Git LFS

.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
+*.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-conda
+  - 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

@@ -1,13 +1,112 @@
----
-title: Facefusion
-emoji: 📊
-colorFrom: red
-colorTo: green
-sdk: gradio
-sdk_version: 4.27.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+FaceFusion
+==========
+
+> 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:
+  --force-download                                                                                                                                      force automate downloads and exit
+  --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, 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_colorizer, 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-landmark-68/5, 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,gpen_bfr_1024,gpen_bfr_2048,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-colorizer-model {ddcolor,ddcolor_artistic,deoldify,deoldify_artistic,deoldify_stable}                                                         choose the model responsible for colorizing the frame
+  --frame-colorizer-blend [0-100]                                                                                                                       blend the colorized into the previous frame
+  --frame-colorizer-size {192x192,256x256,384x384,512x512}                                                                                              specify the size of the frame provided to the frame colorizer
+  --frame-enhancer-model {lsdir_x4,nomos8k_sc_x4,real_esrgan_x2,real_esrgan_x2_fp16,real_esrgan_x4,real_esrgan_x4_fp16,real_hatgan_x4,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 +1,72 @@
+[general]
+source_paths =
+target_path =
+output_path =
+
+[misc]
+force_download =
+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_colorizer_model =
+frame_colorizer_blend =
+frame_colorizer_size =
+frame_enhancer_model =
+frame_enhancer_blend =
+lip_syncer_model =
+
+[uis]
+ui_layouts =

facefusion/audio.py

@@ -0,0 +1,137 @@
+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, AudioFrame, Spectrogram, MelFilterBank
+from facefusion.voice_extractor import batch_extract_voice
+
+
+@lru_cache(maxsize = 128)
+def read_static_audio(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
+	return read_audio(audio_path, fps)
+
+
+def read_audio(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
+	sample_rate = 48000
+	channel_total = 2
+
+	if is_audio(audio_path):
+		audio_buffer = read_audio_buffer(audio_path, sample_rate, channel_total)
+		audio = numpy.frombuffer(audio_buffer, dtype = numpy.int16).reshape(-1, 2)
+		audio = prepare_audio(audio)
+		spectrogram = create_spectrogram(audio)
+		audio_frames = extract_audio_frames(spectrogram, fps)
+		return audio_frames
+	return None
+
+
+@lru_cache(maxsize = 128)
+def read_static_voice(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
+	return read_voice(audio_path, fps)
+
+
+def read_voice(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
+	sample_rate = 48000
+	channel_total = 2
+	chunk_size = 1024 * 240
+	step_size = 1024 * 180
+
+	if is_audio(audio_path):
+		audio_buffer = read_audio_buffer(audio_path, sample_rate, channel_total)
+		audio = numpy.frombuffer(audio_buffer, dtype = numpy.int16).reshape(-1, 2)
+		audio = batch_extract_voice(audio, chunk_size, step_size)
+		audio = prepare_voice(audio)
+		spectrogram = create_spectrogram(audio)
+		audio_frames = extract_audio_frames(spectrogram, fps)
+		return audio_frames
+	return None
+
+
+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 get_voice_frame(audio_path : str, fps : Fps, frame_number : int = 0) -> Optional[AudioFrame]:
+	if is_audio(audio_path):
+		voice_frames = read_static_voice(audio_path, fps)
+		if frame_number in range(len(voice_frames)):
+			return voice_frames[frame_number]
+	return None
+
+
+def create_empty_audio_frame() -> AudioFrame:
+	mel_filter_total = 80
+	step_size = 16
+	audio_frame = numpy.zeros((mel_filter_total, step_size)).astype(numpy.int16)
+	return audio_frame
+
+
+def prepare_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)
+	audio = scipy.signal.lfilter([ 1.0, -0.97 ], [ 1.0 ], audio)
+	return audio
+
+
+def prepare_voice(audio : numpy.ndarray[Any, Any]) -> Audio:
+	sample_rate = 48000
+	resample_rate = 16000
+
+	audio = scipy.signal.resample(audio, int(len(audio) * resample_rate / sample_rate))
+	audio = prepare_audio(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)
+
+
+def create_mel_filter_bank() -> MelFilterBank:
+	mel_filter_total = 80
+	mel_bin_total = 800
+	sample_rate = 16000
+	min_frequency = 55.0
+	max_frequency = 7600.0
+	mel_filter_bank = numpy.zeros((mel_filter_total, mel_bin_total // 2 + 1))
+	mel_frequency_range = numpy.linspace(convert_hertz_to_mel(min_frequency), convert_hertz_to_mel(max_frequency), mel_filter_total + 2)
+	indices = numpy.floor((mel_bin_total + 1) * convert_mel_to_hertz(mel_frequency_range) / sample_rate).astype(numpy.int16)
+
+	for index in range(mel_filter_total):
+		start = indices[index]
+		end = indices[index + 1]
+		mel_filter_bank[index, start:end] = scipy.signal.windows.triang(end - start)
+	return mel_filter_bank
+
+
+def create_spectrogram(audio : Audio) -> Spectrogram:
+	mel_bin_total = 800
+	mel_bin_overlap = 600
+	mel_filter_bank = create_mel_filter_bank()
+	spectrogram = scipy.signal.stft(audio, nperseg = mel_bin_total, nfft = mel_bin_total, noverlap = mel_bin_overlap)[2]
+	spectrogram = numpy.dot(mel_filter_bank, numpy.abs(spectrogram))
+	return spectrogram
+
+
+def extract_audio_frames(spectrogram : Spectrogram, fps : Fps) -> List[AudioFrame]:
+	mel_filter_total = 80
+	step_size = 16
+	audio_frames = []
+	indices = numpy.arange(0, spectrogram.shape[1], mel_filter_total / fps).astype(numpy.int16)
+	indices = indices[indices >= step_size]
+
+	for index in indices:
+		start = max(0, index - step_size)
+		audio_frames.append(spectrogram[:, start: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', '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 +1,18 @@
+from typing import List, Any
+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)

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 +1,112 @@
+from typing import Any
+from functools import lru_cache
+from time import sleep
+import cv2
+import numpy
+import onnxruntime
+from tqdm import tqdm
+
+import facefusion.globals
+from facefusion import process_manager, wording
+from facefusion.thread_helper import thread_lock, conditional_thread_semaphore
+from facefusion.typing import VisionFrame, ModelSet, 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, is_file
+from facefusion.download import conditional_download
+
+CONTENT_ANALYSER = None
+MODELS : ModelSet =\
+{
+	'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 = 10
+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:
+	download_directory_path = resolve_relative_path('../.assets/models')
+	model_url = MODELS.get('open_nsfw').get('url')
+	model_path = MODELS.get('open_nsfw').get('path')
+
+	if not facefusion.globals.skip_download:
+		process_manager.check()
+		conditional_download(download_directory_path, [ model_url ])
+		process_manager.end()
+	return is_file(model_path)
+
+
+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)
+	with conditional_thread_semaphore(facefusion.globals.execution_providers):
+		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 +1,416 @@
+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, voice_extractor
+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.download import conditional_download
+from facefusion.filesystem import list_directory, get_temp_frame_paths, create_temp, move_temp, clear_temp, is_image, is_video, filter_audio_paths, resolve_relative_path
+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 = 160), 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('--force-download', help = wording.get('help.force_download'), action = 'store_true', default = config.get_bool_value('misc.force_download'))
+	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, default = config.get_str_value('output_creation.output_video_fps'))
+	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 validate_args(program : ArgumentParser) -> None:
+	try:
+		for action in program._actions:
+			if action.default:
+				if isinstance(action.default, list):
+					for default in action.default:
+						program._check_value(action, default)
+				else:
+					program._check_value(action, action.default)
+	except Exception as exception:
+		program.error(str(exception))
+
+
+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.force_download = args.force_download
+	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:
+	validate_args(program)
+	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 facefusion.globals.force_download:
+		force_download()
+		return
+	if not pre_check() or not content_analyser.pre_check() or not face_analyser.pre_check() or not face_masker.pre_check() or not voice_extractor.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 force_download() -> None:
+	download_directory_path = resolve_relative_path('../.assets/models')
+	available_frame_processors = list_directory('facefusion/processors/frame/modules')
+	model_list =\
+	[
+		content_analyser.MODELS,
+		face_analyser.MODELS,
+		face_masker.MODELS,
+		voice_extractor.MODELS
+	]
+
+	for frame_processor_module in get_frame_processors_modules(available_frame_processors):
+		if hasattr(frame_processor_module, 'MODELS'):
+			model_list.append(frame_processor_module.MODELS)
+	model_urls = [ models[model].get('url') for models in model_list for model in models ]
+	conditional_download(download_directory_path, model_urls)
+
+
+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 +1,48 @@
+import os
+import subprocess
+import platform
+import ssl
+import urllib.request
+from typing import List
+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:
+	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