Upload folder using huggingface_hub

.editorconfig

@@ -0,0 +1,8 @@
+root = true
+
+[*]
+end_of_line = lf
+insert_final_newline = true
+indent_size = 4
+indent_style = tab
+trim_trailing_whitespace = true

.flake8

@@ -0,0 +1,3 @@
+[flake8]
+select = E3, E4, F
+per-file-ignores = facefusion/core.py:E402

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+.github/preview.png filter=lfs diff=lfs merge=lfs -text

.github/FUNDING.yml

@@ -0,0 +1,2 @@
+github: henryruhs
+custom: https://paypal.me/henryruhs

.github/workflows/ci.yml

@@ -0,0 +1,35 @@
+name: ci
+
+on: [ push, pull_request ]
+
+jobs:
+ lint:
+  runs-on: ubuntu-latest
+  steps:
+  - name: Checkout
+    uses: actions/checkout@v2
+  - name: Set up Python 3.10
+    uses: actions/setup-python@v2
+    with:
+     python-version: '3.10'
+  - run: pip install flake8
+  - run: pip install mypy
+  - run: flake8 run.py facefusion tests
+  - run: mypy run.py facefusion tests
+ test:
+  strategy:
+   matrix:
+    os: [ macos-latest, ubuntu-latest, windows-latest ]
+  runs-on: ${{ matrix.os }}
+  steps:
+  - name: Checkout
+    uses: actions/checkout@v2
+  - name: Set up ffmpeg
+    uses: FedericoCarboni/setup-ffmpeg@v2
+  - name: Set up Python 3.10
+    uses: actions/setup-python@v2
+    with:
+     python-version: '3.10'
+  - run: python install.py --onnxruntime default --skip-venv
+  - run: pip install pytest
+  - run: pytest

.gitignore

@@ -0,0 +1,3 @@
+.assets
+.idea
+.vscode

LICENSE.md

@@ -0,0 +1,3 @@
+MIT license
+
+Copyright (c) 2023 Henry Ruhs

README.md

@@ -1,12 +1,114 @@
 ---
-title: Facefusion
-emoji: ⚡
-colorFrom: red
-colorTo: purple
+title: facefusion
+app_file: facefusion
 sdk: gradio
-sdk_version: 4.25.0
-app_file: app.py
-pinned: false
+sdk_version: 3.41.2
 ---
+FaceFusion
+==========
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+> Next generation face swapper and enhancer.
+
+[![Build Status](https://img.shields.io/github/actions/workflow/status/facefusion/facefusion/ci.yml.svg?branch=master)](https://github.com/facefusion/facefusion/actions?query=workflow:ci)
+![License](https://img.shields.io/badge/license-MIT-green)
+
+
+Preview
+-------
+
+![Preview](https://raw.githubusercontent.com/facefusion/facefusion/master/.github/preview.png?sanitize=true)
+
+
+Installation
+------------
+
+Be aware, the installation needs technical skills and is not for beginners. Please do not open platform and installation related issues on GitHub. We have a very helpful [Discord](https://join.facefusion.io) community that will guide you to complete the installation.
+
+Get started with the [installation](https://docs.facefusion.io/installation) guide.
+
+
+Usage
+-----
+
+Run the command:
+
+```
+python run.py [options]
+
+options:
+  -h, --help                                                                                                             show this help message and exit
+  -s SOURCE_PATHS, --source SOURCE_PATHS                                                                                 choose single or multiple source images or audios
+  -t TARGET_PATH, --target TARGET_PATH                                                                                   choose single target image or video
+  -o OUTPUT_PATH, --output OUTPUT_PATH                                                                                   specify the output file or directory
+  -v, --version                                                                                                          show program's version number and exit
+
+misc:
+  --skip-download                                                                                                        omit automate downloads and remote lookups
+  --headless                                                                                                             run the program without a user interface
+  --log-level {error,warn,info,debug}                                                                                    adjust the message severity displayed in the terminal
+
+execution:
+  --execution-providers EXECUTION_PROVIDERS [EXECUTION_PROVIDERS ...]                                                    accelerate the model inference using different providers (choices: cpu, ...)
+  --execution-thread-count [1-128]                                                                                       specify the amount of parallel threads while processing
+  --execution-queue-count [1-32]                                                                                         specify the amount of frames each thread is processing
+
+memory:
+  --video-memory-strategy {strict,moderate,tolerant}                                                                     balance fast frame processing and low vram usage
+  --system-memory-limit [0-128]                                                                                          limit the available ram that can be used while processing
+
+face analyser:
+  --face-analyser-order {left-right,right-left,top-bottom,bottom-top,small-large,large-small,best-worst,worst-best}      specify the order in which the face analyser detects faces.
+  --face-analyser-age {child,teen,adult,senior}                                                                          filter the detected faces based on their age
+  --face-analyser-gender {female,male}                                                                                   filter the detected faces based on their gender
+  --face-detector-model {many,retinaface,scrfd,yoloface,yunet}                                                           choose the model responsible for detecting the face
+  --face-detector-size FACE_DETECTOR_SIZE                                                                                specify the size of the frame provided to the face detector
+  --face-detector-score [0.0-1.0]                                                                                        filter the detected faces base on the confidence score
+  --face-landmarker-score [0.0-1.0]                                                                                      filter the detected landmarks base on the confidence score
+
+face selector:
+  --face-selector-mode {many,one,reference}                                                                              use reference based tracking or simple matching
+  --reference-face-position REFERENCE_FACE_POSITION                                                                      specify the position used to create the reference face
+  --reference-face-distance [0.0-1.5]                                                                                    specify the desired similarity between the reference face and target face
+  --reference-frame-number REFERENCE_FRAME_NUMBER                                                                        specify the frame used to create the reference face
+
+face mask:
+  --face-mask-types FACE_MASK_TYPES [FACE_MASK_TYPES ...]                                                                mix and match different face mask types (choices: box, occlusion, region)
+  --face-mask-blur [0.0-1.0]                                                                                             specify the degree of blur applied the box mask
+  --face-mask-padding FACE_MASK_PADDING [FACE_MASK_PADDING ...]                                                          apply top, right, bottom and left padding to the box mask
+  --face-mask-regions FACE_MASK_REGIONS [FACE_MASK_REGIONS ...]                                                          choose the facial features used for the region mask (choices: skin, left-eyebrow, right-eyebrow, left-eye, right-eye, eye-glasses, nose, mouth, upper-lip, lower-lip)
+
+frame extraction:
+  --trim-frame-start TRIM_FRAME_START                                                                                    specify the the start frame of the target video
+  --trim-frame-end TRIM_FRAME_END                                                                                        specify the the end frame of the target video
+  --temp-frame-format {bmp,jpg,png}                                                                                      specify the temporary resources format
+  --keep-temp                                                                                                            keep the temporary resources after processing
+
+output creation:
+  --output-image-quality [0-100]                                                                                         specify the image quality which translates to the compression factor
+  --output-image-resolution OUTPUT_IMAGE_RESOLUTION                                                                      specify the image output resolution based on the target image
+  --output-video-encoder {libx264,libx265,libvpx-vp9,h264_nvenc,hevc_nvenc,h264_amf,hevc_amf}                            specify the encoder use for the video compression
+  --output-video-preset {ultrafast,superfast,veryfast,faster,fast,medium,slow,slower,veryslow}                           balance fast video processing and video file size
+  --output-video-quality [0-100]                                                                                         specify the video quality which translates to the compression factor
+  --output-video-resolution OUTPUT_VIDEO_RESOLUTION                                                                      specify the video output resolution based on the target video
+  --output-video-fps OUTPUT_VIDEO_FPS                                                                                    specify the video output fps based on the target video
+  --skip-audio                                                                                                           omit the audio from the target video
+
+frame processors:
+  --frame-processors FRAME_PROCESSORS [FRAME_PROCESSORS ...]                                                             load a single or multiple frame processors. (choices: face_debugger, face_enhancer, face_swapper, frame_enhancer, lip_syncer, ...)
+  --face-debugger-items FACE_DEBUGGER_ITEMS [FACE_DEBUGGER_ITEMS ...]                                                    load a single or multiple frame processors (choices: bounding-box, face-landmark-5, face-landmark-5/68, face-landmark-68, face-mask, face-detector-score, face-landmarker-score, age, gender)
+  --face-enhancer-model {codeformer,gfpgan_1.2,gfpgan_1.3,gfpgan_1.4,gpen_bfr_256,gpen_bfr_512,restoreformer_plus_plus}  choose the model responsible for enhancing the face
+  --face-enhancer-blend [0-100]                                                                                          blend the enhanced into the previous face
+  --face-swapper-model {blendswap_256,inswapper_128,inswapper_128_fp16,simswap_256,simswap_512_unofficial,uniface_256}   choose the model responsible for swapping the face
+  --frame-enhancer-model {lsdir_x4,nomos8k_sc_x4,real_esrgan_x4,real_esrgan_x4_fp16,span_kendata_x4}                     choose the model responsible for enhancing the frame
+  --frame-enhancer-blend [0-100]                                                                                         blend the enhanced into the previous frame
+  --lip-syncer-model {wav2lip_gan}                                                                                       choose the model responsible for syncing the lips
+
+uis:
+  --ui-layouts UI_LAYOUTS [UI_LAYOUTS ...]                                                                               launch a single or multiple UI layouts (choices: benchmark, default, webcam, ...)
+```
+
+
+Documentation
+-------------
+
+Read the [documentation](https://docs.facefusion.io) for a deep dive.

facefusion.ini

@@ -0,0 +1,68 @@
+[general]
+source_paths =
+target_path =
+output_path =
+
+[misc]
+skip_download =
+headless =
+log_level =
+
+[execution]
+execution_providers =
+execution_thread_count =
+execution_queue_count =
+
+[memory]
+video_memory_strategy =
+system_memory_limit =
+
+[face_analyser]
+face_analyser_order =
+face_analyser_age =
+face_analyser_gender =
+face_detector_model =
+face_detector_size =
+face_detector_score =
+face_landmarker_score =
+
+[face_selector]
+face_selector_mode =
+reference_face_position =
+reference_face_distance =
+reference_frame_number =
+
+[face_mask]
+face_mask_types =
+face_mask_blur =
+face_mask_padding =
+face_mask_regions =
+
+[frame_extraction]
+trim_frame_start =
+trim_frame_end =
+temp_frame_format =
+keep_temp =
+
+[output_creation]
+output_image_quality =
+output_image_resolution =
+output_video_encoder =
+output_video_preset =
+output_video_quality =
+output_video_resolution =
+output_video_fps =
+skip_audio =
+
+[frame_processors]
+frame_processors =
+face_debugger_items =
+face_enhancer_model =
+face_enhancer_blend =
+face_swapper_model =
+frame_enhancer_model =
+frame_enhancer_blend =
+lip_syncer_model =
+
+[uis]
+ui_layouts =

facefusion/audio.py

@@ -0,0 +1,81 @@
+from typing import Optional, Any, List
+from functools import lru_cache
+import numpy
+import scipy
+
+from facefusion.filesystem import is_audio
+from facefusion.ffmpeg import read_audio_buffer
+from facefusion.typing import Fps, Audio, Spectrogram, AudioFrame
+
+
+def get_audio_frame(audio_path : str, fps : Fps, frame_number : int = 0) -> Optional[AudioFrame]:
+	if is_audio(audio_path):
+		audio_frames = read_static_audio(audio_path, fps)
+		if frame_number in range(len(audio_frames)):
+			return audio_frames[frame_number]
+	return None
+
+
+def create_empty_audio_frame() -> AudioFrame:
+	audio_frame = numpy.zeros((80, 16), dtype = numpy.int16)
+	return audio_frame
+
+
+@lru_cache(maxsize = None)
+def read_static_audio(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
+	if is_audio(audio_path):
+		audio_buffer = read_audio_buffer(audio_path, 16000, 2)
+		audio = numpy.frombuffer(audio_buffer, dtype = numpy.int16).reshape(-1, 2)
+		audio = normalize_audio(audio)
+		audio = filter_audio(audio, -0.97)
+		spectrogram = create_spectrogram(audio, 16000, 80, 800, 55.0, 7600.0)
+		audio_frames = extract_audio_frames(spectrogram, 80, 16, fps)
+		return audio_frames
+	return None
+
+
+def normalize_audio(audio : numpy.ndarray[Any, Any]) -> Audio:
+	if audio.ndim > 1:
+		audio = numpy.mean(audio, axis = 1)
+	audio = audio / numpy.max(numpy.abs(audio), axis = 0)
+	return audio
+
+
+def filter_audio(audio : Audio, filter_coefficient : float) -> Audio:
+	audio = scipy.signal.lfilter([ 1.0, filter_coefficient ], [1.0], audio)
+	return audio
+
+
+def convert_hertz_to_mel(hertz : float) -> float:
+	return 2595 * numpy.log10(1 + hertz / 700)
+
+
+def convert_mel_to_hertz(mel : numpy.ndarray[Any, Any]) -> numpy.ndarray[Any, Any]:
+	return 700 * (10 ** (mel / 2595) - 1)
+
+
+@lru_cache(maxsize = None)
+def create_static_mel_filter(sample_rate : int, filter_total : int, filter_size : int, frequency_minimum : float, frequency_maximum : float) -> numpy.ndarray[Any, Any]:
+	frequency_maximum = min(sample_rate / 2, frequency_maximum)
+	mel_filter = numpy.zeros((filter_total, filter_size // 2 + 1))
+	mel_bins = numpy.linspace(convert_hertz_to_mel(frequency_minimum), convert_hertz_to_mel(frequency_maximum), filter_total + 2)
+	indices = numpy.floor((filter_size + 1) * convert_mel_to_hertz(mel_bins) / sample_rate).astype(numpy.int16)
+	for index in range(filter_total):
+		mel_filter[index, indices[index]: indices[index + 1]] = scipy.signal.windows.triang(indices[index + 1] - indices[index])
+	return mel_filter
+
+
+def create_spectrogram(audio : Audio, sample_rate : int, filter_total : int, filter_size : int, frequency_minimum : float, frequency_maximum : float) -> Spectrogram:
+	mel_filter = create_static_mel_filter(sample_rate, filter_total, filter_size, frequency_minimum, frequency_maximum)
+	spectrogram = scipy.signal.stft(audio, nperseg = filter_size, noverlap = 600, nfft = filter_size)[2]
+	spectrogram = numpy.dot(mel_filter, numpy.abs(spectrogram))
+	return spectrogram
+
+
+def extract_audio_frames(spectrogram : Spectrogram, filter_total : int, audio_frame_step : int, fps : Fps) -> List[AudioFrame]:
+	indices = numpy.arange(0, spectrogram.shape[1], filter_total / fps).astype(numpy.int16)
+	indices = indices[indices >= audio_frame_step]
+	audio_frames = []
+	for index in indices:
+		audio_frames.append(spectrogram[:, max(0, index - audio_frame_step) : index])
+	return audio_frames

facefusion/choices.py

@@ -0,0 +1,37 @@
+from typing import List, Dict
+
+from facefusion.typing import VideoMemoryStrategy, FaceSelectorMode, FaceAnalyserOrder, FaceAnalyserAge, FaceAnalyserGender, FaceDetectorModel, FaceMaskType, FaceMaskRegion, TempFrameFormat, OutputVideoEncoder, OutputVideoPreset
+from facefusion.common_helper import create_int_range, create_float_range
+
+video_memory_strategies : List[VideoMemoryStrategy] = [ 'strict', 'moderate', 'tolerant' ]
+face_analyser_orders : List[FaceAnalyserOrder] = [ 'left-right', 'right-left', 'top-bottom', 'bottom-top', 'small-large', 'large-small', 'best-worst', 'worst-best' ]
+face_analyser_ages : List[FaceAnalyserAge] = [ 'child', 'teen', 'adult', 'senior' ]
+face_analyser_genders : List[FaceAnalyserGender] = [ 'female', 'male' ]
+face_detector_set : Dict[FaceDetectorModel, List[str]] =\
+{
+	'many': [ '640x640' ],
+	'retinaface': [ '160x160', '320x320', '480x480', '512x512', '640x640' ],
+	'scrfd': [ '160x160', '320x320', '480x480', '512x512', '640x640' ],
+	'yoloface': [ '640x640' ],
+	'yunet': [ '160x160', '320x320', '480x480', '512x512', '640x640', '768x768', '960x960', '1024x1024' ]
+}
+face_selector_modes : List[FaceSelectorMode] = [ 'many', 'one', 'reference' ]
+face_mask_types : List[FaceMaskType] = [ 'box', 'occlusion', 'region' ]
+face_mask_regions : List[FaceMaskRegion] = [ 'skin', 'left-eyebrow', 'right-eyebrow', 'left-eye', 'right-eye', 'eye-glasses', 'nose', 'mouth', 'upper-lip', 'lower-lip' ]
+temp_frame_formats : List[TempFrameFormat] = [ 'bmp', 'jpg', 'png' ]
+output_video_encoders : List[OutputVideoEncoder] = [ 'libx264', 'libx265', 'libvpx-vp9', 'h264_nvenc', 'hevc_nvenc', 'h264_amf', 'hevc_amf' ]
+output_video_presets : List[OutputVideoPreset] = [ 'ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow' ]
+
+image_template_sizes : List[float] = [ 0.25, 0.5, 0.75, 1, 1.5, 2, 2.5, 3, 3.5, 4 ]
+video_template_sizes : List[int] = [ 240, 360, 480, 540, 720, 1080, 1440, 2160, 4320 ]
+
+execution_thread_count_range : List[int] = create_int_range(1, 128, 1)
+execution_queue_count_range : List[int] = create_int_range(1, 32, 1)
+system_memory_limit_range : List[int] = create_int_range(0, 128, 1)
+face_detector_score_range : List[float] = create_float_range(0.0, 1.0, 0.05)
+face_landmarker_score_range : List[float] = create_float_range(0.0, 1.0, 0.05)
+face_mask_blur_range : List[float] = create_float_range(0.0, 1.0, 0.05)
+face_mask_padding_range : List[int] = create_int_range(0, 100, 1)
+reference_face_distance_range : List[float] = create_float_range(0.0, 1.5, 0.05)
+output_image_quality_range : List[int] = create_int_range(0, 100, 1)
+output_video_quality_range : List[int] = create_int_range(0, 100, 1)

facefusion/common_helper.py

@@ -0,0 +1,27 @@
+from typing import List, Any, Tuple
+import numpy
+
+
+def create_metavar(ranges : List[Any]) -> str:
+	return '[' + str(ranges[0]) + '-' + str(ranges[-1]) + ']'
+
+
+def create_int_range(start : int, stop : int, step : int) -> List[int]:
+	return (numpy.arange(start, stop + step, step)).tolist()
+
+
+def create_float_range(start : float, stop : float, step : float) -> List[float]:
+	return (numpy.around(numpy.arange(start, stop + step, step), decimals = 2)).tolist()
+
+
+def get_first(__list__ : Any) -> Any:
+	return next(iter(__list__), None)
+
+
+def extract_major_version(version : str) -> Tuple[int, int]:
+	versions = version.split('.')
+	if len(versions) > 1:
+		return int(versions[0]), int(versions[1])
+	if len(versions) == 1:
+		return int(versions[0]), 0
+	return 0, 0

facefusion/config.py

@@ -0,0 +1,92 @@
+from configparser import ConfigParser
+from typing import Any, Optional, List
+
+from facefusion.filesystem import resolve_relative_path
+
+CONFIG = None
+
+
+def get_config() -> ConfigParser:
+	global CONFIG
+
+	if CONFIG is None:
+		config_path = resolve_relative_path('../facefusion.ini')
+		CONFIG = ConfigParser()
+		CONFIG.read(config_path, encoding = 'utf-8')
+	return CONFIG
+
+
+def clear_config() -> None:
+	global CONFIG
+
+	CONFIG = None
+
+
+def get_str_value(key : str, fallback : Optional[str] = None) -> Optional[str]:
+	value = get_value_by_notation(key)
+
+	if value or fallback:
+		return str(value or fallback)
+	return None
+
+
+def get_int_value(key : str, fallback : Optional[str] = None) -> Optional[int]:
+	value = get_value_by_notation(key)
+
+	if value or fallback:
+		return int(value or fallback)
+	return None
+
+
+def get_float_value(key : str, fallback : Optional[str] = None) -> Optional[float]:
+	value = get_value_by_notation(key)
+
+	if value or fallback:
+		return float(value or fallback)
+	return None
+
+
+def get_bool_value(key : str, fallback : Optional[str] = None) -> Optional[bool]:
+	value = get_value_by_notation(key)
+
+	if value == 'True' or fallback == 'True':
+		return True
+	if value == 'False' or fallback == 'False':
+		return False
+	return None
+
+
+def get_str_list(key : str, fallback : Optional[str] = None) -> Optional[List[str]]:
+	value = get_value_by_notation(key)
+
+	if value or fallback:
+		return [ str(value) for value in (value or fallback).split(' ') ]
+	return None
+
+
+def get_int_list(key : str, fallback : Optional[str] = None) -> Optional[List[int]]:
+	value = get_value_by_notation(key)
+
+	if value or fallback:
+		return [ int(value) for value in (value or fallback).split(' ') ]
+	return None
+
+
+def get_float_list(key : str, fallback : Optional[str] = None) -> Optional[List[float]]:
+	value = get_value_by_notation(key)
+
+	if value or fallback:
+		return [ float(value) for value in (value or fallback).split(' ') ]
+	return None
+
+
+def get_value_by_notation(key : str) -> Optional[Any]:
+	config = get_config()
+
+	if '.' in key:
+		section, name = key.split('.')
+		if section in config and name in config[section]:
+			return config[section][name]
+	if key in config:
+		return config[key]
+	return None

facefusion/content_analyser.py

@@ -0,0 +1,110 @@
+from typing import Any, Dict
+from functools import lru_cache
+from time import sleep
+import threading
+import cv2
+import numpy
+import onnxruntime
+from tqdm import tqdm
+
+import facefusion.globals
+from facefusion import process_manager, wording
+from facefusion.typing import VisionFrame, ModelValue, Fps
+from facefusion.execution import apply_execution_provider_options
+from facefusion.vision import get_video_frame, count_video_frame_total, read_image, detect_video_fps
+from facefusion.filesystem import resolve_relative_path
+from facefusion.download import conditional_download
+
+CONTENT_ANALYSER = None
+THREAD_LOCK : threading.Lock = threading.Lock()
+MODELS : Dict[str, ModelValue] =\
+{
+	'open_nsfw':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/open_nsfw.onnx',
+		'path': resolve_relative_path('../.assets/models/open_nsfw.onnx')
+	}
+}
+PROBABILITY_LIMIT = 0.80
+RATE_LIMIT = 5
+STREAM_COUNTER = 0
+
+
+def get_content_analyser() -> Any:
+	global CONTENT_ANALYSER
+
+	with THREAD_LOCK:
+		while process_manager.is_checking():
+			sleep(0.5)
+		if CONTENT_ANALYSER is None:
+			model_path = MODELS.get('open_nsfw').get('path')
+			CONTENT_ANALYSER = onnxruntime.InferenceSession(model_path, providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+	return CONTENT_ANALYSER
+
+
+def clear_content_analyser() -> None:
+	global CONTENT_ANALYSER
+
+	CONTENT_ANALYSER = None
+
+
+def pre_check() -> bool:
+	if not facefusion.globals.skip_download:
+		download_directory_path = resolve_relative_path('../.assets/models')
+		model_url = MODELS.get('open_nsfw').get('url')
+		process_manager.check()
+		conditional_download(download_directory_path, [ model_url ])
+		process_manager.end()
+	return True
+
+
+def analyse_stream(vision_frame : VisionFrame, video_fps : Fps) -> bool:
+	global STREAM_COUNTER
+
+	STREAM_COUNTER = STREAM_COUNTER + 1
+	if STREAM_COUNTER % int(video_fps) == 0:
+		return analyse_frame(vision_frame)
+	return False
+
+
+def analyse_frame(vision_frame : VisionFrame) -> bool:
+	content_analyser = get_content_analyser()
+	vision_frame = prepare_frame(vision_frame)
+	probability = content_analyser.run(None,
+	{
+		content_analyser.get_inputs()[0].name: vision_frame
+	})[0][0][1]
+	return probability > PROBABILITY_LIMIT
+
+
+def prepare_frame(vision_frame : VisionFrame) -> VisionFrame:
+	vision_frame = cv2.resize(vision_frame, (224, 224)).astype(numpy.float32)
+	vision_frame -= numpy.array([ 104, 117, 123 ]).astype(numpy.float32)
+	vision_frame = numpy.expand_dims(vision_frame, axis = 0)
+	return vision_frame
+
+
+@lru_cache(maxsize = None)
+def analyse_image(image_path : str) -> bool:
+	frame = read_image(image_path)
+	return analyse_frame(frame)
+
+
+@lru_cache(maxsize = None)
+def analyse_video(video_path : str, start_frame : int, end_frame : int) -> bool:
+	video_frame_total = count_video_frame_total(video_path)
+	video_fps = detect_video_fps(video_path)
+	frame_range = range(start_frame or 0, end_frame or video_frame_total)
+	rate = 0.0
+	counter = 0
+
+	with tqdm(total = len(frame_range), desc = wording.get('analysing'), unit = 'frame', ascii = ' =', disable = facefusion.globals.log_level in [ 'warn', 'error' ]) as progress:
+		for frame_number in frame_range:
+			if frame_number % int(video_fps) == 0:
+				frame = get_video_frame(video_path, frame_number)
+				if analyse_frame(frame):
+					counter += 1
+			rate = counter * int(video_fps) / len(frame_range) * 100
+			progress.update()
+			progress.set_postfix(rate = rate)
+	return rate > RATE_LIMIT

facefusion/core.py

@@ -0,0 +1,377 @@
+import os
+
+os.environ['OMP_NUM_THREADS'] = '1'
+
+import signal
+import sys
+import warnings
+import shutil
+import numpy
+import onnxruntime
+from time import sleep, time
+from argparse import ArgumentParser, HelpFormatter
+
+import facefusion.choices
+import facefusion.globals
+from facefusion.face_analyser import get_one_face, get_average_face
+from facefusion.face_store import get_reference_faces, append_reference_face
+from facefusion import face_analyser, face_masker, content_analyser, config, process_manager, metadata, logger, wording
+from facefusion.content_analyser import analyse_image, analyse_video
+from facefusion.processors.frame.core import get_frame_processors_modules, load_frame_processor_module
+from facefusion.common_helper import create_metavar, get_first
+from facefusion.execution import encode_execution_providers, decode_execution_providers
+from facefusion.normalizer import normalize_output_path, normalize_padding, normalize_fps
+from facefusion.memory import limit_system_memory
+from facefusion.statistics import conditional_log_statistics
+from facefusion.filesystem import list_directory, get_temp_frame_paths, create_temp, move_temp, clear_temp, is_image, is_video, filter_audio_paths
+from facefusion.ffmpeg import extract_frames, merge_video, copy_image, finalize_image, restore_audio, replace_audio
+from facefusion.vision import read_image, read_static_images, detect_image_resolution, restrict_video_fps, create_image_resolutions, get_video_frame, detect_video_resolution, detect_video_fps, restrict_video_resolution, restrict_image_resolution, create_video_resolutions, pack_resolution, unpack_resolution
+
+onnxruntime.set_default_logger_severity(3)
+warnings.filterwarnings('ignore', category = UserWarning, module = 'gradio')
+
+
+def cli() -> None:
+	signal.signal(signal.SIGINT, lambda signal_number, frame: destroy())
+	program = ArgumentParser(formatter_class = lambda prog: HelpFormatter(prog, max_help_position = 130), add_help = False)
+	# general
+	program.add_argument('-s', '--source', help = wording.get('help.source'), action = 'append', dest = 'source_paths', default = config.get_str_list('general.source_paths'))
+	program.add_argument('-t', '--target', help = wording.get('help.target'), dest = 'target_path', default = config.get_str_value('general.target_path'))
+	program.add_argument('-o', '--output', help = wording.get('help.output'), dest = 'output_path', default = config.get_str_value('general.output_path'))
+	program.add_argument('-v', '--version', version = metadata.get('name') + ' ' + metadata.get('version'), action = 'version')
+	# misc
+	group_misc = program.add_argument_group('misc')
+	group_misc.add_argument('--skip-download', help = wording.get('help.skip_download'), action = 'store_true', default = config.get_bool_value('misc.skip_download'))
+	group_misc.add_argument('--headless', help = wording.get('help.headless'), action = 'store_true', default = config.get_bool_value('misc.headless'))
+	group_misc.add_argument('--log-level', help = wording.get('help.log_level'), default = config.get_str_value('misc.log_level', 'info'), choices = logger.get_log_levels())
+	# execution
+	execution_providers = encode_execution_providers(onnxruntime.get_available_providers())
+	group_execution = program.add_argument_group('execution')
+	group_execution.add_argument('--execution-providers', help = wording.get('help.execution_providers').format(choices = ', '.join(execution_providers)), default = config.get_str_list('execution.execution_providers', 'cpu'), choices = execution_providers, nargs = '+', metavar = 'EXECUTION_PROVIDERS')
+	group_execution.add_argument('--execution-thread-count', help = wording.get('help.execution_thread_count'), type = int, default = config.get_int_value('execution.execution_thread_count', '4'), choices = facefusion.choices.execution_thread_count_range, metavar = create_metavar(facefusion.choices.execution_thread_count_range))
+	group_execution.add_argument('--execution-queue-count', help = wording.get('help.execution_queue_count'), type = int, default = config.get_int_value('execution.execution_queue_count', '1'), choices = facefusion.choices.execution_queue_count_range, metavar = create_metavar(facefusion.choices.execution_queue_count_range))
+	# memory
+	group_memory = program.add_argument_group('memory')
+	group_memory.add_argument('--video-memory-strategy', help = wording.get('help.video_memory_strategy'), default = config.get_str_value('memory.video_memory_strategy', 'strict'), choices = facefusion.choices.video_memory_strategies)
+	group_memory.add_argument('--system-memory-limit', help = wording.get('help.system_memory_limit'), type = int, default = config.get_int_value('memory.system_memory_limit', '0'), choices = facefusion.choices.system_memory_limit_range, metavar = create_metavar(facefusion.choices.system_memory_limit_range))
+	# face analyser
+	group_face_analyser = program.add_argument_group('face analyser')
+	group_face_analyser.add_argument('--face-analyser-order', help = wording.get('help.face_analyser_order'), default = config.get_str_value('face_analyser.face_analyser_order', 'left-right'), choices = facefusion.choices.face_analyser_orders)
+	group_face_analyser.add_argument('--face-analyser-age', help = wording.get('help.face_analyser_age'), default = config.get_str_value('face_analyser.face_analyser_age'), choices = facefusion.choices.face_analyser_ages)
+	group_face_analyser.add_argument('--face-analyser-gender', help = wording.get('help.face_analyser_gender'), default = config.get_str_value('face_analyser.face_analyser_gender'), choices = facefusion.choices.face_analyser_genders)
+	group_face_analyser.add_argument('--face-detector-model', help = wording.get('help.face_detector_model'), default = config.get_str_value('face_analyser.face_detector_model', 'yoloface'), choices = facefusion.choices.face_detector_set.keys())
+	group_face_analyser.add_argument('--face-detector-size', help = wording.get('help.face_detector_size'), default = config.get_str_value('face_analyser.face_detector_size', '640x640'))
+	group_face_analyser.add_argument('--face-detector-score', help = wording.get('help.face_detector_score'), type = float, default = config.get_float_value('face_analyser.face_detector_score', '0.5'), choices = facefusion.choices.face_detector_score_range, metavar = create_metavar(facefusion.choices.face_detector_score_range))
+	group_face_analyser.add_argument('--face-landmarker-score', help = wording.get('help.face_landmarker_score'), type = float, default = config.get_float_value('face_analyser.face_landmarker_score', '0.5'), choices = facefusion.choices.face_landmarker_score_range, metavar = create_metavar(facefusion.choices.face_landmarker_score_range))
+	# face selector
+	group_face_selector = program.add_argument_group('face selector')
+	group_face_selector.add_argument('--face-selector-mode', help = wording.get('help.face_selector_mode'), default = config.get_str_value('face_selector.face_selector_mode', 'reference'), choices = facefusion.choices.face_selector_modes)
+	group_face_selector.add_argument('--reference-face-position', help = wording.get('help.reference_face_position'), type = int, default = config.get_int_value('face_selector.reference_face_position', '0'))
+	group_face_selector.add_argument('--reference-face-distance', help = wording.get('help.reference_face_distance'), type = float, default = config.get_float_value('face_selector.reference_face_distance', '0.6'), choices = facefusion.choices.reference_face_distance_range, metavar = create_metavar(facefusion.choices.reference_face_distance_range))
+	group_face_selector.add_argument('--reference-frame-number', help = wording.get('help.reference_frame_number'), type = int, default = config.get_int_value('face_selector.reference_frame_number', '0'))
+	# face mask
+	group_face_mask = program.add_argument_group('face mask')
+	group_face_mask.add_argument('--face-mask-types', help = wording.get('help.face_mask_types').format(choices = ', '.join(facefusion.choices.face_mask_types)), default = config.get_str_list('face_mask.face_mask_types', 'box'), choices = facefusion.choices.face_mask_types, nargs = '+', metavar = 'FACE_MASK_TYPES')
+	group_face_mask.add_argument('--face-mask-blur', help = wording.get('help.face_mask_blur'), type = float, default = config.get_float_value('face_mask.face_mask_blur', '0.3'), choices = facefusion.choices.face_mask_blur_range, metavar = create_metavar(facefusion.choices.face_mask_blur_range))
+	group_face_mask.add_argument('--face-mask-padding', help = wording.get('help.face_mask_padding'), type = int, default = config.get_int_list('face_mask.face_mask_padding', '0 0 0 0'), nargs = '+')
+	group_face_mask.add_argument('--face-mask-regions', help = wording.get('help.face_mask_regions').format(choices = ', '.join(facefusion.choices.face_mask_regions)), default = config.get_str_list('face_mask.face_mask_regions', ' '.join(facefusion.choices.face_mask_regions)), choices = facefusion.choices.face_mask_regions, nargs = '+', metavar = 'FACE_MASK_REGIONS')
+	# frame extraction
+	group_frame_extraction = program.add_argument_group('frame extraction')
+	group_frame_extraction.add_argument('--trim-frame-start', help = wording.get('help.trim_frame_start'), type = int, default = facefusion.config.get_int_value('frame_extraction.trim_frame_start'))
+	group_frame_extraction.add_argument('--trim-frame-end',	help = wording.get('help.trim_frame_end'), type = int, default = facefusion.config.get_int_value('frame_extraction.trim_frame_end'))
+	group_frame_extraction.add_argument('--temp-frame-format', help = wording.get('help.temp_frame_format'), default = config.get_str_value('frame_extraction.temp_frame_format', 'png'), choices = facefusion.choices.temp_frame_formats)
+	group_frame_extraction.add_argument('--keep-temp', help = wording.get('help.keep_temp'), action = 'store_true',	default = config.get_bool_value('frame_extraction.keep_temp'))
+	# output creation
+	group_output_creation = program.add_argument_group('output creation')
+	group_output_creation.add_argument('--output-image-quality', help = wording.get('help.output_image_quality'), type = int, default = config.get_int_value('output_creation.output_image_quality', '80'), choices = facefusion.choices.output_image_quality_range, metavar = create_metavar(facefusion.choices.output_image_quality_range))
+	group_output_creation.add_argument('--output-image-resolution', help = wording.get('help.output_image_resolution'), default = config.get_str_value('output_creation.output_image_resolution'))
+	group_output_creation.add_argument('--output-video-encoder', help = wording.get('help.output_video_encoder'), default = config.get_str_value('output_creation.output_video_encoder', 'libx264'), choices = facefusion.choices.output_video_encoders)
+	group_output_creation.add_argument('--output-video-preset', help = wording.get('help.output_video_preset'), default = config.get_str_value('output_creation.output_video_preset', 'veryfast'), choices = facefusion.choices.output_video_presets)
+	group_output_creation.add_argument('--output-video-quality', help = wording.get('help.output_video_quality'), type = int, default = config.get_int_value('output_creation.output_video_quality', '80'), choices = facefusion.choices.output_video_quality_range, metavar = create_metavar(facefusion.choices.output_video_quality_range))
+	group_output_creation.add_argument('--output-video-resolution', help = wording.get('help.output_video_resolution'), default = config.get_str_value('output_creation.output_video_resolution'))
+	group_output_creation.add_argument('--output-video-fps', help = wording.get('help.output_video_fps'), type = float)
+	group_output_creation.add_argument('--skip-audio', help = wording.get('help.skip_audio'), action = 'store_true', default = config.get_bool_value('output_creation.skip_audio'))
+	# frame processors
+	available_frame_processors = list_directory('facefusion/processors/frame/modules')
+	program = ArgumentParser(parents = [ program ], formatter_class = program.formatter_class, add_help = True)
+	group_frame_processors = program.add_argument_group('frame processors')
+	group_frame_processors.add_argument('--frame-processors', help = wording.get('help.frame_processors').format(choices = ', '.join(available_frame_processors)), default = config.get_str_list('frame_processors.frame_processors', 'face_swapper'), nargs = '+')
+	for frame_processor in available_frame_processors:
+		frame_processor_module = load_frame_processor_module(frame_processor)
+		frame_processor_module.register_args(group_frame_processors)
+	# uis
+	available_ui_layouts = list_directory('facefusion/uis/layouts')
+	group_uis = program.add_argument_group('uis')
+	group_uis.add_argument('--ui-layouts', help = wording.get('help.ui_layouts').format(choices = ', '.join(available_ui_layouts)), default = config.get_str_list('uis.ui_layouts', 'default'), nargs = '+')
+	run(program)
+
+
+def apply_args(program : ArgumentParser) -> None:
+	args = program.parse_args()
+	# general
+	facefusion.globals.source_paths = args.source_paths
+	facefusion.globals.target_path = args.target_path
+	facefusion.globals.output_path = args.output_path
+	# misc
+	facefusion.globals.skip_download = args.skip_download
+	facefusion.globals.headless = args.headless
+	facefusion.globals.log_level = args.log_level
+	# execution
+	facefusion.globals.execution_providers = decode_execution_providers(args.execution_providers)
+	facefusion.globals.execution_thread_count = args.execution_thread_count
+	facefusion.globals.execution_queue_count = args.execution_queue_count
+	# memory
+	facefusion.globals.video_memory_strategy = args.video_memory_strategy
+	facefusion.globals.system_memory_limit = args.system_memory_limit
+	# face analyser
+	facefusion.globals.face_analyser_order = args.face_analyser_order
+	facefusion.globals.face_analyser_age = args.face_analyser_age
+	facefusion.globals.face_analyser_gender = args.face_analyser_gender
+	facefusion.globals.face_detector_model = args.face_detector_model
+	if args.face_detector_size in facefusion.choices.face_detector_set[args.face_detector_model]:
+		facefusion.globals.face_detector_size = args.face_detector_size
+	else:
+		facefusion.globals.face_detector_size = '640x640'
+	facefusion.globals.face_detector_score = args.face_detector_score
+	facefusion.globals.face_landmarker_score = args.face_landmarker_score
+	# face selector
+	facefusion.globals.face_selector_mode = args.face_selector_mode
+	facefusion.globals.reference_face_position = args.reference_face_position
+	facefusion.globals.reference_face_distance = args.reference_face_distance
+	facefusion.globals.reference_frame_number = args.reference_frame_number
+	# face mask
+	facefusion.globals.face_mask_types = args.face_mask_types
+	facefusion.globals.face_mask_blur = args.face_mask_blur
+	facefusion.globals.face_mask_padding = normalize_padding(args.face_mask_padding)
+	facefusion.globals.face_mask_regions = args.face_mask_regions
+	# frame extraction
+	facefusion.globals.trim_frame_start = args.trim_frame_start
+	facefusion.globals.trim_frame_end = args.trim_frame_end
+	facefusion.globals.temp_frame_format = args.temp_frame_format
+	facefusion.globals.keep_temp = args.keep_temp
+	# output creation
+	facefusion.globals.output_image_quality = args.output_image_quality
+	if is_image(args.target_path):
+		output_image_resolution = detect_image_resolution(args.target_path)
+		output_image_resolutions = create_image_resolutions(output_image_resolution)
+		if args.output_image_resolution in output_image_resolutions:
+			facefusion.globals.output_image_resolution = args.output_image_resolution
+		else:
+			facefusion.globals.output_image_resolution = pack_resolution(output_image_resolution)
+	facefusion.globals.output_video_encoder = args.output_video_encoder
+	facefusion.globals.output_video_preset = args.output_video_preset
+	facefusion.globals.output_video_quality = args.output_video_quality
+	if is_video(args.target_path):
+		output_video_resolution = detect_video_resolution(args.target_path)
+		output_video_resolutions = create_video_resolutions(output_video_resolution)
+		if args.output_video_resolution in output_video_resolutions:
+			facefusion.globals.output_video_resolution = args.output_video_resolution
+		else:
+			facefusion.globals.output_video_resolution = pack_resolution(output_video_resolution)
+	if args.output_video_fps or is_video(args.target_path):
+		facefusion.globals.output_video_fps = normalize_fps(args.output_video_fps) or detect_video_fps(args.target_path)
+	facefusion.globals.skip_audio = args.skip_audio
+	# frame processors
+	available_frame_processors = list_directory('facefusion/processors/frame/modules')
+	facefusion.globals.frame_processors = args.frame_processors
+	for frame_processor in available_frame_processors:
+		frame_processor_module = load_frame_processor_module(frame_processor)
+		frame_processor_module.apply_args(program)
+	# uis
+	facefusion.globals.ui_layouts = args.ui_layouts
+
+
+def run(program : ArgumentParser) -> None:
+	apply_args(program)
+	logger.init(facefusion.globals.log_level)
+	if facefusion.globals.system_memory_limit > 0:
+		limit_system_memory(facefusion.globals.system_memory_limit)
+	if not pre_check() or not content_analyser.pre_check() or not face_analyser.pre_check() or not face_masker.pre_check():
+		return
+	for frame_processor_module in get_frame_processors_modules(facefusion.globals.frame_processors):
+		if not frame_processor_module.pre_check():
+			return
+	if facefusion.globals.headless:
+		conditional_process()
+	else:
+		import facefusion.uis.core as ui
+
+		for ui_layout in ui.get_ui_layouts_modules(facefusion.globals.ui_layouts):
+			if not ui_layout.pre_check():
+				return
+		ui.launch()
+
+
+def destroy() -> None:
+	process_manager.stop()
+	while process_manager.is_processing():
+		sleep(0.5)
+	if facefusion.globals.target_path:
+		clear_temp(facefusion.globals.target_path)
+	sys.exit(0)
+
+
+def pre_check() -> bool:
+	if sys.version_info < (3, 9):
+		logger.error(wording.get('python_not_supported').format(version = '3.9'), __name__.upper())
+		return False
+	if not shutil.which('ffmpeg'):
+		logger.error(wording.get('ffmpeg_not_installed'), __name__.upper())
+		return False
+	return True
+
+
+def conditional_process() -> None:
+	start_time = time()
+	for frame_processor_module in get_frame_processors_modules(facefusion.globals.frame_processors):
+		while not frame_processor_module.post_check():
+			logger.disable()
+			sleep(0.5)
+		logger.enable()
+		if not frame_processor_module.pre_process('output'):
+			return
+	conditional_append_reference_faces()
+	if is_image(facefusion.globals.target_path):
+		process_image(start_time)
+	if is_video(facefusion.globals.target_path):
+		process_video(start_time)
+
+
+def conditional_append_reference_faces() -> None:
+	if 'reference' in facefusion.globals.face_selector_mode and not get_reference_faces():
+		source_frames = read_static_images(facefusion.globals.source_paths)
+		source_face = get_average_face(source_frames)
+		if is_video(facefusion.globals.target_path):
+			reference_frame = get_video_frame(facefusion.globals.target_path, facefusion.globals.reference_frame_number)
+		else:
+			reference_frame = read_image(facefusion.globals.target_path)
+		reference_face = get_one_face(reference_frame, facefusion.globals.reference_face_position)
+		append_reference_face('origin', reference_face)
+		if source_face and reference_face:
+			for frame_processor_module in get_frame_processors_modules(facefusion.globals.frame_processors):
+				abstract_reference_frame = frame_processor_module.get_reference_frame(source_face, reference_face, reference_frame)
+				if numpy.any(abstract_reference_frame):
+					reference_frame = abstract_reference_frame
+					reference_face = get_one_face(reference_frame, facefusion.globals.reference_face_position)
+					append_reference_face(frame_processor_module.__name__, reference_face)
+
+
+def process_image(start_time : float) -> None:
+	normed_output_path = normalize_output_path(facefusion.globals.target_path, facefusion.globals.output_path)
+	if analyse_image(facefusion.globals.target_path):
+		return
+	# copy image
+	process_manager.start()
+	temp_image_resolution = pack_resolution(restrict_image_resolution(facefusion.globals.target_path, unpack_resolution(facefusion.globals.output_image_resolution)))
+	logger.info(wording.get('copying_image').format(resolution = temp_image_resolution), __name__.upper())
+	if copy_image(facefusion.globals.target_path, normed_output_path, temp_image_resolution):
+		logger.debug(wording.get('copying_image_succeed'), __name__.upper())
+	else:
+		logger.error(wording.get('copying_image_failed'), __name__.upper())
+		return
+	# process image
+	for frame_processor_module in get_frame_processors_modules(facefusion.globals.frame_processors):
+		logger.info(wording.get('processing'), frame_processor_module.NAME)
+		frame_processor_module.process_image(facefusion.globals.source_paths, normed_output_path, normed_output_path)
+		frame_processor_module.post_process()
+	if is_process_stopping():
+		return
+	# finalize image
+	logger.info(wording.get('finalizing_image').format(resolution = facefusion.globals.output_image_resolution), __name__.upper())
+	if finalize_image(normed_output_path, facefusion.globals.output_image_resolution):
+		logger.debug(wording.get('finalizing_image_succeed'), __name__.upper())
+	else:
+		logger.warn(wording.get('finalizing_image_skipped'), __name__.upper())
+	# validate image
+	if is_image(normed_output_path):
+		seconds = '{:.2f}'.format((time() - start_time) % 60)
+		logger.info(wording.get('processing_image_succeed').format(seconds = seconds), __name__.upper())
+		conditional_log_statistics()
+	else:
+		logger.error(wording.get('processing_image_failed'), __name__.upper())
+	process_manager.end()
+
+
+def process_video(start_time : float) -> None:
+	normed_output_path = normalize_output_path(facefusion.globals.target_path, facefusion.globals.output_path)
+	if analyse_video(facefusion.globals.target_path, facefusion.globals.trim_frame_start, facefusion.globals.trim_frame_end):
+		return
+	# clear temp
+	logger.debug(wording.get('clearing_temp'), __name__.upper())
+	clear_temp(facefusion.globals.target_path)
+	# create temp
+	logger.debug(wording.get('creating_temp'), __name__.upper())
+	create_temp(facefusion.globals.target_path)
+	# extract frames
+	process_manager.start()
+	temp_video_resolution = pack_resolution(restrict_video_resolution(facefusion.globals.target_path, unpack_resolution(facefusion.globals.output_video_resolution)))
+	temp_video_fps = restrict_video_fps(facefusion.globals.target_path, facefusion.globals.output_video_fps)
+	logger.info(wording.get('extracting_frames').format(resolution = temp_video_resolution, fps = temp_video_fps), __name__.upper())
+	if extract_frames(facefusion.globals.target_path, temp_video_resolution, temp_video_fps):
+		logger.debug(wording.get('extracting_frames_succeed'), __name__.upper())
+	else:
+		if is_process_stopping():
+			return
+		logger.error(wording.get('extracting_frames_failed'), __name__.upper())
+		return
+	# process frames
+	temp_frame_paths = get_temp_frame_paths(facefusion.globals.target_path)
+	if temp_frame_paths:
+		for frame_processor_module in get_frame_processors_modules(facefusion.globals.frame_processors):
+			logger.info(wording.get('processing'), frame_processor_module.NAME)
+			frame_processor_module.process_video(facefusion.globals.source_paths, temp_frame_paths)
+			frame_processor_module.post_process()
+		if is_process_stopping():
+			return
+	else:
+		logger.error(wording.get('temp_frames_not_found'), __name__.upper())
+		return
+	# merge video
+	logger.info(wording.get('merging_video').format(resolution = facefusion.globals.output_video_resolution, fps = facefusion.globals.output_video_fps), __name__.upper())
+	if merge_video(facefusion.globals.target_path, facefusion.globals.output_video_resolution, facefusion.globals.output_video_fps):
+		logger.debug(wording.get('merging_video_succeed'), __name__.upper())
+	else:
+		if is_process_stopping():
+			return
+		logger.error(wording.get('merging_video_failed'), __name__.upper())
+		return
+	# handle audio
+	if facefusion.globals.skip_audio:
+		logger.info(wording.get('skipping_audio'), __name__.upper())
+		move_temp(facefusion.globals.target_path, normed_output_path)
+	else:
+		if 'lip_syncer' in facefusion.globals.frame_processors:
+			source_audio_path = get_first(filter_audio_paths(facefusion.globals.source_paths))
+			if source_audio_path and replace_audio(facefusion.globals.target_path, source_audio_path, normed_output_path):
+				logger.debug(wording.get('restoring_audio_succeed'), __name__.upper())
+			else:
+				if is_process_stopping():
+					return
+				logger.warn(wording.get('restoring_audio_skipped'), __name__.upper())
+				move_temp(facefusion.globals.target_path, normed_output_path)
+		else:
+			if restore_audio(facefusion.globals.target_path, normed_output_path, facefusion.globals.output_video_fps):
+				logger.debug(wording.get('restoring_audio_succeed'), __name__.upper())
+			else:
+				if is_process_stopping():
+					return
+				logger.warn(wording.get('restoring_audio_skipped'), __name__.upper())
+				move_temp(facefusion.globals.target_path, normed_output_path)
+	# clear temp
+	logger.debug(wording.get('clearing_temp'), __name__.upper())
+	clear_temp(facefusion.globals.target_path)
+	# validate video
+	if is_video(normed_output_path):
+		seconds = '{:.2f}'.format((time() - start_time))
+		logger.info(wording.get('processing_video_succeed').format(seconds = seconds), __name__.upper())
+		conditional_log_statistics()
+	else:
+		logger.error(wording.get('processing_video_failed'), __name__.upper())
+	process_manager.end()
+
+
+def is_process_stopping() -> bool:
+	if process_manager.is_stopping():
+		process_manager.end()
+		logger.info(wording.get('processing_stopped'), __name__.upper())
+	return process_manager.is_pending()

facefusion/download.py

@@ -0,0 +1,52 @@
+import os
+import subprocess
+import platform
+import ssl
+import urllib.request
+from typing import List
+from concurrent.futures import ThreadPoolExecutor
+from functools import lru_cache
+from tqdm import tqdm
+
+import facefusion.globals
+from facefusion import wording
+from facefusion.filesystem import is_file
+
+if platform.system().lower() == 'darwin':
+	ssl._create_default_https_context = ssl._create_unverified_context
+
+
+def conditional_download(download_directory_path : str, urls : List[str]) -> None:
+	with ThreadPoolExecutor() as executor:
+		for url in urls:
+			executor.submit(get_download_size, url)
+	for url in urls:
+		download_file_path = os.path.join(download_directory_path, os.path.basename(url))
+		initial_size = os.path.getsize(download_file_path) if is_file(download_file_path) else 0
+		download_size = get_download_size(url)
+		if initial_size < download_size:
+			with tqdm(total = download_size, initial = initial_size, desc = wording.get('downloading'), unit = 'B', unit_scale = True, unit_divisor = 1024, ascii = ' =', disable = facefusion.globals.log_level in [ 'warn', 'error' ]) as progress:
+				subprocess.Popen([ 'curl', '--create-dirs', '--silent', '--insecure', '--location', '--continue-at', '-', '--output', download_file_path, url ])
+				current_size = initial_size
+				while current_size < download_size:
+					if is_file(download_file_path):
+						current_size = os.path.getsize(download_file_path)
+						progress.update(current_size - progress.n)
+		if download_size and not is_download_done(url, download_file_path):
+			os.remove(download_file_path)
+			conditional_download(download_directory_path, [ url ])
+
+
+@lru_cache(maxsize = None)
+def get_download_size(url : str) -> int:
+	try:
+		response = urllib.request.urlopen(url, timeout = 10)
+		return int(response.getheader('Content-Length'))
+	except (OSError, ValueError):
+		return 0
+
+
+def is_download_done(url : str, file_path : str) -> bool:
+	if is_file(file_path):
+		return get_download_size(url) == os.path.getsize(file_path)
+	return False

facefusion/execution.py

@@ -0,0 +1,97 @@
+from typing import List, Any
+from functools import lru_cache
+import subprocess
+import xml.etree.ElementTree as ElementTree
+import onnxruntime
+
+from facefusion.typing import ExecutionDevice, ValueAndUnit
+
+
+def encode_execution_providers(execution_providers : List[str]) -> List[str]:
+	return [ execution_provider.replace('ExecutionProvider', '').lower() for execution_provider in execution_providers ]
+
+
+def decode_execution_providers(execution_providers: List[str]) -> List[str]:
+	available_execution_providers = onnxruntime.get_available_providers()
+	encoded_execution_providers = encode_execution_providers(available_execution_providers)
+
+	return [ execution_provider for execution_provider, encoded_execution_provider in zip(available_execution_providers, encoded_execution_providers) if any(execution_provider in encoded_execution_provider for execution_provider in execution_providers) ]
+
+
+def apply_execution_provider_options(execution_providers: List[str]) -> List[Any]:
+	execution_providers_with_options : List[Any] = []
+
+	for execution_provider in execution_providers:
+		if execution_provider == 'CUDAExecutionProvider':
+			execution_providers_with_options.append((execution_provider,
+			{
+				'cudnn_conv_algo_search': 'EXHAUSTIVE' if use_exhaustive() else 'DEFAULT'
+			}))
+		else:
+			execution_providers_with_options.append(execution_provider)
+	return execution_providers_with_options
+
+
+def use_exhaustive() -> bool:
+	execution_devices = detect_static_execution_devices()
+	product_names = ('GeForce GTX 1630', 'GeForce GTX 1650', 'GeForce GTX 1660')
+
+	return any(execution_device.get('product').get('name').startswith(product_names) for execution_device in execution_devices)
+
+
+def run_nvidia_smi() -> subprocess.Popen[bytes]:
+	commands = [ 'nvidia-smi', '--query', '--xml-format' ]
+	return subprocess.Popen(commands, stdout = subprocess.PIPE)
+
+
+@lru_cache(maxsize = None)
+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.find('driver_version').text,
+			'framework':
+			{
+				'name': 'CUDA',
+				'version': root_element.find('cuda_version').text,
+			},
+			'product':
+			{
+				'vendor': 'NVIDIA',
+				'name': gpu_element.find('product_name').text.replace('NVIDIA ', ''),
+				'architecture': gpu_element.find('product_architecture').text,
+			},
+			'video_memory':
+			{
+				'total': create_value_and_unit(gpu_element.find('fb_memory_usage/total').text),
+				'free': create_value_and_unit(gpu_element.find('fb_memory_usage/free').text)
+			},
+			'utilization':
+			{
+				'gpu': create_value_and_unit(gpu_element.find('utilization/gpu_util').text),
+				'memory': create_value_and_unit(gpu_element.find('utilization/memory_util').text)
+			}
+		})
+	return execution_devices
+
+
+def create_value_and_unit(text : str) -> ValueAndUnit:
+	value, unit = text.split()
+	value_and_unit : ValueAndUnit =\
+	{
+		'value': value,
+		'unit': unit
+	}
+
+	return value_and_unit

facefusion/face_analyser.py

@@ -0,0 +1,550 @@
+from typing import Any, Optional, List, Tuple
+from time import sleep
+import threading
+import cv2
+import numpy
+import onnxruntime
+
+import facefusion.globals
+from facefusion import process_manager
+from facefusion.common_helper import get_first
+from facefusion.face_helper import warp_face_by_face_landmark_5, warp_face_by_translation, create_static_anchors, distance_to_face_landmark_5, distance_to_bounding_box, convert_face_landmark_68_to_5, apply_nms, categorize_age, categorize_gender
+from facefusion.face_store import get_static_faces, set_static_faces
+from facefusion.execution import apply_execution_provider_options
+from facefusion.download import conditional_download
+from facefusion.filesystem import resolve_relative_path
+from facefusion.typing import VisionFrame, Face, FaceSet, FaceAnalyserOrder, FaceAnalyserAge, FaceAnalyserGender, ModelSet, BoundingBox, FaceLandmarkSet, FaceLandmark5, FaceLandmark68, Score, FaceScoreSet, Embedding
+from facefusion.vision import resize_frame_resolution, unpack_resolution
+
+FACE_ANALYSER = None
+THREAD_SEMAPHORE : threading.Semaphore = threading.Semaphore()
+THREAD_LOCK : threading.Lock = threading.Lock()
+MODELS : ModelSet =\
+{
+	'face_detector_retinaface':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/retinaface_10g.onnx',
+		'path': resolve_relative_path('../.assets/models/retinaface_10g.onnx')
+	},
+	'face_detector_scrfd':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/scrfd_2.5g.onnx',
+		'path': resolve_relative_path('../.assets/models/scrfd_2.5g.onnx')
+	},
+	'face_detector_yoloface':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/yoloface_8n.onnx',
+		'path': resolve_relative_path('../.assets/models/yoloface_8n.onnx')
+	},
+	'face_detector_yunet':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/yunet_2023mar.onnx',
+		'path': resolve_relative_path('../.assets/models/yunet_2023mar.onnx')
+	},
+	'face_recognizer_arcface_blendswap':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/arcface_w600k_r50.onnx',
+		'path': resolve_relative_path('../.assets/models/arcface_w600k_r50.onnx')
+	},
+	'face_recognizer_arcface_inswapper':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/arcface_w600k_r50.onnx',
+		'path': resolve_relative_path('../.assets/models/arcface_w600k_r50.onnx')
+	},
+	'face_recognizer_arcface_simswap':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/arcface_simswap.onnx',
+		'path': resolve_relative_path('../.assets/models/arcface_simswap.onnx')
+	},
+	'face_recognizer_arcface_uniface':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/arcface_w600k_r50.onnx',
+		'path': resolve_relative_path('../.assets/models/arcface_w600k_r50.onnx')
+	},
+	'face_landmarker':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/2dfan4.onnx',
+		'path': resolve_relative_path('../.assets/models/2dfan4.onnx')
+	},
+	'gender_age':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/gender_age.onnx',
+		'path': resolve_relative_path('../.assets/models/gender_age.onnx')
+	}
+}
+
+
+def get_face_analyser() -> Any:
+	global FACE_ANALYSER
+
+	face_detectors = {}
+	with THREAD_LOCK:
+		while process_manager.is_checking():
+			sleep(0.5)
+		if FACE_ANALYSER is None:
+			if facefusion.globals.face_detector_model in [ 'many', 'retinaface' ]:
+				face_detector = onnxruntime.InferenceSession(MODELS.get('face_detector_retinaface').get('path'), providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+				face_detectors['retinaface'] = face_detector
+			if facefusion.globals.face_detector_model in [ 'many', 'scrfd' ]:
+				face_detector = onnxruntime.InferenceSession(MODELS.get('face_detector_scrfd').get('path'), providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+				face_detectors['scrfd'] = face_detector
+			if facefusion.globals.face_detector_model in [ 'many', 'yoloface' ]:
+				face_detector = onnxruntime.InferenceSession(MODELS.get('face_detector_yoloface').get('path'), providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+				face_detectors['yoloface'] = face_detector
+			if facefusion.globals.face_detector_model in [ 'yunet' ]:
+				face_detector = cv2.FaceDetectorYN.create(MODELS.get('face_detector_yunet').get('path'), '', (0, 0))
+				face_detectors['yunet'] = face_detector
+			if facefusion.globals.face_recognizer_model == 'arcface_blendswap':
+				face_recognizer = onnxruntime.InferenceSession(MODELS.get('face_recognizer_arcface_blendswap').get('path'), providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+			if facefusion.globals.face_recognizer_model == 'arcface_inswapper':
+				face_recognizer = onnxruntime.InferenceSession(MODELS.get('face_recognizer_arcface_inswapper').get('path'), providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+			if facefusion.globals.face_recognizer_model == 'arcface_simswap':
+				face_recognizer = onnxruntime.InferenceSession(MODELS.get('face_recognizer_arcface_simswap').get('path'), providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+			if facefusion.globals.face_recognizer_model == 'arcface_uniface':
+				face_recognizer = onnxruntime.InferenceSession(MODELS.get('face_recognizer_arcface_uniface').get('path'), providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+			face_landmarker = onnxruntime.InferenceSession(MODELS.get('face_landmarker').get('path'), providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+			gender_age = onnxruntime.InferenceSession(MODELS.get('gender_age').get('path'), providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+			FACE_ANALYSER =\
+			{
+				'face_detectors': face_detectors,
+				'face_recognizer': face_recognizer,
+				'face_landmarker': face_landmarker,
+				'gender_age': gender_age
+			}
+	return FACE_ANALYSER
+
+
+def clear_face_analyser() -> Any:
+	global FACE_ANALYSER
+
+	FACE_ANALYSER = None
+
+
+def pre_check() -> bool:
+	if not facefusion.globals.skip_download:
+		download_directory_path = resolve_relative_path('../.assets/models')
+		model_urls =\
+		[
+			MODELS.get('face_landmarker').get('url'),
+			MODELS.get('gender_age').get('url')
+		]
+
+		if facefusion.globals.face_detector_model in [ 'many', 'retinaface' ]:
+			model_urls.append(MODELS.get('face_detector_retinaface').get('url'))
+		if facefusion.globals.face_detector_model in [ 'many', 'scrfd' ]:
+			model_urls.append(MODELS.get('face_detector_scrfd').get('url'))
+		if facefusion.globals.face_detector_model in [ 'many', 'yoloface' ]:
+			model_urls.append(MODELS.get('face_detector_yoloface').get('url'))
+		if facefusion.globals.face_detector_model in [ 'yunet' ]:
+			model_urls.append(MODELS.get('face_detector_yunet').get('url'))
+		if facefusion.globals.face_recognizer_model == 'arcface_blendswap':
+			model_urls.append(MODELS.get('face_recognizer_arcface_blendswap').get('url'))
+		if facefusion.globals.face_recognizer_model == 'arcface_inswapper':
+			model_urls.append(MODELS.get('face_recognizer_arcface_inswapper').get('url'))
+		if facefusion.globals.face_recognizer_model == 'arcface_simswap':
+			model_urls.append(MODELS.get('face_recognizer_arcface_simswap').get('url'))
+		if facefusion.globals.face_recognizer_model == 'arcface_uniface':
+			model_urls.append(MODELS.get('face_recognizer_arcface_uniface').get('url'))
+		process_manager.check()
+		conditional_download(download_directory_path, model_urls)
+		process_manager.end()
+	return True
+
+
+def detect_with_retinaface(vision_frame : VisionFrame, face_detector_size : str) -> Tuple[List[BoundingBox], List[FaceLandmark5], List[Score]]:
+	face_detector = get_face_analyser().get('face_detectors').get('retinaface')
+	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
+	temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height))
+	ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0]
+	ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1]
+	feature_strides = [ 8, 16, 32 ]
+	feature_map_channel = 3
+	anchor_total = 2
+	bounding_box_list = []
+	face_landmark_5_list = []
+	score_list = []
+
+	detect_vision_frame = prepare_detect_frame(temp_vision_frame, face_detector_size)
+	with THREAD_SEMAPHORE:
+		detections = face_detector.run(None,
+		{
+			face_detector.get_inputs()[0].name: detect_vision_frame
+		})
+	for index, feature_stride in enumerate(feature_strides):
+		keep_indices = numpy.where(detections[index] >= facefusion.globals.face_detector_score)[0]
+		if keep_indices.any():
+			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)
+			bounding_box_raw = detections[index + feature_map_channel] * feature_stride
+			face_landmark_5_raw = detections[index + feature_map_channel * 2] * feature_stride
+			for bounding_box in distance_to_bounding_box(anchors, bounding_box_raw)[keep_indices]:
+				bounding_box_list.append(numpy.array(
+				[
+					bounding_box[0] * ratio_width,
+					bounding_box[1] * ratio_height,
+					bounding_box[2] * ratio_width,
+					bounding_box[3] * ratio_height
+				]))
+			for face_landmark_5 in distance_to_face_landmark_5(anchors, face_landmark_5_raw)[keep_indices]:
+				face_landmark_5_list.append(face_landmark_5 * [ ratio_width, ratio_height ])
+			for score in detections[index][keep_indices]:
+				score_list.append(score[0])
+	return bounding_box_list, face_landmark_5_list, score_list
+
+
+def detect_with_scrfd(vision_frame : VisionFrame, face_detector_size : str) -> Tuple[List[BoundingBox], List[FaceLandmark5], List[Score]]:
+	face_detector = get_face_analyser().get('face_detectors').get('scrfd')
+	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
+	temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height))
+	ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0]
+	ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1]
+	feature_strides = [ 8, 16, 32 ]
+	feature_map_channel = 3
+	anchor_total = 2
+	bounding_box_list = []
+	face_landmark_5_list = []
+	score_list = []
+
+	detect_vision_frame = prepare_detect_frame(temp_vision_frame, face_detector_size)
+	with THREAD_SEMAPHORE:
+		detections = face_detector.run(None,
+		{
+			face_detector.get_inputs()[0].name: detect_vision_frame
+		})
+	for index, feature_stride in enumerate(feature_strides):
+		keep_indices = numpy.where(detections[index] >= facefusion.globals.face_detector_score)[0]
+		if keep_indices.any():
+			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)
+			bounding_box_raw = detections[index + feature_map_channel] * feature_stride
+			face_landmark_5_raw = detections[index + feature_map_channel * 2] * feature_stride
+			for bounding_box in distance_to_bounding_box(anchors, bounding_box_raw)[keep_indices]:
+				bounding_box_list.append(numpy.array(
+				[
+					bounding_box[0] * ratio_width,
+					bounding_box[1] * ratio_height,
+					bounding_box[2] * ratio_width,
+					bounding_box[3] * ratio_height
+				]))
+			for face_landmark_5 in distance_to_face_landmark_5(anchors, face_landmark_5_raw)[keep_indices]:
+				face_landmark_5_list.append(face_landmark_5 * [ ratio_width, ratio_height ])
+			for score in detections[index][keep_indices]:
+				score_list.append(score[0])
+	return bounding_box_list, face_landmark_5_list, score_list
+
+
+def detect_with_yoloface(vision_frame : VisionFrame, face_detector_size : str) -> Tuple[List[BoundingBox], List[FaceLandmark5], List[Score]]:
+	face_detector = get_face_analyser().get('face_detectors').get('yoloface')
+	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
+	temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height))
+	ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0]
+	ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1]
+	bounding_box_list = []
+	face_landmark_5_list = []
+	score_list = []
+
+	detect_vision_frame = prepare_detect_frame(temp_vision_frame, face_detector_size)
+	with THREAD_SEMAPHORE:
+		detections = face_detector.run(None,
+		{
+			face_detector.get_inputs()[0].name: detect_vision_frame
+		})
+	detections = numpy.squeeze(detections).T
+	bounding_box_raw, score_raw, face_landmark_5_raw = numpy.split(detections, [ 4, 5 ], axis = 1)
+	keep_indices = numpy.where(score_raw > facefusion.globals.face_detector_score)[0]
+	if keep_indices.any():
+		bounding_box_raw, face_landmark_5_raw, score_raw = bounding_box_raw[keep_indices], face_landmark_5_raw[keep_indices], score_raw[keep_indices]
+		for bounding_box in bounding_box_raw:
+			bounding_box_list.append(numpy.array(
+			[
+				(bounding_box[0] - bounding_box[2] / 2) * ratio_width,
+				(bounding_box[1] - bounding_box[3] / 2) * ratio_height,
+				(bounding_box[0] + bounding_box[2] / 2) * ratio_width,
+				(bounding_box[1] + bounding_box[3] / 2) * ratio_height
+			]))
+		face_landmark_5_raw[:, 0::3] = (face_landmark_5_raw[:, 0::3]) * ratio_width
+		face_landmark_5_raw[:, 1::3] = (face_landmark_5_raw[:, 1::3]) * ratio_height
+		for face_landmark_5 in face_landmark_5_raw:
+			face_landmark_5_list.append(numpy.array(face_landmark_5.reshape(-1, 3)[:, :2]))
+		score_list = score_raw.ravel().tolist()
+	return bounding_box_list, face_landmark_5_list, score_list
+
+
+def detect_with_yunet(vision_frame : VisionFrame, face_detector_size : str) -> Tuple[List[BoundingBox], List[FaceLandmark5], List[Score]]:
+	face_detector = get_face_analyser().get('face_detectors').get('yunet')
+	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
+	temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height))
+	ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0]
+	ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1]
+	bounding_box_list = []
+	face_landmark_5_list = []
+	score_list = []
+
+	face_detector.setInputSize((temp_vision_frame.shape[1], temp_vision_frame.shape[0]))
+	face_detector.setScoreThreshold(facefusion.globals.face_detector_score)
+	with THREAD_SEMAPHORE:
+		_, detections = face_detector.detect(temp_vision_frame)
+	if numpy.any(detections):
+		for detection in detections:
+			bounding_box_list.append(numpy.array(
+			[
+				detection[0] * ratio_width,
+				detection[1] * ratio_height,
+				(detection[0] + detection[2]) * ratio_width,
+				(detection[1] + detection[3]) * ratio_height
+			]))
+			face_landmark_5_list.append(detection[4:14].reshape((5, 2)) * [ ratio_width, ratio_height ])
+			score_list.append(detection[14])
+	return bounding_box_list, face_landmark_5_list, score_list
+
+
+def prepare_detect_frame(temp_vision_frame : VisionFrame, face_detector_size : str) -> VisionFrame:
+	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
+	detect_vision_frame = numpy.zeros((face_detector_height, face_detector_width, 3))
+	detect_vision_frame[:temp_vision_frame.shape[0], :temp_vision_frame.shape[1], :] = temp_vision_frame
+	detect_vision_frame = (detect_vision_frame - 127.5) / 128.0
+	detect_vision_frame = numpy.expand_dims(detect_vision_frame.transpose(2, 0, 1), axis = 0).astype(numpy.float32)
+	return detect_vision_frame
+
+
+def create_faces(vision_frame : VisionFrame, bounding_box_list : List[BoundingBox], face_landmark_5_list : List[FaceLandmark5], score_list : List[Score]) -> List[Face]:
+	faces = []
+	if facefusion.globals.face_detector_score > 0:
+		sort_indices = numpy.argsort(-numpy.array(score_list))
+		bounding_box_list = [ bounding_box_list[index] for index in sort_indices ]
+		face_landmark_5_list = [face_landmark_5_list[index] for index in sort_indices]
+		score_list = [ score_list[index] for index in sort_indices ]
+		iou_threshold = 0.1 if facefusion.globals.face_detector_model == 'many' else 0.4
+		keep_indices = apply_nms(bounding_box_list, iou_threshold)
+		for index in keep_indices:
+			bounding_box = bounding_box_list[index]
+			face_landmark_5_68 = face_landmark_5_list[index]
+			face_landmark_68 = None
+			face_landmark_68_score = 0.0
+			if facefusion.globals.face_landmarker_score > 0:
+				face_landmark_68, face_landmark_68_score = detect_face_landmark_68(vision_frame, bounding_box)
+				if face_landmark_68_score > facefusion.globals.face_landmarker_score:
+					face_landmark_5_68 = convert_face_landmark_68_to_5(face_landmark_68)
+			landmarks : FaceLandmarkSet =\
+			{
+				'5': face_landmark_5_list[index],
+				'5/68': face_landmark_5_68,
+				'68': face_landmark_68
+			}
+			scores : FaceScoreSet = \
+			{
+				'detector': score_list[index],
+				'landmarker': face_landmark_68_score
+			}
+			embedding, normed_embedding = calc_embedding(vision_frame, landmarks.get('5/68'))
+			gender, age = detect_gender_age(vision_frame, bounding_box)
+			faces.append(Face(
+				bounding_box = bounding_box,
+				landmarks = landmarks,
+				scores = scores,
+				embedding = embedding,
+				normed_embedding = normed_embedding,
+				gender = gender,
+				age = age
+			))
+	return faces
+
+
+def calc_embedding(temp_vision_frame : VisionFrame, face_landmark_5 : FaceLandmark5) -> Tuple[Embedding, Embedding]:
+	face_recognizer = get_face_analyser().get('face_recognizer')
+	crop_vision_frame, matrix = warp_face_by_face_landmark_5(temp_vision_frame, face_landmark_5, 'arcface_112_v2', (112, 112))
+	crop_vision_frame = crop_vision_frame / 127.5 - 1
+	crop_vision_frame = crop_vision_frame[:, :, ::-1].transpose(2, 0, 1).astype(numpy.float32)
+	crop_vision_frame = numpy.expand_dims(crop_vision_frame, axis = 0)
+	embedding = face_recognizer.run(None,
+	{
+		face_recognizer.get_inputs()[0].name: crop_vision_frame
+	})[0]
+	embedding = embedding.ravel()
+	normed_embedding = embedding / numpy.linalg.norm(embedding)
+	return embedding, normed_embedding
+
+
+def detect_face_landmark_68(temp_vision_frame : VisionFrame, bounding_box : BoundingBox) -> Tuple[FaceLandmark68, Score]:
+	face_landmarker = get_face_analyser().get('face_landmarker')
+	scale = 195 / numpy.subtract(bounding_box[2:], bounding_box[:2]).max()
+	translation = (256 - numpy.add(bounding_box[2:], bounding_box[:2]) * scale) * 0.5
+	crop_vision_frame, affine_matrix = warp_face_by_translation(temp_vision_frame, translation, scale, (256, 256))
+	crop_vision_frame = cv2.cvtColor(crop_vision_frame, cv2.COLOR_RGB2Lab)
+	if numpy.mean(crop_vision_frame[:, :, 0]) < 30:
+		crop_vision_frame[:, :, 0] = cv2.createCLAHE(clipLimit = 2).apply(crop_vision_frame[:, :, 0])
+	crop_vision_frame = cv2.cvtColor(crop_vision_frame, cv2.COLOR_Lab2RGB)
+	crop_vision_frame = crop_vision_frame.transpose(2, 0, 1).astype(numpy.float32) / 255.0
+	face_landmark_68, face_heatmap = face_landmarker.run(None,
+	{
+		face_landmarker.get_inputs()[0].name: [ crop_vision_frame ]
+	})
+	face_landmark_68 = face_landmark_68[:, :, :2][0] / 64
+	face_landmark_68 = face_landmark_68.reshape(1, -1, 2) * 256
+	face_landmark_68 = cv2.transform(face_landmark_68, cv2.invertAffineTransform(affine_matrix))
+	face_landmark_68 = face_landmark_68.reshape(-1, 2)
+	face_landmark_68_score = numpy.amax(face_heatmap, axis = (2, 3))
+	face_landmark_68_score = numpy.mean(face_landmark_68_score)
+	return face_landmark_68, face_landmark_68_score
+
+
+def detect_gender_age(temp_vision_frame : VisionFrame, bounding_box : BoundingBox) -> Tuple[int, int]:
+	gender_age = get_face_analyser().get('gender_age')
+	bounding_box = bounding_box.reshape(2, -1)
+	scale = 64 / numpy.subtract(*bounding_box[::-1]).max()
+	translation = 48 - bounding_box.sum(axis = 0) * scale * 0.5
+	crop_vision_frame, affine_matrix = warp_face_by_translation(temp_vision_frame, translation, scale, (96, 96))
+	crop_vision_frame = crop_vision_frame[:, :, ::-1].transpose(2, 0, 1).astype(numpy.float32)
+	crop_vision_frame = numpy.expand_dims(crop_vision_frame, axis = 0)
+	prediction = gender_age.run(None,
+	{
+		gender_age.get_inputs()[0].name: crop_vision_frame
+	})[0][0]
+	gender = int(numpy.argmax(prediction[:2]))
+	age = int(numpy.round(prediction[2] * 100))
+	return gender, age
+
+
+def get_one_face(vision_frame : VisionFrame, position : int = 0) -> Optional[Face]:
+	many_faces = get_many_faces(vision_frame)
+	if many_faces:
+		try:
+			return many_faces[position]
+		except IndexError:
+			return many_faces[-1]
+	return None
+
+
+def get_average_face(vision_frames : List[VisionFrame], position : int = 0) -> Optional[Face]:
+	average_face = None
+	faces = []
+	embedding_list = []
+	normed_embedding_list = []
+
+	for vision_frame in vision_frames:
+		face = get_one_face(vision_frame, position)
+		if face:
+			faces.append(face)
+			embedding_list.append(face.embedding)
+			normed_embedding_list.append(face.normed_embedding)
+	if faces:
+		first_face = get_first(faces)
+		average_face = Face(
+			bounding_box = first_face.bounding_box,
+			landmarks = first_face.landmarks,
+			scores = first_face.scores,
+			embedding = numpy.mean(embedding_list, axis = 0),
+			normed_embedding = numpy.mean(normed_embedding_list, axis = 0),
+			gender = first_face.gender,
+			age = first_face.age
+		)
+	return average_face
+
+
+def get_many_faces(vision_frame : VisionFrame) -> List[Face]:
+	faces = []
+	try:
+		faces_cache = get_static_faces(vision_frame)
+		if faces_cache:
+			faces = faces_cache
+		else:
+			bounding_box_list = []
+			face_landmark_5_list = []
+			score_list = []
+
+			if facefusion.globals.face_detector_model in [ 'many', 'retinaface']:
+				bounding_box_list_retinaface, face_landmark_5_list_retinaface, score_list_retinaface = detect_with_retinaface(vision_frame, facefusion.globals.face_detector_size)
+				bounding_box_list.extend(bounding_box_list_retinaface)
+				face_landmark_5_list.extend(face_landmark_5_list_retinaface)
+				score_list.extend(score_list_retinaface)
+			if facefusion.globals.face_detector_model in [ 'many', 'scrfd' ]:
+				bounding_box_list_scrfd, face_landmark_5_list_scrfd, score_list_scrfd = detect_with_scrfd(vision_frame, facefusion.globals.face_detector_size)
+				bounding_box_list.extend(bounding_box_list_scrfd)
+				face_landmark_5_list.extend(face_landmark_5_list_scrfd)
+				score_list.extend(score_list_scrfd)
+			if facefusion.globals.face_detector_model in [ 'many', 'yoloface' ]:
+				bounding_box_list_yoloface, face_landmark_5_list_yoloface, score_list_yoloface = detect_with_yoloface(vision_frame, facefusion.globals.face_detector_size)
+				bounding_box_list.extend(bounding_box_list_yoloface)
+				face_landmark_5_list.extend(face_landmark_5_list_yoloface)
+				score_list.extend(score_list_yoloface)
+			if facefusion.globals.face_detector_model in [ 'yunet' ]:
+				bounding_box_list_yunet, face_landmark_5_list_yunet, score_list_yunet = detect_with_yunet(vision_frame, facefusion.globals.face_detector_size)
+				bounding_box_list.extend(bounding_box_list_yunet)
+				face_landmark_5_list.extend(face_landmark_5_list_yunet)
+				score_list.extend(score_list_yunet)
+			if bounding_box_list and face_landmark_5_list and score_list:
+				faces = create_faces(vision_frame, bounding_box_list, face_landmark_5_list, score_list)
+			if faces:
+				set_static_faces(vision_frame, faces)
+		if facefusion.globals.face_analyser_order:
+			faces = sort_by_order(faces, facefusion.globals.face_analyser_order)
+		if facefusion.globals.face_analyser_age:
+			faces = filter_by_age(faces, facefusion.globals.face_analyser_age)
+		if facefusion.globals.face_analyser_gender:
+			faces = filter_by_gender(faces, facefusion.globals.face_analyser_gender)
+	except (AttributeError, ValueError):
+		pass
+	return faces
+
+
+def find_similar_faces(reference_faces : FaceSet, vision_frame : VisionFrame, face_distance : float) -> List[Face]:
+	similar_faces : List[Face] = []
+	many_faces = get_many_faces(vision_frame)
+
+	if reference_faces:
+		for reference_set in reference_faces:
+			if not similar_faces:
+				for reference_face in reference_faces[reference_set]:
+					for face in many_faces:
+						if compare_faces(face, reference_face, face_distance):
+							similar_faces.append(face)
+	return similar_faces
+
+
+def compare_faces(face : Face, reference_face : Face, face_distance : float) -> bool:
+	current_face_distance = calc_face_distance(face, reference_face)
+	return current_face_distance < face_distance
+
+
+def calc_face_distance(face : Face, reference_face : Face) -> float:
+	if hasattr(face, 'normed_embedding') and hasattr(reference_face, 'normed_embedding'):
+		return 1 - numpy.dot(face.normed_embedding, reference_face.normed_embedding)
+	return 0
+
+
+def sort_by_order(faces : List[Face], order : FaceAnalyserOrder) -> List[Face]:
+	if order == 'left-right':
+		return sorted(faces, key = lambda face: face.bounding_box[0])
+	if order == 'right-left':
+		return sorted(faces, key = lambda face: face.bounding_box[0], reverse = True)
+	if order == 'top-bottom':
+		return sorted(faces, key = lambda face: face.bounding_box[1])
+	if order == 'bottom-top':
+		return sorted(faces, key = lambda face: face.bounding_box[1], reverse = True)
+	if order == 'small-large':
+		return sorted(faces, key = lambda face: (face.bounding_box[2] - face.bounding_box[0]) * (face.bounding_box[3] - face.bounding_box[1]))
+	if order == 'large-small':
+		return sorted(faces, key = lambda face: (face.bounding_box[2] - face.bounding_box[0]) * (face.bounding_box[3] - face.bounding_box[1]), reverse = True)
+	if order == 'best-worst':
+		return sorted(faces, key = lambda face: face.scores.get('detector'), reverse = True)
+	if order == 'worst-best':
+		return sorted(faces, key = lambda face: face.scores.get('detector'))
+	return faces
+
+
+def filter_by_age(faces : List[Face], age : FaceAnalyserAge) -> List[Face]:
+	filter_faces = []
+	for face in faces:
+		if categorize_age(face.age) == age:
+			filter_faces.append(face)
+	return filter_faces
+
+
+def filter_by_gender(faces : List[Face], gender : FaceAnalyserGender) -> List[Face]:
+	filter_faces = []
+	for face in faces:
+		if categorize_gender(face.gender) == gender:
+			filter_faces.append(face)
+	return filter_faces

facefusion/face_helper.py

@@ -0,0 +1,164 @@
+from typing import Any, Tuple, List
+from cv2.typing import Size
+from functools import lru_cache
+import cv2
+import numpy
+
+from facefusion.typing import BoundingBox, FaceLandmark5, FaceLandmark68, VisionFrame, Mask, Matrix, Translation, WarpTemplate, WarpTemplateSet, FaceAnalyserAge, FaceAnalyserGender
+
+WARP_TEMPLATES : WarpTemplateSet =\
+{
+	'arcface_112_v1': numpy.array(
+	[
+		[ 0.35473214, 0.45658929 ],
+		[ 0.64526786, 0.45658929 ],
+		[ 0.50000000, 0.61154464 ],
+		[ 0.37913393, 0.77687500 ],
+		[ 0.62086607, 0.77687500 ]
+	]),
+	'arcface_112_v2': numpy.array(
+	[
+		[ 0.34191607, 0.46157411 ],
+		[ 0.65653393, 0.45983393 ],
+		[ 0.50022500, 0.64050536 ],
+		[ 0.37097589, 0.82469196 ],
+		[ 0.63151696, 0.82325089 ]
+	]),
+	'arcface_128_v2': numpy.array(
+	[
+		[ 0.36167656, 0.40387734 ],
+		[ 0.63696719, 0.40235469 ],
+		[ 0.50019687, 0.56044219 ],
+		[ 0.38710391, 0.72160547 ],
+		[ 0.61507734, 0.72034453 ]
+	]),
+	'ffhq_512': numpy.array(
+	[
+		[ 0.37691676, 0.46864664 ],
+		[ 0.62285697, 0.46912813 ],
+		[ 0.50123859, 0.61331904 ],
+		[ 0.39308822, 0.72541100 ],
+		[ 0.61150205, 0.72490465 ]
+	])
+}
+
+
+def warp_face_by_face_landmark_5(temp_vision_frame : VisionFrame, face_landmark_5 : FaceLandmark5, warp_template : WarpTemplate, crop_size : Size) -> Tuple[VisionFrame, Matrix]:
+	normed_warp_template = WARP_TEMPLATES.get(warp_template) * crop_size
+	affine_matrix = cv2.estimateAffinePartial2D(face_landmark_5, normed_warp_template, method = cv2.RANSAC, ransacReprojThreshold = 100)[0]
+	crop_vision_frame = cv2.warpAffine(temp_vision_frame, affine_matrix, crop_size, borderMode = cv2.BORDER_REPLICATE, flags = cv2.INTER_AREA)
+	return crop_vision_frame, affine_matrix
+
+
+def warp_face_by_bounding_box(temp_vision_frame : VisionFrame, bounding_box : BoundingBox, crop_size : Size) -> Tuple[VisionFrame, Matrix]:
+	source_points = numpy.array([ [ bounding_box[0], bounding_box[1] ], [bounding_box[2], bounding_box[1] ], [ bounding_box[0], bounding_box[3] ] ], dtype = numpy.float32)
+	target_points = numpy.array([ [ 0, 0 ], [ crop_size[0], 0 ], [ 0, crop_size[1] ] ], dtype = numpy.float32)
+	affine_matrix = cv2.getAffineTransform(source_points, target_points)
+	if bounding_box[2] - bounding_box[0] > crop_size[0] or bounding_box[3] - bounding_box[1] > crop_size[1]:
+		interpolation_method = cv2.INTER_AREA
+	else:
+		interpolation_method = cv2.INTER_LINEAR
+	crop_vision_frame = cv2.warpAffine(temp_vision_frame, affine_matrix, crop_size, flags = interpolation_method)
+	return crop_vision_frame, affine_matrix
+
+
+def warp_face_by_translation(temp_vision_frame : VisionFrame, translation : Translation, scale : float, crop_size : Size) -> Tuple[VisionFrame, Matrix]:
+	affine_matrix = numpy.array([ [ scale, 0, translation[0] ], [ 0, scale, translation[1] ] ])
+	crop_vision_frame = cv2.warpAffine(temp_vision_frame, affine_matrix, crop_size)
+	return crop_vision_frame, affine_matrix
+
+
+def paste_back(temp_vision_frame : VisionFrame, crop_vision_frame : VisionFrame, crop_mask : Mask, affine_matrix : Matrix) -> VisionFrame:
+	inverse_matrix = cv2.invertAffineTransform(affine_matrix)
+	temp_size = temp_vision_frame.shape[:2][::-1]
+	inverse_mask = cv2.warpAffine(crop_mask, inverse_matrix, temp_size).clip(0, 1)
+	inverse_vision_frame = cv2.warpAffine(crop_vision_frame, inverse_matrix, temp_size, borderMode = cv2.BORDER_REPLICATE)
+	paste_vision_frame = temp_vision_frame.copy()
+	paste_vision_frame[:, :, 0] = inverse_mask * inverse_vision_frame[:, :, 0] + (1 - inverse_mask) * temp_vision_frame[:, :, 0]
+	paste_vision_frame[:, :, 1] = inverse_mask * inverse_vision_frame[:, :, 1] + (1 - inverse_mask) * temp_vision_frame[:, :, 1]
+	paste_vision_frame[:, :, 2] = inverse_mask * inverse_vision_frame[:, :, 2] + (1 - inverse_mask) * temp_vision_frame[:, :, 2]
+	return paste_vision_frame
+
+
+@lru_cache(maxsize = None)
+def create_static_anchors(feature_stride : int, anchor_total : int, stride_height : int, stride_width : int) -> numpy.ndarray[Any, Any]:
+	y, x = numpy.mgrid[:stride_height, :stride_width][::-1]
+	anchors = numpy.stack((y, x), axis = -1)
+	anchors = (anchors * feature_stride).reshape((-1, 2))
+	anchors = numpy.stack([ anchors ] * anchor_total, axis = 1).reshape((-1, 2))
+	return anchors
+
+
+def create_bounding_box_from_face_landmark_68(face_landmark_68 : FaceLandmark68) -> BoundingBox:
+	min_x, min_y = numpy.min(face_landmark_68, axis = 0)
+	max_x, max_y = numpy.max(face_landmark_68, axis = 0)
+	bounding_box = numpy.array([ min_x, min_y, max_x, max_y ]).astype(numpy.int16)
+	return bounding_box
+
+
+def distance_to_bounding_box(points : numpy.ndarray[Any, Any], distance : numpy.ndarray[Any, Any]) -> BoundingBox:
+	x1 = points[:, 0] - distance[:, 0]
+	y1 = points[:, 1] - distance[:, 1]
+	x2 = points[:, 0] + distance[:, 2]
+	y2 = points[:, 1] + distance[:, 3]
+	bounding_box = numpy.column_stack([ x1, y1, x2, y2 ])
+	return bounding_box
+
+
+def distance_to_face_landmark_5(points : numpy.ndarray[Any, Any], distance : numpy.ndarray[Any, Any]) -> FaceLandmark5:
+	x = points[:, 0::2] + distance[:, 0::2]
+	y = points[:, 1::2] + distance[:, 1::2]
+	face_landmark_5 = numpy.stack((x, y), axis = -1)
+	return face_landmark_5
+
+
+def convert_face_landmark_68_to_5(landmark_68 : FaceLandmark68) -> FaceLandmark5:
+	face_landmark_5 = numpy.array(
+	[
+		numpy.mean(landmark_68[36:42], axis = 0),
+		numpy.mean(landmark_68[42:48], axis = 0),
+		landmark_68[30],
+		landmark_68[48],
+		landmark_68[54]
+	])
+	return face_landmark_5
+
+
+def apply_nms(bounding_box_list : List[BoundingBox], iou_threshold : float) -> List[int]:
+	keep_indices = []
+	dimension_list = numpy.reshape(bounding_box_list, (-1, 4))
+	x1 = dimension_list[:, 0]
+	y1 = dimension_list[:, 1]
+	x2 = dimension_list[:, 2]
+	y2 = dimension_list[:, 3]
+	areas = (x2 - x1 + 1) * (y2 - y1 + 1)
+	indices = numpy.arange(len(bounding_box_list))
+	while indices.size > 0:
+		index = indices[0]
+		remain_indices = indices[1:]
+		keep_indices.append(index)
+		xx1 = numpy.maximum(x1[index], x1[remain_indices])
+		yy1 = numpy.maximum(y1[index], y1[remain_indices])
+		xx2 = numpy.minimum(x2[index], x2[remain_indices])
+		yy2 = numpy.minimum(y2[index], y2[remain_indices])
+		width = numpy.maximum(0, xx2 - xx1 + 1)
+		height = numpy.maximum(0, yy2 - yy1 + 1)
+		iou = width * height / (areas[index] + areas[remain_indices] - width * height)
+		indices = indices[numpy.where(iou <= iou_threshold)[0] + 1]
+	return keep_indices
+
+
+def categorize_age(age : int) -> FaceAnalyserAge:
+	if age < 13:
+		return 'child'
+	elif age < 19:
+		return 'teen'
+	elif age < 60:
+		return 'adult'
+	return 'senior'
+
+
+def categorize_gender(gender : int) -> FaceAnalyserGender:
+	if gender == 0:
+		return 'female'
+	return 'male'

facefusion/face_masker.py

@@ -0,0 +1,146 @@
+from typing import Any, Dict, List
+from cv2.typing import Size
+from functools import lru_cache
+from time import sleep
+import threading
+import cv2
+import numpy
+import onnxruntime
+
+import facefusion.globals
+from facefusion import process_manager
+from facefusion.typing import FaceLandmark68, VisionFrame, Mask, Padding, FaceMaskRegion, ModelSet
+from facefusion.execution import apply_execution_provider_options
+from facefusion.filesystem import resolve_relative_path
+from facefusion.download import conditional_download
+
+FACE_OCCLUDER = None
+FACE_PARSER = None
+THREAD_LOCK : threading.Lock = threading.Lock()
+MODELS : ModelSet =\
+{
+	'face_occluder':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/face_occluder.onnx',
+		'path': resolve_relative_path('../.assets/models/face_occluder.onnx')
+	},
+	'face_parser':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/face_parser.onnx',
+		'path': resolve_relative_path('../.assets/models/face_parser.onnx')
+	}
+}
+FACE_MASK_REGIONS : Dict[FaceMaskRegion, int] =\
+{
+	'skin': 1,
+	'left-eyebrow': 2,
+	'right-eyebrow': 3,
+	'left-eye': 4,
+	'right-eye': 5,
+	'eye-glasses': 6,
+	'nose': 10,
+	'mouth': 11,
+	'upper-lip': 12,
+	'lower-lip': 13
+}
+
+
+def get_face_occluder() -> Any:
+	global FACE_OCCLUDER
+
+	with THREAD_LOCK:
+		if FACE_OCCLUDER is None:
+			model_path = MODELS.get('face_occluder').get('path')
+			FACE_OCCLUDER = onnxruntime.InferenceSession(model_path, providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+	return FACE_OCCLUDER
+
+
+def get_face_parser() -> Any:
+	global FACE_PARSER
+
+	with THREAD_LOCK:
+		while process_manager.is_checking():
+			sleep(0.5)
+		if FACE_PARSER is None:
+			model_path = MODELS.get('face_parser').get('path')
+			FACE_PARSER = onnxruntime.InferenceSession(model_path, providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+	return FACE_PARSER
+
+
+def clear_face_occluder() -> None:
+	global FACE_OCCLUDER
+
+	FACE_OCCLUDER = None
+
+
+def clear_face_parser() -> None:
+	global FACE_PARSER
+
+	FACE_PARSER = None
+
+
+def pre_check() -> bool:
+	if not facefusion.globals.skip_download:
+		download_directory_path = resolve_relative_path('../.assets/models')
+		model_urls =\
+		[
+			MODELS.get('face_occluder').get('url'),
+			MODELS.get('face_parser').get('url'),
+		]
+		process_manager.check()
+		conditional_download(download_directory_path, model_urls)
+		process_manager.end()
+	return True
+
+
+@lru_cache(maxsize = None)
+def create_static_box_mask(crop_size : Size, face_mask_blur : float, face_mask_padding : Padding) -> Mask:
+	blur_amount = int(crop_size[0] * 0.5 * face_mask_blur)
+	blur_area = max(blur_amount // 2, 1)
+	box_mask : Mask = numpy.ones(crop_size, numpy.float32)
+	box_mask[:max(blur_area, int(crop_size[1] * face_mask_padding[0] / 100)), :] = 0
+	box_mask[-max(blur_area, int(crop_size[1] * face_mask_padding[2] / 100)):, :] = 0
+	box_mask[:, :max(blur_area, int(crop_size[0] * face_mask_padding[3] / 100))] = 0
+	box_mask[:, -max(blur_area, int(crop_size[0] * face_mask_padding[1] / 100)):] = 0
+	if blur_amount > 0:
+		box_mask = cv2.GaussianBlur(box_mask, (0, 0), blur_amount * 0.25)
+	return box_mask
+
+
+def create_occlusion_mask(crop_vision_frame : VisionFrame) -> Mask:
+	face_occluder = get_face_occluder()
+	prepare_vision_frame = cv2.resize(crop_vision_frame, face_occluder.get_inputs()[0].shape[1:3][::-1])
+	prepare_vision_frame = numpy.expand_dims(prepare_vision_frame, axis = 0).astype(numpy.float32) / 255
+	prepare_vision_frame = prepare_vision_frame.transpose(0, 1, 2, 3)
+	occlusion_mask : Mask = face_occluder.run(None,
+	{
+		face_occluder.get_inputs()[0].name: prepare_vision_frame
+	})[0][0]
+	occlusion_mask = occlusion_mask.transpose(0, 1, 2).clip(0, 1).astype(numpy.float32)
+	occlusion_mask = cv2.resize(occlusion_mask, crop_vision_frame.shape[:2][::-1])
+	occlusion_mask = (cv2.GaussianBlur(occlusion_mask.clip(0, 1), (0, 0), 5).clip(0.5, 1) - 0.5) * 2
+	return occlusion_mask
+
+
+def create_region_mask(crop_vision_frame : VisionFrame, face_mask_regions : List[FaceMaskRegion]) -> Mask:
+	face_parser = get_face_parser()
+	prepare_vision_frame = cv2.flip(cv2.resize(crop_vision_frame, (512, 512)), 1)
+	prepare_vision_frame = numpy.expand_dims(prepare_vision_frame, axis = 0).astype(numpy.float32)[:, :, ::-1] / 127.5 - 1
+	prepare_vision_frame = prepare_vision_frame.transpose(0, 3, 1, 2)
+	region_mask : Mask = face_parser.run(None,
+	{
+		face_parser.get_inputs()[0].name: prepare_vision_frame
+	})[0][0]
+	region_mask = numpy.isin(region_mask.argmax(0), [ FACE_MASK_REGIONS[region] for region in face_mask_regions ])
+	region_mask = cv2.resize(region_mask.astype(numpy.float32), crop_vision_frame.shape[:2][::-1])
+	region_mask = (cv2.GaussianBlur(region_mask.clip(0, 1), (0, 0), 5).clip(0.5, 1) - 0.5) * 2
+	return region_mask
+
+
+def create_mouth_mask(face_landmark_68 : FaceLandmark68) -> Mask:
+	convex_hull = cv2.convexHull(face_landmark_68[numpy.r_[3:14, 31:36]].astype(numpy.int32))
+	mouth_mask : Mask = numpy.zeros((512, 512), dtype = numpy.float32)
+	mouth_mask = cv2.fillConvexPoly(mouth_mask, convex_hull, 1.0)
+	mouth_mask = cv2.erode(mouth_mask.clip(0, 1), numpy.ones((21, 3)))
+	mouth_mask = cv2.GaussianBlur(mouth_mask, (0, 0), sigmaX = 1, sigmaY = 15)
+	return mouth_mask

facefusion/face_store.py

@@ -0,0 +1,48 @@
+from typing import Optional, List
+import hashlib
+import numpy
+
+from facefusion.typing import VisionFrame, Face, FaceStore, FaceSet
+
+FACE_STORE: FaceStore =\
+{
+	'static_faces': {},
+	'reference_faces': {}
+}
+
+
+def get_static_faces(vision_frame : VisionFrame) -> Optional[List[Face]]:
+	frame_hash = create_frame_hash(vision_frame)
+	if frame_hash in FACE_STORE['static_faces']:
+		return FACE_STORE['static_faces'][frame_hash]
+	return None
+
+
+def set_static_faces(vision_frame : VisionFrame, faces : List[Face]) -> None:
+	frame_hash = create_frame_hash(vision_frame)
+	if frame_hash:
+		FACE_STORE['static_faces'][frame_hash] = faces
+
+
+def clear_static_faces() -> None:
+	FACE_STORE['static_faces'] = {}
+
+
+def create_frame_hash(vision_frame : VisionFrame) -> Optional[str]:
+	return hashlib.sha1(vision_frame.tobytes()).hexdigest() if numpy.any(vision_frame) else None
+
+
+def get_reference_faces() -> Optional[FaceSet]:
+	if FACE_STORE['reference_faces']:
+		return FACE_STORE['reference_faces']
+	return None
+
+
+def append_reference_face(name : str, face : Face) -> None:
+	if name not in FACE_STORE['reference_faces']:
+		FACE_STORE['reference_faces'][name] = []
+	FACE_STORE['reference_faces'][name].append(face)
+
+
+def clear_reference_faces() -> None:
+	FACE_STORE['reference_faces'] = {}

facefusion/ffmpeg.py

@@ -0,0 +1,138 @@
+from typing import List, Optional
+import subprocess
+import filetype
+
+import facefusion.globals
+from facefusion import process_manager
+from facefusion.typing import OutputVideoPreset, Fps, AudioBuffer
+from facefusion.filesystem import get_temp_frames_pattern, get_temp_output_video_path
+
+
+def run_ffmpeg(args : List[str]) -> bool:
+	commands = [ 'ffmpeg', '-hide_banner', '-loglevel', 'quiet' ]
+	commands.extend(args)
+	process = subprocess.Popen(commands, stdout = subprocess.PIPE)
+
+	while process_manager.is_processing():
+		try:
+			return process.wait(timeout = 0.5) == 0
+		except subprocess.TimeoutExpired:
+			continue
+	return process.returncode == 0
+
+
+def open_ffmpeg(args : List[str]) -> subprocess.Popen[bytes]:
+	commands = [ 'ffmpeg', '-hide_banner', '-loglevel', 'quiet' ]
+	commands.extend(args)
+	return subprocess.Popen(commands, stdin = subprocess.PIPE, stdout = subprocess.PIPE)
+
+
+def extract_frames(target_path : str, temp_video_resolution : str, temp_video_fps : Fps) -> bool:
+	trim_frame_start = facefusion.globals.trim_frame_start
+	trim_frame_end = facefusion.globals.trim_frame_end
+	temp_frames_pattern = get_temp_frames_pattern(target_path, '%04d')
+	commands = [ '-hwaccel', 'auto', '-i', target_path, '-q:v', '0' ]
+
+	if trim_frame_start is not None and trim_frame_end is not None:
+		commands.extend([ '-vf', 'trim=start_frame=' + str(trim_frame_start) + ':end_frame=' + str(trim_frame_end) + ',scale=' + str(temp_video_resolution) + ',fps=' + str(temp_video_fps) ])
+	elif trim_frame_start is not None:
+		commands.extend([ '-vf', 'trim=start_frame=' + str(trim_frame_start) + ',scale=' + str(temp_video_resolution) + ',fps=' + str(temp_video_fps) ])
+	elif trim_frame_end is not None:
+		commands.extend([ '-vf', 'trim=end_frame=' + str(trim_frame_end) + ',scale=' + str(temp_video_resolution) + ',fps=' + str(temp_video_fps) ])
+	else:
+		commands.extend([ '-vf', 'scale=' + str(temp_video_resolution) + ',fps=' + str(temp_video_fps) ])
+	commands.extend([ '-vsync', '0', temp_frames_pattern ])
+	return run_ffmpeg(commands)
+
+
+def merge_video(target_path : str, output_video_resolution : str, output_video_fps : Fps) -> bool:
+	temp_output_video_path = get_temp_output_video_path(target_path)
+	temp_frames_pattern = get_temp_frames_pattern(target_path, '%04d')
+	commands = [ '-hwaccel', 'auto', '-s', str(output_video_resolution), '-r', str(output_video_fps), '-i', temp_frames_pattern, '-c:v', facefusion.globals.output_video_encoder ]
+
+	if facefusion.globals.output_video_encoder in [ 'libx264', 'libx265' ]:
+		output_video_compression = round(51 - (facefusion.globals.output_video_quality * 0.51))
+		commands.extend([ '-crf', str(output_video_compression), '-preset', facefusion.globals.output_video_preset ])
+	if facefusion.globals.output_video_encoder in [ 'libvpx-vp9' ]:
+		output_video_compression = round(63 - (facefusion.globals.output_video_quality * 0.63))
+		commands.extend([ '-crf', str(output_video_compression) ])
+	if facefusion.globals.output_video_encoder in [ 'h264_nvenc', 'hevc_nvenc' ]:
+		output_video_compression = round(51 - (facefusion.globals.output_video_quality * 0.51))
+		commands.extend([ '-cq', str(output_video_compression), '-preset', map_nvenc_preset(facefusion.globals.output_video_preset) ])
+	if facefusion.globals.output_video_encoder in [ 'h264_amf', 'hevc_amf' ]:
+		output_video_compression = round(51 - (facefusion.globals.output_video_quality * 0.51))
+		commands.extend([ '-qp_i', str(output_video_compression), '-qp_p', str(output_video_compression), '-quality', map_amf_preset(facefusion.globals.output_video_preset) ])
+	commands.extend([ '-pix_fmt', 'yuv420p', '-colorspace', 'bt709', '-y', temp_output_video_path ])
+	return run_ffmpeg(commands)
+
+
+def copy_image(target_path : str, output_path : str, temp_image_resolution : str) -> bool:
+	is_webp = filetype.guess_mime(target_path) == 'image/webp'
+	temp_image_compression = 100 if is_webp else 0
+	commands = [ '-i', target_path, '-q:v', str(temp_image_compression), '-vf', 'scale=' + str(temp_image_resolution), '-y', output_path ]
+	return run_ffmpeg(commands)
+
+
+def finalize_image(output_path : str, output_image_resolution : str) -> bool:
+	output_image_compression = round(31 - (facefusion.globals.output_image_quality * 0.31))
+	commands = [ '-i', output_path, '-q:v', str(output_image_compression), '-vf', 'scale=' + str(output_image_resolution), '-y', output_path ]
+	return run_ffmpeg(commands)
+
+
+def read_audio_buffer(target_path : str, sample_rate : int, total_channel : int) -> Optional[AudioBuffer]:
+	commands = [ '-i', target_path, '-vn', '-f', 's16le', '-acodec', 'pcm_s16le', '-ar', str(sample_rate), '-ac', str(total_channel), '-' ]
+	process = open_ffmpeg(commands)
+	audio_buffer, _ = process.communicate()
+	if process.returncode == 0:
+		return audio_buffer
+	return None
+
+
+def restore_audio(target_path : str, output_path : str, output_video_fps : Fps) -> bool:
+	trim_frame_start = facefusion.globals.trim_frame_start
+	trim_frame_end = facefusion.globals.trim_frame_end
+	temp_output_video_path = get_temp_output_video_path(target_path)
+	commands = [ '-hwaccel', 'auto', '-i', temp_output_video_path ]
+
+	if trim_frame_start is not None:
+		start_time = trim_frame_start / output_video_fps
+		commands.extend([ '-ss', str(start_time) ])
+	if trim_frame_end is not None:
+		end_time = trim_frame_end / output_video_fps
+		commands.extend([ '-to', str(end_time) ])
+	commands.extend([ '-i', target_path, '-c', 'copy', '-map', '0:v:0', '-map', '1:a:0', '-shortest', '-y', output_path ])
+	return run_ffmpeg(commands)
+
+
+def replace_audio(target_path : str, audio_path : str, output_path : str) -> bool:
+	temp_output_path = get_temp_output_video_path(target_path)
+	commands = [ '-hwaccel', 'auto', '-i', temp_output_path, '-i', audio_path, '-c:v', 'copy', '-af', 'apad', '-shortest', '-map', '0:v:0', '-map', '1:a:0', '-y', output_path ]
+	return run_ffmpeg(commands)
+
+
+def map_nvenc_preset(output_video_preset : OutputVideoPreset) -> Optional[str]:
+	if output_video_preset in [ 'ultrafast', 'superfast', 'veryfast' ]:
+		return 'p1'
+	if output_video_preset == 'faster':
+		return 'p2'
+	if output_video_preset == 'fast':
+		return 'p3'
+	if output_video_preset == 'medium':
+		return 'p4'
+	if output_video_preset == 'slow':
+		return 'p5'
+	if output_video_preset == 'slower':
+		return 'p6'
+	if output_video_preset == 'veryslow':
+		return 'p7'
+	return None
+
+
+def map_amf_preset(output_video_preset : OutputVideoPreset) -> Optional[str]:
+	if output_video_preset in [ 'ultrafast', 'superfast', 'veryfast' ]:
+		return 'speed'
+	if output_video_preset in [ 'faster', 'fast', 'medium' ]:
+		return 'balanced'
+	if output_video_preset in [ 'slow', 'slower', 'veryslow' ]:
+		return 'quality'
+	return None

facefusion/filesystem.py

@@ -0,0 +1,109 @@
+from typing import List, Optional
+import glob
+import os
+import shutil
+import tempfile
+import filetype
+from pathlib import Path
+
+import facefusion.globals
+
+TEMP_DIRECTORY_PATH = os.path.join(tempfile.gettempdir(), 'facefusion')
+TEMP_OUTPUT_VIDEO_NAME = 'temp.mp4'
+
+
+def get_temp_frame_paths(target_path : str) -> List[str]:
+	temp_frames_pattern = get_temp_frames_pattern(target_path, '*')
+	return sorted(glob.glob(temp_frames_pattern))
+
+
+def get_temp_frames_pattern(target_path : str, temp_frame_prefix : str) -> str:
+	temp_directory_path = get_temp_directory_path(target_path)
+	return os.path.join(temp_directory_path, temp_frame_prefix + '.' + facefusion.globals.temp_frame_format)
+
+
+def get_temp_directory_path(target_path : str) -> str:
+	target_name, _ = os.path.splitext(os.path.basename(target_path))
+	return os.path.join(TEMP_DIRECTORY_PATH, target_name)
+
+
+def get_temp_output_video_path(target_path : str) -> str:
+	temp_directory_path = get_temp_directory_path(target_path)
+	return os.path.join(temp_directory_path, TEMP_OUTPUT_VIDEO_NAME)
+
+
+def create_temp(target_path : str) -> None:
+	temp_directory_path = get_temp_directory_path(target_path)
+	Path(temp_directory_path).mkdir(parents = True, exist_ok = True)
+
+
+def move_temp(target_path : str, output_path : str) -> None:
+	temp_output_video_path = get_temp_output_video_path(target_path)
+	if is_file(temp_output_video_path):
+		if is_file(output_path):
+			os.remove(output_path)
+		shutil.move(temp_output_video_path, output_path)
+
+
+def clear_temp(target_path : str) -> None:
+	temp_directory_path = get_temp_directory_path(target_path)
+	parent_directory_path = os.path.dirname(temp_directory_path)
+	if not facefusion.globals.keep_temp and is_directory(temp_directory_path):
+		shutil.rmtree(temp_directory_path, ignore_errors = True)
+	if os.path.exists(parent_directory_path) and not os.listdir(parent_directory_path):
+		os.rmdir(parent_directory_path)
+
+
+def is_file(file_path : str) -> bool:
+	return bool(file_path and os.path.isfile(file_path))
+
+
+def is_directory(directory_path : str) -> bool:
+	return bool(directory_path and os.path.isdir(directory_path))
+
+
+def is_audio(audio_path : str) -> bool:
+	return is_file(audio_path) and filetype.helpers.is_audio(audio_path)
+
+
+def has_audio(audio_paths : List[str]) -> bool:
+	if audio_paths:
+		return any(is_audio(audio_path) for audio_path in audio_paths)
+	return False
+
+
+def is_image(image_path : str) -> bool:
+	return is_file(image_path) and filetype.helpers.is_image(image_path)
+
+
+def has_image(image_paths: List[str]) -> bool:
+	if image_paths:
+		return any(is_image(image_path) for image_path in image_paths)
+	return False
+
+
+def is_video(video_path : str) -> bool:
+	return is_file(video_path) and filetype.helpers.is_video(video_path)
+
+
+def filter_audio_paths(paths : List[str]) -> List[str]:
+	if paths:
+		return [ path for path in paths if is_audio(path) ]
+	return []
+
+
+def filter_image_paths(paths : List[str]) -> List[str]:
+	if paths:
+		return [ path for path in paths if is_image(path) ]
+	return []
+
+
+def resolve_relative_path(path : str) -> str:
+	return os.path.abspath(os.path.join(os.path.dirname(__file__), path))
+
+
+def list_directory(directory_path : str) -> Optional[List[str]]:
+	if is_directory(directory_path):
+		files = os.listdir(directory_path)
+		return sorted([ Path(file).stem for file in files if not Path(file).stem.startswith(('.', '__')) ])
+	return None

facefusion/globals.py

@@ -0,0 +1,56 @@
+from typing import List, Optional
+
+from facefusion.typing import LogLevel, VideoMemoryStrategy, FaceSelectorMode, FaceAnalyserOrder, FaceAnalyserAge, FaceAnalyserGender, FaceMaskType, FaceMaskRegion, OutputVideoEncoder, OutputVideoPreset, FaceDetectorModel, FaceRecognizerModel, TempFrameFormat, Padding
+
+# general
+source_paths : Optional[List[str]] = None
+target_path : Optional[str] = None
+output_path : Optional[str] = None
+# misc
+skip_download : Optional[bool] = None
+headless : Optional[bool] = None
+log_level : Optional[LogLevel] = None
+# execution
+execution_providers : List[str] = []
+execution_thread_count : Optional[int] = None
+execution_queue_count : Optional[int] = None
+# memory
+video_memory_strategy : Optional[VideoMemoryStrategy] = None
+system_memory_limit : Optional[int] = None
+# face analyser
+face_analyser_order : Optional[FaceAnalyserOrder] = None
+face_analyser_age : Optional[FaceAnalyserAge] = None
+face_analyser_gender : Optional[FaceAnalyserGender] = None
+face_detector_model : Optional[FaceDetectorModel] = None
+face_detector_size : Optional[str] = None
+face_detector_score : Optional[float] = None
+face_landmarker_score : Optional[float] = None
+face_recognizer_model : Optional[FaceRecognizerModel] = None
+# face selector
+face_selector_mode : Optional[FaceSelectorMode] = None
+reference_face_position : Optional[int] = None
+reference_face_distance : Optional[float] = None
+reference_frame_number : Optional[int] = None
+# face mask
+face_mask_types : Optional[List[FaceMaskType]] = None
+face_mask_blur : Optional[float] = None
+face_mask_padding : Optional[Padding] = None
+face_mask_regions : Optional[List[FaceMaskRegion]] = None
+# frame extraction
+trim_frame_start : Optional[int] = None
+trim_frame_end : Optional[int] = None
+temp_frame_format : Optional[TempFrameFormat] = None
+keep_temp : Optional[bool] = None
+# output creation
+output_image_quality : Optional[int] = None
+output_image_resolution : Optional[str] = None
+output_video_encoder : Optional[OutputVideoEncoder] = None
+output_video_preset : Optional[OutputVideoPreset] = None
+output_video_quality : Optional[int] = None
+output_video_resolution : Optional[str] = None
+output_video_fps : Optional[float] = None
+skip_audio : Optional[bool] = None
+# frame processors
+frame_processors : List[str] = []
+# uis
+ui_layouts : List[str] = []

facefusion/installer.py

@@ -0,0 +1,75 @@
+from typing import Dict, Tuple
+import sys
+import os
+import platform
+import tempfile
+import subprocess
+import inquirer
+from argparse import ArgumentParser, HelpFormatter
+
+from facefusion import metadata, wording
+
+ONNXRUNTIMES : Dict[str, Tuple[str, str]] = {}
+
+if platform.system().lower() == 'darwin':
+	ONNXRUNTIMES['default'] = ('onnxruntime', '1.17.1')
+else:
+	ONNXRUNTIMES['default'] = ('onnxruntime', '1.16.3')
+	ONNXRUNTIMES['cuda-12.2'] = ('onnxruntime-gpu', '1.17.1')
+	ONNXRUNTIMES['cuda-11.8'] = ('onnxruntime-gpu', '1.16.3')
+	ONNXRUNTIMES['openvino'] = ('onnxruntime-openvino', '1.16.0')
+if platform.system().lower() == 'linux':
+	ONNXRUNTIMES['rocm-5.4.2'] = ('onnxruntime-rocm', '1.16.3')
+	ONNXRUNTIMES['rocm-5.6'] = ('onnxruntime-rocm', '1.16.3')
+if platform.system().lower() == 'windows':
+	ONNXRUNTIMES['directml'] = ('onnxruntime-directml', '1.16.0')
+
+
+def cli() -> None:
+	program = ArgumentParser(formatter_class = lambda prog: HelpFormatter(prog, max_help_position = 130))
+	program.add_argument('--onnxruntime', help = wording.get('help.install_dependency').format(dependency = 'onnxruntime'), choices = ONNXRUNTIMES.keys())
+	program.add_argument('--skip-venv', help = wording.get('help.skip_venv'), action = 'store_true')
+	program.add_argument('-v', '--version', version = metadata.get('name') + ' ' + metadata.get('version'), action = 'version')
+	run(program)
+
+
+def run(program : ArgumentParser) -> None:
+	args = program.parse_args()
+	python_id = 'cp' + str(sys.version_info.major) + str(sys.version_info.minor)
+
+	if platform.system().lower() == 'darwin':
+		os.environ['SYSTEM_VERSION_COMPAT'] = '0'
+	if not args.skip_venv:
+		os.environ['PIP_REQUIRE_VIRTUALENV'] = '1'
+	if args.onnxruntime:
+		answers =\
+		{
+			'onnxruntime': args.onnxruntime
+		}
+	else:
+		answers = inquirer.prompt(
+		[
+			inquirer.List('onnxruntime', message = wording.get('help.install_dependency').format(dependency = 'onnxruntime'), choices = list(ONNXRUNTIMES.keys()))
+		])
+	if answers:
+		onnxruntime = answers['onnxruntime']
+		onnxruntime_name, onnxruntime_version = ONNXRUNTIMES[onnxruntime]
+
+		subprocess.call([ 'pip', 'install', '-r', 'requirements.txt', '--force-reinstall' ])
+		if onnxruntime == 'rocm-5.4.2' or onnxruntime == 'rocm-5.6':
+			if python_id in [ 'cp39', 'cp310', 'cp311' ]:
+				rocm_version = onnxruntime.replace('-', '')
+				rocm_version = rocm_version.replace('.', '')
+				wheel_name = 'onnxruntime_training-' + onnxruntime_version + '+' + rocm_version + '-' + python_id + '-' + python_id + '-manylinux_2_17_x86_64.manylinux2014_x86_64.whl'
+				wheel_path = os.path.join(tempfile.gettempdir(), wheel_name)
+				wheel_url = 'https://download.onnxruntime.ai/' + wheel_name
+				subprocess.call([ 'curl', '--silent', '--location', '--continue-at', '-', '--output', wheel_path, wheel_url ])
+				subprocess.call([ 'pip', 'uninstall', wheel_path, '-y', '-q' ])
+				subprocess.call([ 'pip', 'install', wheel_path, '--force-reinstall' ])
+				os.remove(wheel_path)
+		else:
+			subprocess.call([ 'pip', 'uninstall', 'onnxruntime', onnxruntime_name, '-y', '-q' ])
+			if onnxruntime == 'cuda-12.2':
+				subprocess.call([ 'pip', 'install', onnxruntime_name + '==' + onnxruntime_version, '--extra-index-url', 'https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple', '--force-reinstall' ])
+			else:
+				subprocess.call([ 'pip', 'install', onnxruntime_name + '==' + onnxruntime_version, '--force-reinstall' ])

facefusion/logger.py

@@ -0,0 +1,47 @@
+from typing import Dict
+from logging import basicConfig, getLogger, Logger, DEBUG, INFO, WARNING, ERROR
+
+from facefusion.typing import LogLevel
+
+
+def init(log_level : LogLevel) -> None:
+	basicConfig(format = None)
+	get_package_logger().setLevel(get_log_levels()[log_level])
+
+
+def get_package_logger() -> Logger:
+	return getLogger('facefusion')
+
+
+def debug(message : str, scope : str) -> None:
+	get_package_logger().debug('[' + scope + '] ' + message)
+
+
+def info(message : str, scope : str) -> None:
+	get_package_logger().info('[' + scope + '] ' + message)
+
+
+def warn(message : str, scope : str) -> None:
+	get_package_logger().warning('[' + scope + '] ' + message)
+
+
+def error(message : str, scope : str) -> None:
+	get_package_logger().error('[' + scope + '] ' + message)
+
+
+def enable() -> None:
+	get_package_logger().disabled = False
+
+
+def disable() -> None:
+	get_package_logger().disabled = True
+
+
+def get_log_levels() -> Dict[LogLevel, int]:
+	return\
+	{
+		'error': ERROR,
+		'warn': WARNING,
+		'info': INFO,
+		'debug': DEBUG
+	}

facefusion/memory.py

@@ -0,0 +1,21 @@
+import platform
+
+if platform.system().lower() == 'windows':
+	import ctypes
+else:
+	import resource
+
+
+def limit_system_memory(system_memory_limit : int = 1) -> bool:
+	if platform.system().lower() == 'darwin':
+		system_memory_limit = system_memory_limit * (1024 ** 6)
+	else:
+		system_memory_limit = system_memory_limit * (1024 ** 3)
+	try:
+		if platform.system().lower() == '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

facefusion/metadata.py

@@ -0,0 +1,13 @@
+METADATA =\
+{
+	'name': 'FaceFusion',
+	'description': 'Next generation face swapper and enhancer',
+	'version': '2.4.1',
+	'license': 'MIT',
+	'author': 'Henry Ruhs',
+	'url': 'https://facefusion.io'
+}
+
+
+def get(key : str) -> str:
+	return METADATA[key]

facefusion/normalizer.py

@@ -0,0 +1,43 @@
+from typing import List, Optional
+import hashlib
+import os
+
+import facefusion.globals
+from facefusion.filesystem import is_directory
+from facefusion.typing import Padding, Fps
+
+
+def normalize_output_path(target_path : Optional[str], output_path : Optional[str]) -> Optional[str]:
+	if target_path and output_path:
+		target_name, target_extension = os.path.splitext(os.path.basename(target_path))
+		if is_directory(output_path):
+			output_hash = hashlib.sha1(str(facefusion.globals.__dict__).encode('utf-8')).hexdigest()[:8]
+			output_name = target_name + '-' + output_hash
+			return os.path.join(output_path, output_name + target_extension)
+		output_name, output_extension = os.path.splitext(os.path.basename(output_path))
+		output_directory_path = os.path.dirname(output_path)
+		if is_directory(output_directory_path) and output_extension:
+			return os.path.join(output_directory_path, output_name + target_extension)
+	return None
+
+
+def normalize_padding(padding : Optional[List[int]]) -> Optional[Padding]:
+	if padding and len(padding) == 1:
+		return tuple([ padding[0], padding[0], padding[0], padding[0] ]) # type: ignore[return-value]
+	if padding and len(padding) == 2:
+		return tuple([ padding[0], padding[1], padding[0], padding[1] ]) # type: ignore[return-value]
+	if padding and len(padding) == 3:
+		return tuple([ padding[0], padding[1], padding[2], padding[1] ]) # type: ignore[return-value]
+	if padding and len(padding) == 4:
+		return tuple(padding) # type: ignore[return-value]
+	return None
+
+
+def normalize_fps(fps : Optional[float]) -> Optional[Fps]:
+	if fps is not None:
+		if fps < 1.0:
+			return 1.0
+		if fps > 60.0:
+			return 60.0
+		return fps
+	return None

facefusion/process_manager.py

@@ -0,0 +1,53 @@
+from typing import Generator, List
+
+from facefusion.typing import QueuePayload, ProcessState
+
+PROCESS_STATE : ProcessState = 'pending'
+
+
+def get_process_state() -> ProcessState:
+	return PROCESS_STATE
+
+
+def set_process_state(process_state : ProcessState) -> None:
+	global PROCESS_STATE
+
+	PROCESS_STATE = process_state
+
+
+def is_checking() -> bool:
+	return get_process_state() == 'checking'
+
+
+def is_processing() -> bool:
+	return get_process_state() == 'processing'
+
+
+def is_stopping() -> bool:
+	return get_process_state() == 'stopping'
+
+
+def is_pending() -> bool:
+	return get_process_state() == 'pending'
+
+
+def check() -> None:
+	set_process_state('checking')
+
+
+def start() -> None:
+	set_process_state('processing')
+
+
+def stop() -> None:
+	set_process_state('stopping')
+
+
+def end() -> None:
+	set_process_state('pending')
+
+
+def manage(queue_payloads : List[QueuePayload]) -> Generator[QueuePayload, None, None]:
+	for query_payload in queue_payloads:
+		if is_processing():
+			yield query_payload

facefusion/processors/frame/choices.py

@@ -0,0 +1,13 @@
+from typing import List
+
+from facefusion.common_helper import create_int_range
+from facefusion.processors.frame.typings import FaceDebuggerItem, FaceEnhancerModel, FaceSwapperModel, FrameEnhancerModel, LipSyncerModel
+
+face_debugger_items : List[FaceDebuggerItem] = [ 'bounding-box', 'face-landmark-5', 'face-landmark-5/68', 'face-landmark-68', 'face-mask', 'face-detector-score', 'face-landmarker-score', 'age', 'gender' ]
+face_enhancer_models : List[FaceEnhancerModel] = [ 'codeformer', 'gfpgan_1.2', 'gfpgan_1.3', 'gfpgan_1.4', 'gpen_bfr_256', 'gpen_bfr_512', 'restoreformer_plus_plus' ]
+face_swapper_models : List[FaceSwapperModel] = [ 'blendswap_256', 'inswapper_128', 'inswapper_128_fp16', 'simswap_256', 'simswap_512_unofficial', 'uniface_256' ]
+frame_enhancer_models : List[FrameEnhancerModel] = [ 'lsdir_x4', 'nomos8k_sc_x4', 'real_esrgan_x4',  'real_esrgan_x4_fp16', 'span_kendata_x4' ]
+lip_syncer_models : List[LipSyncerModel] = [ 'wav2lip_gan' ]
+
+face_enhancer_blend_range : List[int] = create_int_range(0, 100, 1)
+frame_enhancer_blend_range : List[int] = create_int_range(0, 100, 1)

facefusion/processors/frame/core.py

@@ -0,0 +1,116 @@
+import os
+import sys
+import importlib
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from queue import Queue
+from types import ModuleType
+from typing import Any, List
+from tqdm import tqdm
+
+import facefusion.globals
+from facefusion.typing import ProcessFrames, QueuePayload
+from facefusion.execution import encode_execution_providers
+from facefusion import logger, wording
+
+FRAME_PROCESSORS_MODULES : List[ModuleType] = []
+FRAME_PROCESSORS_METHODS =\
+[
+	'get_frame_processor',
+	'clear_frame_processor',
+	'get_options',
+	'set_options',
+	'register_args',
+	'apply_args',
+	'pre_check',
+	'post_check',
+	'pre_process',
+	'post_process',
+	'get_reference_frame',
+	'process_frame',
+	'process_frames',
+	'process_image',
+	'process_video'
+]
+
+
+def load_frame_processor_module(frame_processor : str) -> Any:
+	try:
+		frame_processor_module = importlib.import_module('facefusion.processors.frame.modules.' + frame_processor)
+		for method_name in FRAME_PROCESSORS_METHODS:
+			if not hasattr(frame_processor_module, method_name):
+				raise NotImplementedError
+	except ModuleNotFoundError as exception:
+		logger.error(wording.get('frame_processor_not_loaded').format(frame_processor = frame_processor), __name__.upper())
+		logger.debug(exception.msg, __name__.upper())
+		sys.exit(1)
+	except NotImplementedError:
+		logger.error(wording.get('frame_processor_not_implemented').format(frame_processor = frame_processor), __name__.upper())
+		sys.exit(1)
+	return frame_processor_module
+
+
+def get_frame_processors_modules(frame_processors : List[str]) -> List[ModuleType]:
+	global FRAME_PROCESSORS_MODULES
+
+	if not FRAME_PROCESSORS_MODULES:
+		for frame_processor in frame_processors:
+			frame_processor_module = load_frame_processor_module(frame_processor)
+			FRAME_PROCESSORS_MODULES.append(frame_processor_module)
+	return FRAME_PROCESSORS_MODULES
+
+
+def clear_frame_processors_modules() -> None:
+	global FRAME_PROCESSORS_MODULES
+
+	for frame_processor_module in get_frame_processors_modules(facefusion.globals.frame_processors):
+		frame_processor_module.clear_frame_processor()
+	FRAME_PROCESSORS_MODULES = []
+
+
+def multi_process_frames(source_paths : List[str], temp_frame_paths : List[str], process_frames : ProcessFrames) -> None:
+	queue_payloads = create_queue_payloads(temp_frame_paths)
+	with tqdm(total = len(queue_payloads), desc = wording.get('processing'), unit = 'frame', ascii = ' =', disable = facefusion.globals.log_level in [ 'warn', 'error' ]) as progress:
+		progress.set_postfix(
+		{
+			'execution_providers': encode_execution_providers(facefusion.globals.execution_providers),
+			'execution_thread_count': facefusion.globals.execution_thread_count,
+			'execution_queue_count': facefusion.globals.execution_queue_count
+		})
+		with ThreadPoolExecutor(max_workers = facefusion.globals.execution_thread_count) as executor:
+			futures = []
+			queue : Queue[QueuePayload] = create_queue(queue_payloads)
+			queue_per_future = max(len(queue_payloads) // facefusion.globals.execution_thread_count * facefusion.globals.execution_queue_count, 1)
+			while not queue.empty():
+				future = executor.submit(process_frames, source_paths, pick_queue(queue, queue_per_future), progress.update)
+				futures.append(future)
+			for future_done in as_completed(futures):
+				future_done.result()
+
+
+def create_queue(queue_payloads : List[QueuePayload]) -> Queue[QueuePayload]:
+	queue : Queue[QueuePayload] = Queue()
+	for queue_payload in queue_payloads:
+		queue.put(queue_payload)
+	return queue
+
+
+def pick_queue(queue : Queue[QueuePayload], queue_per_future : int) -> List[QueuePayload]:
+	queues = []
+	for _ in range(queue_per_future):
+		if not queue.empty():
+			queues.append(queue.get())
+	return queues
+
+
+def create_queue_payloads(temp_frame_paths : List[str]) -> List[QueuePayload]:
+	queue_payloads = []
+	temp_frame_paths = sorted(temp_frame_paths, key = os.path.basename)
+
+	for frame_number, frame_path in enumerate(temp_frame_paths):
+		frame_payload : QueuePayload =\
+		{
+			'frame_number': frame_number,
+			'frame_path': frame_path
+		}
+		queue_payloads.append(frame_payload)
+	return queue_payloads

facefusion/processors/frame/globals.py

@@ -0,0 +1,11 @@
+from typing import List, Optional
+
+from facefusion.processors.frame.typings import FaceDebuggerItem, FaceEnhancerModel, FaceSwapperModel, FrameEnhancerModel, LipSyncerModel
+
+face_debugger_items : Optional[List[FaceDebuggerItem]] = None
+face_enhancer_model : Optional[FaceEnhancerModel] = None
+face_enhancer_blend : Optional[int] = None
+face_swapper_model : Optional[FaceSwapperModel] = None
+frame_enhancer_model : Optional[FrameEnhancerModel] = None
+frame_enhancer_blend : Optional[int] = None
+lip_syncer_model : Optional[LipSyncerModel] = None

facefusion/processors/frame/modules/face_debugger.py

@@ -0,0 +1,187 @@
+from typing import Any, List, Literal
+from argparse import ArgumentParser
+import cv2
+import numpy
+
+import facefusion.globals
+import facefusion.processors.frame.core as frame_processors
+from facefusion import config, process_manager, wording
+from facefusion.face_analyser import get_one_face, get_many_faces, find_similar_faces, clear_face_analyser
+from facefusion.face_masker import create_static_box_mask, create_occlusion_mask, create_region_mask, clear_face_occluder, clear_face_parser
+from facefusion.face_helper import warp_face_by_face_landmark_5, categorize_age, categorize_gender
+from facefusion.face_store import get_reference_faces
+from facefusion.content_analyser import clear_content_analyser
+from facefusion.typing import Face, VisionFrame, UpdateProcess, ProcessMode, QueuePayload
+from facefusion.vision import read_image, read_static_image, write_image
+from facefusion.processors.frame.typings import FaceDebuggerInputs
+from facefusion.processors.frame import globals as frame_processors_globals, choices as frame_processors_choices
+
+NAME = __name__.upper()
+
+
+def get_frame_processor() -> None:
+	pass
+
+
+def clear_frame_processor() -> None:
+	pass
+
+
+def get_options(key : Literal['model']) -> None:
+	pass
+
+
+def set_options(key : Literal['model'], value : Any) -> None:
+	pass
+
+
+def register_args(program : ArgumentParser) -> None:
+	program.add_argument('--face-debugger-items', help = wording.get('help.face_debugger_items').format(choices = ', '.join(frame_processors_choices.face_debugger_items)), default = config.get_str_list('frame_processors.face_debugger_items', 'face-landmark-5/68 face-mask'), choices = frame_processors_choices.face_debugger_items, nargs = '+', metavar = 'FACE_DEBUGGER_ITEMS')
+
+
+def apply_args(program : ArgumentParser) -> None:
+	args = program.parse_args()
+	frame_processors_globals.face_debugger_items = args.face_debugger_items
+
+
+def pre_check() -> bool:
+	return True
+
+
+def post_check() -> bool:
+	return True
+
+
+def pre_process(mode : ProcessMode) -> bool:
+	return True
+
+
+def post_process() -> None:
+	read_static_image.cache_clear()
+	if facefusion.globals.video_memory_strategy == 'strict' or facefusion.globals.video_memory_strategy == 'moderate':
+		clear_frame_processor()
+	if facefusion.globals.video_memory_strategy == 'strict':
+		clear_face_analyser()
+		clear_content_analyser()
+		clear_face_occluder()
+		clear_face_parser()
+
+
+def debug_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	primary_color = (0, 0, 255)
+	secondary_color = (0, 255, 0)
+	tertiary_color = (255, 255, 0)
+	bounding_box = target_face.bounding_box.astype(numpy.int32)
+	temp_vision_frame = temp_vision_frame.copy()
+	has_face_landmark_5_fallback = numpy.array_equal(target_face.landmarks.get('5'), target_face.landmarks.get('5/68'))
+
+	if 'bounding-box' in frame_processors_globals.face_debugger_items:
+		cv2.rectangle(temp_vision_frame, (bounding_box[0], bounding_box[1]), (bounding_box[2], bounding_box[3]), primary_color, 2)
+	if 'face-mask' in frame_processors_globals.face_debugger_items:
+		crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmarks.get('5/68'), 'arcface_128_v2', (512, 512))
+		inverse_matrix = cv2.invertAffineTransform(affine_matrix)
+		temp_size = temp_vision_frame.shape[:2][::-1]
+		crop_mask_list = []
+		if 'box' in facefusion.globals.face_mask_types:
+			box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], 0, facefusion.globals.face_mask_padding)
+			crop_mask_list.append(box_mask)
+		if 'occlusion' in facefusion.globals.face_mask_types:
+			occlusion_mask = create_occlusion_mask(crop_vision_frame)
+			crop_mask_list.append(occlusion_mask)
+		if 'region' in facefusion.globals.face_mask_types:
+			region_mask = create_region_mask(crop_vision_frame, facefusion.globals.face_mask_regions)
+			crop_mask_list.append(region_mask)
+		crop_mask = numpy.minimum.reduce(crop_mask_list).clip(0, 1)
+		crop_mask = (crop_mask * 255).astype(numpy.uint8)
+		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_vision_frame[inverse_vision_frame > 0] = 255
+		inverse_contours = cv2.findContours(inverse_vision_frame, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)[0]
+		cv2.drawContours(temp_vision_frame, inverse_contours, -1, tertiary_color if has_face_landmark_5_fallback else secondary_color, 2)
+	if 'face-landmark-5' in frame_processors_globals.face_debugger_items and numpy.any(target_face.landmarks.get('5')):
+		face_landmark_5 = target_face.landmarks.get('5').astype(numpy.int32)
+		for index in range(face_landmark_5.shape[0]):
+			cv2.circle(temp_vision_frame, (face_landmark_5[index][0], face_landmark_5[index][1]), 3, primary_color, -1)
+	if 'face-landmark-5/68' in frame_processors_globals.face_debugger_items and numpy.any(target_face.landmarks.get('5/68')):
+		face_landmark_5_68 = target_face.landmarks.get('5/68').astype(numpy.int32)
+		for index in range(face_landmark_5_68.shape[0]):
+			cv2.circle(temp_vision_frame, (face_landmark_5_68[index][0], face_landmark_5_68[index][1]), 3, tertiary_color if has_face_landmark_5_fallback else secondary_color, -1)
+	if 'face-landmark-68' in frame_processors_globals.face_debugger_items and numpy.any(target_face.landmarks.get('68')):
+		face_landmark_68 = target_face.landmarks.get('68').astype(numpy.int32)
+		for index in range(face_landmark_68.shape[0]):
+			cv2.circle(temp_vision_frame, (face_landmark_68[index][0], face_landmark_68[index][1]), 3, secondary_color, -1)
+	if bounding_box[3] - bounding_box[1] > 50 and bounding_box[2] - bounding_box[0] > 50:
+		top = bounding_box[1]
+		left = bounding_box[0] - 20
+		if 'face-detector-score' in frame_processors_globals.face_debugger_items:
+			face_score_text = str(round(target_face.scores.get('detector'), 2))
+			top = top + 20
+			cv2.putText(temp_vision_frame, face_score_text, (left, top), cv2.FONT_HERSHEY_SIMPLEX, 0.5, primary_color, 2)
+		if 'face-landmarker-score' in frame_processors_globals.face_debugger_items:
+			face_score_text = str(round(target_face.scores.get('landmarker'), 2))
+			top = top + 20
+			cv2.putText(temp_vision_frame, face_score_text, (left, top), cv2.FONT_HERSHEY_SIMPLEX, 0.5, tertiary_color if has_face_landmark_5_fallback else secondary_color, 2)
+		if 'age' in frame_processors_globals.face_debugger_items:
+			face_age_text = categorize_age(target_face.age)
+			top = top + 20
+			cv2.putText(temp_vision_frame, face_age_text, (left, top), cv2.FONT_HERSHEY_SIMPLEX, 0.5, primary_color, 2)
+		if 'gender' in frame_processors_globals.face_debugger_items:
+			face_gender_text = categorize_gender(target_face.gender)
+			top = top + 20
+			cv2.putText(temp_vision_frame, face_gender_text, (left, top), cv2.FONT_HERSHEY_SIMPLEX, 0.5, primary_color, 2)
+	return temp_vision_frame
+
+
+def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	pass
+
+
+def process_frame(inputs : FaceDebuggerInputs) -> VisionFrame:
+	reference_faces = inputs.get('reference_faces')
+	target_vision_frame = inputs.get('target_vision_frame')
+
+	if facefusion.globals.face_selector_mode == 'many':
+		many_faces = get_many_faces(target_vision_frame)
+		if many_faces:
+			for target_face in many_faces:
+				target_vision_frame = debug_face(target_face, target_vision_frame)
+	if facefusion.globals.face_selector_mode == 'one':
+		target_face = get_one_face(target_vision_frame)
+		if target_face:
+			target_vision_frame = debug_face(target_face, target_vision_frame)
+	if facefusion.globals.face_selector_mode == 'reference':
+		similar_faces = find_similar_faces(reference_faces, target_vision_frame, facefusion.globals.reference_face_distance)
+		if similar_faces:
+			for similar_face in similar_faces:
+				target_vision_frame = debug_face(similar_face, target_vision_frame)
+	return target_vision_frame
+
+
+def process_frames(source_paths : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProcess) -> None:
+	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
+
+	for queue_payload in process_manager.manage(queue_payloads):
+		target_vision_path = queue_payload['frame_path']
+		target_vision_frame = read_image(target_vision_path)
+		output_vision_frame = process_frame(
+		{
+			'reference_faces': reference_faces,
+			'target_vision_frame': target_vision_frame
+		})
+		write_image(target_vision_path, output_vision_frame)
+		update_progress()
+
+
+def process_image(source_paths : List[str], target_path : str, output_path : str) -> None:
+	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
+	target_vision_frame = read_static_image(target_path)
+	output_vision_frame = process_frame(
+	{
+		'reference_faces': reference_faces,
+		'target_vision_frame': target_vision_frame
+	})
+	write_image(output_path, output_vision_frame)
+
+
+def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
+	frame_processors.multi_process_frames(source_paths, temp_frame_paths, process_frames)

facefusion/processors/frame/modules/face_enhancer.py

@@ -0,0 +1,286 @@
+from typing import Any, List, Literal, Optional
+from argparse import ArgumentParser
+from time import sleep
+import cv2
+import threading
+import numpy
+import onnxruntime
+
+import facefusion.globals
+import facefusion.processors.frame.core as frame_processors
+from facefusion import config, process_manager, logger, wording
+from facefusion.face_analyser import get_many_faces, clear_face_analyser, find_similar_faces, get_one_face
+from facefusion.face_masker import create_static_box_mask, create_occlusion_mask, clear_face_occluder
+from facefusion.face_helper import warp_face_by_face_landmark_5, paste_back
+from facefusion.execution import apply_execution_provider_options
+from facefusion.content_analyser import clear_content_analyser
+from facefusion.face_store import get_reference_faces
+from facefusion.normalizer import normalize_output_path
+from facefusion.typing import Face, VisionFrame, UpdateProcess, ProcessMode, ModelSet, OptionsWithModel, QueuePayload
+from facefusion.common_helper import create_metavar
+from facefusion.filesystem import is_file, is_image, is_video, resolve_relative_path
+from facefusion.download import conditional_download, is_download_done
+from facefusion.vision import read_image, read_static_image, write_image
+from facefusion.processors.frame.typings import FaceEnhancerInputs
+from facefusion.processors.frame import globals as frame_processors_globals
+from facefusion.processors.frame import choices as frame_processors_choices
+
+FRAME_PROCESSOR = None
+THREAD_SEMAPHORE : threading.Semaphore = threading.Semaphore()
+THREAD_LOCK : threading.Lock = threading.Lock()
+NAME = __name__.upper()
+MODELS : ModelSet =\
+{
+	'codeformer':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/codeformer.onnx',
+		'path': resolve_relative_path('../.assets/models/codeformer.onnx'),
+		'template': 'ffhq_512',
+		'size': (512, 512)
+	},
+	'gfpgan_1.2':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/gfpgan_1.2.onnx',
+		'path': resolve_relative_path('../.assets/models/gfpgan_1.2.onnx'),
+		'template': 'ffhq_512',
+		'size': (512, 512)
+	},
+	'gfpgan_1.3':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/gfpgan_1.3.onnx',
+		'path': resolve_relative_path('../.assets/models/gfpgan_1.3.onnx'),
+		'template': 'ffhq_512',
+		'size': (512, 512)
+	},
+	'gfpgan_1.4':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/gfpgan_1.4.onnx',
+		'path': resolve_relative_path('../.assets/models/gfpgan_1.4.onnx'),
+		'template': 'ffhq_512',
+		'size': (512, 512)
+	},
+	'gpen_bfr_256':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/gpen_bfr_256.onnx',
+		'path': resolve_relative_path('../.assets/models/gpen_bfr_256.onnx'),
+		'template': 'arcface_128_v2',
+		'size': (256, 256)
+	},
+	'gpen_bfr_512':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/gpen_bfr_512.onnx',
+		'path': resolve_relative_path('../.assets/models/gpen_bfr_512.onnx'),
+		'template': 'ffhq_512',
+		'size': (512, 512)
+	},
+	'restoreformer_plus_plus':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/restoreformer_plus_plus.onnx',
+		'path': resolve_relative_path('../.assets/models/restoreformer_plus_plus.onnx'),
+		'template': 'ffhq_512',
+		'size': (512, 512)
+	}
+}
+OPTIONS : Optional[OptionsWithModel] = None
+
+
+def get_frame_processor() -> Any:
+	global FRAME_PROCESSOR
+
+	with THREAD_LOCK:
+		while process_manager.is_checking():
+			sleep(0.5)
+		if FRAME_PROCESSOR is None:
+			model_path = get_options('model').get('path')
+			FRAME_PROCESSOR = onnxruntime.InferenceSession(model_path, providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+	return FRAME_PROCESSOR
+
+
+def clear_frame_processor() -> None:
+	global FRAME_PROCESSOR
+
+	FRAME_PROCESSOR = None
+
+
+def get_options(key : Literal['model']) -> Any:
+	global OPTIONS
+
+	if OPTIONS is None:
+		OPTIONS =\
+		{
+			'model': MODELS[frame_processors_globals.face_enhancer_model]
+		}
+	return OPTIONS.get(key)
+
+
+def set_options(key : Literal['model'], value : Any) -> None:
+	global OPTIONS
+
+	OPTIONS[key] = value
+
+
+def register_args(program : ArgumentParser) -> None:
+	program.add_argument('--face-enhancer-model', help = wording.get('help.face_enhancer_model'), default = config.get_str_value('frame_processors.face_enhancer_model', 'gfpgan_1.4'), choices = frame_processors_choices.face_enhancer_models)
+	program.add_argument('--face-enhancer-blend', help = wording.get('help.face_enhancer_blend'), type = int, default = config.get_int_value('frame_processors.face_enhancer_blend', '80'), choices = frame_processors_choices.face_enhancer_blend_range, metavar = create_metavar(frame_processors_choices.face_enhancer_blend_range))
+
+
+def apply_args(program : ArgumentParser) -> None:
+	args = program.parse_args()
+	frame_processors_globals.face_enhancer_model = args.face_enhancer_model
+	frame_processors_globals.face_enhancer_blend = args.face_enhancer_blend
+
+
+def pre_check() -> bool:
+	if not facefusion.globals.skip_download:
+		download_directory_path = resolve_relative_path('../.assets/models')
+		model_url = get_options('model').get('url')
+		process_manager.check()
+		conditional_download(download_directory_path, [ model_url ])
+		process_manager.end()
+	return True
+
+
+def post_check() -> bool:
+	model_url = get_options('model').get('url')
+	model_path = get_options('model').get('path')
+	if not facefusion.globals.skip_download and not is_download_done(model_url, model_path):
+		logger.error(wording.get('model_download_not_done') + wording.get('exclamation_mark'), NAME)
+		return False
+	elif not is_file(model_path):
+		logger.error(wording.get('model_file_not_present') + wording.get('exclamation_mark'), NAME)
+		return False
+	return True
+
+
+def pre_process(mode : ProcessMode) -> bool:
+	if mode in [ 'output', 'preview' ] and not is_image(facefusion.globals.target_path) and not is_video(facefusion.globals.target_path):
+		logger.error(wording.get('select_image_or_video_target') + wording.get('exclamation_mark'), NAME)
+		return False
+	if mode == 'output' and not normalize_output_path(facefusion.globals.target_path, facefusion.globals.output_path):
+		logger.error(wording.get('select_file_or_directory_output') + wording.get('exclamation_mark'), NAME)
+		return False
+	return True
+
+
+def post_process() -> None:
+	read_static_image.cache_clear()
+	if facefusion.globals.video_memory_strategy == 'strict' or facefusion.globals.video_memory_strategy == 'moderate':
+		clear_frame_processor()
+	if facefusion.globals.video_memory_strategy == 'strict':
+		clear_face_analyser()
+		clear_content_analyser()
+		clear_face_occluder()
+
+
+def enhance_face(target_face: Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	model_template = get_options('model').get('template')
+	model_size = get_options('model').get('size')
+	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmarks.get('5/68'), model_template, model_size)
+	box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], facefusion.globals.face_mask_blur, (0, 0, 0, 0))
+	crop_mask_list =\
+	[
+		box_mask
+	]
+
+	if 'occlusion' in facefusion.globals.face_mask_types:
+		occlusion_mask = create_occlusion_mask(crop_vision_frame)
+		crop_mask_list.append(occlusion_mask)
+	crop_vision_frame = prepare_crop_frame(crop_vision_frame)
+	crop_vision_frame = apply_enhance(crop_vision_frame)
+	crop_vision_frame = normalize_crop_frame(crop_vision_frame)
+	crop_mask = numpy.minimum.reduce(crop_mask_list).clip(0, 1)
+	paste_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, crop_mask, affine_matrix)
+	temp_vision_frame = blend_frame(temp_vision_frame, paste_vision_frame)
+	return temp_vision_frame
+
+
+def apply_enhance(crop_vision_frame : VisionFrame) -> VisionFrame:
+	frame_processor = get_frame_processor()
+	frame_processor_inputs = {}
+
+	for frame_processor_input in frame_processor.get_inputs():
+		if frame_processor_input.name == 'input':
+			frame_processor_inputs[frame_processor_input.name] = crop_vision_frame
+		if frame_processor_input.name == 'weight':
+			weight = numpy.array([ 1 ], dtype = numpy.double)
+			frame_processor_inputs[frame_processor_input.name] = weight
+	with THREAD_SEMAPHORE:
+		crop_vision_frame = frame_processor.run(None, frame_processor_inputs)[0][0]
+	return crop_vision_frame
+
+
+def prepare_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+	crop_vision_frame = crop_vision_frame[:, :, ::-1] / 255.0
+	crop_vision_frame = (crop_vision_frame - 0.5) / 0.5
+	crop_vision_frame = numpy.expand_dims(crop_vision_frame.transpose(2, 0, 1), axis = 0).astype(numpy.float32)
+	return crop_vision_frame
+
+
+def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+	crop_vision_frame = numpy.clip(crop_vision_frame, -1, 1)
+	crop_vision_frame = (crop_vision_frame + 1) / 2
+	crop_vision_frame = crop_vision_frame.transpose(1, 2, 0)
+	crop_vision_frame = (crop_vision_frame * 255.0).round()
+	crop_vision_frame = crop_vision_frame.astype(numpy.uint8)[:, :, ::-1]
+	return crop_vision_frame
+
+
+def blend_frame(temp_vision_frame : VisionFrame, paste_vision_frame : VisionFrame) -> VisionFrame:
+	face_enhancer_blend = 1 - (frame_processors_globals.face_enhancer_blend / 100)
+	temp_vision_frame = cv2.addWeighted(temp_vision_frame, face_enhancer_blend, paste_vision_frame, 1 - face_enhancer_blend, 0)
+	return temp_vision_frame
+
+
+def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	return enhance_face(target_face, temp_vision_frame)
+
+
+def process_frame(inputs : FaceEnhancerInputs) -> VisionFrame:
+	reference_faces = inputs.get('reference_faces')
+	target_vision_frame = inputs.get('target_vision_frame')
+
+	if facefusion.globals.face_selector_mode == 'many':
+		many_faces = get_many_faces(target_vision_frame)
+		if many_faces:
+			for target_face in many_faces:
+				target_vision_frame = enhance_face(target_face, target_vision_frame)
+	if facefusion.globals.face_selector_mode == 'one':
+		target_face = get_one_face(target_vision_frame)
+		if target_face:
+			target_vision_frame = enhance_face(target_face, target_vision_frame)
+	if facefusion.globals.face_selector_mode == 'reference':
+		similar_faces = find_similar_faces(reference_faces, target_vision_frame, facefusion.globals.reference_face_distance)
+		if similar_faces:
+			for similar_face in similar_faces:
+				target_vision_frame = enhance_face(similar_face, target_vision_frame)
+	return target_vision_frame
+
+
+def process_frames(source_path : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProcess) -> None:
+	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
+
+	for queue_payload in process_manager.manage(queue_payloads):
+		target_vision_path = queue_payload['frame_path']
+		target_vision_frame = read_image(target_vision_path)
+		output_vision_frame = process_frame(
+		{
+			'reference_faces': reference_faces,
+			'target_vision_frame': target_vision_frame
+		})
+		write_image(target_vision_path, output_vision_frame)
+		update_progress()
+
+
+def process_image(source_path : str, target_path : str, output_path : str) -> None:
+	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
+	target_vision_frame = read_static_image(target_path)
+	output_vision_frame = process_frame(
+	{
+		'reference_faces': reference_faces,
+		'target_vision_frame': target_vision_frame
+	})
+	write_image(output_path, output_vision_frame)
+
+
+def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
+	frame_processors.multi_process_frames(None, temp_frame_paths, process_frames)

facefusion/processors/frame/modules/face_swapper.py

@@ -0,0 +1,368 @@
+from typing import Any, List, Literal, Optional
+from argparse import ArgumentParser
+from time import sleep
+import threading
+import numpy
+import onnx
+import onnxruntime
+from onnx import numpy_helper
+
+import facefusion.globals
+import facefusion.processors.frame.core as frame_processors
+from facefusion import config, process_manager, logger, wording
+from facefusion.execution import apply_execution_provider_options
+from facefusion.face_analyser import get_one_face, get_average_face, get_many_faces, find_similar_faces, clear_face_analyser
+from facefusion.face_masker import create_static_box_mask, create_occlusion_mask, create_region_mask, clear_face_occluder, clear_face_parser
+from facefusion.face_helper import warp_face_by_face_landmark_5, paste_back
+from facefusion.face_store import get_reference_faces
+from facefusion.common_helper import extract_major_version
+from facefusion.content_analyser import clear_content_analyser
+from facefusion.normalizer import normalize_output_path
+from facefusion.typing import Face, Embedding, VisionFrame, UpdateProcess, ProcessMode, ModelSet, OptionsWithModel, QueuePayload
+from facefusion.filesystem import is_file, is_image, has_image, is_video, filter_image_paths, resolve_relative_path
+from facefusion.download import conditional_download, is_download_done
+from facefusion.vision import read_image, read_static_image, read_static_images, write_image
+from facefusion.processors.frame.typings import FaceSwapperInputs
+from facefusion.processors.frame import globals as frame_processors_globals
+from facefusion.processors.frame import choices as frame_processors_choices
+
+FRAME_PROCESSOR = None
+MODEL_MATRIX = None
+THREAD_LOCK : threading.Lock = threading.Lock()
+NAME = __name__.upper()
+MODELS : ModelSet =\
+{
+	'blendswap_256':
+	{
+		'type': 'blendswap',
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/blendswap_256.onnx',
+		'path': resolve_relative_path('../.assets/models/blendswap_256.onnx'),
+		'template': 'ffhq_512',
+		'size': (256, 256),
+		'mean': [ 0.0, 0.0, 0.0 ],
+		'standard_deviation': [ 1.0, 1.0, 1.0 ]
+	},
+	'inswapper_128':
+	{
+		'type': 'inswapper',
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/inswapper_128.onnx',
+		'path': resolve_relative_path('../.assets/models/inswapper_128.onnx'),
+		'template': 'arcface_128_v2',
+		'size': (128, 128),
+		'mean': [ 0.0, 0.0, 0.0 ],
+		'standard_deviation': [ 1.0, 1.0, 1.0 ]
+	},
+	'inswapper_128_fp16':
+	{
+		'type': 'inswapper',
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/inswapper_128_fp16.onnx',
+		'path': resolve_relative_path('../.assets/models/inswapper_128_fp16.onnx'),
+		'template': 'arcface_128_v2',
+		'size': (128, 128),
+		'mean': [ 0.0, 0.0, 0.0 ],
+		'standard_deviation': [ 1.0, 1.0, 1.0 ]
+	},
+	'simswap_256':
+	{
+		'type': 'simswap',
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/simswap_256.onnx',
+		'path': resolve_relative_path('../.assets/models/simswap_256.onnx'),
+		'template': 'arcface_112_v1',
+		'size': (256, 256),
+		'mean': [ 0.485, 0.456, 0.406 ],
+		'standard_deviation': [ 0.229, 0.224, 0.225 ]
+	},
+	'simswap_512_unofficial':
+	{
+		'type': 'simswap',
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/simswap_512_unofficial.onnx',
+		'path': resolve_relative_path('../.assets/models/simswap_512_unofficial.onnx'),
+		'template': 'arcface_112_v1',
+		'size': (512, 512),
+		'mean': [ 0.0, 0.0, 0.0 ],
+		'standard_deviation': [ 1.0, 1.0, 1.0 ]
+	},
+	'uniface_256':
+	{
+		'type': 'uniface',
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/uniface_256.onnx',
+		'path': resolve_relative_path('../.assets/models/uniface_256.onnx'),
+		'template': 'ffhq_512',
+		'size': (256, 256),
+		'mean': [ 0.0, 0.0, 0.0 ],
+		'standard_deviation': [ 1.0, 1.0, 1.0 ]
+	}
+}
+OPTIONS : Optional[OptionsWithModel] = None
+
+
+def get_frame_processor() -> Any:
+	global FRAME_PROCESSOR
+
+	with THREAD_LOCK:
+		while process_manager.is_checking():
+			sleep(0.5)
+		if FRAME_PROCESSOR is None:
+			model_path = get_options('model').get('path')
+			FRAME_PROCESSOR = onnxruntime.InferenceSession(model_path, providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+	return FRAME_PROCESSOR
+
+
+def clear_frame_processor() -> None:
+	global FRAME_PROCESSOR
+
+	FRAME_PROCESSOR = None
+
+
+def get_model_matrix() -> Any:
+	global MODEL_MATRIX
+
+	with THREAD_LOCK:
+		while process_manager.is_checking():
+			sleep(0.5)
+		if MODEL_MATRIX is None:
+			model_path = get_options('model').get('path')
+			model = onnx.load(model_path)
+			MODEL_MATRIX = numpy_helper.to_array(model.graph.initializer[-1])
+	return MODEL_MATRIX
+
+
+def clear_model_matrix() -> None:
+	global MODEL_MATRIX
+
+	MODEL_MATRIX = None
+
+
+def get_options(key : Literal['model']) -> Any:
+	global OPTIONS
+
+	if OPTIONS is None:
+		OPTIONS =\
+		{
+			'model': MODELS[frame_processors_globals.face_swapper_model]
+		}
+	return OPTIONS.get(key)
+
+
+def set_options(key : Literal['model'], value : Any) -> None:
+	global OPTIONS
+
+	OPTIONS[key] = value
+
+
+def register_args(program : ArgumentParser) -> None:
+	onnxruntime_version = extract_major_version(onnxruntime.__version__)
+	if onnxruntime_version > (1, 16):
+		face_swapper_model_fallback = 'inswapper_128'
+	else:
+		face_swapper_model_fallback = 'inswapper_128_fp16'
+	program.add_argument('--face-swapper-model', help = wording.get('help.face_swapper_model'), default = config.get_str_value('frame_processors.face_swapper_model', face_swapper_model_fallback), choices = frame_processors_choices.face_swapper_models)
+
+
+def apply_args(program : ArgumentParser) -> None:
+	args = program.parse_args()
+	frame_processors_globals.face_swapper_model = args.face_swapper_model
+	if args.face_swapper_model == 'blendswap_256':
+		facefusion.globals.face_recognizer_model = 'arcface_blendswap'
+	if args.face_swapper_model == 'inswapper_128' or args.face_swapper_model == 'inswapper_128_fp16':
+		facefusion.globals.face_recognizer_model = 'arcface_inswapper'
+	if args.face_swapper_model == 'simswap_256' or args.face_swapper_model == 'simswap_512_unofficial':
+		facefusion.globals.face_recognizer_model = 'arcface_simswap'
+	if args.face_swapper_model == 'uniface_256':
+		facefusion.globals.face_recognizer_model = 'arcface_uniface'
+
+
+def pre_check() -> bool:
+	if not facefusion.globals.skip_download:
+		download_directory_path = resolve_relative_path('../.assets/models')
+		model_url = get_options('model').get('url')
+		process_manager.check()
+		conditional_download(download_directory_path, [ model_url ])
+		process_manager.end()
+	return True
+
+
+def post_check() -> bool:
+	model_url = get_options('model').get('url')
+	model_path = get_options('model').get('path')
+	if not facefusion.globals.skip_download and not is_download_done(model_url, model_path):
+		logger.error(wording.get('model_download_not_done') + wording.get('exclamation_mark'), NAME)
+		return False
+	elif not is_file(model_path):
+		logger.error(wording.get('model_file_not_present') + wording.get('exclamation_mark'), NAME)
+		return False
+	return True
+
+
+def pre_process(mode : ProcessMode) -> bool:
+	if not has_image(facefusion.globals.source_paths):
+		logger.error(wording.get('select_image_source') + wording.get('exclamation_mark'), NAME)
+		return False
+	source_image_paths = filter_image_paths(facefusion.globals.source_paths)
+	source_frames = read_static_images(source_image_paths)
+	for source_frame in source_frames:
+		if not get_one_face(source_frame):
+			logger.error(wording.get('no_source_face_detected') + wording.get('exclamation_mark'), NAME)
+			return False
+	if mode in [ 'output', 'preview' ] and not is_image(facefusion.globals.target_path) and not is_video(facefusion.globals.target_path):
+		logger.error(wording.get('select_image_or_video_target') + wording.get('exclamation_mark'), NAME)
+		return False
+	if mode == 'output' and not normalize_output_path(facefusion.globals.target_path, facefusion.globals.output_path):
+		logger.error(wording.get('select_file_or_directory_output') + wording.get('exclamation_mark'), NAME)
+		return False
+	return True
+
+
+def post_process() -> None:
+	read_static_image.cache_clear()
+	if facefusion.globals.video_memory_strategy == 'strict' or facefusion.globals.video_memory_strategy == 'moderate':
+		clear_frame_processor()
+		clear_model_matrix()
+	if facefusion.globals.video_memory_strategy == 'strict':
+		clear_face_analyser()
+		clear_content_analyser()
+		clear_face_occluder()
+		clear_face_parser()
+
+
+def swap_face(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	model_template = get_options('model').get('template')
+	model_size = get_options('model').get('size')
+	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmarks.get('5/68'), model_template, model_size)
+	crop_mask_list = []
+
+	if 'box' in facefusion.globals.face_mask_types:
+		box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], facefusion.globals.face_mask_blur, facefusion.globals.face_mask_padding)
+		crop_mask_list.append(box_mask)
+	if 'occlusion' in facefusion.globals.face_mask_types:
+		occlusion_mask = create_occlusion_mask(crop_vision_frame)
+		crop_mask_list.append(occlusion_mask)
+	crop_vision_frame = prepare_crop_frame(crop_vision_frame)
+	crop_vision_frame = apply_swap(source_face, crop_vision_frame)
+	crop_vision_frame = normalize_crop_frame(crop_vision_frame)
+	if 'region' in facefusion.globals.face_mask_types:
+		region_mask = create_region_mask(crop_vision_frame, facefusion.globals.face_mask_regions)
+		crop_mask_list.append(region_mask)
+	crop_mask = numpy.minimum.reduce(crop_mask_list).clip(0, 1)
+	temp_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, crop_mask, affine_matrix)
+	return temp_vision_frame
+
+
+def apply_swap(source_face : Face, crop_vision_frame : VisionFrame) -> VisionFrame:
+	frame_processor = get_frame_processor()
+	model_type = get_options('model').get('type')
+	frame_processor_inputs = {}
+
+	for frame_processor_input in frame_processor.get_inputs():
+		if frame_processor_input.name == 'source':
+			if model_type == 'blendswap' or model_type == 'uniface':
+				frame_processor_inputs[frame_processor_input.name] = prepare_source_frame(source_face)
+			else:
+				frame_processor_inputs[frame_processor_input.name] = prepare_source_embedding(source_face)
+		if frame_processor_input.name == 'target':
+			frame_processor_inputs[frame_processor_input.name] = crop_vision_frame
+	crop_vision_frame = frame_processor.run(None, frame_processor_inputs)[0][0]
+	return crop_vision_frame
+
+
+def prepare_source_frame(source_face : Face) -> VisionFrame:
+	model_type = get_options('model').get('type')
+	source_vision_frame = read_static_image(facefusion.globals.source_paths[0])
+	if model_type == 'blendswap':
+		source_vision_frame, _ = warp_face_by_face_landmark_5(source_vision_frame, source_face.landmarks.get('5/68'), 'arcface_112_v2', (112, 112))
+	if model_type == 'uniface':
+		source_vision_frame, _ = warp_face_by_face_landmark_5(source_vision_frame, source_face.landmarks.get('5/68'), 'ffhq_512', (256, 256))
+	source_vision_frame = source_vision_frame[:, :, ::-1] / 255.0
+	source_vision_frame = source_vision_frame.transpose(2, 0, 1)
+	source_vision_frame = numpy.expand_dims(source_vision_frame, axis = 0).astype(numpy.float32)
+	return source_vision_frame
+
+
+def prepare_source_embedding(source_face : Face) -> Embedding:
+	model_type = get_options('model').get('type')
+	if model_type == 'inswapper':
+		model_matrix = get_model_matrix()
+		source_embedding = source_face.embedding.reshape((1, -1))
+		source_embedding = numpy.dot(source_embedding, model_matrix) / numpy.linalg.norm(source_embedding)
+	else:
+		source_embedding = source_face.normed_embedding.reshape(1, -1)
+	return source_embedding
+
+
+def prepare_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+	model_mean = get_options('model').get('mean')
+	model_standard_deviation = get_options('model').get('standard_deviation')
+	crop_vision_frame = crop_vision_frame[:, :, ::-1] / 255.0
+	crop_vision_frame = (crop_vision_frame - model_mean) / model_standard_deviation
+	crop_vision_frame = crop_vision_frame.transpose(2, 0, 1)
+	crop_vision_frame = numpy.expand_dims(crop_vision_frame, axis = 0).astype(numpy.float32)
+	return crop_vision_frame
+
+
+def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+	crop_vision_frame = crop_vision_frame.transpose(1, 2, 0)
+	crop_vision_frame = (crop_vision_frame * 255.0).round()
+	crop_vision_frame = crop_vision_frame[:, :, ::-1]
+	return crop_vision_frame
+
+
+def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	return swap_face(source_face, target_face, temp_vision_frame)
+
+
+def process_frame(inputs : FaceSwapperInputs) -> VisionFrame:
+	reference_faces = inputs.get('reference_faces')
+	source_face = inputs.get('source_face')
+	target_vision_frame = inputs.get('target_vision_frame')
+
+	if facefusion.globals.face_selector_mode == 'many':
+		many_faces = get_many_faces(target_vision_frame)
+		if many_faces:
+			for target_face in many_faces:
+				target_vision_frame = swap_face(source_face, target_face, target_vision_frame)
+	if facefusion.globals.face_selector_mode == 'one':
+		target_face = get_one_face(target_vision_frame)
+		if target_face:
+			target_vision_frame = swap_face(source_face, target_face, target_vision_frame)
+	if facefusion.globals.face_selector_mode == 'reference':
+		similar_faces = find_similar_faces(reference_faces, target_vision_frame, facefusion.globals.reference_face_distance)
+		if similar_faces:
+			for similar_face in similar_faces:
+				target_vision_frame = swap_face(source_face, similar_face, target_vision_frame)
+	return target_vision_frame
+
+
+def process_frames(source_paths : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProcess) -> None:
+	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
+	source_frames = read_static_images(source_paths)
+	source_face = get_average_face(source_frames)
+
+	for queue_payload in process_manager.manage(queue_payloads):
+		target_vision_path = queue_payload['frame_path']
+		target_vision_frame = read_image(target_vision_path)
+		output_vision_frame = process_frame(
+		{
+			'reference_faces': reference_faces,
+			'source_face': source_face,
+			'target_vision_frame': target_vision_frame
+		})
+		write_image(target_vision_path, output_vision_frame)
+		update_progress()
+
+
+def process_image(source_paths : List[str], target_path : str, output_path : str) -> None:
+	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
+	source_frames = read_static_images(source_paths)
+	source_face = get_average_face(source_frames)
+	target_vision_frame = read_static_image(target_path)
+	output_vision_frame = process_frame(
+	{
+		'reference_faces': reference_faces,
+		'source_face': source_face,
+		'target_vision_frame': target_vision_frame
+	})
+	write_image(output_path, output_vision_frame)
+
+
+def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
+	frame_processors.multi_process_frames(source_paths, temp_frame_paths, process_frames)

facefusion/processors/frame/modules/frame_enhancer.py

@@ -0,0 +1,225 @@
+from typing import Any, List, Literal, Optional
+from argparse import ArgumentParser
+from time import sleep
+import threading
+import cv2
+import numpy
+import onnxruntime
+
+import facefusion.globals
+import facefusion.processors.frame.core as frame_processors
+from facefusion import config, process_manager, logger, wording
+from facefusion.face_analyser import clear_face_analyser
+from facefusion.content_analyser import clear_content_analyser
+from facefusion.execution import apply_execution_provider_options
+from facefusion.normalizer import normalize_output_path
+from facefusion.typing import Face, VisionFrame, UpdateProcess, ProcessMode, ModelSet, OptionsWithModel, QueuePayload
+from facefusion.common_helper import create_metavar
+from facefusion.filesystem import is_file, resolve_relative_path, is_image, is_video
+from facefusion.download import conditional_download, is_download_done
+from facefusion.vision import read_image, read_static_image, write_image, merge_tile_frames, create_tile_frames
+from facefusion.processors.frame.typings import FrameEnhancerInputs
+from facefusion.processors.frame import globals as frame_processors_globals
+from facefusion.processors.frame import choices as frame_processors_choices
+
+FRAME_PROCESSOR = None
+THREAD_LOCK : threading.Lock = threading.Lock()
+NAME = __name__.upper()
+MODELS : ModelSet =\
+{
+	'lsdir_x4':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/lsdir_x4.onnx',
+		'path': resolve_relative_path('../.assets/models/lsdir_x4.onnx'),
+		'size': (128, 8, 2),
+		'scale': 4
+	},
+	'nomos8k_sc_x4':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/nomos8k_sc_x4.onnx',
+		'path': resolve_relative_path('../.assets/models/nomos8k_sc_x4.onnx'),
+		'size': (128, 8, 2),
+		'scale': 4
+	},
+	'real_esrgan_x4':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/real_esrgan_x4.onnx',
+		'path': resolve_relative_path('../.assets/models/real_esrgan_x4.onnx'),
+		'size': (128, 8, 2),
+		'scale': 4
+	},
+	'real_esrgan_x4_fp16':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/real_esrgan_x4_fp16.onnx',
+		'path': resolve_relative_path('../.assets/models/real_esrgan_x4_fp16.onnx'),
+		'size': (128, 8, 2),
+		'scale': 4
+	},
+	'span_kendata_x4':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/span_kendata_x4.onnx',
+		'path': resolve_relative_path('../.assets/models/span_kendata_x4.onnx'),
+		'size': (128, 8, 2),
+		'scale': 4
+	}
+}
+OPTIONS : Optional[OptionsWithModel] = None
+
+
+def get_frame_processor() -> Any:
+	global FRAME_PROCESSOR
+
+	with THREAD_LOCK:
+		while process_manager.is_checking():
+			sleep(0.5)
+		if FRAME_PROCESSOR is None:
+			model_path = get_options('model').get('path')
+			FRAME_PROCESSOR = onnxruntime.InferenceSession(model_path, providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+	return FRAME_PROCESSOR
+
+
+def clear_frame_processor() -> None:
+	global FRAME_PROCESSOR
+
+	FRAME_PROCESSOR = None
+
+
+def get_options(key : Literal['model']) -> Any:
+	global OPTIONS
+
+	if OPTIONS is None:
+		OPTIONS =\
+		{
+			'model': MODELS[frame_processors_globals.frame_enhancer_model]
+		}
+	return OPTIONS.get(key)
+
+
+def set_options(key : Literal['model'], value : Any) -> None:
+	global OPTIONS
+
+	OPTIONS[key] = value
+
+
+def register_args(program : ArgumentParser) -> None:
+	program.add_argument('--frame-enhancer-model', help = wording.get('help.frame_enhancer_model'), default = config.get_str_value('frame_processors.frame_enhancer_model', 'span_kendata_x4'), choices = frame_processors_choices.frame_enhancer_models)
+	program.add_argument('--frame-enhancer-blend', help = wording.get('help.frame_enhancer_blend'), type = int, default = config.get_int_value('frame_processors.frame_enhancer_blend', '80'), choices = frame_processors_choices.frame_enhancer_blend_range, metavar = create_metavar(frame_processors_choices.frame_enhancer_blend_range))
+
+
+def apply_args(program : ArgumentParser) -> None:
+	args = program.parse_args()
+	frame_processors_globals.frame_enhancer_model = args.frame_enhancer_model
+	frame_processors_globals.frame_enhancer_blend = args.frame_enhancer_blend
+
+
+def pre_check() -> bool:
+	if not facefusion.globals.skip_download:
+		download_directory_path = resolve_relative_path('../.assets/models')
+		model_url = get_options('model').get('url')
+		process_manager.check()
+		conditional_download(download_directory_path, [ model_url ])
+		process_manager.end()
+	return True
+
+
+def post_check() -> bool:
+	model_url = get_options('model').get('url')
+	model_path = get_options('model').get('path')
+	if not facefusion.globals.skip_download and not is_download_done(model_url, model_path):
+		logger.error(wording.get('model_download_not_done') + wording.get('exclamation_mark'), NAME)
+		return False
+	elif not is_file(model_path):
+		logger.error(wording.get('model_file_not_present') + wording.get('exclamation_mark'), NAME)
+		return False
+	return True
+
+
+def pre_process(mode : ProcessMode) -> bool:
+	if mode in [ 'output', 'preview' ] and not is_image(facefusion.globals.target_path) and not is_video(facefusion.globals.target_path):
+		logger.error(wording.get('select_image_or_video_target') + wording.get('exclamation_mark'), NAME)
+		return False
+	if mode == 'output' and not normalize_output_path(facefusion.globals.target_path, facefusion.globals.output_path):
+		logger.error(wording.get('select_file_or_directory_output') + wording.get('exclamation_mark'), NAME)
+		return False
+	return True
+
+
+def post_process() -> None:
+	read_static_image.cache_clear()
+	if facefusion.globals.video_memory_strategy == 'strict' or facefusion.globals.video_memory_strategy == 'moderate':
+		clear_frame_processor()
+	if facefusion.globals.video_memory_strategy == 'strict':
+		clear_face_analyser()
+		clear_content_analyser()
+
+
+def enhance_frame(temp_vision_frame : VisionFrame) -> VisionFrame:
+	frame_processor = get_frame_processor()
+	size = get_options('model').get('size')
+	scale = get_options('model').get('scale')
+	temp_height, temp_width = temp_vision_frame.shape[:2]
+	tile_vision_frames, pad_width, pad_height = create_tile_frames(temp_vision_frame, size)
+
+	for index, tile_vision_frame in enumerate(tile_vision_frames):
+		tile_vision_frame = frame_processor.run(None,
+		{
+			frame_processor.get_inputs()[0].name : prepare_tile_frame(tile_vision_frame)
+		})[0]
+		tile_vision_frames[index] = normalize_tile_frame(tile_vision_frame)
+	merge_vision_frame = merge_tile_frames(tile_vision_frames, temp_width * scale, temp_height * scale, pad_width * scale, pad_height * scale, (size[0] * scale, size[1] * scale, size[2] * scale))
+	temp_vision_frame = blend_frame(temp_vision_frame, merge_vision_frame)
+	return temp_vision_frame
+
+
+def prepare_tile_frame(vision_tile_frame : VisionFrame) -> VisionFrame:
+	vision_tile_frame = numpy.expand_dims(vision_tile_frame[:,:,::-1], axis = 0)
+	vision_tile_frame = vision_tile_frame.transpose(0, 3, 1, 2)
+	vision_tile_frame = vision_tile_frame.astype(numpy.float32) / 255
+	return vision_tile_frame
+
+
+def normalize_tile_frame(vision_tile_frame : VisionFrame) -> VisionFrame:
+	vision_tile_frame = vision_tile_frame.transpose(0, 2, 3, 1).squeeze(0) * 255
+	vision_tile_frame = vision_tile_frame.clip(0, 255).astype(numpy.uint8)[:,:,::-1]
+	return vision_tile_frame
+
+
+def blend_frame(temp_vision_frame : VisionFrame, paste_vision_frame : VisionFrame) -> VisionFrame:
+	frame_enhancer_blend = 1 - (frame_processors_globals.frame_enhancer_blend / 100)
+	temp_vision_frame = cv2.resize(temp_vision_frame, (paste_vision_frame.shape[1], paste_vision_frame.shape[0]))
+	temp_vision_frame = cv2.addWeighted(temp_vision_frame, frame_enhancer_blend, paste_vision_frame, 1 - frame_enhancer_blend, 0)
+	return temp_vision_frame
+
+
+def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	pass
+
+
+def process_frame(inputs : FrameEnhancerInputs) -> VisionFrame:
+	target_vision_frame = inputs.get('target_vision_frame')
+	return enhance_frame(target_vision_frame)
+
+
+def process_frames(source_paths : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProcess) -> None:
+	for queue_payload in process_manager.manage(queue_payloads):
+		target_vision_path = queue_payload['frame_path']
+		target_vision_frame = read_image(target_vision_path)
+		output_vision_frame = process_frame(
+		{
+			'target_vision_frame': target_vision_frame
+		})
+		write_image(target_vision_path, output_vision_frame)
+		update_progress()
+
+
+def process_image(source_paths : List[str], target_path : str, output_path : str) -> None:
+	target_vision_frame = read_static_image(target_path)
+	output_vision_frame = process_frame(
+	{
+		'target_vision_frame': target_vision_frame
+	})
+	write_image(output_path, output_vision_frame)
+
+
+def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
+	frame_processors.multi_process_frames(None, temp_frame_paths, process_frames)

facefusion/processors/frame/modules/lip_syncer.py

@@ -0,0 +1,254 @@
+from typing import Any, List, Literal, Optional
+from argparse import ArgumentParser
+from time import sleep
+import threading
+import cv2
+import numpy
+import onnxruntime
+
+import facefusion.globals
+import facefusion.processors.frame.core as frame_processors
+from facefusion import config, process_manager, logger, wording
+from facefusion.execution import apply_execution_provider_options
+from facefusion.face_analyser import get_one_face, get_many_faces, find_similar_faces, clear_face_analyser
+from facefusion.face_masker import create_static_box_mask, create_occlusion_mask, create_mouth_mask, clear_face_occluder, clear_face_parser
+from facefusion.face_helper import warp_face_by_face_landmark_5, warp_face_by_bounding_box, paste_back, create_bounding_box_from_face_landmark_68
+from facefusion.face_store import get_reference_faces
+from facefusion.content_analyser import clear_content_analyser
+from facefusion.normalizer import normalize_output_path
+from facefusion.typing import Face, VisionFrame, UpdateProcess, ProcessMode, ModelSet, OptionsWithModel, AudioFrame, QueuePayload
+from facefusion.filesystem import is_file, has_audio, resolve_relative_path
+from facefusion.download import conditional_download, is_download_done
+from facefusion.audio import read_static_audio, get_audio_frame, create_empty_audio_frame
+from facefusion.filesystem import is_image, is_video, filter_audio_paths
+from facefusion.common_helper import get_first
+from facefusion.vision import read_image, write_image, read_static_image
+from facefusion.processors.frame.typings import LipSyncerInputs
+from facefusion.processors.frame import globals as frame_processors_globals
+from facefusion.processors.frame import choices as frame_processors_choices
+
+FRAME_PROCESSOR = None
+MODEL_MATRIX = None
+THREAD_LOCK : threading.Lock = threading.Lock()
+NAME = __name__.upper()
+MODELS : ModelSet =\
+{
+	'wav2lip_gan':
+	{
+		'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models/wav2lip_gan.onnx',
+		'path': resolve_relative_path('../.assets/models/wav2lip_gan.onnx'),
+	}
+}
+OPTIONS : Optional[OptionsWithModel] = None
+
+
+def get_frame_processor() -> Any:
+	global FRAME_PROCESSOR
+
+	with THREAD_LOCK:
+		while process_manager.is_checking():
+			sleep(0.5)
+		if FRAME_PROCESSOR is None:
+			model_path = get_options('model').get('path')
+			FRAME_PROCESSOR = onnxruntime.InferenceSession(model_path, providers = apply_execution_provider_options(facefusion.globals.execution_providers))
+	return FRAME_PROCESSOR
+
+
+def clear_frame_processor() -> None:
+	global FRAME_PROCESSOR
+
+	FRAME_PROCESSOR = None
+
+
+def get_options(key : Literal['model']) -> Any:
+	global OPTIONS
+
+	if OPTIONS is None:
+		OPTIONS =\
+		{
+			'model': MODELS[frame_processors_globals.lip_syncer_model]
+		}
+	return OPTIONS.get(key)
+
+
+def set_options(key : Literal['model'], value : Any) -> None:
+	global OPTIONS
+
+	OPTIONS[key] = value
+
+
+def register_args(program : ArgumentParser) -> None:
+	program.add_argument('--lip-syncer-model', help = wording.get('help.lip_syncer_model'), default = config.get_str_value('frame_processors.lip_syncer_model', 'wav2lip_gan'), choices = frame_processors_choices.lip_syncer_models)
+
+
+def apply_args(program : ArgumentParser) -> None:
+	args = program.parse_args()
+	frame_processors_globals.lip_syncer_model = args.lip_syncer_model
+
+
+def pre_check() -> bool:
+	if not facefusion.globals.skip_download:
+		download_directory_path = resolve_relative_path('../.assets/models')
+		model_url = get_options('model').get('url')
+		process_manager.check()
+		conditional_download(download_directory_path, [ model_url ])
+		process_manager.end()
+	return True
+
+
+def post_check() -> bool:
+	model_url = get_options('model').get('url')
+	model_path = get_options('model').get('path')
+	if not facefusion.globals.skip_download and not is_download_done(model_url, model_path):
+		logger.error(wording.get('model_download_not_done') + wording.get('exclamation_mark'), NAME)
+		return False
+	elif not is_file(model_path):
+		logger.error(wording.get('model_file_not_present') + wording.get('exclamation_mark'), NAME)
+		return False
+	return True
+
+
+def pre_process(mode : ProcessMode) -> bool:
+	if not has_audio(facefusion.globals.source_paths):
+		logger.error(wording.get('select_audio_source') + wording.get('exclamation_mark'), NAME)
+		return False
+	if mode in [ 'output', 'preview' ] and not is_image(facefusion.globals.target_path) and not is_video(facefusion.globals.target_path):
+		logger.error(wording.get('select_image_or_video_target') + wording.get('exclamation_mark'), NAME)
+		return False
+	if mode == 'output' and not normalize_output_path(facefusion.globals.target_path, facefusion.globals.output_path):
+		logger.error(wording.get('select_file_or_directory_output') + wording.get('exclamation_mark'), NAME)
+		return False
+	return True
+
+
+def post_process() -> None:
+	read_static_image.cache_clear()
+	read_static_audio.cache_clear()
+	if facefusion.globals.video_memory_strategy == 'strict' or facefusion.globals.video_memory_strategy == 'moderate':
+		clear_frame_processor()
+	if facefusion.globals.video_memory_strategy == 'strict':
+		clear_face_analyser()
+		clear_content_analyser()
+		clear_face_occluder()
+		clear_face_parser()
+
+
+def sync_lip(target_face : Face, temp_audio_frame : AudioFrame, temp_vision_frame : VisionFrame) -> VisionFrame:
+	frame_processor = get_frame_processor()
+	crop_mask_list = []
+	temp_audio_frame = prepare_audio_frame(temp_audio_frame)
+	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmarks.get('5/68'), 'ffhq_512', (512, 512))
+	if numpy.any(target_face.landmarks.get('68')):
+		face_landmark_68 = cv2.transform(target_face.landmarks.get('68').reshape(1, -1, 2), affine_matrix).reshape(-1, 2)
+		bounding_box = create_bounding_box_from_face_landmark_68(face_landmark_68)
+		bounding_box[1] -= numpy.abs(bounding_box[3] - bounding_box[1]) * 0.125
+		mouth_mask = create_mouth_mask(face_landmark_68)
+		crop_mask_list.append(mouth_mask)
+	else:
+		bounding_box = target_face.bounding_box
+	box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], facefusion.globals.face_mask_blur, facefusion.globals.face_mask_padding)
+	crop_mask_list.append(box_mask)
+
+	if 'occlusion' in facefusion.globals.face_mask_types:
+		occlusion_mask = create_occlusion_mask(crop_vision_frame)
+		crop_mask_list.append(occlusion_mask)
+	close_vision_frame, close_matrix = warp_face_by_bounding_box(crop_vision_frame, bounding_box, (96, 96))
+	close_vision_frame = prepare_crop_frame(close_vision_frame)
+	close_vision_frame = frame_processor.run(None,
+	{
+		'source': temp_audio_frame,
+		'target': close_vision_frame
+	})[0]
+	crop_vision_frame = normalize_crop_frame(close_vision_frame)
+	crop_vision_frame = cv2.warpAffine(crop_vision_frame, cv2.invertAffineTransform(close_matrix), (512, 512), borderMode = cv2.BORDER_REPLICATE)
+	crop_mask = numpy.minimum.reduce(crop_mask_list)
+	paste_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, crop_mask, affine_matrix)
+	return paste_vision_frame
+
+
+def prepare_audio_frame(temp_audio_frame : AudioFrame) -> AudioFrame:
+	temp_audio_frame = numpy.maximum(numpy.exp(-5 * numpy.log(10)), temp_audio_frame)
+	temp_audio_frame = numpy.log10(temp_audio_frame) * 1.6 + 3.2
+	temp_audio_frame = temp_audio_frame.clip(-4, 4).astype(numpy.float32)
+	temp_audio_frame = numpy.expand_dims(temp_audio_frame, axis = (0, 1))
+	return temp_audio_frame
+
+
+def prepare_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+	crop_vision_frame = numpy.expand_dims(crop_vision_frame, axis = 0)
+	prepare_vision_frame = crop_vision_frame.copy()
+	prepare_vision_frame[:, 48:] = 0
+	crop_vision_frame = numpy.concatenate((prepare_vision_frame, crop_vision_frame), axis = 3)
+	crop_vision_frame = crop_vision_frame.transpose(0, 3, 1, 2).astype('float32') / 255.0
+	return crop_vision_frame
+
+
+def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+	crop_vision_frame = crop_vision_frame[0].transpose(1, 2, 0)
+	crop_vision_frame = crop_vision_frame.clip(0, 1) * 255
+	crop_vision_frame = crop_vision_frame.astype(numpy.uint8)
+	return crop_vision_frame
+
+
+def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	pass
+
+
+def process_frame(inputs : LipSyncerInputs) -> VisionFrame:
+	reference_faces = inputs.get('reference_faces')
+	source_audio_frame = inputs.get('source_audio_frame')
+	target_vision_frame = inputs.get('target_vision_frame')
+
+	if facefusion.globals.face_selector_mode == 'many':
+		many_faces = get_many_faces(target_vision_frame)
+		if many_faces:
+			for target_face in many_faces:
+				target_vision_frame = sync_lip(target_face, source_audio_frame, target_vision_frame)
+	if facefusion.globals.face_selector_mode == 'one':
+		target_face = get_one_face(target_vision_frame)
+		if target_face:
+			target_vision_frame = sync_lip(target_face, source_audio_frame, target_vision_frame)
+	if facefusion.globals.face_selector_mode == 'reference':
+		similar_faces = find_similar_faces(reference_faces, target_vision_frame, facefusion.globals.reference_face_distance)
+		if similar_faces:
+			for similar_face in similar_faces:
+				target_vision_frame = sync_lip(similar_face, source_audio_frame, target_vision_frame)
+	return target_vision_frame
+
+
+def process_frames(source_paths : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProcess) -> None:
+	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
+	source_audio_path = get_first(filter_audio_paths(source_paths))
+
+	for queue_payload in process_manager.manage(queue_payloads):
+		frame_number = queue_payload['frame_number']
+		target_vision_path = queue_payload['frame_path']
+		source_audio_frame = get_audio_frame(source_audio_path, facefusion.globals.output_video_fps, frame_number)
+		if not numpy.any(source_audio_frame):
+			source_audio_frame = create_empty_audio_frame()
+		target_vision_frame = read_image(target_vision_path)
+		output_vision_frame = process_frame(
+		{
+			'reference_faces': reference_faces,
+			'source_audio_frame': source_audio_frame,
+			'target_vision_frame': target_vision_frame
+		})
+		write_image(target_vision_path, output_vision_frame)
+		update_progress()
+
+
+def process_image(source_paths : List[str], target_path : str, output_path : str) -> None:
+	reference_faces = get_reference_faces() if 'reference' in facefusion.globals.face_selector_mode else None
+	source_audio_frame = create_empty_audio_frame()
+	target_vision_frame = read_static_image(target_path)
+	output_vision_frame = process_frame(
+	{
+		'reference_faces': reference_faces,
+		'source_audio_frame': source_audio_frame,
+		'target_vision_frame': target_vision_frame
+	})
+	write_image(output_path, output_vision_frame)
+
+
+def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
+	frame_processors.multi_process_frames(source_paths, temp_frame_paths, process_frames)

facefusion/processors/frame/typings.py

@@ -0,0 +1,36 @@
+from typing import Literal, TypedDict
+
+from facefusion.typing import Face, FaceSet, AudioFrame, VisionFrame
+
+FaceDebuggerItem = Literal['bounding-box', 'face-landmark-5', 'face-landmark-5/68', 'face-landmark-68', 'face-mask', 'face-detector-score', 'face-landmarker-score', 'age', 'gender']
+FaceEnhancerModel = Literal['codeformer', 'gfpgan_1.2', 'gfpgan_1.3', 'gfpgan_1.4', 'gpen_bfr_256', 'gpen_bfr_512', 'restoreformer_plus_plus']
+FaceSwapperModel = Literal['blendswap_256', 'inswapper_128', 'inswapper_128_fp16', 'simswap_256', 'simswap_512_unofficial', 'uniface_256']
+FrameEnhancerModel = Literal['lsdir_x4', 'nomos8k_sc_x4', 'real_esrgan_x4',  'real_esrgan_x4_fp16', 'span_kendata_x4']
+LipSyncerModel = Literal['wav2lip_gan']
+
+FaceDebuggerInputs = TypedDict('FaceDebuggerInputs',
+{
+	'reference_faces' : FaceSet,
+	'target_vision_frame' : VisionFrame
+})
+FaceEnhancerInputs = TypedDict('FaceEnhancerInputs',
+{
+	'reference_faces' : FaceSet,
+	'target_vision_frame' : VisionFrame
+})
+FaceSwapperInputs = TypedDict('FaceSwapperInputs',
+{
+	'reference_faces' : FaceSet,
+	'source_face' : Face,
+	'target_vision_frame' : VisionFrame
+})
+FrameEnhancerInputs = TypedDict('FrameEnhancerInputs',
+{
+	'target_vision_frame' : VisionFrame
+})
+LipSyncerInputs = TypedDict('LipSyncerInputs',
+{
+	'reference_faces' : FaceSet,
+	'source_audio_frame' : AudioFrame,
+	'target_vision_frame' : VisionFrame
+})

facefusion/statistics.py

@@ -0,0 +1,51 @@
+from typing import Any, Dict
+import numpy
+
+import facefusion.globals
+from facefusion.face_store import FACE_STORE
+from facefusion.typing import FaceSet
+from facefusion import logger
+
+
+def create_statistics(static_faces : FaceSet) -> Dict[str, Any]:
+	face_detector_score_list = []
+	face_landmarker_score_list = []
+	statistics =\
+	{
+		'min_face_detector_score': 0,
+		'min_face_landmarker_score': 0,
+		'max_face_detector_score': 0,
+		'max_face_landmarker_score': 0,
+		'average_face_detector_score': 0,
+		'average_face_landmarker_score': 0,
+		'total_face_landmark_5_fallbacks': 0,
+		'total_frames_with_faces': 0,
+		'total_faces': 0
+	}
+
+	for faces in static_faces.values():
+		statistics['total_frames_with_faces'] = statistics.get('total_frames_with_faces') + 1
+		for face in faces:
+			statistics['total_faces'] = statistics.get('total_faces') + 1
+			face_detector_score_list.append(face.scores.get('detector'))
+			face_landmarker_score_list.append(face.scores.get('landmarker'))
+			if numpy.array_equal(face.landmarks.get('5'), face.landmarks.get('5/68')):
+				statistics['total_face_landmark_5_fallbacks'] = statistics.get('total_face_landmark_5_fallbacks') + 1
+
+	if face_detector_score_list:
+		statistics['min_face_detector_score'] = round(min(face_detector_score_list), 2)
+		statistics['max_face_detector_score'] = round(max(face_detector_score_list), 2)
+		statistics['average_face_detector_score'] = round(numpy.mean(face_detector_score_list), 2)
+	if face_landmarker_score_list:
+		statistics['min_face_landmarker_score'] = round(min(face_landmarker_score_list), 2)
+		statistics['max_face_landmarker_score'] = round(max(face_landmarker_score_list), 2)
+		statistics['average_face_landmarker_score'] = round(numpy.mean(face_landmarker_score_list), 2)
+	return statistics
+
+
+def conditional_log_statistics() -> None:
+	if facefusion.globals.log_level == 'debug':
+		statistics = create_statistics(FACE_STORE.get('static_faces'))
+
+		for name, value in statistics.items():
+			logger.debug(str(name) + ': ' + str(value), __name__.upper())

facefusion/typing.py

@@ -0,0 +1,120 @@
+from typing import Any, Literal, Callable, List, Tuple, Dict, TypedDict
+from collections import namedtuple
+import numpy
+
+BoundingBox = numpy.ndarray[Any, Any]
+FaceLandmark5 = numpy.ndarray[Any, Any]
+FaceLandmark68 = numpy.ndarray[Any, Any]
+FaceLandmarkSet = TypedDict('FaceLandmarkSet',
+{
+	'5' : FaceLandmark5, # type: ignore[valid-type]
+	'5/68' : FaceLandmark5, # type: ignore[valid-type]
+	'68' : FaceLandmark68 # type: ignore[valid-type]
+})
+Score = float
+FaceScoreSet = TypedDict('FaceScoreSet',
+{
+	'detector' : Score,
+	'landmarker' : Score
+})
+Embedding = numpy.ndarray[Any, Any]
+Face = namedtuple('Face',
+[
+	'bounding_box',
+	'landmarks',
+	'scores',
+	'embedding',
+	'normed_embedding',
+	'gender',
+	'age'
+])
+FaceSet = Dict[str, List[Face]]
+FaceStore = TypedDict('FaceStore',
+{
+	'static_faces' : FaceSet,
+	'reference_faces': FaceSet
+})
+
+VisionFrame = numpy.ndarray[Any, Any]
+Mask = numpy.ndarray[Any, Any]
+Matrix = numpy.ndarray[Any, Any]
+Translation = numpy.ndarray[Any, Any]
+
+AudioBuffer = bytes
+Audio = numpy.ndarray[Any, Any]
+AudioFrame = numpy.ndarray[Any, Any]
+Spectrogram = numpy.ndarray[Any, Any]
+
+Fps = float
+Padding = Tuple[int, int, int, int]
+Resolution = Tuple[int, int]
+
+ProcessState = Literal['checking', 'processing', 'stopping', 'pending']
+QueuePayload = TypedDict('QueuePayload',
+{
+	'frame_number' : int,
+	'frame_path' : str
+})
+UpdateProcess = Callable[[], None]
+ProcessFrames = Callable[[List[str], List[QueuePayload], UpdateProcess], None]
+
+WarpTemplate = Literal['arcface_112_v1', 'arcface_112_v2', 'arcface_128_v2', 'ffhq_512']
+WarpTemplateSet = Dict[WarpTemplate, numpy.ndarray[Any, Any]]
+ProcessMode = Literal['output', 'preview', 'stream']
+
+LogLevel = Literal['error', 'warn', 'info', 'debug']
+VideoMemoryStrategy = Literal['strict', 'moderate', 'tolerant']
+FaceSelectorMode = Literal['many', 'one', 'reference']
+FaceAnalyserOrder = Literal['left-right', 'right-left', 'top-bottom', 'bottom-top', 'small-large', 'large-small', 'best-worst', 'worst-best']
+FaceAnalyserAge = Literal['child', 'teen', 'adult', 'senior']
+FaceAnalyserGender = Literal['female', 'male']
+FaceDetectorModel = Literal['many', 'retinaface', 'scrfd', 'yoloface', 'yunet']
+FaceDetectorTweak = Literal['low-luminance', 'high-luminance']
+FaceRecognizerModel = Literal['arcface_blendswap', 'arcface_inswapper', 'arcface_simswap', 'arcface_uniface']
+FaceMaskType = Literal['box', 'occlusion', 'region']
+FaceMaskRegion = Literal['skin', 'left-eyebrow', 'right-eyebrow', 'left-eye', 'right-eye', 'eye-glasses', 'nose', 'mouth', 'upper-lip', 'lower-lip']
+TempFrameFormat = Literal['jpg', 'png', 'bmp']
+OutputVideoEncoder = Literal['libx264', 'libx265', 'libvpx-vp9', 'h264_nvenc', 'hevc_nvenc', 'h264_amf', 'hevc_amf']
+OutputVideoPreset = Literal['ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow']
+
+ModelValue = Dict[str, Any]
+ModelSet = Dict[str, ModelValue]
+OptionsWithModel = TypedDict('OptionsWithModel',
+{
+	'model' : ModelValue
+})
+
+ValueAndUnit = TypedDict('ValueAndUnit',
+{
+	'value' : str,
+	'unit' : str
+})
+ExecutionDeviceFramework = TypedDict('ExecutionDeviceFramework',
+{
+	'name' : str,
+	'version' : str
+})
+ExecutionDeviceProduct = TypedDict('ExecutionDeviceProduct',
+{
+	'vendor' : str,
+	'name' : str,
+	'architecture' : str,
+})
+ExecutionDeviceVideoMemory = TypedDict('ExecutionDeviceVideoMemory',
+{
+	'total' : ValueAndUnit,
+	'free' : ValueAndUnit
+})
+ExecutionDeviceUtilization = TypedDict('ExecutionDeviceUtilization',
+{
+	'gpu' : ValueAndUnit,
+	'memory' : ValueAndUnit
+})
+ExecutionDevice = TypedDict('ExecutionDevice',
+{
+	'driver_version' : str,
+	'framework' : ExecutionDeviceFramework,
+	'product' : ExecutionDeviceProduct,
+	'video_memory' : ExecutionDeviceVideoMemory,
+	'utilization' : ExecutionDeviceUtilization
+})

facefusion/uis/assets/fixes.css

@@ -0,0 +1,7 @@
+:root:root:root button:not([class])
+{
+	border-radius: 0.375rem;
+	float: left;
+	overflow: hidden;
+	width: 100%;
+}

facefusion/uis/assets/overrides.css

@@ -0,0 +1,58 @@
+:root:root:root input[type="number"]
+{
+	max-width: 6rem;
+}
+
+:root:root:root [type="checkbox"],
+:root:root:root [type="radio"]
+{
+	border-radius: 50%;
+	height: 1.125rem;
+	width: 1.125rem;
+}
+
+:root:root:root input[type="range"]
+{
+	height: 0.5rem;
+}
+
+:root:root:root input[type="range"]::-moz-range-thumb,
+:root:root:root input[type="range"]::-webkit-slider-thumb
+{
+	background: var(--neutral-300);
+	border: unset;
+	border-radius: 50%;
+	height: 1.125rem;
+	width: 1.125rem;
+}
+
+:root:root:root input[type="range"]::-webkit-slider-thumb
+{
+	margin-top: 0.375rem;
+}
+
+:root:root:root .grid-wrap.fixed-height
+{
+	min-height: unset;
+}
+
+:root:root:root .grid-container
+{
+	grid-auto-rows: minmax(5em, 1fr);
+	grid-template-columns: repeat(var(--grid-cols), minmax(5em, 1fr));
+	grid-template-rows: repeat(var(--grid-rows), minmax(5em, 1fr));
+}
+
+:root:root:root .tab-nav > button
+{
+	border: unset;
+	border-bottom: 0.125rem solid transparent;
+	font-size: 1.125em;
+	margin: 0.5rem 1rem;
+	padding: 0;
+}
+
+:root:root:root .tab-nav > button.selected
+{
+	border-bottom: 0.125rem solid;
+}

facefusion/uis/choices.py

@@ -0,0 +1,7 @@
+from typing import List
+
+from facefusion.uis.typing import WebcamMode
+
+common_options : List[str] = [ 'keep-temp', 'skip-audio', 'skip-download' ]
+webcam_modes : List[WebcamMode] = [ 'inline', 'udp', 'v4l2' ]
+webcam_resolutions : List[str] = [ '320x240', '640x480', '800x600', '1024x768', '1280x720', '1280x960', '1920x1080', '2560x1440', '3840x2160' ]