_width)
+			anchors = create_static_anchors(feature_stride, anchor_total, stride_width, stride_height)
 			bounding_boxes_raw = detection[index + feature_map_channel] * feature_stride
 			face_landmarks_5_raw = detection[index + feature_map_channel * 2] * feature_stride

@@ -356,7 +356,7 @@ def detect_with_yunet(vision_frame : VisionFrame, face_detector_size : str) -> T
 		if numpy.any(keep_indices):
 			stride_height = face_detector_height // feature_stride
 			stride_width = face_detector_width // feature_stride
-			anchors = create_static_anchors(feature_stride, anchor_total, stride_height, stride_width)
+			anchors = create_static_anchors(feature_stride, anchor_total, stride_width, stride_height)
 			bounding_boxes_center = detection[index + feature_map_channel * 2].squeeze(0)[:, :2] * feature_stride + anchors
 			bounding_boxes_size = numpy.exp(detection[index + feature_map_channel * 2].squeeze(0)[:, 2:4]) * feature_stride
 			face_landmarks_5_raw = detection[index + feature_map_channel * 3].squeeze(0)
@@ -131,7 +131,7 @@ def calculate_paste_area(temp_vision_frame : VisionFrame, crop_vision_frame : Vi


@lru_cache()
-def create_static_anchors(feature_stride : int, anchor_total : int, stride_height : int, stride_width : int) -> Anchors:
+def create_static_anchors(feature_stride : int, anchor_total : int, stride_width : int, stride_height : int) -> Anchors:
 	x, y = numpy.mgrid[:stride_width, :stride_height]
 	anchors = numpy.stack((y, x), axis = -1)
 	anchors = (anchors * feature_stride).reshape((-1, 2))
@@ -254,3 +254,23 @@ def merge_matrix(temp_matrices : List[Matrix]) -> Matrix:
 		matrix = numpy.dot(temp_matrix, matrix)

 	return matrix[:2, :]
+
+
+def calculate_bounding_box_overlap(bounding_box_a : BoundingBox, bounding_box_b : BoundingBox) -> float:
+	intersection_x1 = max(bounding_box_a[0], bounding_box_b[0])
+	intersection_y1 = max(bounding_box_a[1], bounding_box_b[1])
+	intersection_x2 = min(bounding_box_a[2], bounding_box_b[2])
+	intersection_y2 = min(bounding_box_a[3], bounding_box_b[3])
+	intersection = max(0, intersection_x2 - intersection_x1) * max(0, intersection_y2 - intersection_y1)
+	bounding_box_area = (bounding_box_a[2] - bounding_box_a[0]) * (bounding_box_a[3] - bounding_box_a[1])
+	reference_bounding_box_area = (bounding_box_b[2] - bounding_box_b[0]) * (bounding_box_b[3] - bounding_box_b[1])
+	union = bounding_box_area + reference_bounding_box_area - intersection
+
+	if union > 0:
+		return intersection / union
+
+	return 0.0
+
+
+def average_points(points_previous : Points, points_next : Points, average_factor : float) -> Points:
+	return points_previous * (1 - average_factor) + points_next * average_factor
@@ -2,26 +2,35 @@ from typing import List

 import numpy

+import facefusion.choices
 from facefusion import state_manager
-from facefusion.face_analyser import get_many_faces, get_one_face
+from facefusion.common_helper import get_first, get_middle
+from facefusion.face_creator import get_one_face, get_static_faces
+from facefusion.face_tracker import track_faces
 from facefusion.types import Face, FaceSelectorOrder, Gender, Race, Score, VisionFrame


-def select_faces(reference_vision_frame : VisionFrame, target_vision_frame : VisionFrame) -> List[Face]:
-	target_faces = get_many_faces([ target_vision_frame ])
+def select_faces(reference_vision_frame : VisionFrame, source_vision_frames : List[VisionFrame], target_vision_frames : List[VisionFrame]) -> List[Face]:
+	source_faces = get_static_faces(source_vision_frames)
+
+	if state_manager.get_item('face_tracker_score') > 0:
+		target_faces = track_faces(target_vision_frames, state_manager.get_item('face_tracker_score'))
+	else:
+		target_faces = get_static_faces([ get_middle(target_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 = get_static_faces([ reference_vision_frame ])
+		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 +62,33 @@ 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]:
@@ -1,28 +1,42 @@
+import threading
 from typing import List, Optional

+import numpy
+
 from facefusion.hash_helper import create_hash
 from facefusion.types import Face, FaceStore, VisionFrame

-FACE_STORE : FaceStore =\
-{
-	'static_faces': {}
-}
+FACE_STORE : FaceStore = {}


-def get_face_store() -> FaceStore:
-	return FACE_STORE
+def get_faces(vision_frame : VisionFrame) -> Optional[List[Face]]:
+	if numpy.any(vision_frame):
+		vision_hash = create_hash(vision_frame.tobytes())
+
+		if FACE_STORE.get(vision_hash):
+			return FACE_STORE.get(vision_hash).get('faces')
+
+	return None


-def get_static_faces(vision_frame : VisionFrame) -> Optional[List[Face]]:
-	vision_hash = create_hash(vision_frame.tobytes())
-	return FACE_STORE.get('static_faces').get(vision_hash)
+def set_faces(vision_frame : VisionFrame, faces : List[Face]) -> None:
+	if numpy.any(vision_frame):
+		vision_hash = create_hash(vision_frame.tobytes())
+		FACE_STORE.setdefault(vision_hash,
+		{
+			'lock': threading.Lock()
+		})['faces'] = faces


-def set_static_faces(vision_frame : VisionFrame, faces : List[Face]) -> None:
-	vision_hash = create_hash(vision_frame.tobytes())
-	if vision_hash:
-		FACE_STORE['static_faces'][vision_hash] = faces
+def resolve_lock(vision_frame : VisionFrame) -> threading.Lock:
+	if numpy.any(vision_frame):
+		vision_hash = create_hash(vision_frame.tobytes())
+		return FACE_STORE.setdefault(vision_hash,
+		{
+			'lock': threading.Lock()
+		}).get('lock')
+	return threading.Lock()


-def clear_static_faces() -> None:
-	FACE_STORE['static_faces'].clear()
+def clear_faces() -> None:
+	FACE_STORE.clear()
@@ -0,0 +1,61 @@
+from typing import List
+
+from facefusion.common_helper import get_first, get_last
+from facefusion.face_creator import get_static_faces, refill_faces
+from facefusion.face_helper import calculate_bounding_box_overlap
+from facefusion.types import Face, FaceTrack, Score, VisionFrame
+
+
+def track_faces(vision_frames : List[VisionFrame], score : Score) -> List[Face]:
+	target_index = len(vision_frames) // 2
+	face_tracks = create_face_tracks(vision_frames, score)
+	temp_faces = []
+
+	for face_track in face_tracks:
+		track_indices = sorted(face_track)
+		track_index_first = get_first(track_indices)
+		track_index_last = get_last(track_indices)
+		track_range = range(track_index_first, track_index_last + 1)
+
+		if target_index in track_range:
+			fill_faces = []
+
+			for index in track_range:
+				fill_faces.append(face_track.get(index))
+
+			temp_faces.append(refill_faces(fill_faces)[target_index - track_index_first])
+
+	return temp_faces
+
+
+def create_face_tracks(vision_frames : List[VisionFrame], score : Score) -> List[FaceTrack]:
+	face_tracks : List[FaceTrack] = []
+
+	for frame_index, vision_frame in enumerate(vision_frames):
+		for face in get_static_faces([ vision_frame ]):
+			face_track = select_face_track(face_tracks, face, score)
+
+			if face_track:
+				face_track[frame_index] = face
+			else:
+				face_tracks.append(
+				{
+					frame_index : face
+				})
+
+	return face_tracks
+
+
+def select_face_track(face_tracks : List[FaceTrack], face : Face, score : Score) -> FaceTrack:
+	select_track : FaceTrack = {}
+	select_score = score
+
+	for face_track in face_tracks:
+		track_face = face_track.get(get_last(face_track))
+		track_score = calculate_bounding_box_overlap(face.bounding_box, track_face.bounding_box)
+
+		if track_score > select_score:
+			select_score = track_score
+			select_track = face_track
+
+	return select_track
@@ -1,7 +1,7 @@
 import os
 import subprocess
 import tempfile
-from functools import partial
+from functools import lru_cache, partial
 from typing import List, Optional, cast

 from tqdm import tqdm
@@ -10,11 +10,11 @@ import facefusion.choices
 from facefusion import ffmpeg_builder, logger, process_manager, state_manager, translator
 from facefusion.filesystem import get_file_format, remove_file
 from facefusion.temp_helper import get_temp_file_path, get_temp_frames_pattern
-from facefusion.types import AudioBuffer, AudioEncoder, Command, EncoderSet, Fps, Resolution, UpdateProgress, VideoEncoder, VideoFormat
+from facefusion.types import ApiSecurityStrategy, AudioEncoder, Buffer, Command, EncoderSet, Fps, Resolution, SampleRate, UpdateProgress, VideoEncoder, VideoFormat
 from facefusion.vision import detect_video_duration, detect_video_fps, pack_resolution, predict_video_frame_total


-def run_ffmpeg_with_progress(commands : List[Command], update_progress : UpdateProgress) -> subprocess.Popen[bytes]:
+def run_ffmpeg_with_progress(commands : List[Command], update_progress : UpdateProgress) -> subprocess.Popen[Buffer]:
 	log_level = state_manager.get_item('log_level')
 	commands.extend(ffmpeg_builder.set_progress())
 	commands.extend(ffmpeg_builder.cast_stream())
@@ -45,7 +45,14 @@ def update_progress(progress : tqdm, frame_number : int) -> None:
 	progress.update(frame_number - progress.n)


-def run_ffmpeg(commands : List[Command]) -> subprocess.Popen[bytes]:
+def run_ffmpeg_with_pipe(commands : List[Command], file_content : Buffer) -> subprocess.Popen[Buffer]:
+	commands = ffmpeg_builder.run(commands)
+	process = subprocess.Popen(commands, stdin = subprocess.PIPE, stderr = subprocess.PIPE, stdout = subprocess.PIPE)
+	process.communicate(input = file_content)
+	return process
+
+
+def run_ffmpeg(commands : List[Command]) -> subprocess.Popen[Buffer]:
 	log_level = state_manager.get_item('log_level')
 	commands = ffmpeg_builder.run(commands)
 	process = subprocess.Popen(commands, stderr = subprocess.PIPE, stdout = subprocess.PIPE)
@@ -65,14 +72,14 @@ def run_ffmpeg(commands : List[Command]) -> subprocess.Popen[bytes]:
 	return process


-def open_ffmpeg(commands : List[Command]) -> subprocess.Popen[bytes]:
+def open_ffmpeg(commands : List[Command]) -> subprocess.Popen[Buffer]:
 	commands = ffmpeg_builder.run(commands)
 	return subprocess.Popen(commands, stdin = subprocess.PIPE, stdout = subprocess.PIPE)


-def log_debug(process : subprocess.Popen[bytes]) -> None:
+def log_debug(process : subprocess.Popen[Buffer]) -> None:
 	_, stderr = process.communicate()
-	errors = stderr.decode().split(os.linesep)
+	errors = stderr.decode().splitlines()

 	for error in errors:
 		if error.strip():
@@ -83,6 +90,7 @@ def get_available_encoder_set() -> EncoderSet:
 	available_encoder_set : EncoderSet =\
 	{
 		'audio': [],
+		'image': [],
 		'video': []
 	}
 	commands = ffmpeg_builder.chain(
@@ -94,22 +102,29 @@ def get_available_encoder_set() -> EncoderSet:
 		if line.startswith(' a'):
 			audio_encoder = line.split()[1]

-			if audio_encoder in facefusion.choices.output_audio_encoders:
-				index = facefusion.choices.output_audio_encoders.index(audio_encoder) #type:ignore[arg-type]
-				available_encoder_set['audio'].insert(index, audio_encoder) #type:ignore[arg-type]
-		if line.startswith(' v'):
-			video_encoder = line.split()[1]
+			if audio_encoder in facefusion.choices.audio_encoders and audio_encoder not in available_encoder_set.get('audio'):
+				available_encoder_set['audio'].append(audio_encoder) #type:ignore[arg-type]

-			if video_encoder in facefusion.choices.output_video_encoders:
-				index = facefusion.choices.output_video_encoders.index(video_encoder) #type:ignore[arg-type]
-				available_encoder_set['video'].insert(index, video_encoder) #type:ignore[arg-type]
+		if line.startswith(' v'):
+			vision_encoder = line.split()[1]
+
+			if vision_encoder in facefusion.choices.image_encoders and vision_encoder not in available_encoder_set.get('image'):
+				available_encoder_set['image'].append(vision_encoder) #type:ignore[arg-type]
+
+			if vision_encoder in facefusion.choices.video_encoders and vision_encoder not in available_encoder_set.get('video'):
+				available_encoder_set['video'].append(vision_encoder) #type:ignore[arg-type]

 	return available_encoder_set


-def extract_frames(target_path : str, temp_video_resolution : Resolution, temp_video_fps : Fps, trim_frame_start : int, trim_frame_end : int) -> bool:
+@lru_cache(maxsize = None)
+def get_static_available_encoder_set() -> EncoderSet:
+	return get_available_encoder_set()
+
+
+def extract_frames(target_path : str, output_path : str, temp_video_resolution : Resolution, temp_video_fps : Fps, trim_frame_start : int, trim_frame_end : int) -> bool:
 	extract_frame_total = predict_video_frame_total(target_path, temp_video_fps, trim_frame_start, trim_frame_end)
-	temp_frames_pattern = get_temp_frames_pattern(target_path, '%08d')
+	temp_frames_pattern = get_temp_frames_pattern(state_manager.get_temp_path(), output_path, state_manager.get_item('temp_frame_format'), '%08d')
 	commands = ffmpeg_builder.chain(
 		ffmpeg_builder.set_input(target_path),
 		ffmpeg_builder.set_media_resolution(pack_resolution(temp_video_resolution)),
@@ -117,6 +132,7 @@ def extract_frames(target_path : str, temp_video_resolution : Resolution, temp_v
 		ffmpeg_builder.enforce_pixel_format('rgb24'),
 		ffmpeg_builder.select_frame_range(trim_frame_start, trim_frame_end, temp_video_fps),
 		ffmpeg_builder.prevent_frame_drop(),
+		ffmpeg_builder.set_start_number(trim_frame_start),
 		ffmpeg_builder.set_output(temp_frames_pattern)
 	)

@@ -125,8 +141,26 @@ def extract_frames(target_path : str, temp_video_resolution : Resolution, temp_v
 		return process.returncode == 0


-def copy_image(target_path : str, temp_image_resolution : Resolution) -> bool:
-	temp_image_path = get_temp_file_path(target_path)
+def spawn_frames(target_path : str, output_path : str, temp_video_resolution : Resolution, temp_video_fps : Fps, trim_frame_start : int, trim_frame_end : int) -> bool:
+	spawn_frame_total = trim_frame_end - trim_frame_start
+	duration = spawn_frame_total / temp_video_fps
+	temp_frames_pattern = get_temp_frames_pattern(state_manager.get_temp_path(), output_path, state_manager.get_item('temp_frame_format'), '%08d')
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_loop(),
+		ffmpeg_builder.set_input(target_path),
+		ffmpeg_builder.set_video_duration(duration),
+		ffmpeg_builder.set_video_fps(temp_video_fps),
+		ffmpeg_builder.set_media_resolution(pack_resolution(temp_video_resolution)),
+		ffmpeg_builder.set_output(temp_frames_pattern)
+	)
+
+	with tqdm(total = spawn_frame_total, desc = translator.get('spawning'), unit = 'frame', ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
+		process = run_ffmpeg_with_progress(commands, partial(update_progress, progress))
+		return process.returncode == 0
+
+
+def copy_image(target_path : str, output_path : str, temp_image_resolution : Resolution) -> bool:
+	temp_image_path = get_temp_file_path(state_manager.get_temp_path(), output_path)
 	commands = ffmpeg_builder.chain(
 		ffmpeg_builder.set_input(target_path),
 		ffmpeg_builder.set_media_resolution(pack_resolution(temp_image_resolution)),
@@ -136,19 +170,19 @@ def copy_image(target_path : str, temp_image_resolution : Resolution) -> bool:
 	return run_ffmpeg(commands).returncode == 0


-def finalize_image(target_path : str, output_path : str, output_image_resolution : Resolution) -> bool:
+def finalize_image(output_path : str, output_image_resolution : Resolution) -> bool:
 	output_image_quality = state_manager.get_item('output_image_quality')
-	temp_image_path = get_temp_file_path(target_path)
+	temp_image_path = get_temp_file_path(state_manager.get_temp_path(), output_path)
 	commands = ffmpeg_builder.chain(
 		ffmpeg_builder.set_input(temp_image_path),
 		ffmpeg_builder.set_media_resolution(pack_resolution(output_image_resolution)),
-		ffmpeg_builder.set_image_quality(target_path, output_image_quality),
+		ffmpeg_builder.set_image_quality(output_path, output_image_quality),
 		ffmpeg_builder.force_output(output_path)
 	)
 	return run_ffmpeg(commands).returncode == 0


-def read_audio_buffer(target_path : str, audio_sample_rate : int, audio_sample_size : int, audio_channel_total : int) -> Optional[AudioBuffer]:
+def read_audio_buffer(target_path : str, audio_sample_rate : SampleRate, audio_sample_size : int, audio_channel_total : int) -> Optional[Buffer]:
 	commands = ffmpeg_builder.chain(
 		ffmpeg_builder.set_input(target_path),
 		ffmpeg_builder.ignore_video_stream(),
@@ -160,6 +194,7 @@ def read_audio_buffer(target_path : str, audio_sample_rate : int, audio_sample_s

 	process = open_ffmpeg(commands)
 	audio_buffer, _ = process.communicate()
+
 	if process.returncode == 0:
 		return audio_buffer
 	return None
@@ -170,9 +205,10 @@ def restore_audio(target_path : str, output_path : str, trim_frame_start : int,
 	output_audio_quality = state_manager.get_item('output_audio_quality')
 	output_audio_volume = state_manager.get_item('output_audio_volume')
 	target_video_fps = detect_video_fps(target_path)
-	temp_video_path = get_temp_file_path(target_path)
-	temp_video_format = cast(VideoFormat, get_file_format(temp_video_path))
+	temp_video_path = get_temp_file_path(state_manager.get_temp_path(), output_path)
+	temp_video_format = cast(VideoFormat, get_file_format(output_path))
 	temp_video_duration = detect_video_duration(temp_video_path)
+	output_video_format = cast(VideoFormat, get_file_format(output_path))

 	output_audio_encoder = fix_audio_encoder(temp_video_format, output_audio_encoder)
 	commands = ffmpeg_builder.chain(
@@ -186,18 +222,20 @@ def restore_audio(target_path : str, output_path : str, trim_frame_start : int,
 		ffmpeg_builder.select_media_stream('0:v:0'),
 		ffmpeg_builder.select_media_stream('1:a:0'),
 		ffmpeg_builder.set_video_duration(temp_video_duration),
+		ffmpeg_builder.set_faststart(output_video_format),
 		ffmpeg_builder.force_output(output_path)
 	)
 	return run_ffmpeg(commands).returncode == 0


-def replace_audio(target_path : str, audio_path : str, output_path : str) -> bool:
+def replace_audio(audio_path : str, output_path : str) -> bool:
 	output_audio_encoder = state_manager.get_item('output_audio_encoder')
 	output_audio_quality = state_manager.get_item('output_audio_quality')
 	output_audio_volume = state_manager.get_item('output_audio_volume')
-	temp_video_path = get_temp_file_path(target_path)
-	temp_video_format = cast(VideoFormat, get_file_format(temp_video_path))
+	temp_video_path = get_temp_file_path(state_manager.get_temp_path(), output_path)
+	temp_video_format = cast(VideoFormat, get_file_format(output_path))
 	temp_video_duration = detect_video_duration(temp_video_path)
+	output_video_format = cast(VideoFormat, get_file_format(output_path))

 	output_audio_encoder = fix_audio_encoder(temp_video_format, output_audio_encoder)
 	commands = ffmpeg_builder.chain(
@@ -208,26 +246,29 @@ def replace_audio(target_path : str, audio_path : str, output_path : str) -> boo
 		ffmpeg_builder.set_audio_quality(output_audio_encoder, output_audio_quality),
 		ffmpeg_builder.set_audio_volume(output_audio_volume),
 		ffmpeg_builder.set_video_duration(temp_video_duration),
+		ffmpeg_builder.set_faststart(output_video_format),
 		ffmpeg_builder.force_output(output_path)
 	)
 	return run_ffmpeg(commands).returncode == 0


-def merge_video(target_path : str, temp_video_fps : Fps, output_video_resolution : Resolution, output_video_fps : Fps, trim_frame_start : int, trim_frame_end : int) -> bool:
+def merge_video(target_path : str, output_path : str, temp_video_fps : Fps, output_video_fps : Fps, output_video_resolution : Resolution, trim_frame_start : int, trim_frame_end : int) -> bool:
 	output_video_encoder = state_manager.get_item('output_video_encoder')
 	output_video_quality = state_manager.get_item('output_video_quality')
 	output_video_preset = state_manager.get_item('output_video_preset')
 	merge_frame_total = predict_video_frame_total(target_path, output_video_fps, trim_frame_start, trim_frame_end)
-	temp_video_path = get_temp_file_path(target_path)
-	temp_video_format = cast(VideoFormat, get_file_format(temp_video_path))
-	temp_frames_pattern = get_temp_frames_pattern(target_path, '%08d')
+	temp_video_path = get_temp_file_path(state_manager.get_temp_path(), output_path)
+	temp_video_format = cast(VideoFormat, get_file_format(output_path))
+	temp_frames_pattern = get_temp_frames_pattern(state_manager.get_temp_path(), output_path, state_manager.get_item('temp_frame_format'), '%08d')

 	output_video_encoder = fix_video_encoder(temp_video_format, output_video_encoder)
 	commands = ffmpeg_builder.chain(
 		ffmpeg_builder.set_input_fps(temp_video_fps),
+		ffmpeg_builder.set_start_number(trim_frame_start),
 		ffmpeg_builder.set_input(temp_frames_pattern),
 		ffmpeg_builder.set_media_resolution(pack_resolution(output_video_resolution)),
 		ffmpeg_builder.set_video_encoder(output_video_encoder),
+		ffmpeg_builder.set_video_tag(output_video_encoder, temp_video_format),
 		ffmpeg_builder.set_video_quality(output_video_encoder, output_video_quality),
 		ffmpeg_builder.set_video_preset(output_video_encoder, output_video_preset),
 		ffmpeg_builder.concat(
@@ -254,11 +295,13 @@ def concat_video(output_path : str, temp_output_paths : List[str]) -> bool:
 		concat_video_file.close()

 	output_path = os.path.abspath(output_path)
+	output_video_format = cast(VideoFormat, get_file_format(output_path))
 	commands = ffmpeg_builder.chain(
 		ffmpeg_builder.unsafe_concat(),
 		ffmpeg_builder.set_input(concat_video_file.name),
 		ffmpeg_builder.copy_video_encoder(),
 		ffmpeg_builder.copy_audio_encoder(),
+		ffmpeg_builder.set_faststart(output_video_format),
 		ffmpeg_builder.force_output(output_path)
 	)
 	process = run_ffmpeg(commands)
@@ -267,6 +310,60 @@ def concat_video(output_path : str, temp_output_paths : List[str]) -> bool:
 	return process.returncode == 0


+def sanitize_audio(file_content : Buffer, asset_path : str, security_strategy : ApiSecurityStrategy) -> bool:
+	if security_strategy == 'strict':
+		commands = ffmpeg_builder.chain(
+			ffmpeg_builder.set_input('pipe:0'),
+			ffmpeg_builder.deep_copy_audio(),
+			ffmpeg_builder.strip_metadata(),
+			ffmpeg_builder.force_output(asset_path)
+		)
+		return run_ffmpeg_with_pipe(commands, file_content).returncode == 0
+
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input('pipe:0'),
+		ffmpeg_builder.copy_audio_encoder(),
+		ffmpeg_builder.strip_metadata(),
+		ffmpeg_builder.force_output(asset_path)
+	)
+	return run_ffmpeg_with_pipe(commands, file_content).returncode == 0
+
+
+def sanitize_image(file_content : Buffer, asset_path : str) -> bool:
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input('pipe:0'),
+		ffmpeg_builder.deep_copy_image(),
+		ffmpeg_builder.strip_metadata(),
+		ffmpeg_builder.force_output(asset_path)
+	)
+	return run_ffmpeg_with_pipe(commands, file_content).returncode == 0
+
+
+def sanitize_video(file_content : Buffer, asset_path : str, security_strategy : ApiSecurityStrategy) -> bool:
+	if security_strategy == 'strict':
+		available_video_encoders = get_static_available_encoder_set().get('video')
+		commands = ffmpeg_builder.chain(
+			ffmpeg_builder.set_input('pipe:0'),
+			ffmpeg_builder.set_video_encoder(available_video_encoders[0]),
+			ffmpeg_builder.set_video_preset(available_video_encoders[0], 'ultrafast'),
+			ffmpeg_builder.set_pixel_format(available_video_encoders[0]),
+			ffmpeg_builder.deep_copy_video(),
+			ffmpeg_builder.deep_copy_audio(),
+			ffmpeg_builder.strip_metadata(),
+			ffmpeg_builder.force_output(asset_path)
+		)
+		return run_ffmpeg_with_pipe(commands, file_content).returncode == 0
+
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input('pipe:0'),
+		ffmpeg_builder.copy_video_encoder(),
+		ffmpeg_builder.copy_audio_encoder(),
+		ffmpeg_builder.strip_metadata(),
+		ffmpeg_builder.force_output(asset_path)
+	)
+	return run_ffmpeg_with_pipe(commands, file_content).returncode == 0
+
+
 def fix_audio_encoder(video_format : VideoFormat, audio_encoder : AudioEncoder) -> AudioEncoder:
 	if video_format == 'avi' and audio_encoder == 'libopus':
 		return 'aac'
@@ -5,7 +5,7 @@ from typing import List, Optional
 import numpy

 from facefusion.filesystem import get_file_format
-from facefusion.types import AudioEncoder, Command, CommandSet, Duration, Fps, StreamMode, VideoEncoder, VideoPreset
+from facefusion.types import AudioEncoder, Command, CommandSet, Duration, Fps, SampleRate, StreamMode, VideoEncoder, VideoFormat, VideoPreset


 def run(commands : List[Command]) -> List[Command]:
@@ -51,6 +51,10 @@ def set_input_fps(input_fps : Fps) -> List[Command]:
 	return [ '-r', str(input_fps) ]


+def set_start_number(frame_number : int) -> List[Command]:
+	return [ '-start_number', str(frame_number) ]
+
+
 def set_output(output_path : str) -> List[Command]:
 	return [ output_path ]

@@ -59,6 +63,10 @@ def force_output(output_path : str) -> List[Command]:
 	return [ '-y', output_path ]


+def set_loop() -> List[Command]:
+	return [ '-loop', '1' ]
+
+
 def cast_stream() -> List[Command]:
 	return [ '-' ]

@@ -83,6 +91,10 @@ def enforce_pixel_format(pixel_format : str) -> List[Command]:
 	return [ '-pix_fmt', pixel_format ]


+def strip_metadata() -> List[Command]:
+	return [ '-map_metadata', '-1' ]
+
+
 def set_pixel_format(video_encoder : VideoEncoder) -> List[Command]:
 	if video_encoder == 'rawvideo':
 		return [ '-pix_fmt', 'rgb24' ]
@@ -127,12 +139,8 @@ def set_media_resolution(video_resolution : str) -> List[Command]:
 	return [ '-s', video_resolution ]


-def set_image_quality(image_path : str, image_quality : int) -> List[Command]:
-	if get_file_format(image_path) == 'webp':
-		return [ '-q:v', str(image_quality) ]
-
-	image_compression = round(31 - (image_quality * 0.31))
-	return [ '-q:v', str(image_compression) ]
+def deep_copy_audio() -> List[Command]:
+	return [ '-q:a', '0' ]


 def set_audio_encoder(audio_codec : str) -> List[Command]:
@@ -143,7 +151,7 @@ def copy_audio_encoder() -> List[Command]:
 	return set_audio_encoder('copy')


-def set_audio_sample_rate(audio_sample_rate : int) -> List[Command]:
+def set_audio_sample_rate(audio_sample_rate : SampleRate) -> List[Command]:
 	return [ '-ar', str(audio_sample_rate) ]


@@ -179,6 +187,22 @@ def set_audio_volume(audio_volume : int) -> List[Command]:
 	return [ '-filter:a', 'volume=' + str(audio_volume / 100) ]


+def deep_copy_image() -> List[Command]:
+	return [ '-q:v', '0' ]
+
+
+def set_image_quality(image_path : str, image_quality : int) -> List[Command]:
+	if get_file_format(image_path) == 'webp':
+		return [ '-q:v', str(image_quality) ]
+
+	image_compression = round(31 - (image_quality * 0.31))
+	return [ '-q:v', str(image_compression) ]
+
+
+def deep_copy_video() -> List[Command]:
+	return [ '-q:v', '0' ]
+
+
 def set_video_encoder(video_encoder : str) -> List[Command]:
 	return [ '-c:v', video_encoder ]

@@ -187,6 +211,18 @@ def copy_video_encoder() -> List[Command]:
 	return set_video_encoder('copy')


+def set_faststart(video_format : VideoFormat) -> List[Command]:
+	if video_format in [ 'm4v', 'mov', 'mp4' ]:
+		return [ '-movflags', '+faststart' ]
+	return []
+
+
+def set_video_tag(video_encoder : VideoEncoder, video_format : VideoFormat) -> List[Command]:
+	if video_format in [ 'm4v', 'mov', 'mp4' ] and video_encoder in [ 'libx265', 'hevc_nvenc', 'hevc_amf', 'hevc_qsv', 'hevc_videotoolbox' ]:
+		return [ '-tag:v', 'hvc1' ]
+	return []
+
+
 def set_video_quality(video_encoder : VideoEncoder, video_quality : int) -> List[Command]:
 	if video_encoder in [ 'libx264', 'libx264rgb', 'libx265' ]:
 		video_compression = numpy.round(numpy.interp(video_quality, [ 0, 100 ], [ 51, 0 ])).astype(int).item()
@@ -269,3 +305,5 @@ def map_qsv_preset(video_preset : VideoPreset) -> Optional[str]:
 	if video_preset in [ 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow' ]:
 		return video_preset
 	return None
+
+
@@ -0,0 +1,84 @@
+import subprocess
+from typing import Dict, List
+
+from facefusion import ffprobe_builder
+from facefusion.types import AudioMetadata, Buffer, Command, Fps, VideoMetadata
+
+
+def run_ffprobe(commands : List[Command]) -> subprocess.Popen[Buffer]:
+	commands = ffprobe_builder.run(commands)
+	return subprocess.Popen(commands, stderr = subprocess.PIPE, stdout = subprocess.PIPE)
+
+
+def probe_entries(media_path : str, entries : List[str]) -> Dict[str, str]:
+	media_entries = {}
+
+	commands = ffprobe_builder.chain(
+		ffprobe_builder.show_entries(entries),
+		ffprobe_builder.format_to_key_value(),
+		ffprobe_builder.set_input(media_path)
+	)
+	output, _ = run_ffprobe(commands).communicate()
+
+	if output:
+		lines = output.decode().strip().splitlines()
+
+		for line in lines:
+			if '=' in line:
+				key, value = line.split('=', 1)
+				media_entries[key] = value
+
+	return media_entries
+
+
+def extract_audio_metadata(audio_path : str) -> AudioMetadata:
+	audio_entries = probe_entries(audio_path, [ 'duration', 'sample_rate', 'channels', 'bit_rate' ])
+
+	duration = float(audio_entries.get('duration'))
+	sample_rate = int(audio_entries.get('sample_rate'))
+	frame_total = int(duration * sample_rate)
+	channel_total = int(audio_entries.get('channels'))
+	bit_rate = int(audio_entries.get('bit_rate'))
+
+	audio_metadata : AudioMetadata =\
+	{
+		'duration' : duration,
+		'frame_total' : frame_total,
+		'channel_total' : channel_total,
+		'sample_rate' : sample_rate,
+		'bit_rate' : bit_rate
+	}
+
+	return audio_metadata
+
+
+def extract_video_metadata(video_path : str) -> VideoMetadata:
+	video_entries = probe_entries(video_path, [ 'duration', 'width', 'height', 'r_frame_rate', 'bit_rate' ])
+
+	duration = float(video_entries.get('duration'))
+	fps = extract_video_fps(video_entries.get('r_frame_rate'))
+	frame_total = int(duration * fps)
+	width = int(video_entries.get('width'))
+	height = int(video_entries.get('height'))
+	bit_rate = int(video_entries.get('bit_rate'))
+
+	video_metadata : VideoMetadata =\
+	{
+		'duration' : duration,
+		'frame_total' : frame_total,
+		'fps' : fps,
+		'resolution' : (width, height),
+		'bit_rate' : bit_rate
+	}
+
+	return video_metadata
+
+
+def extract_video_fps(frame_rate : str) -> Fps:
+	if frame_rate and '/' in frame_rate:
+		numerator, denominator = frame_rate.split('/')
+
+		if int(numerator) and int(denominator):
+			return int(numerator) / int(denominator)
+
+	return 0.0
@@ -0,0 +1,29 @@
+import itertools
+import shutil
+from typing import List
+
+from facefusion.types import Command
+
+
+def run(commands : List[Command]) -> List[Command]:
+	return [ shutil.which('ffprobe'), '-loglevel', 'error' ] + commands
+
+
+def chain(*commands : List[Command]) -> List[Command]:
+	return list(itertools.chain(*commands))
+
+
+def show_entries(entries : List[str]) -> List[Command]:
+	return [ '-show_entries', 'stream=' + ','.join(entries) ]
+
+
+def format_to_value() -> List[Command]:
+	return [ '-of', 'default=noprint_wrappers=1:nokey=1' ]
+
+
+def format_to_key_value() -> List[Command]:
+	return [ '-of', 'default=noprint_wrappers=1' ]
+
+
+def set_input(input_path : str) -> List[Command]:
+	return [ '-i', input_path ]
@@ -42,15 +42,6 @@ def get_file_format(file_path : str) -> Optional[str]:
 	return None


-def same_file_extension(first_file_path : str, second_file_path : str) -> bool:
-	first_file_extension = get_file_extension(first_file_path)
-	second_file_extension = get_file_extension(second_file_path)
-
-	if first_file_extension and second_file_extension:
-		return get_file_extension(first_file_path) == get_file_extension(second_file_path)
-	return False
-
-
 def is_file(file_path : str) -> bool:
 	if file_path:
 		return os.path.isfile(file_path)
@@ -179,6 +170,13 @@ def create_directory(directory_path : str) -> bool:
 	return False


+def move_directory(directory_path : str, move_path : str) -> bool:
+	if is_directory(directory_path):
+		shutil.move(directory_path, move_path)
+		return is_directory(move_path)
+	return False
+
+
 def remove_directory(directory_path : str) -> bool:
 	if is_directory(directory_path):
 		shutil.rmtree(directory_path, ignore_errors = True)
@@ -3,10 +3,11 @@ import zlib
 from typing import Optional

 from facefusion.filesystem import get_file_name, is_file
+from facefusion.types import Buffer


-def create_hash(content : bytes) -> str:
-	return format(zlib.crc32(content), '08x')
+def create_hash(buffer : Buffer) -> str:
+	return format(zlib.crc32(buffer), '08x')


 def validate_hash(validate_path : str) -> bool:
@@ -1,5 +1,6 @@
 import importlib
 import random
+from functools import lru_cache
 from time import sleep, time
 from typing import List

@@ -12,12 +13,12 @@ from facefusion.execution import create_inference_providers, has_execution_provi
 from facefusion.exit_helper import fatal_exit
 from facefusion.filesystem import get_file_name, is_file
 from facefusion.time_helper import calculate_end_time
-from facefusion.types import DownloadSet, ExecutionProvider, InferencePool, InferencePoolSet
+from facefusion.types import DownloadSet, ExecutionProvider, InferencePool, InferencePoolSet, InferenceProvider

 INFERENCE_POOL_SET : InferencePoolSet =\
 {
 	'cli': {},
-	'ui': {}
+	'api': {}
 }


@@ -25,37 +26,38 @@ def get_inference_pool(module_name : str, model_names : List[str], model_source_
 	while process_manager.is_checking():
 		sleep(0.5)
 	execution_device_ids = state_manager.get_item('execution_device_ids')
-	execution_providers = resolve_execution_providers(module_name)
+	execution_providers = state_manager.get_item('execution_providers')
 	app_context = detect_app_context()

 	for execution_device_id in execution_device_ids:
 		inference_context = get_inference_context(module_name, model_names, execution_device_id, execution_providers)

-		if app_context == 'cli' and INFERENCE_POOL_SET.get('ui').get(inference_context):
-			INFERENCE_POOL_SET['cli'][inference_context] = INFERENCE_POOL_SET.get('ui').get(inference_context)
-		if app_context == 'ui' and INFERENCE_POOL_SET.get('cli').get(inference_context):
-			INFERENCE_POOL_SET['ui'][inference_context] = INFERENCE_POOL_SET.get('cli').get(inference_context)
+		if app_context == 'cli' and INFERENCE_POOL_SET.get('api').get(inference_context):
+			INFERENCE_POOL_SET['cli'][inference_context] = INFERENCE_POOL_SET.get('api').get(inference_context)
+		if app_context == 'api' and INFERENCE_POOL_SET.get('cli').get(inference_context):
+			INFERENCE_POOL_SET['api'][inference_context] = INFERENCE_POOL_SET.get('cli').get(inference_context)
 		if not INFERENCE_POOL_SET.get(app_context).get(inference_context):
-			INFERENCE_POOL_SET[app_context][inference_context] = create_inference_pool(model_source_set, execution_device_id, execution_providers)
+			inference_providers = resolve_static_inference_providers(module_name, execution_device_id)
+			INFERENCE_POOL_SET[app_context][inference_context] = create_inference_pool(model_source_set, inference_providers)

 	current_inference_context = get_inference_context(module_name, model_names, random.choice(execution_device_ids), execution_providers)
 	return INFERENCE_POOL_SET.get(app_context).get(current_inference_context)


-def create_inference_pool(model_source_set : DownloadSet, execution_device_id : int, execution_providers : List[ExecutionProvider]) -> InferencePool:
+def create_inference_pool(model_source_set : DownloadSet, inference_providers : List[InferenceProvider]) -> InferencePool:
 	inference_pool : InferencePool = {}

 	for model_name in model_source_set.keys():
 		model_path = model_source_set.get(model_name).get('path')
 		if is_file(model_path):
-			inference_pool[model_name] = create_inference_session(model_path, execution_device_id, execution_providers)
+			inference_pool[model_name] = create_inference_session(model_path, inference_providers)

 	return inference_pool


 def clear_inference_pool(module_name : str, model_names : List[str]) -> None:
 	execution_device_ids = state_manager.get_item('execution_device_ids')
-	execution_providers = resolve_execution_providers(module_name)
+	execution_providers = state_manager.get_item('execution_providers')
 	app_context = detect_app_context()

 	if is_windows() and has_execution_provider('directml'):
@@ -67,12 +69,11 @@ def clear_inference_pool(module_name : str, model_names : List[str]) -> None:
 			del INFERENCE_POOL_SET[app_context][inference_context]


-def create_inference_session(model_path : str, execution_device_id : int, execution_providers : List[ExecutionProvider]) -> InferenceSession:
+def create_inference_session(model_path : str, inference_providers : List[InferenceProvider]) -> InferenceSession:
 	model_file_name = get_file_name(model_path)
 	start_time = time()

 	try:
-		inference_providers = create_inference_providers(execution_device_id, execution_providers)
 		inference_session = InferenceSession(model_path, providers = inference_providers)
 		logger.debug(translator.get('loading_model_succeeded').format(model_name = model_file_name, seconds = calculate_end_time(start_time)), __name__)
 		return inference_session
@@ -87,9 +88,15 @@ def get_inference_context(module_name : str, model_names : List[str], execution_
 	return inference_context


-def resolve_execution_providers(module_name : str) -> List[ExecutionProvider]:
+@lru_cache()
+def resolve_static_inference_providers(module_name : str, execution_device_id : int) -> List[InferenceProvider]:
 	module = importlib.import_module(module_name)
+	execution_providers = state_manager.get_item('execution_providers')

-	if hasattr(module, 'resolve_execution_providers'):
-		return getattr(module, 'resolve_execution_providers')()
-	return state_manager.get_item('execution_providers')
+	if hasattr(module, 'resolve_inference_providers'):
+		inference_providers = getattr(module, 'resolve_inference_providers')()
+
+		if inference_providers:
+			return inference_providers
+
+	return create_inference_providers(execution_device_id, execution_providers)
@@ -19,23 +19,23 @@ LOCALES =\
 }
 ONNXRUNTIME_SET =\
 {
-	'default': ('onnxruntime', '1.24.4')
+	'default': ('onnxruntime', '1.26.0')
 }
 if is_windows() or is_linux():
-	ONNXRUNTIME_SET['cuda'] = ('onnxruntime-gpu', '1.24.4')
+	ONNXRUNTIME_SET['cuda'] = ('onnxruntime-gpu', '1.26.0')
 	ONNXRUNTIME_SET['openvino'] = ('onnxruntime-openvino', '1.24.1')
 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', '1.24.2')
+	ONNXRUNTIME_SET['migraphx'] = ('onnxruntime-migraphx', '1.25.0')
 	ONNXRUNTIME_SET['rocm'] = ('onnxruntime-rocm', '1.22.2.post1')


 def cli() -> None:
 	signal.signal(signal.SIGINT, signal_exit)
 	program = ArgumentParser(formatter_class = partial(HelpFormatter, max_help_position = 50))
-	program.add_argument('--onnxruntime', help = LOCALES.get('install_dependency').format(dependency = 'onnxruntime'), choices = ONNXRUNTIME_SET.keys(), required = True)
+	program.add_argument('onnxruntime', help = LOCALES.get('install_dependency').format(dependency = 'onnxruntime'), choices = ONNXRUNTIME_SET.keys())
 	program.add_argument('--force-reinstall', help = LOCALES.get('force_reinstall'), action = 'store_true')
 	program.add_argument('--skip-conda', help = LOCALES.get('skip_conda'), action = 'store_true')
 	program.add_argument('-v', '--version', version = metadata.get('name') + ' ' + metadata.get('version'), action = 'version')
@@ -13,6 +13,8 @@ def get_step_output_path(job_id : str, step_index : int, output_path : str) -> O

 		if output_file_name and output_file_extension:
 			return os.path.join(output_directory_path, output_file_name + '-' + job_id + '-' + str(step_index) + output_file_extension)
+		if output_file_path and output_directory_path:
+			return os.path.join(output_directory_path, output_file_path + '-' + job_id + '-' + str(step_index))
 	return None


@@ -6,6 +6,7 @@ import facefusion.choices
 from facefusion.filesystem import create_directory, get_file_name, is_directory, is_file, move_file, remove_directory, remove_file, resolve_file_pattern
 from facefusion.jobs.job_helper import get_step_output_path
 from facefusion.json import read_json, write_json
+from facefusion.sanitizer import sanitize_job_id
 from facefusion.time_helper import get_current_date_time
 from facefusion.types import Args, Job, JobSet, JobStatus, JobStep, JobStepStatus

@@ -261,5 +262,6 @@ def find_job_path(job_id : str) -> Optional[str]:

 def get_job_file_name(job_id : str) -> Optional[str]:
 	if job_id:
+		job_id = sanitize_job_id(job_id)
 		return job_id + '.json'
 	return None
@@ -1,5 +1,7 @@
+import os
+
 from facefusion.ffmpeg import concat_video
-from facefusion.filesystem import are_images, are_videos, move_file, remove_file
+from facefusion.filesystem import are_images, are_videos, copy_file, create_directory, is_directory, is_file, move_directory, move_file, remove_directory, remove_file, resolve_file_paths
 from facefusion.jobs import job_helper, job_manager
 from facefusion.types import JobOutputSet, JobStep, ProcessStep

@@ -59,6 +61,8 @@ def run_step(job_id : str, step_index : int, step : JobStep, process_step : Proc
 		output_path = step_args.get('output_path')
 		step_output_path = job_helper.get_step_output_path(job_id, step_index, output_path)

+		if is_directory(output_path):
+			return move_directory(output_path, step_output_path) and job_manager.set_step_status(job_id, step_index, 'completed')
 		return move_file(output_path, step_output_path) and job_manager.set_step_status(job_id, step_index, 'completed')
 	job_manager.set_step_status(job_id, step_index, 'failed')
 	return False
@@ -79,13 +83,26 @@ def finalize_steps(job_id : str) -> bool:
 	output_set = collect_output_set(job_id)

 	for output_path, temp_output_paths in output_set.items():
-		if are_videos(temp_output_paths):
+		has_videos = are_videos(temp_output_paths)
+		has_images = are_images(temp_output_paths)
+
+		if has_videos:
 			if not concat_video(output_path, temp_output_paths):
 				return False
-		if are_images(temp_output_paths):
+		if not has_videos and has_images:
 			for temp_output_path in temp_output_paths:
 				if not move_file(temp_output_path, output_path):
 					return False
+		if not has_videos and not has_images:
+			if not create_directory(output_path):
+				return False
+
+			for temp_output_path in temp_output_paths:
+				if is_directory(temp_output_path):
+					temp_frame_paths = resolve_file_paths(temp_output_path)
+					for temp_frame_path in temp_frame_paths:
+						if not copy_file(temp_frame_path, os.path.join(output_path, os.path.basename(temp_frame_path))):
+							return False
 	return True


@@ -94,8 +111,12 @@ def clean_steps(job_id: str) -> bool:

 	for temp_output_paths in output_set.values():
 		for temp_output_path in temp_output_paths:
-			if not remove_file(temp_output_path):
-				return False
+			if is_file(temp_output_path):
+				if not remove_file(temp_output_path):
+					return False
+			if is_directory(temp_output_path):
+				if not remove_directory(temp_output_path):
+					return False
 	return True


@@ -1,27 +0,0 @@
-from typing import List
-
-from facefusion.types import JobStore
-
-JOB_STORE : JobStore =\
-{
-	'job_keys': [],
-	'step_keys': []
-}
-
-
-def get_job_keys() -> List[str]:
-	return JOB_STORE.get('job_keys')
-
-
-def get_step_keys() -> List[str]:
-	return JOB_STORE.get('step_keys')
-
-
-def register_job_keys(job_keys : List[str]) -> None:
-	for job_key in job_keys:
-		JOB_STORE['job_keys'].append(job_key)
-
-
-def register_step_keys(step_keys : List[str]) -> None:
-	for step_key in step_keys:
-		JOB_STORE['step_keys'].append(step_key)
@@ -0,0 +1,115 @@
+import ctypes
+import ctypes.util
+from functools import lru_cache
+from typing import List, Optional
+
+
+@lru_cache
+def create_static_library() -> Optional[ctypes.CDLL]:
+	library_path = ctypes.util.find_library('amd_smi')
+
+	if library_path:
+		library = ctypes.CDLL(library_path)
+
+		if library:
+			return init_ctypes(library)
+
+	return None
+
+
+def init_ctypes(library : ctypes.CDLL) -> ctypes.CDLL:
+	library.amdsmi_init.argtypes = [ ctypes.c_uint64 ]
+	library.amdsmi_init.restype = ctypes.c_uint32
+
+	library.amdsmi_shut_down.argtypes = []
+	library.amdsmi_shut_down.restype = ctypes.c_uint32
+
+	library.amdsmi_get_socket_handles.argtypes = [ ctypes.POINTER(ctypes.c_uint32), ctypes.POINTER(ctypes.c_void_p) ]
+	library.amdsmi_get_socket_handles.restype = ctypes.c_uint32
+
+	library.amdsmi_get_processor_handles.argtypes = [ ctypes.c_void_p, ctypes.POINTER(ctypes.c_uint32), ctypes.POINTER(ctypes.c_void_p) ]
+	library.amdsmi_get_processor_handles.restype = ctypes.c_uint32
+
+	library.amdsmi_get_gpu_vram_usage.argtypes = [ ctypes.c_void_p, ctypes.c_void_p ]
+	library.amdsmi_get_gpu_vram_usage.restype = ctypes.c_uint32
+
+	library.amdsmi_get_gpu_activity.argtypes = [ ctypes.c_void_p, ctypes.c_void_p ]
+	library.amdsmi_get_gpu_activity.restype = ctypes.c_uint32
+
+	library.amdsmi_get_gpu_asic_info.argtypes = [ ctypes.c_void_p, ctypes.c_void_p ]
+	library.amdsmi_get_gpu_asic_info.restype = ctypes.c_uint32
+
+	library.amdsmi_get_temp_metric.argtypes = [ ctypes.c_void_p, ctypes.c_uint32, ctypes.c_uint32, ctypes.POINTER(ctypes.c_int64) ]
+	library.amdsmi_get_temp_metric.restype = ctypes.c_uint32
+
+	return library
+
+
+def find_device_handles(amd_smi_library : ctypes.CDLL) -> List[ctypes.c_void_p]:
+	device_handles : List[ctypes.c_void_p] = []
+
+	socket_count = ctypes.c_uint32()
+	amd_smi_library.amdsmi_get_socket_handles(ctypes.byref(socket_count), ctypes.POINTER(ctypes.c_void_p)())
+	socket_handles = (ctypes.c_void_p * socket_count.value)()
+	amd_smi_library.amdsmi_get_socket_handles(ctypes.byref(socket_count), socket_handles)
+
+	for socket_index in range(socket_count.value):
+		device_count = ctypes.c_uint32()
+		amd_smi_library.amdsmi_get_processor_handles(socket_handles[socket_index], ctypes.byref(device_count), ctypes.POINTER(ctypes.c_void_p)())
+		processor_handles = (ctypes.c_void_p * device_count.value)()
+		amd_smi_library.amdsmi_get_processor_handles(socket_handles[socket_index], ctypes.byref(device_count), processor_handles)
+
+		for device_index in range(device_count.value):
+			device_handles.append(ctypes.c_void_p(processor_handles[device_index]))
+
+	return device_handles
+
+
+def define_product_info() -> ctypes.Structure:
+	return type('AMDSMI_ASIC_INFO', (ctypes.Structure,),
+	{
+		'_pack_': 1,
+		'_fields_':
+		[
+			('market_name', ctypes.c_char * 256),
+			('vendor_id', ctypes.c_uint32),
+			('vendor_name', ctypes.c_char * 256),
+			('subvendor_id', ctypes.c_uint32),
+			('device_id', ctypes.c_uint64),
+			('rev_id', ctypes.c_uint32),
+			('asic_serial', ctypes.c_char * 256),
+			('oam_id', ctypes.c_uint32),
+			('num_of_compute_units', ctypes.c_uint32),
+			('padding', ctypes.c_ubyte * 4),
+			('target_graphics_version', ctypes.c_uint64),
+			('subsystem_id', ctypes.c_uint32),
+			('reserved', ctypes.c_uint32 * 21)
+		]
+	})()
+
+
+def define_device_memory() -> ctypes.Structure:
+	return type('AMDSMI_VRAM_USAGE', (ctypes.Structure,),
+	{
+		'_pack_': 1,
+		'_fields_':
+		[
+			('vram_total', ctypes.c_uint32),
+			('vram_used', ctypes.c_uint32),
+			('reserved', ctypes.c_uint32 * 2)
+		]
+	})()
+
+
+def define_device_utilization() -> ctypes.Structure:
+	return type('AMDSMI_ENGINE_USAGE', (ctypes.Structure,),
+	{
+		'_pack_': 1,
+		'_fields_':
+		[
+			('gfx_activity', ctypes.c_uint32),
+			('umc_activity', ctypes.c_uint32),
+			('mm_activity', ctypes.c_uint32),
+			('reserved', ctypes.c_uint32 * 13)
+		]
+	})()
@@ -0,0 +1,134 @@
+import ctypes
+from functools import lru_cache
+from typing import Optional
+
+from facefusion.common_helper import is_linux, is_macos, is_windows
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url_by_provider
+from facefusion.filesystem import resolve_relative_path
+from facefusion.types import LibrarySet
+
+
+@lru_cache
+def create_static_library_set() -> Optional[LibrarySet]:
+	if is_linux():
+		return\
+		{
+			'hashes':
+			{
+				'aom':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libaom.hash'),
+					'path': resolve_relative_path('../.libraries/libaom.hash')
+				}
+			},
+			'sources':
+			{
+				'aom':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libaom.so'),
+					'path': resolve_relative_path('../.libraries/libaom.so')
+				}
+			}
+		}
+	if is_macos():
+		return\
+		{
+			'hashes':
+			{
+				'aom':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libaom.hash'),
+					'path': resolve_relative_path('../.libraries/libaom.hash')
+				}
+			},
+			'sources':
+			{
+				'aom':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libaom.dylib'),
+					'path': resolve_relative_path('../.libraries/libaom.dylib')
+				}
+			}
+		}
+	if is_windows():
+		return\
+		{
+			'hashes':
+			{
+				'aom':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/aom.hash'),
+					'path': resolve_relative_path('../.libraries/aom.hash')
+				}
+			},
+			'sources':
+			{
+				'aom':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/aom.dll'),
+					'path': resolve_relative_path('../.libraries/aom.dll')
+				}
+			}
+		}
+
+	return None
+
+
+def pre_check() -> bool:
+	library_hash_set = create_static_library_set().get('hashes')
+	library_source_set = create_static_library_set().get('sources')
+
+	return conditional_download_hashes(library_hash_set) and conditional_download_sources(library_source_set)
+
+
+@lru_cache
+def create_static_library() -> Optional[ctypes.CDLL]:
+	library_path = create_static_library_set().get('sources').get('aom').get('path')
+
+	if library_path:
+		if is_windows():
+			library = ctypes.CDLL(library_path, winmode = 0)
+		else:
+			library = ctypes.CDLL(library_path)
+
+		if library:
+			return init_ctypes(library)
+
+	return None
+
+
+def init_ctypes(library : ctypes.CDLL) -> ctypes.CDLL:
+	library.aom_codec_enc_config_default.argtypes = [ ctypes.c_void_p, ctypes.c_void_p, ctypes.c_uint ]
+	library.aom_codec_enc_config_default.restype = ctypes.c_int
+
+	library.aom_codec_enc_init_ver.argtypes = [ ctypes.c_void_p, ctypes.c_void_p, ctypes.c_void_p, ctypes.c_long, ctypes.c_int ]
+	library.aom_codec_enc_init_ver.restype = ctypes.c_int
+
+	library.aom_codec_encode.argtypes = [ ctypes.c_void_p, ctypes.c_void_p, ctypes.c_int64, ctypes.c_ulong, ctypes.c_long, ctypes.c_ulong ]
+	library.aom_codec_encode.restype = ctypes.c_int
+
+	library.aom_codec_get_cx_data.argtypes = [ ctypes.c_void_p, ctypes.POINTER(ctypes.c_void_p) ]
+	library.aom_codec_get_cx_data.restype = ctypes.c_void_p
+
+	library.aom_codec_enc_config_set.argtypes = [ ctypes.c_void_p, ctypes.c_void_p ]
+	library.aom_codec_enc_config_set.restype = ctypes.c_int
+
+	library.aom_codec_destroy.argtypes = [ ctypes.c_void_p ]
+	library.aom_codec_destroy.restype = ctypes.c_int
+
+	library.aom_img_wrap.argtypes = [ ctypes.c_void_p, ctypes.c_int, ctypes.c_uint, ctypes.c_uint, ctypes.c_uint, ctypes.c_void_p ]
+	library.aom_img_wrap.restype = ctypes.c_void_p
+
+	library.aom_codec_control.argtypes = [ ctypes.c_void_p, ctypes.c_int, ctypes.c_int ]
+	library.aom_codec_control.restype = ctypes.c_int
+
+	library.aom_codec_dec_init_ver.argtypes = [ ctypes.c_void_p, ctypes.c_void_p, ctypes.c_void_p, ctypes.c_long, ctypes.c_int ]
+	library.aom_codec_dec_init_ver.restype = ctypes.c_int
+
+	library.aom_codec_decode.argtypes = [ ctypes.c_void_p, ctypes.c_void_p, ctypes.c_uint, ctypes.c_void_p ]
+	library.aom_codec_decode.restype = ctypes.c_int
+
+	library.aom_codec_get_frame.argtypes = [ ctypes.c_void_p, ctypes.POINTER(ctypes.c_void_p) ]
+	library.aom_codec_get_frame.restype = ctypes.c_void_p
+
+	return library
@@ -0,0 +1,294 @@
+import ctypes
+from functools import lru_cache
+from typing import Optional
+
+from facefusion.common_helper import is_linux, is_macos, is_windows
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url_by_provider
+from facefusion.filesystem import resolve_relative_path
+from facefusion.types import LibrarySet
+
+
+@lru_cache
+def create_static_library_set() -> Optional[LibrarySet]:
+	if is_linux():
+		return\
+		{
+			'hashes':
+			{
+				'crypto':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libcrypto.hash'),
+					'path': resolve_relative_path('../.libraries/libcrypto.hash')
+				},
+				'datachannel':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libdatachannel_next.hash'),
+					'path': resolve_relative_path('../.libraries/libdatachannel_next.hash')
+				},
+				'ssl':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libssl.hash'),
+					'path': resolve_relative_path('../.libraries/libssl.hash')
+				}
+			},
+			'sources':
+			{
+				'crypto':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libcrypto.so'),
+					'path': resolve_relative_path('../.libraries/libcrypto.so')
+				},
+				'datachannel':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libdatachannel_next.so'),
+					'path': resolve_relative_path('../.libraries/libdatachannel_next.so')
+				},
+				'ssl':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libssl.so'),
+					'path': resolve_relative_path('../.libraries/libssl.so')
+				}
+			}
+		}
+	if is_macos():
+		return\
+		{
+			'hashes':
+			{
+				'crypto':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libcrypto.hash'),
+					'path': resolve_relative_path('../.libraries/libcrypto.hash')
+				},
+				'datachannel':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libdatachannel_next.hash'),
+					'path': resolve_relative_path('../.libraries/libdatachannel_next.hash')
+				},
+				'ssl':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libssl.hash'),
+					'path': resolve_relative_path('../.libraries/libssl.hash')
+				}
+			},
+			'sources':
+			{
+				'crypto':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libcrypto.dylib'),
+					'path': resolve_relative_path('../.libraries/libcrypto.dylib')
+				},
+				'datachannel':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libdatachannel_next.dylib'),
+					'path': resolve_relative_path('../.libraries/libdatachannel_next.dylib')
+				},
+				'ssl':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libssl.dylib'),
+					'path': resolve_relative_path('../.libraries/libssl.dylib')
+				}
+			}
+		}
+	if is_windows():
+		return\
+		{
+			'hashes':
+			{
+				'crypto':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/crypto.hash'),
+					'path': resolve_relative_path('../.libraries/crypto.hash')
+				},
+				'datachannel':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/datachannel_next.hash'),
+					'path': resolve_relative_path('../.libraries/datachannel_next.hash')
+				},
+				'ssl':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/ssl.hash'),
+					'path': resolve_relative_path('../.libraries/ssl.hash')
+				}
+			},
+			'sources':
+			{
+				'crypto':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/crypto.dll'),
+					'path': resolve_relative_path('../.libraries/crypto.dll')
+				},
+				'datachannel':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/datachannel_next.dll'),
+					'path': resolve_relative_path('../.libraries/datachannel_next.dll')
+				},
+				'ssl':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/ssl.dll'),
+					'path': resolve_relative_path('../.libraries/ssl.dll')
+				}
+			}
+		}
+
+	return None
+
+
+def pre_check() -> bool:
+	library_hash_set = create_static_library_set().get('hashes')
+	library_source_set = create_static_library_set().get('sources')
+
+	return conditional_download_hashes(library_hash_set) and conditional_download_sources(library_source_set)
+
+
+@lru_cache
+def create_static_library() -> Optional[ctypes.CDLL]:
+	crypto_source_path = create_static_library_set().get('sources').get('crypto').get('path')
+	datachannel_source_path = create_static_library_set().get('sources').get('datachannel').get('path')
+	ssl_source_path = create_static_library_set().get('sources').get('ssl').get('path')
+
+	if crypto_source_path and datachannel_source_path and ssl_source_path:
+		if is_windows():
+			ctypes.CDLL(crypto_source_path, winmode = 0)
+			ctypes.CDLL(ssl_source_path, winmode = 0)
+			library = ctypes.CDLL(datachannel_source_path, winmode = 0)
+		else:
+			ctypes.CDLL(crypto_source_path)
+			ctypes.CDLL(ssl_source_path)
+			library = ctypes.CDLL(datachannel_source_path)
+
+		if library:
+			return init_ctypes(library)
+
+	return None
+
+
+def init_ctypes(library : ctypes.CDLL) -> ctypes.CDLL:
+	library.rtcInitLogger.argtypes = [ ctypes.c_int, ctypes.CFUNCTYPE(None, ctypes.c_int, ctypes.c_char_p) ]
+	library.rtcInitLogger.restype = None
+	library.rtcInitLogger(2, ctypes.CFUNCTYPE(None, ctypes.c_int, ctypes.c_char_p)(0))
+
+	library.rtcCreatePeerConnection.restype = ctypes.c_int
+
+	library.rtcDeletePeerConnection.argtypes = [ ctypes.c_int ]
+	library.rtcDeletePeerConnection.restype = ctypes.c_int
+
+	library.rtcSetLocalDescription.argtypes = [ ctypes.c_int, ctypes.c_char_p ]
+	library.rtcSetLocalDescription.restype = ctypes.c_int
+
+	library.rtcSetRemoteDescription.argtypes = [ ctypes.c_int, ctypes.c_char_p, ctypes.c_char_p ]
+	library.rtcSetRemoteDescription.restype = ctypes.c_int
+
+	library.rtcAddTrackEx.restype = ctypes.c_int
+
+	library.rtcSendMessage.argtypes = [ ctypes.c_int, ctypes.c_void_p, ctypes.c_int ]
+	library.rtcSendMessage.restype = ctypes.c_int
+
+	library.rtcSetAV1Packetizer.restype = ctypes.c_int
+	library.rtcSetVP8Packetizer.restype = ctypes.c_int
+	library.rtcSetVP9Packetizer.restype = ctypes.c_int
+
+	library.rtcChainRtcpSrReporter.argtypes = [ ctypes.c_int ]
+	library.rtcChainRtcpSrReporter.restype = ctypes.c_int
+
+	library.rtcSetTrackRtpTimestamp.argtypes = [ ctypes.c_int, ctypes.c_uint32 ]
+	library.rtcSetTrackRtpTimestamp.restype = ctypes.c_int
+
+	library.rtcIsOpen.argtypes = [ ctypes.c_int ]
+	library.rtcIsOpen.restype = ctypes.c_bool
+
+	library.rtcChainRtcpNackResponder.argtypes = [ ctypes.c_int, ctypes.c_uint ]
+	library.rtcChainRtcpNackResponder.restype = ctypes.c_int
+
+	library.rtcGetLocalDescription.argtypes = [ ctypes.c_int, ctypes.c_char_p, ctypes.c_int ]
+	library.rtcGetLocalDescription.restype = ctypes.c_int
+
+	library.rtcSetOpusPacketizer.restype = ctypes.c_int
+
+	library.rtcGetPayloadTypesForCodec.argtypes = [ ctypes.c_char_p, ctypes.c_char_p, ctypes.POINTER(ctypes.c_int), ctypes.c_int ]
+	library.rtcGetPayloadTypesForCodec.restype = ctypes.c_int
+
+	library.rtcSetAV1Depacketizer.argtypes = [ ctypes.c_int, ctypes.c_int ]
+	library.rtcSetAV1Depacketizer.restype = ctypes.c_int
+	library.rtcSetVP8Depacketizer.restype = ctypes.c_int
+	library.rtcSetVP9Depacketizer.restype = ctypes.c_int
+	library.rtcSetOpusDepacketizer.restype = ctypes.c_int
+
+	library.rtcChainRtcpReceivingSession.argtypes = [ ctypes.c_int ]
+	library.rtcChainRtcpReceivingSession.restype = ctypes.c_int
+
+	library.rtcSetFrameCallback.argtypes = [ ctypes.c_int, ctypes.CFUNCTYPE(None, ctypes.c_int, ctypes.c_void_p, ctypes.c_int, ctypes.c_void_p, ctypes.c_void_p) ]
+	library.rtcSetFrameCallback.restype = ctypes.c_int
+
+	library.rtcSetUserPointer.argtypes = [ ctypes.c_int, ctypes.c_void_p ]
+	library.rtcSetUserPointer.restype = None
+
+	library.rtcChainRembHandler.argtypes = [ ctypes.c_int, ctypes.CFUNCTYPE(None, ctypes.c_int, ctypes.c_uint, ctypes.c_void_p) ]
+	library.rtcChainRembHandler.restype = ctypes.c_int
+
+	library.rtcRequestBitrate.argtypes = [ ctypes.c_int, ctypes.c_uint ]
+	library.rtcRequestBitrate.restype = ctypes.c_int
+
+	library.rtcSetClosedCallback.argtypes = [ ctypes.c_int, ctypes.CFUNCTYPE(None, ctypes.c_int, ctypes.c_void_p) ]
+	library.rtcSetClosedCallback.restype = ctypes.c_int
+
+	return library
+
+
+def define_rtc_configuration() -> ctypes.Structure:
+	return type('RTC_CONFIGURATION', (ctypes.Structure,),
+	{
+		'_fields_':
+		[
+			('iceServers', ctypes.POINTER(ctypes.c_char_p)),
+			('iceServersCount', ctypes.c_int),
+			('proxyServer', ctypes.c_char_p),
+			('bindAddress', ctypes.c_char_p),
+			('certificateType', ctypes.c_int),
+			('iceTransportPolicy', ctypes.c_int),
+			('enableIceTcp', ctypes.c_bool),
+			('enableIceUdpMux', ctypes.c_bool),
+			('disableAutoNegotiation', ctypes.c_bool),
+			('forceMediaTransport', ctypes.c_bool),
+			('portRangeBegin', ctypes.c_ushort),
+			('portRangeEnd', ctypes.c_ushort),
+			('mtu', ctypes.c_int),
+			('maxMessageSize', ctypes.c_int)
+		]
+	})()
+
+
+def define_rtc_track_init() -> ctypes.Structure:
+	return type('RTC_TRACK_INIT', (ctypes.Structure,),
+	{
+		'_fields_':
+		[
+			('direction', ctypes.c_int),
+			('codec', ctypes.c_int),
+			('payloadType', ctypes.c_int),
+			('ssrc', ctypes.c_uint32),
+			('mid', ctypes.c_char_p),
+			('name', ctypes.c_char_p),
+			('msid', ctypes.c_char_p),
+			('trackId', ctypes.c_char_p),
+			('profile', ctypes.c_char_p)
+		]
+	})()
+
+
+def define_rtc_packetizer_init() -> ctypes.Structure:
+	return type('RTC_PACKETIZER_INIT', (ctypes.Structure,),
+	{
+		'_fields_':
+		[
+			('ssrc', ctypes.c_uint32),
+			('cname', ctypes.c_char_p),
+			('payloadType', ctypes.c_uint8),
+			('clockRate', ctypes.c_uint32),
+			('sequenceNumber', ctypes.c_uint16),
+			('timestamp', ctypes.c_uint32),
+			('maxFragmentSize', ctypes.c_uint16),
+			('nalSeparator', ctypes.c_int),
+			('obuPacketization', ctypes.c_int)
+		]
+	})()
@@ -0,0 +1,88 @@
+import ctypes
+import ctypes.util
+from functools import lru_cache
+from typing import List, Optional
+
+
+@lru_cache
+def create_static_library() -> Optional[ctypes.CDLL]:
+	library_path = ctypes.util.find_library('nvidia-ml') or ctypes.util.find_library('nvml')
+
+	if library_path:
+		library = ctypes.CDLL(library_path)
+
+		if library:
+			return init_ctypes(library)
+
+	return None
+
+
+def init_ctypes(library : ctypes.CDLL) -> ctypes.CDLL:
+	library.nvmlInit_v2.argtypes = []
+	library.nvmlInit_v2.restype = ctypes.c_int
+
+	library.nvmlShutdown.argtypes = []
+	library.nvmlShutdown.restype = ctypes.c_int
+
+	library.nvmlDeviceGetCount_v2.argtypes = [ ctypes.POINTER(ctypes.c_uint) ]
+	library.nvmlDeviceGetCount_v2.restype = ctypes.c_int
+
+	library.nvmlSystemGetDriverVersion.argtypes = [ ctypes.c_char_p, ctypes.c_uint ]
+	library.nvmlSystemGetDriverVersion.restype = ctypes.c_int
+
+	library.nvmlSystemGetCudaDriverVersion.argtypes = [ ctypes.POINTER(ctypes.c_int) ]
+	library.nvmlSystemGetCudaDriverVersion.restype = ctypes.c_int
+
+	library.nvmlDeviceGetHandleByIndex_v2.argtypes = [ ctypes.c_uint, ctypes.POINTER(ctypes.c_void_p) ]
+	library.nvmlDeviceGetHandleByIndex_v2.restype = ctypes.c_int
+
+	library.nvmlDeviceGetName.argtypes = [ ctypes.c_void_p, ctypes.c_char_p, ctypes.c_uint ]
+	library.nvmlDeviceGetName.restype = ctypes.c_int
+
+	library.nvmlDeviceGetMemoryInfo.argtypes = [ ctypes.c_void_p, ctypes.c_void_p ]
+	library.nvmlDeviceGetMemoryInfo.restype = ctypes.c_int
+
+	library.nvmlDeviceGetTemperature.argtypes = [ ctypes.c_void_p, ctypes.c_int, ctypes.POINTER(ctypes.c_uint) ]
+	library.nvmlDeviceGetTemperature.restype = ctypes.c_int
+
+	library.nvmlDeviceGetUtilizationRates.argtypes = [ ctypes.c_void_p, ctypes.c_void_p ]
+	library.nvmlDeviceGetUtilizationRates.restype = ctypes.c_int
+
+	return library
+
+
+def find_device_handles(nvidia_ml_library : ctypes.CDLL) -> List[ctypes.c_void_p]:
+	device_handles : List[ctypes.c_void_p] = []
+
+	device_count = ctypes.c_uint()
+	nvidia_ml_library.nvmlDeviceGetCount_v2(ctypes.byref(device_count))
+
+	for device_id in range(device_count.value):
+		device_handle = ctypes.c_void_p()
+		nvidia_ml_library.nvmlDeviceGetHandleByIndex_v2(device_id, ctypes.byref(device_handle))
+		device_handles.append(device_handle)
+
+	return device_handles
+
+
+def define_device_memory() -> ctypes.Structure:
+	return type('NVML_MEMORY', (ctypes.Structure,),
+	{
+		'_fields_':
+		[
+			('total', ctypes.c_ulonglong),
+			('free', ctypes.c_ulonglong),
+			('used', ctypes.c_ulonglong)
+		]
+	})()
+
+
+def define_device_utilization() -> ctypes.Structure:
+	return type('NVML_UTILIZATION', (ctypes.Structure,),
+	{
+		'_fields_':
+		[
+			('gpu', ctypes.c_uint),
+			('memory', ctypes.c_uint)
+		]
+	})()
@@ -0,0 +1,124 @@
+import ctypes
+from functools import lru_cache
+from typing import Optional
+
+from facefusion.common_helper import is_linux, is_macos, is_windows
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url_by_provider
+from facefusion.filesystem import resolve_relative_path
+from facefusion.types import LibrarySet
+
+
+@lru_cache
+def create_static_library_set() -> Optional[LibrarySet]:
+	if is_linux():
+		return\
+		{
+			'hashes':
+			{
+				'opus':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libopus.hash'),
+					'path': resolve_relative_path('../.libraries/libopus.hash')
+				}
+			},
+			'sources':
+			{
+				'opus':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libopus.so'),
+					'path': resolve_relative_path('../.libraries/libopus.so')
+				}
+			}
+		}
+
+	if is_macos():
+		return\
+		{
+			'hashes':
+			{
+				'opus':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libopus.hash'),
+					'path': resolve_relative_path('../.libraries/libopus.hash')
+				}
+			},
+			'sources':
+			{
+				'opus':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libopus.dylib'),
+					'path': resolve_relative_path('../.libraries/libopus.dylib')
+				}
+			}
+		}
+
+	if is_windows():
+		return\
+		{
+			'hashes':
+			{
+				'opus':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/opus.hash'),
+					'path': resolve_relative_path('../.libraries/opus.hash')
+				}
+			},
+			'sources':
+			{
+				'opus':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/opus.dll'),
+					'path': resolve_relative_path('../.libraries/opus.dll')
+				}
+			}
+		}
+
+	return None
+
+
+def pre_check() -> bool:
+	library_hash_set = create_static_library_set().get('hashes')
+	library_source_set = create_static_library_set().get('sources')
+
+	return conditional_download_hashes(library_hash_set) and conditional_download_sources(library_source_set)
+
+
+@lru_cache
+def create_static_library() -> Optional[ctypes.CDLL]:
+	library_path = create_static_library_set().get('sources').get('opus').get('path')
+
+	if library_path:
+		if is_windows():
+			library = ctypes.CDLL(library_path, winmode = 0)
+		else:
+			library = ctypes.CDLL(library_path)
+
+		if library:
+			return init_ctypes(library)
+
+	return None
+
+
+def init_ctypes(library : ctypes.CDLL) -> ctypes.CDLL:
+	library.opus_encoder_create.argtypes = [ ctypes.c_int, ctypes.c_int, ctypes.c_int, ctypes.POINTER(ctypes.c_int) ]
+	library.opus_encoder_create.restype = ctypes.c_void_p
+
+	library.opus_encode_float.argtypes = [ ctypes.c_void_p, ctypes.POINTER(ctypes.c_float), ctypes.c_int, ctypes.c_char_p, ctypes.c_int ]
+	library.opus_encode_float.restype = ctypes.c_int
+
+	library.opus_encoder_destroy.argtypes = [ ctypes.c_void_p ]
+	library.opus_encoder_destroy.restype = None
+
+	library.opus_decoder_create.argtypes = [ ctypes.c_int, ctypes.c_int, ctypes.POINTER(ctypes.c_int) ]
+	library.opus_decoder_create.restype = ctypes.c_void_p
+
+	library.opus_decode_float.argtypes = [ ctypes.c_void_p, ctypes.c_char_p, ctypes.c_int, ctypes.POINTER(ctypes.c_float), ctypes.c_int, ctypes.c_int ]
+	library.opus_decode_float.restype = ctypes.c_int
+
+	library.opus_decoder_get_nb_samples.argtypes = [ ctypes.c_void_p, ctypes.c_char_p, ctypes.c_int ]
+	library.opus_decoder_get_nb_samples.restype = ctypes.c_int
+
+	library.opus_decoder_destroy.argtypes = [ ctypes.c_void_p ]
+	library.opus_decoder_destroy.restype = None
+
+	return library
@@ -0,0 +1,24 @@
+import ctypes
+import ctypes.util
+from functools import lru_cache
+from typing import Optional
+
+
+@lru_cache
+def create_static_library() -> Optional[ctypes.CDLL]:
+	library_path = ctypes.util.find_library('rocm-core')
+
+	if library_path:
+		library = ctypes.CDLL(library_path)
+
+		if library:
+			return init_ctypes(library)
+
+	return None
+
+
+def init_ctypes(library : ctypes.CDLL) -> ctypes.CDLL:
+	library.getROCmVersion.argtypes = [ ctypes.POINTER(ctypes.c_uint), ctypes.POINTER(ctypes.c_uint), ctypes.POINTER(ctypes.c_uint) ]
+	library.getROCmVersion.restype = ctypes.c_int
+
+	return library
@@ -0,0 +1,134 @@
+import ctypes
+from functools import lru_cache
+from typing import Optional
+
+from facefusion.common_helper import is_linux, is_macos, is_windows
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url_by_provider
+from facefusion.filesystem import resolve_relative_path
+from facefusion.types import LibrarySet
+
+
+@lru_cache
+def create_static_library_set() -> Optional[LibrarySet]:
+	if is_linux():
+		return\
+		{
+			'hashes':
+			{
+				'vpx':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libvpx.hash'),
+					'path': resolve_relative_path('../.libraries/libvpx.hash')
+				}
+			},
+			'sources':
+			{
+				'vpx':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'linux/libvpx.so'),
+					'path': resolve_relative_path('../.libraries/libvpx.so')
+				}
+			}
+		}
+	if is_macos():
+		return\
+		{
+			'hashes':
+			{
+				'vpx':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libvpx.hash'),
+					'path': resolve_relative_path('../.libraries/libvpx.hash')
+				}
+			},
+			'sources':
+			{
+				'vpx':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'macos/libvpx.dylib'),
+					'path': resolve_relative_path('../.libraries/libvpx.dylib')
+				}
+			}
+		}
+	if is_windows():
+		return\
+		{
+			'hashes':
+			{
+				'vpx':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/vpx.hash'),
+					'path': resolve_relative_path('../.libraries/vpx.hash')
+				}
+			},
+			'sources':
+			{
+				'vpx':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'libraries-4.0.0', 'windows/vpx.dll'),
+					'path': resolve_relative_path('../.libraries/vpx.dll')
+				}
+			}
+		}
+
+	return None
+
+
+def pre_check() -> bool:
+	library_hash_set = create_static_library_set().get('hashes')
+	library_source_set = create_static_library_set().get('sources')
+
+	return conditional_download_hashes(library_hash_set) and conditional_download_sources(library_source_set)
+
+
+@lru_cache
+def create_static_library() -> Optional[ctypes.CDLL]:
+	library_path = create_static_library_set().get('sources').get('vpx').get('path')
+
+	if library_path:
+		if is_windows():
+			library = ctypes.CDLL(library_path, winmode = 0)
+		else:
+			library = ctypes.CDLL(library_path)
+
+		if library:
+			return init_ctypes(library)
+
+	return None
+
+
+def init_ctypes(library : ctypes.CDLL) -> ctypes.CDLL:
+	library.vpx_codec_enc_config_default.argtypes = [ ctypes.c_void_p, ctypes.c_void_p, ctypes.c_uint ]
+	library.vpx_codec_enc_config_default.restype = ctypes.c_int
+
+	library.vpx_codec_enc_init_ver.argtypes = [ ctypes.c_void_p, ctypes.c_void_p, ctypes.c_void_p, ctypes.c_long, ctypes.c_int ]
+	library.vpx_codec_enc_init_ver.restype = ctypes.c_int
+
+	library.vpx_codec_encode.argtypes = [ ctypes.c_void_p, ctypes.c_void_p, ctypes.c_int64, ctypes.c_ulong, ctypes.c_long, ctypes.c_ulong ]
+	library.vpx_codec_encode.restype = ctypes.c_int
+
+	library.vpx_codec_get_cx_data.argtypes = [ ctypes.c_void_p, ctypes.POINTER(ctypes.c_void_p) ]
+	library.vpx_codec_get_cx_data.restype = ctypes.c_void_p
+
+	library.vpx_codec_enc_config_set.argtypes = [ ctypes.c_void_p, ctypes.c_void_p ]
+	library.vpx_codec_enc_config_set.restype = ctypes.c_int
+
+	library.vpx_codec_destroy.argtypes = [ ctypes.c_void_p ]
+	library.vpx_codec_destroy.restype = ctypes.c_int
+
+	library.vpx_img_wrap.argtypes = [ ctypes.c_void_p, ctypes.c_int, ctypes.c_uint, ctypes.c_uint, ctypes.c_uint, ctypes.c_void_p ]
+	library.vpx_img_wrap.restype = ctypes.c_void_p
+
+	library.vpx_codec_control_.argtypes = [ ctypes.c_void_p, ctypes.c_int, ctypes.c_int ]
+	library.vpx_codec_control_.restype = ctypes.c_int
+
+	library.vpx_codec_dec_init_ver.argtypes = [ ctypes.c_void_p, ctypes.c_void_p, ctypes.c_void_p, ctypes.c_long, ctypes.c_int ]
+	library.vpx_codec_dec_init_ver.restype = ctypes.c_int
+
+	library.vpx_codec_decode.argtypes = [ ctypes.c_void_p, ctypes.c_void_p, ctypes.c_uint, ctypes.c_void_p, ctypes.c_long ]
+	library.vpx_codec_decode.restype = ctypes.c_int
+
+	library.vpx_codec_get_frame.argtypes = [ ctypes.c_void_p, ctypes.POINTER(ctypes.c_void_p) ]
+	library.vpx_codec_get_frame.restype = ctypes.c_void_p
+
+	return library
@@ -12,8 +12,11 @@ LOCALES : Locales =\
 		'extracting_frames': 'extracting frames with a resolution of {resolution} and {fps} frames per second',
 		'extracting_frames_succeeded': 'extracting frames succeeded',
 		'extracting_frames_failed': 'extracting frames failed',
+		'spawning_frames_succeeded': 'spawning frames succeeded',
+		'spawning_frames_failed': 'spawning frames failed',
 		'analysing': 'analysing',
 		'extracting': 'extracting',
+		'spawning': 'spawning',
 		'streaming': 'streaming',
 		'processing': 'processing',
 		'merging': 'merging',
@@ -37,6 +40,8 @@ LOCALES : Locales =\
 		'processing_stopped': 'processing stopped',
 		'processing_image_succeeded': 'processing to image succeeded in {seconds} seconds',
 		'processing_image_failed': 'processing to image failed',
+		'processing_frames_succeeded': 'processing to frames succeeded in {seconds} seconds',
+		'processing_frames_failed': 'processing to frames failed',
 		'processing_video_succeeded': 'processing to video succeeded in {seconds} seconds',
 		'processing_video_failed': 'processing to video failed',
 		'choose_image_source': 'choose an image for the source',
@@ -48,10 +53,9 @@ LOCALES : Locales =\
 		'no_source_face_detected': 'no source face detected',
 		'processor_not_loaded': 'processor {processor} could not be loaded',
 		'processor_not_implemented': 'processor {processor} not implemented correctly',
-		'ui_layout_not_loaded': 'ui layout {ui_layout} could not be loaded',
-		'ui_layout_not_implemented': 'ui layout {ui_layout} not implemented correctly',
 		'stream_not_loaded': 'stream {stream_mode} could not be loaded',
 		'stream_not_supported': 'stream not supported',
+		'api_started': 'started API on {host}:{port}',
 		'job_created': 'job {job_id} created',
 		'job_not_created': 'job {job_id} not created',
 		'job_submitted': 'job {job_id} submitted',
@@ -99,6 +103,7 @@ LOCALES : Locales =\
 		{
 			'install_dependency': 'choose the variant of {dependency} to install',
 			'skip_conda': 'skip the conda environment check',
+			'workflow': 'choose the workflow',
 			'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',
@@ -124,6 +129,7 @@ LOCALES : Locales =\
 			'reference_face_position': 'specify the position used to create the reference face',
 			'reference_face_distance': 'specify the similarity between the reference face and target face',
 			'reference_frame_number': 'specify the frame used to create the reference face',
+			'face_tracker_score': 'specify the overlap score used to match the tracked faces',
 			'face_occluder_model': 'choose the model responsible for the occlusion mask',
 			'face_parser_model': 'choose the model responsible for the region mask',
 			'face_mask_types': 'mix and match different face mask types (choices: {choices})',
@@ -135,12 +141,13 @@ LOCALES : Locales =\
 			'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',
-			'keep_temp': 'keep the temporary resources after processing',
+			'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',
 			'output_image_scale': 'specify the image scale based on the target image',
 			'output_audio_encoder': 'specify the encoder used for the audio',
 			'output_audio_quality': 'specify the audio quality which translates to the audio compression',
 			'output_audio_volume': 'specify the audio volume based on the target video',
+			'output_audio_fps': 'specify the fps used when converting audio to video frames',
 			'output_video_encoder': 'specify the encoder used for the video',
 			'output_video_preset': 'balance fast video processing and video file size',
 			'output_video_quality': 'specify the video quality which translates to the video compression',
@@ -149,26 +156,25 @@ LOCALES : Locales =\
 			'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',
-			'open_browser': 'open the browser once the program is ready',
-			'ui_layouts': 'launch a single or multiple UI layouts (choices: {choices}, ...)',
-			'ui_workflow': 'choose the ui workflow',
 			'download_providers': 'download using different providers (choices: {choices}, ...)',
 			'download_scope': 'specify the download scope',
 			'benchmark_mode': 'choose the benchmark mode',
 			'benchmark_resolutions': 'choose the resolutions for the benchmarks (choices: {choices}, ...)',
 			'benchmark_cycle_count': 'specify the amount of cycles per benchmark',
+			'api_host': 'specify the API host',
+			'api_port': 'specify the API port',
+			'api_security_strategy': 'specify the API security strategy used for sanitizing uploaded assets',
 			'execution_device_ids': 'specify the devices used for processing',
 			'execution_providers': 'inference using different providers (choices: {choices}, ...)',
 			'execution_thread_count': 'specify the amount of parallel threads while processing',
 			'video_memory_strategy': 'balance fast processing and low VRAM usage',
-			'system_memory_limit': 'limit the available RAM that can be used while processing',
 			'log_level': 'adjust the message severity displayed in the terminal',
 			'halt_on_error': 'halt the program once an error occurred',
 			'run': 'run the program',
-			'headless_run': 'run the program in headless mode',
 			'batch_run': 'run the program in batch mode',
 			'force_download': 'force automate downloads and exit',
 			'benchmark': 'benchmark the program',
+			'api': 'start the API server',
 			'job_id': 'specify the job id',
 			'job_status': 'specify the job status',
 			'step_index': 'specify the step index',
@@ -224,6 +230,7 @@ LOCALES : Locales =\
 			'face_selector_mode_dropdown': 'FACE SELECTOR MODE',
 			'face_selector_order_dropdown': 'FACE SELECTOR ORDER',
 			'face_selector_race_dropdown': 'FACE SELECTOR RACE',
+			'face_tracker_score_slider': 'FACE TRACKER SCORE',
 			'face_occluder_model_dropdown': 'FACE OCCLUDER MODEL',
 			'face_parser_model_dropdown': 'FACE PARSER MODEL',
 			'voice_extractor_model_dropdown': 'VOICE EXTRACTOR MODEL',
@@ -257,12 +264,10 @@ LOCALES : Locales =\
 			'source_file': 'SOURCE',
 			'start_button': 'START',
 			'stop_button': 'STOP',
-			'system_memory_limit_slider': 'SYSTEM MEMORY LIMIT',
 			'target_file': 'TARGET',
 			'temp_frame_format_dropdown': 'TEMP FRAME FORMAT',
 			'terminal_textbox': 'TERMINAL',
 			'trim_frame_slider': 'TRIM FRAME',
-			'ui_workflow': 'UI WORKFLOW',
 			'video_memory_strategy_dropdown': 'VIDEO MEMORY STRATEGY',
 			'webcam_fps_slider': 'WEBCAM FPS',
 			'webcam_image': 'WEBCAM',
@@ -0,0 +1,17 @@
+from typing import Optional, Tuple
+
+
+def restrict_trim_frame(frame_total : int, trim_frame_start : Optional[int], trim_frame_end : Optional[int]) -> Tuple[int, int]:
+	if isinstance(trim_frame_start, int):
+		trim_frame_start = max(0, min(trim_frame_start, frame_total))
+	if isinstance(trim_frame_end, int):
+		trim_frame_end = max(0, min(trim_frame_end, frame_total))
+
+	if isinstance(trim_frame_start, int) and isinstance(trim_frame_end, int):
+		return trim_frame_start, trim_frame_end
+	if isinstance(trim_frame_start, int):
+		return trim_frame_start, frame_total
+	if isinstance(trim_frame_end, int):
+		return 0, trim_frame_end
+
+	return 0, frame_total
@@ -1,21 +0,0 @@
-from facefusion.common_helper import is_macos, is_windows
-
-if is_windows():
-	import ctypes
-else:
-	import resource
-
-
-def limit_system_memory(system_memory_limit : int = 1) -> bool:
-	if is_macos():
-		system_memory_limit = system_memory_limit * (1024 ** 6)
-	else:
-		system_memory_limit = system_memory_limit * (1024 ** 3)
-	try:
-		if is_windows():
-			ctypes.windll.kernel32.SetProcessWorkingSetSize(-1, ctypes.c_size_t(system_memory_limit), ctypes.c_size_t(system_memory_limit)) #type:ignore[attr-defined]
-		else:
-			resource.setrlimit(resource.RLIMIT_DATA, (system_memory_limit, system_memory_limit))
-		return True
-	except Exception:
-		return False
@@ -4,7 +4,7 @@ METADATA =\
 {
 	'name': 'FaceFusion',
 	'description': 'Industry leading face manipulation platform',
-	'version': '3.6.1',
+	'version': 'v4',
 	'license': 'OpenRAIL-AS',
 	'author': 'Henry Ruhs',
 	'url': 'https://facefusion.io'
@@ -12,6 +12,7 @@ PROCESSORS_METHODS =\
 	'clear_inference_pool',
 	'register_args',
 	'apply_args',
+	'get_common_modules',
 	'pre_check',
 	'pre_process',
 	'post_process',
@@ -1,28 +1,29 @@
 from argparse import ArgumentParser
 from functools import lru_cache
+from types import ModuleType
+from typing import List

 import cv2
 import numpy

+import facefusion.capability_store
 import facefusion.choices
 import facefusion.jobs.job_manager
-import facefusion.jobs.job_store
 from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, translator, video_manager
-from facefusion.common_helper import create_int_metavar, is_macos
+from facefusion.common_helper import create_int_metavar, get_middle
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.execution import has_execution_provider
-from facefusion.face_analyser import scale_face
+from facefusion.face_creator import scale_face
 from facefusion.face_helper import merge_matrix, paste_back, scale_face_landmark_5, warp_face_by_face_landmark_5
 from facefusion.face_masker import create_box_mask, create_occlusion_mask
 from facefusion.face_selector import select_faces
-from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
+from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path
 from facefusion.processors.modules.age_modifier import choices as age_modifier_choices
 from facefusion.processors.modules.age_modifier.types import AgeModifierDirection, AgeModifierInputs
-from facefusion.processors.types import ProcessorOutputs
+from facefusion.processors.types import ApplyStateItem, ProcessorOutputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import thread_semaphore
-from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
-from facefusion.vision import match_frame_color, read_static_image, read_static_video_frame
+from facefusion.types import Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import match_frame_color, read_static_image, read_static_video_chunk, read_static_video_frame


@lru_cache()
@@ -124,9 +125,26 @@ def get_model_options() -> ModelOptions:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--age-modifier-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'age_modifier_model', 'fran'), choices = age_modifier_choices.age_modifier_models)
-		group_processors.add_argument('--age-modifier-direction', help = translator.get('help.direction', __package__), type = int, default = config.get_int_value('processors', 'age_modifier_direction', '0'), choices = age_modifier_choices.age_modifier_direction_range, metavar = create_int_metavar(age_modifier_choices.age_modifier_direction_range))
-		facefusion.jobs.job_store.register_step_keys([ 'age_modifier_model', 'age_modifier_direction' ])
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--age-modifier-model',
+					help = translator.get('help.model', __package__),
+					default = config.get_str_value('processors', 'age_modifier_model', 'fran'),
+					choices = age_modifier_choices.age_modifier_models
+				),
+				group_processors.add_argument(
+					'--age-modifier-direction',
+					help = translator.get('help.direction', __package__),
+					type = int,
+					default = config.get_int_value('processors', 'age_modifier_direction', '0'),
+					choices = age_modifier_choices.age_modifier_direction_range,
+					metavar = create_int_metavar(age_modifier_choices.age_modifier_direction_range)
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'age_modifier' ]
+		)


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
@@ -134,10 +152,18 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('age_modifier_direction', args.get('age_modifier_direction'))


+def get_common_modules() -> List[ModuleType]:
+	return [ content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer ]
+
+
 def pre_check() -> bool:
 	model_hash_set = get_model_options().get('hashes')
 	model_source_set = get_model_options().get('sources')

+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
+
 	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)


@@ -145,28 +171,25 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
 		logger.error(translator.get('choose_image_or_video_target') + translator.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
-		logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
-		return False
-	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
-		logger.error(translator.get('match_target_and_output_extension') + translator.get('exclamation_mark'), __name__)
-		return False
+	if state_manager.get_item('workflow') in [ 'audio-to-image:video', 'image-to-image', 'image-to-video' ]:
+		if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
+			logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
+			return False
 	return True


 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_video_frame.cache_clear()
+	read_static_video_chunk.cache_clear()
 	video_manager.clear_video_pool()
+
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
+
 	if state_manager.get_item('video_memory_strategy') == 'strict':
-		content_analyser.clear_inference_pool()
-		face_classifier.clear_inference_pool()
-		face_detector.clear_inference_pool()
-		face_landmarker.clear_inference_pool()
-		face_masker.clear_inference_pool()
-		face_recognizer.clear_inference_pool()
+		for common_module in get_common_modules():
+			common_module.clear_inference_pool()


 def modify_age(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
@@ -231,9 +254,6 @@ def forward(crop_vision_frame : VisionFrame, extend_vision_frame : VisionFrame,
 	age_modifier = get_inference_pool().get('age_modifier')
 	age_modifier_inputs = {}

-	if is_macos() and has_execution_provider('coreml'):
-		age_modifier.set_providers([ facefusion.choices.execution_provider_set.get('cpu') ])
-
 	for age_modifier_input in age_modifier.get_inputs():
 		if age_modifier_input.name == 'target':
 			age_modifier_inputs[age_modifier_input.name] = crop_vision_frame
@@ -280,10 +300,13 @@ def normalize_extend_frame(extend_vision_frame : VisionFrame) -> VisionFrame:

 def process_frame(inputs : AgeModifierInputs) -> ProcessorOutputs:
 	reference_vision_frame = inputs.get('reference_vision_frame')
-	target_vision_frame = inputs.get('target_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
+	target_vision_frames = inputs.get('target_vision_frames')
 	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_vision_frame = get_middle(target_vision_frames)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frames)

 	if target_faces:
 		for target_face in target_faces:
@@ -1,4 +1,4 @@
-from typing import Any, Literal, TypeAlias, TypedDict
+from typing import Any, List, Literal, TypeAlias, TypedDict

 from numpy.typing import NDArray

@@ -7,7 +7,8 @@ from facefusion.types import Mask, VisionFrame
 AgeModifierInputs = TypedDict('AgeModifierInputs',
 {
 	'reference_vision_frame' : VisionFrame,
-	'target_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
+	'target_vision_frames' : List[VisionFrame],
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask
 })
@@ -1,26 +1,28 @@
 from argparse import ArgumentParser
 from functools import lru_cache, partial
+from types import ModuleType
 from typing import List, Tuple

 import cv2
 import numpy

+import facefusion.capability_store
+import facefusion.choices
 import facefusion.jobs.job_manager
-import facefusion.jobs.job_store
 from facefusion import config, content_analyser, inference_manager, logger, state_manager, translator, video_manager
 from facefusion.common_helper import is_macos, is_windows
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.execution import has_execution_provider
-from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
+from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path
 from facefusion.normalizer import normalize_color
 from facefusion.processors.modules.background_remover import choices as background_remover_choices
 from facefusion.processors.modules.background_remover.types import BackgroundRemoverInputs
-from facefusion.processors.types import ProcessorOutputs
+from facefusion.processors.types import ApplyStateItem, ProcessorOutputs
 from facefusion.program_helper import find_argument_group
 from facefusion.sanitizer import sanitize_int_range
 from facefusion.thread_helper import thread_semaphore
-from facefusion.types import ApplyStateItem, Args, DownloadScope, ExecutionProvider, InferencePool, Mask, ModelOptions, ModelSet, ProcessMode, VisionFrame
-from facefusion.vision import read_static_image, read_static_video_frame
+from facefusion.types import Args, DownloadScope, InferencePool, InferenceProvider, Mask, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import read_static_image, read_static_video_chunk, read_static_video_frame


@lru_cache()
@@ -477,12 +479,13 @@ def clear_inference_pool() -> None:
 	inference_manager.clear_inference_pool(__name__, model_names)


-def resolve_execution_providers() -> List[ExecutionProvider]:
+def resolve_inference_providers() -> List[InferenceProvider]:
 	model_type = get_model_options().get('type')

 	if is_macos() and has_execution_provider('coreml') or is_windows() and has_execution_provider('directml') and model_type == 'corridor_key':
-		return [ 'cpu' ]
-	return state_manager.get_item('execution_providers')
+		return [ facefusion.choices.execution_provider_set.get('cpu') ]
+
+	return []


 def get_model_options() -> ModelOptions:
@@ -493,10 +496,32 @@ def get_model_options() -> ModelOptions:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--background-remover-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'background_remover_model', 'modnet'), choices = background_remover_choices.background_remover_models)
-		group_processors.add_argument('--background-remover-fill-color', help = translator.get('help.fill_color', __package__), type = partial(sanitize_int_range, int_range = background_remover_choices.background_remover_color_range), default = config.get_int_list('processors', 'background_remover_fill_color', '0 0 0 0'), nargs = '+')
-		group_processors.add_argument('--background-remover-despill-color', help = translator.get('help.despill_color', __package__), type = partial(sanitize_int_range, int_range = background_remover_choices.background_remover_color_range), default = config.get_int_list('processors', 'background_remover_despill_color', '0 0 0 0'), nargs = '+')
-		facefusion.jobs.job_store.register_step_keys([ 'background_remover_model', 'background_remover_fill_color', 'background_remover_despill_color' ])
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--background-remover-model',
+					help = translator.get('help.model', __package__),
+					default = config.get_str_value('processors', 'background_remover_model', 'modnet'),
+					choices = background_remover_choices.background_remover_models
+				),
+				group_processors.add_argument(
+					'--background-remover-fill-color',
+					help = translator.get('help.fill_color', __package__),
+					type = partial(sanitize_int_range, int_range = background_remover_choices.background_remover_color_range),
+					default = config.get_int_list('processors', 'background_remover_fill_color', '0 0 0 0'),
+					nargs = '+'
+				),
+				group_processors.add_argument(
+					'--background-remover-despill-color',
+					help = translator.get('help.despill_color', __package__),
+					type = partial(sanitize_int_range, int_range = background_remover_choices.background_remover_color_range),
+					default = config.get_int_list('processors', 'background_remover_despill_color', '0 0 0 0'),
+					nargs = '+'
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'background_remover' ]
+		)


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
@@ -505,10 +530,18 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('background_remover_despill_color', normalize_color(args.get('background_remover_despill_color')))


+def get_common_modules() -> List[ModuleType]:
+	return [ content_analyser ]
+
+
 def pre_check() -> bool:
 	model_hash_set = get_model_options().get('hashes')
 	model_source_set = get_model_options().get('sources')

+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
+
 	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)


@@ -516,23 +549,25 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
 		logger.error(translator.get('choose_image_or_video_target') + translator.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
-		logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
-		return False
-	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
-		logger.error(translator.get('match_target_and_output_extension') + translator.get('exclamation_mark'), __name__)
-		return False
+	if state_manager.get_item('workflow') in [ 'audio-to-image:video', 'image-to-image', 'image-to-video' ]:
+		if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
+			logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
+			return False
 	return True


 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_video_frame.cache_clear()
+	read_static_video_chunk.cache_clear()
 	video_manager.clear_video_pool()
+
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
+
 	if state_manager.get_item('video_memory_strategy') == 'strict':
-		content_analyser.clear_inference_pool()
+		for common_module in get_common_modules():
+			common_module.clear_inference_pool()


 def remove_background(temp_vision_frame : VisionFrame) -> Tuple[VisionFrame, Mask]:
@@ -1,10 +1,10 @@
-from typing import Literal, TypedDict
+from typing import List, Literal, TypedDict

 from facefusion.types import Mask, VisionFrame

 BackgroundRemoverInputs = TypedDict('BackgroundRemoverInputs',
 {
-	'target_vision_frame' : VisionFrame,
+	'target_vision_frames' : List[VisionFrame],
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask
 })
@@ -1,28 +1,29 @@
 from argparse import ArgumentParser
 from functools import lru_cache
-from typing import Tuple
+from types import ModuleType
+from typing import List, Tuple

 import cv2
 import numpy
 from cv2.typing import Size

+import facefusion.capability_store
 import facefusion.jobs.job_manager
-import facefusion.jobs.job_store
 from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, translator, video_manager
-from facefusion.common_helper import create_int_metavar
+from facefusion.common_helper import create_int_metavar, get_middle
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url_by_provider
-from facefusion.face_analyser import scale_face
+from facefusion.face_creator import scale_face
 from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
 from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask, create_region_mask
 from facefusion.face_selector import select_faces
-from facefusion.filesystem import get_file_name, in_directory, is_image, is_video, resolve_file_paths, resolve_relative_path, same_file_extension
+from facefusion.filesystem import get_file_name, in_directory, is_image, is_video, resolve_file_paths, resolve_relative_path
 from facefusion.processors.modules.deep_swapper import choices as deep_swapper_choices
 from facefusion.processors.modules.deep_swapper.types import DeepSwapperInputs, DeepSwapperMorph
-from facefusion.processors.types import ProcessorOutputs
+from facefusion.processors.types import ApplyStateItem, ProcessorOutputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import thread_semaphore
-from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, Mask, ModelOptions, ModelSet, ProcessMode, VisionFrame
-from facefusion.vision import conditional_match_frame_color, read_static_image, read_static_video_frame
+from facefusion.types import Args, DownloadScope, Face, InferencePool, Mask, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import conditional_match_frame_color, read_static_image, read_static_video_chunk, read_static_video_frame


@lru_cache()
@@ -276,9 +277,26 @@ def get_model_size() -> Size:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--deep-swapper-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'deep_swapper_model', 'iperov/elon_musk_224'), choices = deep_swapper_choices.deep_swapper_models)
-		group_processors.add_argument('--deep-swapper-morph', help = translator.get('help.morph', __package__), type = int, default = config.get_int_value('processors', 'deep_swapper_morph', '100'), choices = deep_swapper_choices.deep_swapper_morph_range, metavar = create_int_metavar(deep_swapper_choices.deep_swapper_morph_range))
-		facefusion.jobs.job_store.register_step_keys([ 'deep_swapper_model', 'deep_swapper_morph' ])
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--deep-swapper-model',
+					help = translator.get('help.model', __package__),
+					default = config.get_str_value('processors', 'deep_swapper_model', 'iperov/elon_musk_224'),
+					choices = deep_swapper_choices.deep_swapper_models
+				),
+				group_processors.add_argument(
+					'--deep-swapper-morph',
+					help = translator.get('help.morph', __package__),
+					type = int,
+					default = config.get_int_value('processors', 'deep_swapper_morph', '100'),
+					choices = deep_swapper_choices.deep_swapper_morph_range,
+					metavar = create_int_metavar(deep_swapper_choices.deep_swapper_morph_range)
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'deep_swapper' ]
+		)


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
@@ -286,10 +304,18 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('deep_swapper_morph', args.get('deep_swapper_morph'))


+def get_common_modules() -> List[ModuleType]:
+	return [ content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer ]
+
+
 def pre_check() -> bool:
 	model_hash_set = get_model_options().get('hashes')
 	model_source_set = get_model_options().get('sources')

+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
+
 	if model_hash_set and model_source_set:
 		return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 	return True
@@ -299,28 +325,25 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
 		logger.error(translator.get('choose_image_or_video_target') + translator.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
-		logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
-		return False
-	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
-		logger.error(translator.get('match_target_and_output_extension') + translator.get('exclamation_mark'), __name__)
-		return False
+	if state_manager.get_item('workflow') in [ 'audio-to-image:video', 'image-to-image', 'image-to-video' ]:
+		if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
+			logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
+			return False
 	return True


 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_video_frame.cache_clear()
+	read_static_video_chunk.cache_clear()
 	video_manager.clear_video_pool()
+
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
+
 	if state_manager.get_item('video_memory_strategy') == 'strict':
-		content_analyser.clear_inference_pool()
-		face_classifier.clear_inference_pool()
-		face_detector.clear_inference_pool()
-		face_landmarker.clear_inference_pool()
-		face_masker.clear_inference_pool()
-		face_recognizer.clear_inference_pool()
+		for common_module in get_common_modules():
+			common_module.clear_inference_pool()


 def swap_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
@@ -411,10 +434,13 @@ 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')
-	target_vision_frame = inputs.get('target_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
+	target_vision_frames = inputs.get('target_vision_frames')
 	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_vision_frame = get_middle(target_vision_frames)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frames)

 	if target_faces:
 		for target_face in target_faces:
@@ -1,4 +1,4 @@
-from typing import Any, TypeAlias, TypedDict
+from typing import Any, List, TypeAlias, TypedDict

 from numpy.typing import NDArray

@@ -7,7 +7,8 @@ from facefusion.types import Mask, VisionFrame
 DeepSwapperInputs = TypedDict('DeepSwapperInputs',
 {
 	'reference_vision_frame' : VisionFrame,
-	'target_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
+	'target_vision_frames' : List[VisionFrame],
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask
 })
@@ -1,28 +1,29 @@
 from argparse import ArgumentParser
 from functools import lru_cache
-from typing import Tuple
+from types import ModuleType
+from typing import List, Tuple

 import cv2
 import numpy

+import facefusion.capability_store
 import facefusion.jobs.job_manager
-import facefusion.jobs.job_store
 from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, translator, video_manager
-from facefusion.common_helper import create_int_metavar
+from facefusion.common_helper import create_int_metavar, get_middle
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.face_analyser import scale_face
+from facefusion.face_creator import scale_face
 from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
 from facefusion.face_masker import create_box_mask, create_occlusion_mask
 from facefusion.face_selector import select_faces
-from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
+from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path
 from facefusion.processors.live_portrait import create_rotation, limit_expression
 from facefusion.processors.modules.expression_restorer import choices as expression_restorer_choices
 from facefusion.processors.modules.expression_restorer.types import ExpressionRestorerInputs
-from facefusion.processors.types import LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw, ProcessorOutputs
+from facefusion.processors.types import ApplyStateItem, LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw, ProcessorOutputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore, thread_semaphore
-from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
-from facefusion.vision import read_static_image, read_static_video_frame
+from facefusion.types import Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import read_static_image, read_static_video_chunk, read_static_video_frame


@lru_cache()
@@ -99,10 +100,34 @@ def get_model_options() -> ModelOptions:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--expression-restorer-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'expression_restorer_model', 'live_portrait'), choices = expression_restorer_choices.expression_restorer_models)
-		group_processors.add_argument('--expression-restorer-factor', help = translator.get('help.factor', __package__), type = int, default = config.get_int_value('processors', 'expression_restorer_factor', '80'), choices = expression_restorer_choices.expression_restorer_factor_range, metavar = create_int_metavar(expression_restorer_choices.expression_restorer_factor_range))
-		group_processors.add_argument('--expression-restorer-areas', help = translator.get('help.areas', __package__).format(choices = ', '.join(expression_restorer_choices.expression_restorer_areas)), default = config.get_str_list('processors', 'expression_restorer_areas', ' '.join(expression_restorer_choices.expression_restorer_areas)), choices = expression_restorer_choices.expression_restorer_areas, nargs = '+', metavar = 'EXPRESSION_RESTORER_AREAS')
-		facefusion.jobs.job_store.register_step_keys([ 'expression_restorer_model', 'expression_restorer_factor', 'expression_restorer_areas' ])
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--expression-restorer-model',
+					help = translator.get('help.model', __package__),
+					default = config.get_str_value('processors', 'expression_restorer_model', 'live_portrait'),
+					choices = expression_restorer_choices.expression_restorer_models
+				),
+				group_processors.add_argument(
+					'--expression-restorer-factor',
+					help = translator.get('help.factor', __package__),
+					type = int,
+					default = config.get_int_value('processors', 'expression_restorer_factor', '80'),
+					choices = expression_restorer_choices.expression_restorer_factor_range,
+					metavar = create_int_metavar(expression_restorer_choices.expression_restorer_factor_range)
+				),
+				group_processors.add_argument(
+					'--expression-restorer-areas',
+					help = translator.get('help.areas', __package__).format(choices = ', '.join(expression_restorer_choices.expression_restorer_areas)),
+					default = config.get_str_list('processors', 'expression_restorer_areas', ' '.join(expression_restorer_choices.expression_restorer_areas)),
+					choices = expression_restorer_choices.expression_restorer_areas,
+					nargs = '+',
+					metavar = 'EXPRESSION_RESTORER_AREAS'
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'expression_restorer' ]
+		)


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
@@ -111,10 +136,18 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('expression_restorer_areas', args.get('expression_restorer_areas'))


+def get_common_modules() -> List[ModuleType]:
+	return [ content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer ]
+
+
 def pre_check() -> bool:
 	model_hash_set = get_model_options().get('hashes')
 	model_source_set = get_model_options().get('sources')

+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
+
 	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)


@@ -125,28 +158,25 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
 		logger.error(translator.get('choose_image_or_video_target') + translator.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
-		logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
-		return False
-	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
-		logger.error(translator.get('match_target_and_output_extension') + translator.get('exclamation_mark'), __name__)
-		return False
+	if state_manager.get_item('workflow') in [ 'audio-to-image:video', 'image-to-image', 'image-to-video' ]:
+		if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
+			logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
+			return False
 	return True


 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_video_frame.cache_clear()
+	read_static_video_chunk.cache_clear()
 	video_manager.clear_video_pool()
+
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
+
 	if state_manager.get_item('video_memory_strategy') == 'strict':
-		content_analyser.clear_inference_pool()
-		face_classifier.clear_inference_pool()
-		face_detector.clear_inference_pool()
-		face_landmarker.clear_inference_pool()
-		face_masker.clear_inference_pool()
-		face_recognizer.clear_inference_pool()
+		for common_module in get_common_modules():
+			common_module.clear_inference_pool()


 def restore_expression(target_face : Face, target_vision_frame : VisionFrame, temp_vision_frame : VisionFrame) -> VisionFrame:
@@ -257,10 +287,13 @@ def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:

 def process_frame(inputs : ExpressionRestorerInputs) -> ProcessorOutputs:
 	reference_vision_frame = inputs.get('reference_vision_frame')
-	target_vision_frame = inputs.get('target_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
+	target_vision_frames = inputs.get('target_vision_frames')
 	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_vision_frame = get_middle(target_vision_frames)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frames)

 	if target_faces:
 		for target_face in target_faces:
@@ -6,7 +6,7 @@ ExpressionRestorerInputs = TypedDict('ExpressionRestorerInputs',
 {
 	'reference_vision_frame' : VisionFrame,
 	'source_vision_frames' : List[VisionFrame],
-	'target_vision_frame' : VisionFrame,
+	'target_vision_frames' : List[VisionFrame],
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask
 })
@@ -1,22 +1,25 @@
 from argparse import ArgumentParser
+from types import ModuleType
+from typing import List

 import cv2
 import numpy

+import facefusion.capability_store
 import facefusion.jobs.job_manager
-import facefusion.jobs.job_store
 from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, logger, state_manager, translator, video_manager
-from facefusion.face_analyser import scale_face
+from facefusion.common_helper import get_middle
+from facefusion.face_creator import scale_face
 from facefusion.face_helper import warp_face_by_face_landmark_5
 from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask, create_region_mask
 from facefusion.face_selector import select_faces
-from facefusion.filesystem import in_directory, is_image, is_video, same_file_extension
+from facefusion.filesystem import in_directory, is_image, is_video
 from facefusion.processors.modules.face_debugger import choices as face_debugger_choices
 from facefusion.processors.modules.face_debugger.types import FaceDebuggerInputs
-from facefusion.processors.types import ProcessorOutputs
+from facefusion.processors.types import ApplyStateItem, ProcessorOutputs
 from facefusion.program_helper import find_argument_group
-from facefusion.types import ApplyStateItem, Args, Face, InferencePool, ProcessMode, VisionFrame
-from facefusion.vision import read_static_image, read_static_video_frame
+from facefusion.types import Args, Face, InferencePool, ProcessMode, VisionFrame
+from facefusion.vision import read_static_image, read_static_video_chunk, read_static_video_frame


 def get_inference_pool() -> InferencePool:
@@ -30,15 +33,34 @@ def clear_inference_pool() -> None:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-debugger-items', help = translator.get('help.items', __package__).format(choices = ', '.join(face_debugger_choices.face_debugger_items)), default = config.get_str_list('processors', 'face_debugger_items', 'face-landmark-5/68 face-mask'), choices = face_debugger_choices.face_debugger_items, nargs = '+', metavar = 'FACE_DEBUGGER_ITEMS')
-		facefusion.jobs.job_store.register_step_keys([ 'face_debugger_items' ])
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--face-debugger-items',
+					help = translator.get('help.items', __package__).format(choices = ', '.join(face_debugger_choices.face_debugger_items)),
+					default = config.get_str_list('processors', 'face_debugger_items', 'face-landmark-5/68 face-mask'),
+					choices = face_debugger_choices.face_debugger_items,
+					nargs = '+',
+					metavar = 'FACE_DEBUGGER_ITEMS'
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'face_debugger' ]
+		)


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('face_debugger_items', args.get('face_debugger_items'))


+def get_common_modules() -> List[ModuleType]:
+	return [ content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer ]
+
+
 def pre_check() -> bool:
+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
 	return True


@@ -46,26 +68,22 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
 		logger.error(translator.get('choose_image_or_video_target') + translator.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
-		logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
-		return False
-	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
-		logger.error(translator.get('match_target_and_output_extension') + translator.get('exclamation_mark'), __name__)
-		return False
+	if state_manager.get_item('workflow') in [ 'audio-to-image:video', 'image-to-image', 'image-to-video' ]:
+		if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
+			logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
+			return False
 	return True


 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_video_frame.cache_clear()
+	read_static_video_chunk.cache_clear()
 	video_manager.clear_video_pool()
+
 	if state_manager.get_item('video_memory_strategy') == 'strict':
-		content_analyser.clear_inference_pool()
-		face_classifier.clear_inference_pool()
-		face_detector.clear_inference_pool()
-		face_landmarker.clear_inference_pool()
-		face_masker.clear_inference_pool()
-		face_recognizer.clear_inference_pool()
+		for common_module in get_common_modules():
+			common_module.clear_inference_pool()


 def debug_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
@@ -94,21 +112,22 @@ def debug_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFra

 def draw_bounding_box(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
 	temp_vision_frame = numpy.ascontiguousarray(temp_vision_frame)
-	box_color = 0, 0, 255
-	border_color = 100, 100, 255
 	bounding_box = target_face.bounding_box.astype(numpy.int32)
 	x1, y1, x2, y2 = bounding_box
+	box_color = 0, 0, 255
+	border_scale = calculate_scale(temp_vision_frame)
+	border_color = 100, 100, 255

-	cv2.rectangle(temp_vision_frame, (x1, y1), (x2, y2), box_color, 2)
+	cv2.rectangle(temp_vision_frame, (x1, y1), (x2, y2), box_color, border_scale)

 	if target_face.angle == 0:
-		cv2.line(temp_vision_frame, (x1, y1), (x2, y1), border_color, 3)
+		cv2.line(temp_vision_frame, (x1, y1), (x2, y1), border_color, border_scale + 1)
 	if target_face.angle == 180:
-		cv2.line(temp_vision_frame, (x1, y2), (x2, y2), border_color, 3)
+		cv2.line(temp_vision_frame, (x1, y2), (x2, y2), border_color, border_scale + 1)
 	if target_face.angle == 90:
-		cv2.line(temp_vision_frame, (x2, y1), (x2, y2), border_color, 3)
+		cv2.line(temp_vision_frame, (x2, y1), (x2, y2), border_color, border_scale + 1)
 	if target_face.angle == 270:
-		cv2.line(temp_vision_frame, (x1, y1), (x1, y2), border_color, 3)
+		cv2.line(temp_vision_frame, (x1, y1), (x1, y2), border_color, border_scale + 1)

 	return temp_vision_frame

@@ -122,11 +141,15 @@ def draw_face_mask(target_face : Face, temp_vision_frame : VisionFrame) -> Visio
 	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, face_landmark_5_68, 'arcface_128', (512, 512))
 	inverse_matrix = cv2.invertAffineTransform(affine_matrix)
 	temp_size = temp_vision_frame.shape[:2][::-1]
+	mask_scale = calculate_scale(temp_vision_frame)
 	mask_color = 0, 255, 0

 	if numpy.array_equal(face_landmark_5, face_landmark_5_68):
 		mask_color = 255, 255, 0

+	if target_face.origin == 'refill':
+		mask_color = 0, 165, 255
+
 	if 'box' in state_manager.get_item('face_mask_types'):
 		box_mask = create_box_mask(crop_vision_frame, 0, state_manager.get_item('face_mask_padding'))
 		crop_masks.append(box_mask)
@@ -149,7 +172,7 @@ def draw_face_mask(target_face : Face, temp_vision_frame : VisionFrame) -> Visio
 	inverse_vision_frame = cv2.warpAffine(crop_mask, inverse_matrix, temp_size)
 	inverse_vision_frame = cv2.threshold(inverse_vision_frame, 100, 255, cv2.THRESH_BINARY)[1]
 	inverse_contours, _ = cv2.findContours(inverse_vision_frame, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
-	cv2.drawContours(temp_vision_frame, inverse_contours, -1, mask_color, 2)
+	cv2.drawContours(temp_vision_frame, inverse_contours, -1, mask_color, mask_scale)

 	return temp_vision_frame

@@ -157,13 +180,17 @@ def draw_face_mask(target_face : Face, temp_vision_frame : VisionFrame) -> Visio
 def draw_face_landmark_5(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
 	temp_vision_frame = numpy.ascontiguousarray(temp_vision_frame)
 	face_landmark_5 = target_face.landmark_set.get('5')
+	point_scale = calculate_scale(temp_vision_frame)
 	point_color = 0, 0, 255

+	if target_face.origin == 'refill':
+		point_color = 0, 165, 255
+
 	if numpy.any(face_landmark_5):
 		face_landmark_5 = face_landmark_5.astype(numpy.int32)

 		for point in face_landmark_5:
-			cv2.circle(temp_vision_frame, tuple(point), 3, point_color, -1)
+			cv2.circle(temp_vision_frame, tuple(point), point_scale, point_color, -1)

 	return temp_vision_frame

@@ -172,16 +199,20 @@ def draw_face_landmark_5_68(target_face : Face, temp_vision_frame : VisionFrame)
 	temp_vision_frame = numpy.ascontiguousarray(temp_vision_frame)
 	face_landmark_5 = target_face.landmark_set.get('5')
 	face_landmark_5_68 = target_face.landmark_set.get('5/68')
+	point_scale = calculate_scale(temp_vision_frame)
 	point_color = 0, 255, 0

 	if numpy.array_equal(face_landmark_5, face_landmark_5_68):
 		point_color = 255, 255, 0

+	if target_face.origin == 'refill':
+		point_color = 0, 165, 255
+
 	if numpy.any(face_landmark_5_68):
 		face_landmark_5_68 = face_landmark_5_68.astype(numpy.int32)

 		for point in face_landmark_5_68:
-			cv2.circle(temp_vision_frame, tuple(point), 3, point_color, -1)
+			cv2.circle(temp_vision_frame, tuple(point), point_scale, point_color, -1)

 	return temp_vision_frame

@@ -190,16 +221,20 @@ def draw_face_landmark_68(target_face : Face, temp_vision_frame : VisionFrame) -
 	temp_vision_frame = numpy.ascontiguousarray(temp_vision_frame)
 	face_landmark_68 = target_face.landmark_set.get('68')
 	face_landmark_68_5 = target_face.landmark_set.get('68/5')
+	point_scale = calculate_scale(temp_vision_frame)
 	point_color = 0, 255, 0

 	if numpy.array_equal(face_landmark_68, face_landmark_68_5):
 		point_color = 255, 255, 0

+	if target_face.origin == 'refill':
+		point_color = 0, 165, 255
+
 	if numpy.any(face_landmark_68):
 		face_landmark_68 = face_landmark_68.astype(numpy.int32)

 		for point in face_landmark_68:
-			cv2.circle(temp_vision_frame, tuple(point), 3, point_color, -1)
+			cv2.circle(temp_vision_frame, tuple(point), point_scale, point_color, -1)

 	return temp_vision_frame

@@ -207,23 +242,36 @@ def draw_face_landmark_68(target_face : Face, temp_vision_frame : VisionFrame) -
 def draw_face_landmark_68_5(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
 	temp_vision_frame = numpy.ascontiguousarray(temp_vision_frame)
 	face_landmark_68_5 = target_face.landmark_set.get('68/5')
+	point_scale = calculate_scale(temp_vision_frame)
 	point_color = 255, 255, 0

+	if target_face.origin == 'refill':
+		point_color = 0, 165, 255
+
 	if numpy.any(face_landmark_68_5):
 		face_landmark_68_5 = face_landmark_68_5.astype(numpy.int32)

 		for point in face_landmark_68_5:
-			cv2.circle(temp_vision_frame, tuple(point), 3, point_color, -1)
+			cv2.circle(temp_vision_frame, tuple(point), point_scale, point_color, -1)

 	return temp_vision_frame


+def calculate_scale(temp_vision_frame : VisionFrame) -> int:
+	frame_height, _ = temp_vision_frame.shape[:2]
+	frame_scale = round(frame_height / 270)
+	return max(1, min(10, frame_scale))
+
+
 def process_frame(inputs : FaceDebuggerInputs) -> ProcessorOutputs:
 	reference_vision_frame = inputs.get('reference_vision_frame')
-	target_vision_frame = inputs.get('target_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
+	target_vision_frames = inputs.get('target_vision_frames')
 	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_vision_frame = get_middle(target_vision_frames)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frames)

 	if target_faces:
 		for target_face in target_faces:
@@ -231,5 +279,3 @@ def process_frame(inputs : FaceDebuggerInputs) -> ProcessorOutputs:
 			temp_vision_frame = debug_face(target_face, temp_vision_frame)

 	return temp_vision_frame, temp_vision_mask
-
-
@@ -1,11 +1,12 @@
-from typing import Literal, TypedDict
+from typing import List, Literal, TypedDict

 from facefusion.types import Mask, VisionFrame

 FaceDebuggerInputs = TypedDict('FaceDebuggerInputs',
 {
 	'reference_vision_frame' : VisionFrame,
-	'target_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
+	'target_vision_frames' : List[VisionFrame],
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask
 })
@@ -1,28 +1,29 @@
 from argparse import ArgumentParser
 from functools import lru_cache
-from typing import Tuple
+from types import ModuleType
+from typing import List, Tuple

 import cv2
 import numpy

+import facefusion.capability_store
 import facefusion.jobs.job_manager
-import facefusion.jobs.job_store
 from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, translator, video_manager
-from facefusion.common_helper import create_float_metavar
+from facefusion.common_helper import create_float_metavar, get_middle
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.face_analyser import scale_face
+from facefusion.face_creator import scale_face
 from facefusion.face_helper import paste_back, scale_face_landmark_5, warp_face_by_face_landmark_5
 from facefusion.face_masker import create_box_mask
 from facefusion.face_selector import select_faces
-from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
+from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path
 from facefusion.processors.live_portrait import create_rotation, limit_angle, limit_expression
 from facefusion.processors.modules.face_editor import choices as face_editor_choices
 from facefusion.processors.modules.face_editor.types import FaceEditorInputs
-from facefusion.processors.types import LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitRotation, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw, ProcessorOutputs
+from facefusion.processors.types import ApplyStateItem, LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitRotation, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw, ProcessorOutputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore, thread_semaphore
-from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, FaceLandmark68, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
-from facefusion.vision import read_static_image, read_static_video_frame
+from facefusion.types import Args, DownloadScope, Face, FaceLandmark68, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import read_static_image, read_static_video_chunk, read_static_video_frame


@lru_cache()
@@ -129,22 +130,130 @@ def get_model_options() -> ModelOptions:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-editor-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'face_editor_model', 'live_portrait'), choices = face_editor_choices.face_editor_models)
-		group_processors.add_argument('--face-editor-eyebrow-direction', help = translator.get('help.eyebrow_direction', __package__), type = float, default = config.get_float_value('processors', 'face_editor_eyebrow_direction', '0'), choices = face_editor_choices.face_editor_eyebrow_direction_range, metavar = create_float_metavar(face_editor_choices.face_editor_eyebrow_direction_range))
-		group_processors.add_argument('--face-editor-eye-gaze-horizontal', help = translator.get('help.eye_gaze_horizontal', __package__), type = float, default = config.get_float_value('processors', 'face_editor_eye_gaze_horizontal', '0'), choices = face_editor_choices.face_editor_eye_gaze_horizontal_range, metavar = create_float_metavar(face_editor_choices.face_editor_eye_gaze_horizontal_range))
-		group_processors.add_argument('--face-editor-eye-gaze-vertical', help = translator.get('help.eye_gaze_vertical', __package__), type = float, default = config.get_float_value('processors', 'face_editor_eye_gaze_vertical', '0'), choices = face_editor_choices.face_editor_eye_gaze_vertical_range, metavar = create_float_metavar(face_editor_choices.face_editor_eye_gaze_vertical_range))
-		group_processors.add_argument('--face-editor-eye-open-ratio', help = translator.get('help.eye_open_ratio', __package__), type = float, default = config.get_float_value('processors', 'face_editor_eye_open_ratio', '0'), choices = face_editor_choices.face_editor_eye_open_ratio_range, metavar = create_float_metavar(face_editor_choices.face_editor_eye_open_ratio_range))
-		group_processors.add_argument('--face-editor-lip-open-ratio', help = translator.get('help.lip_open_ratio', __package__), type = float, default = config.get_float_value('processors', 'face_editor_lip_open_ratio', '0'), choices = face_editor_choices.face_editor_lip_open_ratio_range, metavar = create_float_metavar(face_editor_choices.face_editor_lip_open_ratio_range))
-		group_processors.add_argument('--face-editor-mouth-grim', help = translator.get('help.mouth_grim', __package__), type = float, default = config.get_float_value('processors', 'face_editor_mouth_grim', '0'), choices = face_editor_choices.face_editor_mouth_grim_range, metavar = create_float_metavar(face_editor_choices.face_editor_mouth_grim_range))
-		group_processors.add_argument('--face-editor-mouth-pout', help = translator.get('help.mouth_pout', __package__), type = float, default = config.get_float_value('processors', 'face_editor_mouth_pout', '0'), choices = face_editor_choices.face_editor_mouth_pout_range, metavar = create_float_metavar(face_editor_choices.face_editor_mouth_pout_range))
-		group_processors.add_argument('--face-editor-mouth-purse', help = translator.get('help.mouth_purse', __package__), type = float, default = config.get_float_value('processors', 'face_editor_mouth_purse', '0'), choices = face_editor_choices.face_editor_mouth_purse_range, metavar = create_float_metavar(face_editor_choices.face_editor_mouth_purse_range))
-		group_processors.add_argument('--face-editor-mouth-smile', help = translator.get('help.mouth_smile', __package__), type = float, default = config.get_float_value('processors', 'face_editor_mouth_smile', '0'), choices = face_editor_choices.face_editor_mouth_smile_range, metavar = create_float_metavar(face_editor_choices.face_editor_mouth_smile_range))
-		group_processors.add_argument('--face-editor-mouth-position-horizontal', help = translator.get('help.mouth_position_horizontal', __package__), type = float, default = config.get_float_value('processors', 'face_editor_mouth_position_horizontal', '0'), choices = face_editor_choices.face_editor_mouth_position_horizontal_range, metavar = create_float_metavar(face_editor_choices.face_editor_mouth_position_horizontal_range))
-		group_processors.add_argument('--face-editor-mouth-position-vertical', help = translator.get('help.mouth_position_vertical', __package__), type = float, default = config.get_float_value('processors', 'face_editor_mouth_position_vertical', '0'), choices = face_editor_choices.face_editor_mouth_position_vertical_range, metavar = create_float_metavar(face_editor_choices.face_editor_mouth_position_vertical_range))
-		group_processors.add_argument('--face-editor-head-pitch', help = translator.get('help.head_pitch', __package__), type = float, default = config.get_float_value('processors', 'face_editor_head_pitch', '0'), choices = face_editor_choices.face_editor_head_pitch_range, metavar = create_float_metavar(face_editor_choices.face_editor_head_pitch_range))
-		group_processors.add_argument('--face-editor-head-yaw', help = translator.get('help.head_yaw', __package__), type = float, default = config.get_float_value('processors', 'face_editor_head_yaw', '0'), choices = face_editor_choices.face_editor_head_yaw_range, metavar = create_float_metavar(face_editor_choices.face_editor_head_yaw_range))
-		group_processors.add_argument('--face-editor-head-roll', help = translator.get('help.head_roll', __package__), type = float, default = config.get_float_value('processors', 'face_editor_head_roll', '0'), choices = face_editor_choices.face_editor_head_roll_range, metavar = create_float_metavar(face_editor_choices.face_editor_head_roll_range))
-		facefusion.jobs.job_store.register_step_keys([ 'face_editor_model', 'face_editor_eyebrow_direction', 'face_editor_eye_gaze_horizontal', 'face_editor_eye_gaze_vertical', 'face_editor_eye_open_ratio', 'face_editor_lip_open_ratio', 'face_editor_mouth_grim', 'face_editor_mouth_pout', 'face_editor_mouth_purse', 'face_editor_mouth_smile', 'face_editor_mouth_position_horizontal', 'face_editor_mouth_position_vertical', 'face_editor_head_pitch', 'face_editor_head_yaw', 'face_editor_head_roll' ])
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--face-editor-model',
+					help = translator.get('help.model', __package__),
+					default = config.get_str_value('processors', 'face_editor_model', 'live_portrait'),
+					choices = face_editor_choices.face_editor_models
+				),
+				group_processors.add_argument(
+					'--face-editor-eyebrow-direction',
+					help = translator.get('help.eyebrow_direction', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_eyebrow_direction', '0'),
+					choices = face_editor_choices.face_editor_eyebrow_direction_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_eyebrow_direction_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-eye-gaze-horizontal',
+					help = translator.get('help.eye_gaze_horizontal', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_eye_gaze_horizontal', '0'),
+					choices = face_editor_choices.face_editor_eye_gaze_horizontal_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_eye_gaze_horizontal_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-eye-gaze-vertical',
+					help = translator.get('help.eye_gaze_vertical', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_eye_gaze_vertical', '0'),
+					choices = face_editor_choices.face_editor_eye_gaze_vertical_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_eye_gaze_vertical_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-eye-open-ratio',
+					help = translator.get('help.eye_open_ratio', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_eye_open_ratio', '0'),
+					choices = face_editor_choices.face_editor_eye_open_ratio_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_eye_open_ratio_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-lip-open-ratio',
+					help = translator.get('help.lip_open_ratio', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_lip_open_ratio', '0'),
+					choices = face_editor_choices.face_editor_lip_open_ratio_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_lip_open_ratio_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-mouth-grim',
+					help = translator.get('help.mouth_grim', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_mouth_grim', '0'),
+					choices = face_editor_choices.face_editor_mouth_grim_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_mouth_grim_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-mouth-pout',
+					help = translator.get('help.mouth_pout', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_mouth_pout', '0'),
+					choices = face_editor_choices.face_editor_mouth_pout_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_mouth_pout_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-mouth-purse',
+					help = translator.get('help.mouth_purse', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_mouth_purse', '0'),
+					choices = face_editor_choices.face_editor_mouth_purse_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_mouth_purse_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-mouth-smile',
+					help = translator.get('help.mouth_smile', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_mouth_smile', '0'),
+					choices = face_editor_choices.face_editor_mouth_smile_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_mouth_smile_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-mouth-position-horizontal',
+					help = translator.get('help.mouth_position_horizontal', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_mouth_position_horizontal', '0'),
+					choices = face_editor_choices.face_editor_mouth_position_horizontal_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_mouth_position_horizontal_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-mouth-position-vertical',
+					help = translator.get('help.mouth_position_vertical', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_mouth_position_vertical', '0'),
+					choices = face_editor_choices.face_editor_mouth_position_vertical_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_mouth_position_vertical_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-head-pitch',
+					help = translator.get('help.head_pitch', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_head_pitch', '0'),
+					choices = face_editor_choices.face_editor_head_pitch_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_head_pitch_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-head-yaw',
+					help = translator.get('help.head_yaw', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_head_yaw', '0'),
+					choices = face_editor_choices.face_editor_head_yaw_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_head_yaw_range)
+				),
+				group_processors.add_argument(
+					'--face-editor-head-roll',
+					help = translator.get('help.head_roll', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_editor_head_roll', '0'),
+					choices = face_editor_choices.face_editor_head_roll_range,
+					metavar = create_float_metavar(face_editor_choices.face_editor_head_roll_range)
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'face_editor' ]
+		)


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
@@ -165,10 +274,18 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('face_editor_head_roll', args.get('face_editor_head_roll'))


+def get_common_modules() -> List[ModuleType]:
+	return [ content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer ]
+
+
 def pre_check() -> bool:
 	model_hash_set = get_model_options().get('hashes')
 	model_source_set = get_model_options().get('sources')

+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
+
 	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)


@@ -176,28 +293,25 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
 		logger.error(translator.get('choose_image_or_video_target') + translator.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
-		logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
-		return False
-	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
-		logger.error(translator.get('match_target_and_output_extension') + translator.get('exclamation_mark'), __name__)
-		return False
+	if state_manager.get_item('workflow') in [ 'audio-to-image:video', 'image-to-image', 'image-to-video' ]:
+		if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
+			logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
+			return False
 	return True


 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_video_frame.cache_clear()
+	read_static_video_chunk.cache_clear()
 	video_manager.clear_video_pool()
+
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
+
 	if state_manager.get_item('video_memory_strategy') == 'strict':
-		content_analyser.clear_inference_pool()
-		face_classifier.clear_inference_pool()
-		face_detector.clear_inference_pool()
-		face_landmarker.clear_inference_pool()
-		face_masker.clear_inference_pool()
-		face_recognizer.clear_inference_pool()
+		for common_module in get_common_modules():
+			common_module.clear_inference_pool()


 def edit_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
@@ -486,10 +600,13 @@ def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:

 def process_frame(inputs : FaceEditorInputs) -> ProcessorOutputs:
 	reference_vision_frame = inputs.get('reference_vision_frame')
-	target_vision_frame = inputs.get('target_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
+	target_vision_frames = inputs.get('target_vision_frames')
 	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_vision_frame = get_middle(target_vision_frames)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frames)

 	if target_faces:
 		for target_face in target_faces:
@@ -1,11 +1,12 @@
-from typing import Literal, TypedDict
+from typing import List, Literal, TypedDict

 from facefusion.types import Mask, VisionFrame

 FaceEditorInputs = TypedDict('FaceEditorInputs',
 {
 	'reference_vision_frame' : VisionFrame,
-	'target_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
+	'target_vision_frames' : List[VisionFrame],
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask
 })
@@ -1,25 +1,27 @@
 from argparse import ArgumentParser
 from functools import lru_cache
+from types import ModuleType
+from typing import List

 import numpy

+import facefusion.capability_store
 import facefusion.jobs.job_manager
-import facefusion.jobs.job_store
 from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, translator, video_manager
-from facefusion.common_helper import create_float_metavar, create_int_metavar
+from facefusion.common_helper import create_float_metavar, create_int_metavar, get_middle
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.face_analyser import scale_face
+from facefusion.face_creator import scale_face
 from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
 from facefusion.face_masker import create_box_mask, create_occlusion_mask
 from facefusion.face_selector import select_faces
-from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
+from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path
 from facefusion.processors.modules.face_enhancer import choices as face_enhancer_choices
 from facefusion.processors.modules.face_enhancer.types import FaceEnhancerInputs, FaceEnhancerWeight
-from facefusion.processors.types import ProcessorOutputs
+from facefusion.processors.types import ApplyStateItem, ProcessorOutputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import thread_semaphore
-from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
-from facefusion.vision import blend_frame, read_static_image, read_static_video_frame
+from facefusion.types import Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import blend_frame, read_static_image, read_static_video_chunk, read_static_video_frame


@lru_cache()
@@ -292,10 +294,34 @@ def get_model_options() -> ModelOptions:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-enhancer-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'face_enhancer_model', 'gfpgan_1.4'), choices = face_enhancer_choices.face_enhancer_models)
-		group_processors.add_argument('--face-enhancer-blend', help = translator.get('help.blend', __package__), type = int, default = config.get_int_value('processors', 'face_enhancer_blend', '80'), choices = face_enhancer_choices.face_enhancer_blend_range, metavar = create_int_metavar(face_enhancer_choices.face_enhancer_blend_range))
-		group_processors.add_argument('--face-enhancer-weight', help = translator.get('help.weight', __package__), type = float, default = config.get_float_value('processors', 'face_enhancer_weight', '0.5'), choices = face_enhancer_choices.face_enhancer_weight_range, metavar = create_float_metavar(face_enhancer_choices.face_enhancer_weight_range))
-		facefusion.jobs.job_store.register_step_keys([ 'face_enhancer_model', 'face_enhancer_blend', 'face_enhancer_weight' ])
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--face-enhancer-model',
+					help = translator.get('help.model', __package__),
+					default = config.get_str_value('processors', 'face_enhancer_model', 'gfpgan_1.4'),
+					choices = face_enhancer_choices.face_enhancer_models
+				),
+				group_processors.add_argument(
+					'--face-enhancer-blend',
+					help = translator.get('help.blend', __package__),
+					type = int,
+					default = config.get_int_value('processors', 'face_enhancer_blend', '80'),
+					choices = face_enhancer_choices.face_enhancer_blend_range,
+					metavar = create_int_metavar(face_enhancer_choices.face_enhancer_blend_range)
+				),
+				group_processors.add_argument(
+					'--face-enhancer-weight',
+					help = translator.get('help.weight', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_enhancer_weight', '0.5'),
+					choices = face_enhancer_choices.face_enhancer_weight_range,
+					metavar = create_float_metavar(face_enhancer_choices.face_enhancer_weight_range)
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'face_enhancer' ]
+		)


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
@@ -304,10 +330,18 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('face_enhancer_weight', args.get('face_enhancer_weight'))


+def get_common_modules() -> List[ModuleType]:
+	return [ content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer ]
+
+
 def pre_check() -> bool:
 	model_hash_set = get_model_options().get('hashes')
 	model_source_set = get_model_options().get('sources')

+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
+
 	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)


@@ -315,28 +349,25 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
 		logger.error(translator.get('choose_image_or_video_target') + translator.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
-		logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
-		return False
-	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
-		logger.error(translator.get('match_target_and_output_extension') + translator.get('exclamation_mark'), __name__)
-		return False
+	if state_manager.get_item('workflow') in [ 'audio-to-image:video', 'image-to-image', 'image-to-video' ]:
+		if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
+			logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
+			return False
 	return True


 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_video_frame.cache_clear()
+	read_static_video_chunk.cache_clear()
 	video_manager.clear_video_pool()
+
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
+
 	if state_manager.get_item('video_memory_strategy') == 'strict':
-		content_analyser.clear_inference_pool()
-		face_classifier.clear_inference_pool()
-		face_detector.clear_inference_pool()
-		face_landmarker.clear_inference_pool()
-		face_masker.clear_inference_pool()
-		face_recognizer.clear_inference_pool()
+		for common_module in get_common_modules():
+			common_module.clear_inference_pool()


 def enhance_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
@@ -413,10 +444,13 @@ 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')
-	target_vision_frame = inputs.get('target_vision_frame')
+	source_vision_frames = inputs.get('source_vision_frames')
+	target_vision_frames = inputs.get('target_vision_frames')
 	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_vision_frame = get_middle(target_vision_frames)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frames)

 	if target_faces:
 		for target_face in target_faces:
@@ -1,4 +1,4 @@
-from typing import Any, Literal, TypeAlias, TypedDict
+from typing import Any, List, Literal, TypeAlias, TypedDict

 from numpy.typing import NDArray

@@ -7,7 +7,8 @@ from facefusion.types import Mask, VisionFrame
 FaceEnhancerInputs = TypedDict('FaceEnhancerInputs',
 {
 	'reference_vision_frame' : VisionFrame,
-	'target_vision_frame' : VisionFrame,
+	'source_vision_frames' : List[VisionFrame],
+	'target_vision_frames' : List[VisionFrame],
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask
 })
@@ -1,31 +1,32 @@
 from argparse import ArgumentParser
 from functools import lru_cache
+from types import ModuleType
 from typing import List, Optional, Tuple

 import cv2
 import numpy

+import facefusion.capability_store
 import facefusion.choices
 import facefusion.jobs.job_manager
-import facefusion.jobs.job_store
 from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, translator, video_manager
-from facefusion.common_helper import get_first, is_macos
+from facefusion.common_helper import get_first, get_middle, is_macos
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.execution import has_execution_provider
-from facefusion.face_analyser import get_average_face, get_many_faces, get_one_face, scale_face
+from facefusion.face_creator import average_face_identity, get_one_face, get_static_faces, scale_face
 from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
 from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask, create_region_mask
 from facefusion.face_selector import select_faces, sort_faces_by_order
-from facefusion.filesystem import filter_image_paths, has_image, in_directory, is_image, is_video, resolve_relative_path, same_file_extension
+from facefusion.filesystem import filter_image_paths, has_image, in_directory, is_image, is_video, resolve_relative_path
 from facefusion.model_helper import get_static_model_initializer
 from facefusion.processors.modules.face_swapper import choices as face_swapper_choices
 from facefusion.processors.modules.face_swapper.types import FaceSwapperInputs
 from facefusion.processors.pixel_boost import explode_pixel_boost, implode_pixel_boost
-from facefusion.processors.types import ProcessorOutputs
+from facefusion.processors.types import ApplyStateItem, ProcessorOutputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.types import ApplyStateItem, Args, DownloadScope, Embedding, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
-from facefusion.vision import read_static_image, read_static_images, read_static_video_frame, unpack_resolution
+from facefusion.types import Args, DownloadScope, Embedding, Face, InferencePool, InferenceProvider, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import read_static_image, read_static_images, read_static_video_chunk, read_static_video_frame, unpack_resolution


@lru_cache()
@@ -246,6 +247,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/hyperswap_1a_256.onnx')
 				}
 			},
+			'precision': 'fp16',
 			'type': 'hyperswap',
 			'template': 'arcface_128',
 			'size': (256, 256),
@@ -276,6 +278,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 						'path': resolve_relative_path('../.assets/models/hyperswap_1b_256.onnx')
 					}
 				},
+			'precision': 'fp16',
 			'type': 'hyperswap',
 			'template': 'arcface_128',
 			'size': (256, 256),
@@ -306,6 +309,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/hyperswap_1c_256.onnx')
 				}
 			},
+			'precision': 'fp16',
 			'type': 'hyperswap',
 			'template': 'arcface_128',
 			'size': (256, 256),
@@ -366,6 +370,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/inswapper_128_fp16.onnx')
 				}
 			},
+			'precision': 'fp16',
 			'type': 'inswapper',
 			'template': 'arcface_128',
 			'size': (128, 128),
@@ -486,39 +491,76 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:


 def get_inference_pool() -> InferencePool:
-	model_names = [ get_model_name() ]
+	model_names = [ state_manager.get_item('face_swapper_model') ]
 	model_source_set = get_model_options().get('sources')

 	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)


 def clear_inference_pool() -> None:
-	model_names = [ get_model_name() ]
+	model_names = [ state_manager.get_item('face_swapper_model') ]
 	inference_manager.clear_inference_pool(__name__, model_names)


+def resolve_inference_providers() -> List[InferenceProvider]:
+	model_precision = get_model_options().get('precision')
+	model_type = get_model_options().get('type')
+
+	if is_macos() and has_execution_provider('coreml'):
+		if model_type in [ 'ghost', 'uniface' ] or model_precision == 'fp16':
+			return\
+			[
+				(facefusion.choices.execution_provider_set.get('coreml'),
+				{
+					'ModelFormat': 'MLProgram',
+					'SpecializationStrategy': 'FastPrediction'
+				})
+			]
+
+	return []
+
+
 def get_model_options() -> ModelOptions:
-	model_name = get_model_name()
-	return create_static_model_set('full').get(model_name)
-
-
-def get_model_name() -> str:
 	model_name = state_manager.get_item('face_swapper_model')
-
-	if is_macos() and has_execution_provider('coreml') and model_name == 'inswapper_128_fp16':
-		return 'inswapper_128'
-	return model_name
+	return create_static_model_set('full').get(model_name)


 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-swapper-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'face_swapper_model', 'hyperswap_1a_256'), choices = face_swapper_choices.face_swapper_models)
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--face-swapper-model',
+					help = translator.get('help.model', __package__),
+					default = config.get_str_value('processors', 'face_swapper_model', 'hyperswap_1a_256'),
+					choices = face_swapper_choices.face_swapper_models
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'face_swapper' ]
+		)
 		known_args, _ = program.parse_known_args()
 		face_swapper_pixel_boost_choices = face_swapper_choices.face_swapper_set.get(known_args.face_swapper_model)
-		group_processors.add_argument('--face-swapper-pixel-boost', help = translator.get('help.pixel_boost', __package__), default = config.get_str_value('processors', 'face_swapper_pixel_boost', get_first(face_swapper_pixel_boost_choices)), choices = face_swapper_pixel_boost_choices)
-		group_processors.add_argument('--face-swapper-weight', help = translator.get('help.weight', __package__), type = float, default = config.get_float_value('processors', 'face_swapper_weight', '0.5'), choices = face_swapper_choices.face_swapper_weight_range)
-		facefusion.jobs.job_store.register_step_keys([ 'face_swapper_model', 'face_swapper_pixel_boost', 'face_swapper_weight' ])
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--face-swapper-pixel-boost',
+					help = translator.get('help.pixel_boost', __package__),
+					default = config.get_str_value('processors', 'face_swapper_pixel_boost', get_first(face_swapper_pixel_boost_choices)),
+					choices = face_swapper_pixel_boost_choices
+				),
+				group_processors.add_argument(
+					'--face-swapper-weight',
+					help = translator.get('help.weight', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'face_swapper_weight', '0.5'),
+					choices = face_swapper_choices.face_swapper_weight_range
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'face_swapper' ]
+		)


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
@@ -527,10 +569,18 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('face_swapper_weight', args.get('face_swapper_weight'))


+def get_common_modules() -> List[ModuleType]:
+	return [ content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer ]
+
+
 def pre_check() -> bool:
 	model_hash_set = get_model_options().get('hashes')
 	model_source_set = get_model_options().get('sources')

+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
+
 	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)


@@ -541,7 +591,7 @@ def pre_process(mode : ProcessMode) -> bool:

 	source_image_paths = filter_image_paths(state_manager.get_item('source_paths'))
 	source_vision_frames = read_static_images(source_image_paths)
-	source_faces = get_many_faces(source_vision_frames)
+	source_faces = get_static_faces(source_vision_frames)

 	if not get_one_face(source_faces):
 		logger.error(translator.get('no_source_face_detected') + translator.get('exclamation_mark'), __name__)
@@ -551,13 +601,10 @@ def pre_process(mode : ProcessMode) -> bool:
 		logger.error(translator.get('choose_image_or_video_target') + translator.get('exclamation_mark'), __name__)
 		return False

-	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
-		logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
-		return False
-
-	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
-		logger.error(translator.get('match_target_and_output_extension') + translator.get('exclamation_mark'), __name__)
-		return False
+	if state_manager.get_item('workflow') in [ 'audio-to-image:video', 'image-to-image', 'image-to-video' ]:
+		if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
+			logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
+			return False

 	return True

@@ -565,20 +612,19 @@ def pre_process(mode : ProcessMode) -> bool:
 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_video_frame.cache_clear()
+	read_static_video_chunk.cache_clear()
 	video_manager.clear_video_pool()
+
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		get_static_model_initializer.cache_clear()
 		clear_inference_pool()
+
 	if state_manager.get_item('video_memory_strategy') == 'strict':
-		content_analyser.clear_inference_pool()
-		face_classifier.clear_inference_pool()
-		face_detector.clear_inference_pool()
-		face_landmarker.clear_inference_pool()
-		face_masker.clear_inference_pool()
-		face_recognizer.clear_inference_pool()
+		for common_module in get_common_modules():
+			common_module.clear_inference_pool()


-def swap_face(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+def swap_face(source_face : Face, target_face : Face, source_vision_frame : VisionFrame, temp_vision_frame : VisionFrame) -> VisionFrame:
 	model_template = get_model_options().get('template')
 	model_size = get_model_options().get('size')
 	pixel_boost_size = unpack_resolution(state_manager.get_item('face_swapper_pixel_boost'))
@@ -598,7 +644,7 @@ def swap_face(source_face : Face, target_face : Face, temp_vision_frame : Vision
 	pixel_boost_vision_frames = implode_pixel_boost(crop_vision_frame, pixel_boost_total, model_size)
 	for pixel_boost_vision_frame in pixel_boost_vision_frames:
 		pixel_boost_vision_frame = prepare_crop_frame(pixel_boost_vision_frame)
-		pixel_boost_vision_frame = forward_swap_face(source_face, target_face, pixel_boost_vision_frame)
+		pixel_boost_vision_frame = forward_swap_face(source_face, target_face, source_vision_frame, pixel_boost_vision_frame)
 		pixel_boost_vision_frame = normalize_crop_frame(pixel_boost_vision_frame)
 		temp_vision_frames.append(pixel_boost_vision_frame)
 	crop_vision_frame = explode_pixel_boost(temp_vision_frames, pixel_boost_total, model_size, pixel_boost_size)
@@ -617,18 +663,15 @@ def swap_face(source_face : Face, target_face : Face, temp_vision_frame : Vision
 	return paste_vision_frame


-def forward_swap_face(source_face : Face, target_face : Face, crop_vision_frame : VisionFrame) -> VisionFrame:
+def forward_swap_face(source_face : Face, target_face : Face, source_vision_frame : VisionFrame, crop_vision_frame : VisionFrame) -> VisionFrame:
 	face_swapper = get_inference_pool().get('face_swapper')
 	model_type = get_model_options().get('type')
 	face_swapper_inputs = {}

-	if is_macos() and has_execution_provider('coreml') and model_type in [ 'ghost', 'uniface' ]:
-		face_swapper.set_providers([ facefusion.choices.execution_provider_set.get('cpu') ])
-
 	for face_swapper_input in face_swapper.get_inputs():
 		if face_swapper_input.name == 'source':
 			if model_type in [ 'blendswap', 'uniface' ]:
-				face_swapper_inputs[face_swapper_input.name] = prepare_source_frame(source_face)
+				face_swapper_inputs[face_swapper_input.name] = prepare_source_frame(source_face, source_vision_frame)
 			else:
 				source_embedding = prepare_source_embedding(source_face)
 				source_embedding = balance_source_embedding(source_embedding, target_face.embedding)
@@ -654,9 +697,8 @@ def forward_convert_embedding(face_embedding : Embedding) -> Embedding:
 	return face_embedding


-def prepare_source_frame(source_face : Face) -> VisionFrame:
+def prepare_source_frame(source_face : Face, source_vision_frame : VisionFrame) -> VisionFrame:
 	model_type = get_model_options().get('type')
-	source_vision_frame = read_static_image(get_first(state_manager.get_item('source_paths')))

 	if model_type == 'blendswap':
 		source_vision_frame, _ = warp_face_by_face_landmark_5(source_vision_frame, source_face.landmark_set.get('5/68'), 'arcface_112_v2', (112, 112))
@@ -748,27 +790,31 @@ def extract_source_face(source_vision_frames : List[VisionFrame]) -> Optional[Fa

 	if source_vision_frames:
 		for source_vision_frame in source_vision_frames:
-			temp_faces = get_many_faces([source_vision_frame])
+			temp_faces = get_static_faces([ source_vision_frame ])
 			temp_faces = sort_faces_by_order(temp_faces, 'large-small')

 			if temp_faces:
 				source_faces.append(get_first(temp_faces))

-	return get_average_face(source_faces)
+	return average_face_identity(source_faces)


 def process_frame(inputs : FaceSwapperInputs) -> 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')
+	target_vision_frames = inputs.get('target_vision_frames')
 	temp_vision_frame = inputs.get('temp_vision_frame')
 	temp_vision_mask = inputs.get('temp_vision_mask')
+
+	target_vision_frame = get_middle(target_vision_frames)
 	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_frames)

 	if source_face and target_faces:
+		source_vision_frame = get_first(source_vision_frames)
+
 		for target_face in target_faces:
 			target_face = scale_face(target_face, target_vision_frame, temp_vision_frame)
-			temp_vision_frame = swap_face(source_face, target_face, temp_vision_frame)
+			temp_vision_frame = swap_face(source_face, target_face, source_vision_frame, temp_vision_frame)

 	return temp_vision_frame, temp_vision_mask
@@ -6,7 +6,7 @@ FaceSwapperInputs = TypedDict('FaceSwapperInputs',
 {
 	'reference_vision_frame' : VisionFrame,
 	'source_vision_frames' : List[VisionFrame],
-	'target_vision_frame' : VisionFrame,
+	'target_vision_frames' : List[VisionFrame],
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask
 })
@@ -1,24 +1,26 @@
 from argparse import ArgumentParser
 from functools import lru_cache
+from types import ModuleType
 from typing import List

 import cv2
 import numpy

+import facefusion.capability_store
+import facefusion.choices
 import facefusion.jobs.job_manager
-import facefusion.jobs.job_store
 from facefusion import config, content_analyser, inference_manager, logger, state_manager, translator, video_manager
 from facefusion.common_helper import create_int_metavar, is_macos
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.execution import has_execution_provider
-from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
+from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path
 from facefusion.processors.modules.frame_colorizer import choices as frame_colorizer_choices
 from facefusion.processors.modules.frame_colorizer.types import FrameColorizerInputs
-from facefusion.processors.types import ProcessorOutputs
+from facefusion.processors.types import ApplyStateItem, ProcessorOutputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import thread_semaphore
-from facefusion.types import ApplyStateItem, Args, DownloadScope, ExecutionProvider, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
-from facefusion.vision import blend_frame, read_static_image, read_static_video_frame, unpack_resolution
+from facefusion.types import Args, DownloadScope, InferencePool, InferenceProvider, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import blend_frame, read_static_image, read_static_video_chunk, read_static_video_frame, unpack_resolution


@lru_cache()
@@ -170,10 +172,11 @@ def clear_inference_pool() -> None:
 	inference_manager.clear_inference_pool(__name__, model_names)


-def resolve_execution_providers() -> List[ExecutionProvider]:
+def resolve_inference_providers() -> List[InferenceProvider]:
 	if is_macos() and has_execution_provider('coreml'):
-		return [ 'cpu' ]
-	return state_manager.get_item('execution_providers')
+		return [ facefusion.choices.execution_provider_set.get('cpu') ]
+
+	return []


 def get_model_options() -> ModelOptions:
@@ -184,10 +187,33 @@ def get_model_options() -> ModelOptions:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--frame-colorizer-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'frame_colorizer_model', 'ddcolor'), choices = frame_colorizer_choices.frame_colorizer_models)
-		group_processors.add_argument('--frame-colorizer-size', help = translator.get('help.size', __package__), type = str, default = config.get_str_value('processors', 'frame_colorizer_size', '256x256'), choices = frame_colorizer_choices.frame_colorizer_sizes)
-		group_processors.add_argument('--frame-colorizer-blend', help = translator.get('help.blend', __package__), type = int, default = config.get_int_value('processors', 'frame_colorizer_blend', '100'), choices = frame_colorizer_choices.frame_colorizer_blend_range, metavar = create_int_metavar(frame_colorizer_choices.frame_colorizer_blend_range))
-		facefusion.jobs.job_store.register_step_keys([ 'frame_colorizer_model', 'frame_colorizer_blend', 'frame_colorizer_size' ])
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--frame-colorizer-model',
+					help = translator.get('help.model', __package__),
+					default = config.get_str_value('processors', 'frame_colorizer_model', 'ddcolor'),
+					choices = frame_colorizer_choices.frame_colorizer_models
+				),
+				group_processors.add_argument(
+					'--frame-colorizer-size',
+					help = translator.get('help.size', __package__),
+					type = str,
+					default = config.get_str_value('processors', 'frame_colorizer_size', '256x256'),
+					choices = frame_colorizer_choices.frame_colorizer_sizes
+				),
+				group_processors.add_argument(
+					'--frame-colorizer-blend',
+					help = translator.get('help.blend', __package__),
+					type = int,
+					default = config.get_int_value('processors', 'frame_colorizer_blend', '100'),
+					choices = frame_colorizer_choices.frame_colorizer_blend_range,
+					metavar = create_int_metavar(frame_colorizer_choices.frame_colorizer_blend_range)
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'frame_colorizer' ]
+		)


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
@@ -196,10 +222,18 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('frame_colorizer_size', args.get('frame_colorizer_size'))


+def get_common_modules() -> List[ModuleType]:
+	return [ content_analyser ]
+
+
 def pre_check() -> bool:
 	model_hash_set = get_model_options().get('hashes')
 	model_source_set = get_model_options().get('sources')

+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
+
 	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)


@@ -207,23 +241,25 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
 		logger.error(translator.get('choose_image_or_video_target') + translator.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
-		logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
-		return False
-	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
-		logger.error(translator.get('match_target_and_output_extension') + translator.get('exclamation_mark'), __name__)
-		return False
+	if state_manager.get_item('workflow') in [ 'audio-to-image:video', 'image-to-image', 'image-to-video' ]:
+		if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
+			logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
+			return False
 	return True


 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_video_frame.cache_clear()
+	read_static_video_chunk.cache_clear()
 	video_manager.clear_video_pool()
+
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
+
 	if state_manager.get_item('video_memory_strategy') == 'strict':
-		content_analyser.clear_inference_pool()
+		for common_module in get_common_modules():
+			common_module.clear_inference_pool()


 def colorize_frame(temp_vision_frame : VisionFrame) -> VisionFrame:
@@ -1,10 +1,10 @@
-from typing import Literal, TypedDict
+from typing import List, Literal, TypedDict

 from facefusion.types import Mask, VisionFrame

 FrameColorizerInputs = TypedDict('FrameColorizerInputs',
 {
-	'target_vision_frame' : VisionFrame,
+	'target_vision_frames' : List[VisionFrame],
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask
 })
@@ -1,23 +1,26 @@
 from argparse import ArgumentParser
 from functools import lru_cache
+from types import ModuleType
+from typing import List

 import cv2
 import numpy

+import facefusion.capability_store
+import facefusion.choices
 import facefusion.jobs.job_manager
-import facefusion.jobs.job_store
 from facefusion import config, content_analyser, inference_manager, logger, state_manager, translator, video_manager
 from facefusion.common_helper import create_int_metavar, is_macos
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.execution import has_execution_provider
-from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
+from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path
 from facefusion.processors.modules.frame_enhancer import choices as frame_enhancer_choices
 from facefusion.processors.modules.frame_enhancer.types import FrameEnhancerInputs
-from facefusion.processors.types import ProcessorOutputs
+from facefusion.processors.types import ApplyStateItem, ProcessorOutputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.types import ApplyStateItem, Args, DownloadScope, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
-from facefusion.vision import blend_frame, create_tile_frames, merge_tile_frames, read_static_image, read_static_video_frame
+from facefusion.types import Args, DownloadScope, InferencePool, InferenceProvider, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import blend_frame, create_tile_frames, merge_tile_frames, read_static_image, read_static_video_chunk, read_static_video_frame


@lru_cache()
@@ -156,6 +159,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/real_esrgan_x2_fp16.onnx')
 				}
 			},
+			'precision': 'fp16',
 			'size': (256, 16, 8),
 			'scale': 2
 		},
@@ -210,6 +214,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/real_esrgan_x4_fp16.onnx')
 				}
 			},
+			'precision': 'fp16',
 			'size': (256, 16, 8),
 			'scale': 4
 		},
@@ -264,6 +269,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
 					'path': resolve_relative_path('../.assets/models/real_esrgan_x8_fp16.onnx')
 				}
 			},
+			'precision': 'fp16',
 			'size': (256, 16, 8),
 			'scale': 8
 		},
@@ -541,41 +547,61 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet:


 def get_inference_pool() -> InferencePool:
-	model_names = [ get_frame_enhancer_model() ]
+	model_names = [ state_manager.get_item('frame_enhancer_model') ]
 	model_source_set = get_model_options().get('sources')

 	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)


 def clear_inference_pool() -> None:
-	model_names = [ get_frame_enhancer_model() ]
+	model_names = [ state_manager.get_item('frame_enhancer_model') ]
 	inference_manager.clear_inference_pool(__name__, model_names)


+def resolve_inference_providers() -> List[InferenceProvider]:
+	model_precision = get_model_options().get('precision')
+
+	if is_macos() and has_execution_provider('coreml') and model_precision == 'fp16':
+		return\
+		[
+			(facefusion.choices.execution_provider_set.get('coreml'),
+			{
+				'ModelFormat': 'MLProgram',
+				'SpecializationStrategy': 'FastPrediction'
+			})
+		]
+
+	return []
+
+
 def get_model_options() -> ModelOptions:
-	model_name = get_frame_enhancer_model()
+	model_name = state_manager.get_item('frame_enhancer_model')
 	return create_static_model_set('full').get(model_name)


-def get_frame_enhancer_model() -> str:
-	frame_enhancer_model = state_manager.get_item('frame_enhancer_model')
-
-	if is_macos() and has_execution_provider('coreml'):
-		if frame_enhancer_model == 'real_esrgan_x2_fp16':
-			return 'real_esrgan_x2'
-		if frame_enhancer_model == 'real_esrgan_x4_fp16':
-			return 'real_esrgan_x4'
-		if frame_enhancer_model == 'real_esrgan_x8_fp16':
-			return 'real_esrgan_x8'
-	return frame_enhancer_model
-
-
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--frame-enhancer-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'frame_enhancer_model', 'span_kendata_x4'), choices = frame_enhancer_choices.frame_enhancer_models)
-		group_processors.add_argument('--frame-enhancer-blend', help = translator.get('help.blend', __package__), type = int, default = config.get_int_value('processors', 'frame_enhancer_blend', '80'), choices = frame_enhancer_choices.frame_enhancer_blend_range, metavar = create_int_metavar(frame_enhancer_choices.frame_enhancer_blend_range))
-		facefusion.jobs.job_store.register_step_keys([ 'frame_enhancer_model', 'frame_enhancer_blend' ])
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--frame-enhancer-model',
+					help = translator.get('help.model', __package__),
+					default = config.get_str_value('processors', 'frame_enhancer_model', 'span_kendata_x4'),
+					choices = frame_enhancer_choices.frame_enhancer_models
+				),
+				group_processors.add_argument(
+					'--frame-enhancer-blend',
+					help = translator.get('help.blend', __package__),
+					type = int,
+					default = config.get_int_value('processors', 'frame_enhancer_blend', '80'),
+					choices = frame_enhancer_choices.frame_enhancer_blend_range,
+					metavar = create_int_metavar(frame_enhancer_choices.frame_enhancer_blend_range)
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'frame_enhancer' ]
+		)


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
@@ -583,10 +609,18 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('frame_enhancer_blend', args.get('frame_enhancer_blend'))


+def get_common_modules() -> List[ModuleType]:
+	return [ content_analyser ]
+
+
 def pre_check() -> bool:
 	model_hash_set = get_model_options().get('hashes')
 	model_source_set = get_model_options().get('sources')

+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
+
 	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)


@@ -594,23 +628,25 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
 		logger.error(translator.get('choose_image_or_video_target') + translator.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
-		logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
-		return False
-	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
-		logger.error(translator.get('match_target_and_output_extension') + translator.get('exclamation_mark'), __name__)
-		return False
+	if state_manager.get_item('workflow') in [ 'audio-to-image:video', 'image-to-image', 'image-to-video' ]:
+		if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
+			logger.error(translator.get('specify_image_or_video_output') + translator.get('exclamation_mark'), __name__)
+			return False
 	return True


 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_video_frame.cache_clear()
+	read_static_video_chunk.cache_clear()
 	video_manager.clear_video_pool()
+
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
+
 	if state_manager.get_item('video_memory_strategy') == 'strict':
-		content_analyser.clear_inference_pool()
+		for common_module in get_common_modules():
+			common_module.clear_inference_pool()


 def enhance_frame(temp_vision_frame : VisionFrame) -> VisionFrame:
@@ -1,10 +1,10 @@
-from typing import Literal, TypedDict
+from typing import List, Literal, TypedDict

 from facefusion.types import Mask, VisionFrame

 FrameEnhancerInputs = TypedDict('FrameEnhancerInputs',
 {
-	'target_vision_frame' : VisionFrame,
+	'target_vision_frames' : List[VisionFrame],
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask
 })
@@ -1,27 +1,29 @@
 from argparse import ArgumentParser
 from functools import lru_cache
+from types import ModuleType
+from typing import List

 import cv2
 import numpy

+import facefusion.capability_store
 import facefusion.jobs.job_manager
-import facefusion.jobs.job_store
 from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, state_manager, translator, video_manager, voice_extractor
 from facefusion.audio import read_static_voice
-from facefusion.common_helper import create_float_metavar
+from facefusion.common_helper import create_float_metavar, get_middle
 from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
-from facefusion.face_analyser import scale_face
+from facefusion.face_creator import scale_face
 from facefusion.face_helper import create_bounding_box, paste_back, warp_face_by_bounding_box, warp_face_by_face_landmark_5
 from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask
 from facefusion.face_selector import select_faces
 from facefusion.filesystem import has_audio, resolve_relative_path
 from facefusion.processors.modules.lip_syncer import choices as lip_syncer_choices
 from facefusion.processors.modules.lip_syncer.types import LipSyncerInputs, LipSyncerWeight
-from facefusion.processors.types import ProcessorOutputs
+from facefusion.processors.types import ApplyStateItem, ProcessorOutputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.types import ApplyStateItem, Args, AudioFrame, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
-from facefusion.vision import read_static_image, read_static_video_frame
+from facefusion.types import Args, AudioFrame, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, VisionFrame
+from facefusion.vision import read_static_image, read_static_video_chunk, read_static_video_frame


@lru_cache()
@@ -132,9 +134,26 @@ def get_model_options() -> ModelOptions:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--lip-syncer-model', help = translator.get('help.model', __package__), default = config.get_str_value('processors', 'lip_syncer_model', 'wav2lip_gan_96'), choices = lip_syncer_choices.lip_syncer_models)
-		group_processors.add_argument('--lip-syncer-weight', help = translator.get('help.weight', __package__), type = float, default = config.get_float_value('processors', 'lip_syncer_weight', '0.5'), choices = lip_syncer_choices.lip_syncer_weight_range, metavar = create_float_metavar(lip_syncer_choices.lip_syncer_weight_range))
-		facefusion.jobs.job_store.register_step_keys([ 'lip_syncer_model', 'lip_syncer_weight' ])
+		facefusion.capability_store.register_capability_set(
+			[
+				group_processors.add_argument(
+					'--lip-syncer-model',
+					help = translator.get('help.model', __package__),
+					default = config.get_str_value('processors', 'lip_syncer_model', 'wav2lip_gan_96'),
+					choices = lip_syncer_choices.lip_syncer_models
+				),
+				group_processors.add_argument(
+					'--lip-syncer-weight',
+					help = translator.get('help.weight', __package__),
+					type = float,
+					default = config.get_float_value('processors', 'lip_syncer_weight', '0.5'),
+					choices = lip_syncer_choices.lip_syncer_weight_range,
+					metavar = create_float_metavar(lip_syncer_choices.lip_syncer_weight_range)
+				)
+			],
+			scopes = [ 'api', 'cli' ],
+			groups = [ 'lip_syncer' ]
+		)


 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
@@ -142,10 +161,18 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('lip_syncer_weight', args.get('lip_syncer_weight'))


+def get_common_modules() -> List[ModuleType]:
+	return [ content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, voice_extractor ]
+
+
 def pre_check() -> bool:
 	model_hash_set = get_model_options().get('hashes')
 	model_source_set = get_model_options().get('sources')

+	for common_module in get_common_modules():
+		if not common_module.pre_check():
+			return False
+
 	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)


@@ -159,18 +186,16 @@ def pre_process(mode : ProcessMode) -> bool:
 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_video_frame.cache_clear()
+	read_static_video_chunk.cache_clear()
 	read_static_voice.cache_clear()
 	video_manager.clear_video_pool()
+
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
+
 	if state_manager.get_item('video_memory_strategy') == 'strict':
-		content_analyser.clear_inference_pool()
-		face_classifier.clear_inference_pool()
-		face_detector.clear_inference_pool()
-		face_landmarker.clear_inference_pool()
-		face_masker.clear_inference_pool()
-		face_recognizer.clear_inference_pool()
-		voice_extractor.clear_inference_pool()
+		for common_module in get_common_modules():
+			common_module.clear_inference_pool()


 def sync_lip(target_face : Face, source_voice_frame : AudioFrame, temp_vision_frame : VisionFrame) -> VisionFrame:
@@ -282,11 +307,14 @@ 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')
+	target_vision_frames = inputs.get('target_vision_frames')
 	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_vision_frame = get_middle(target_vision_frames)
+	target_faces = select_faces(reference_vision_frame, source_vision_frames, target_vision_frames)

 	if target_faces:
 		for target_face in target_faces:
@@ -1,4 +1,4 @@
-from typing import Any, Literal, TypeAlias, TypedDict
+from typing import Any, List, Literal, TypeAlias, TypedDict

 from numpy.typing import NDArray

@@ -7,8 +7,9 @@ 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,
+	'target_vision_frames' : List[VisionFrame],
 	'temp_vision_frame' : VisionFrame,
 	'temp_vision_mask' : Mask
 })
@@ -1,4 +1,4 @@
-from typing import Any, Dict, Tuple, TypeAlias
+from typing import Any, Callable, Dict, Tuple, TypeAlias

 from numpy.typing import NDArray

@@ -14,7 +14,11 @@ LivePortraitRotation : TypeAlias = NDArray[Any]
 LivePortraitScale : TypeAlias = NDArray[Any]
 LivePortraitTranslation : TypeAlias = NDArray[Any]

-ProcessorStateKey = str
-ProcessorState : TypeAlias = Dict[ProcessorStateKey, Any]
+ProcessorStateValue : TypeAlias = Any
+ProcessorStateKey : TypeAlias = str
+ProcessorState : TypeAlias = Dict[ProcessorStateKey, ProcessorStateValue]
 ProcessorStateSet : TypeAlias = Dict[AppContext, ProcessorState]
+
+ApplyStateItem : TypeAlias = Callable[[ProcessorStateKey, ProcessorStateValue], None]
+
 ProcessorOutputs : TypeAlias = Tuple[VisionFrame, Mask]
--- a/Show More
+++ b/Show More