dockndev · Jun 20, 2023
diff --git a/‎.flake8
+2-1 b/‎.flake8
+2-1
diff --git a/‎.github/examples/face.jpg ‎.github/examples/source.jpg b/‎.github/examples/face.jpg ‎.github/examples/source.jpg
diff --git a/‎.github/workflows/ci.yml
+6-5 b/‎.github/workflows/ci.yml
+6-5
diff --git a/‎.gitignore
+2-1 b/‎.gitignore
+2-1
diff --git a/‎CONTRIBUTING.md
+21 b/‎CONTRIBUTING.md
+21
diff --git a/‎README.md
+22-16 b/‎README.md
+22-16
diff --git a/‎gui-demo.png
-11.7 KB b/‎gui-demo.png
-11.7 KB
diff --git a/‎mypi.ini
+7 b/‎mypi.ini
+7
diff --git a/‎requirements-ci.txt
+14 b/‎requirements-ci.txt
+14
diff --git a/‎requirements.txt
+5-1 b/‎requirements.txt
+5-1
diff --git a/‎roop/__init__.py
-1 b/‎roop/__init__.py
-1
diff --git a/‎roop/analyser.py
-27 b/‎roop/analyser.py
-27
diff --git a/‎roop/capturer.py
+20 b/‎roop/capturer.py
+20
diff --git a/‎roop/core.py
+200-242 b/‎roop/core.py
+200-242
diff --git a/‎roop/face_analyser.py
+31 b/‎roop/face_analyser.py
+31
diff --git a/‎roop/globals.py
+15-9 b/‎roop/globals.py
+15-9
diff --git a/‎roop/metadata.py
+2 b/‎roop/metadata.py
+2
diff --git a/‎roop/predicter.py
+25 b/‎roop/predicter.py
+25
diff --git a/‎roop/processors/__init__.py b/‎roop/processors/__init__.py
diff --git a/‎roop/processors/frame/__init__.py b/‎roop/processors/frame/__init__.py
diff --git a/‎roop/processors/frame/core.py
+56 b/‎roop/processors/frame/core.py
+56
diff --git a/‎roop/processors/frame/face_enhancer.py
+75 b/‎roop/processors/frame/face_enhancer.py
+75
diff --git a/‎roop/processors/frame/face_swapper.py
+86 b/‎roop/processors/frame/face_swapper.py
+86
diff --git a/‎roop/swapper.py
-96 b/‎roop/swapper.py
-96
diff --git a/‎roop/typing.py
+7 b/‎roop/typing.py
+7
diff --git a/‎roop/ui.json
+155 b/‎roop/ui.json
+155
diff --git a/‎roop/ui.py
+187-277 b/‎roop/ui.py
+187-277
diff --git a/‎roop/utilities.py
+141 b/‎roop/utilities.py
+141
diff --git a/‎roop/utils.py
-72 b/‎roop/utils.py
-72
@@ -1,2 +1,3 @@
 [flake8]
-select = E3, E4, F
+select = E3, E4, F
+per-file-ignores = roop/core.py:E402
@@ -13,7 +13,9 @@ jobs:
     with:
      python-version: 3.9
   - run: pip install flake8
-  - run: flake8 run.py core
+  - run: pip install mypy
+  - run: flake8 run.py roop
+  - run: mypy --config-file mypi.ini run.py roop
  test:
   runs-on: ubuntu-latest
   steps:
@@ -25,8 +27,7 @@ jobs:
     uses: actions/setup-python@v2
     with:
      python-version: 3.9
-  - run: pip install -r requirements.txt gdown
-  - run: gdown 13QpWFWJ37EB-nHrEOY64CEtQWY-tz7DZ
-  - run: ./run.py -f=.github/examples/face.jpg -t=.github/examples/target.mp4 -o=.github/examples/output.mp4
-  - run: ffmpeg -i .github/examples/snapshot.mp4 -i .github/examples/output.mp4 -filter_complex "psnr" -f null -
+  - run: pip install -r requirements-ci.txt
+  - run: python run.py -s=.github/examples/source.jpg -t=.github/examples/target.mp4 -o=.github/examples/output.mp4
+  - run: ffmpeg -i .github/examples/snapshot.mp4 -i .github/examples/output.mp4 -filter_complex psnr -f null -
 
@@ -1,3 +1,4 @@
 .idea
+models
+temp
 __pycache__
-*.onnx
 
@@ -0,0 +1,21 @@
+## Pull Requests
+
+### Do
+
+- ...consider to fix bugs over adding features
+- ...one pull request for one feature or improvement 
+- ...consult us about implementation details
+- ...proper testing before you submit your code
+- ...resolve failed CI pipelines
+
+### Don't
+
+- ...introduce fundamental changes in terms of software architecture
+- ...introduce OOP - we accept functional programming only
+- ...ignore given requirements or try to work around them
+- ...submit code to a development branch without consulting us
+- ...submit massive amount of code changes
+- ...submit a proof of concept
+- ...submit code that is using undocumented and private APIs
+- ...solve third party issues in our project
+- ...comment what your code does - use proper naming instead
@@ -36,26 +36,32 @@ Additional command line arguments are given below:
 ```
 options:
   -h, --help            show this help message and exit
-  -f SOURCE_IMG, --face SOURCE_IMG
-                        use this face
+  -s SOURCE_PATH, --source SOURCE_PATH
+                        select an source image
   -t TARGET_PATH, --target TARGET_PATH
-                        replace this face
-  -o OUTPUT_FILE, --output OUTPUT_FILE
-                        save output to this file
-  --keep-fps            maintain original fps
-  --keep-frames         keep frames directory
-  --all-faces           swap all faces in frame
+                        select an target image or video
+  -o OUTPUT_PATH, --output OUTPUT_PATH
+                        select output file or directory
+  --frame-processor {face_swapper,face_enhancer} [{face_swapper,face_enhancer} ...]
+                        pipeline of frame processors
+  --keep-fps            keep original fps
+  --keep-audio          keep original audio
+  --keep-frames         keep temporary frames
+  --many-faces          process every face
+  --video-encoder {libx264,libx265,libvpx-vp9}
+                        adjust output video encoder
+  --video-quality VIDEO_QUALITY
+                        adjust output video quality
   --max-memory MAX_MEMORY
-                        maximum amount of RAM in GB to be used
-  --cpu-cores CPU_CORES
-                        number of CPU cores to use
-  --gpu-threads GPU_THREADS
-                        number of threads to be use for the GPU
-  --gpu-vendor {apple,amd,intel,nvidia}
-                        choice your GPU vendor
+                        maximum amount of RAM in GB
+  --execution-provider {cpu,...} [{cpu,...} ...]
+                        execution provider
+  --execution-threads EXECUTION_THREADS
+                        number of execution threads
+  -v, --version         show program's version number and exit
 ```
 
-Looking for a CLI mode? Using the -f/--face argument will make the program in cli mode.
+Looking for a CLI mode? Using the -s/--source argument will make the program in cli mode.
 
 ## Credits
 - [henryruhs](https://github.com/henryruhs): for being an irreplaceable contributor to the project
 
@@ -0,0 +1,7 @@
+[mypy]
+check_untyped_defs = True
+disallow_any_generics = True
+disallow_untyped_calls = True
+disallow_untyped_defs = True
+ignore_missing_imports = True
+strict_optional = False
@@ -0,0 +1,14 @@
+numpy==1.23.5
+opencv-python==4.7.0.72
+onnx==1.14.0
+insightface==0.7.3
+psutil==5.9.5
+tk==0.1.0
+customtkinter==5.1.3
+torch==2.0.1
+torchvision==0.15.2
+onnxruntime==1.15.0
+tensorflow==2.12.0
+opennsfw2==0.10.2
+protobuf==4.23.2
+tqdm==4.65.0
@@ -6,14 +6,18 @@ onnx==1.14.0
 insightface==0.7.3
 psutil==5.9.5
 tk==0.1.0
+customtkinter==5.1.3
 pillow==9.5.0
 torch==2.0.1+cu118; sys_platform != 'darwin'
 torch==2.0.1; sys_platform == 'darwin'
+torchvision==0.15.2+cu118; sys_platform != 'darwin'
+torchvision==0.15.2; sys_platform == 'darwin'
 onnxruntime==1.15.0; sys_platform == 'darwin' and platform_machine != 'arm64'
 onnxruntime-silicon==1.13.1; sys_platform == 'darwin' and platform_machine == 'arm64'
 onnxruntime-gpu==1.15.0; sys_platform != 'darwin'
 tensorflow==2.13.0rc1; sys_platform == 'darwin'
 tensorflow==2.12.0; sys_platform != 'darwin'
 opennsfw2==0.10.2
 protobuf==4.23.2
-tqdm==4.65.0
+tqdm==4.65.0
+gfpgan==1.3.8
@@ -1 +0,0 @@
- 
@@ -0,0 +1,20 @@
+from typing import Any
+import cv2
+
+
+def get_video_frame(video_path: str, frame_number: int = 0) -> Any:
+    capture = cv2.VideoCapture(video_path)
+    frame_total = capture.get(cv2.CAP_PROP_FRAME_COUNT)
+    capture.set(cv2.CAP_PROP_POS_FRAMES, min(frame_total, frame_number - 1))
+    has_frame, frame = capture.read()
+    capture.release()
+    if has_frame:
+        return frame
+    return None
+
+
+def get_video_frame_total(video_path: str) -> int:
+    capture = cv2.VideoCapture(video_path)
+    video_frame_total = int(capture.get(cv2.CAP_PROP_FRAME_COUNT))
+    capture.release()
+    return video_frame_total
@@ -0,0 +1,31 @@
+from typing import Any
+import insightface
+
+import roop.globals
+from roop.typing import Frame
+
+FACE_ANALYSER = None
+
+
+def get_face_analyser() -> Any:
+    global FACE_ANALYSER
+
+    if FACE_ANALYSER is None:
+        FACE_ANALYSER = insightface.app.FaceAnalysis(name='buffalo_l', providers=roop.globals.execution_providers)
+        FACE_ANALYSER.prepare(ctx_id=0, det_size=(640, 640))
+    return FACE_ANALYSER
+
+
+def get_one_face(frame: Frame) -> Any:
+    face = get_face_analyser().get(frame)
+    try:
+        return min(face, key=lambda x: x.bbox[0])
+    except ValueError:
+        return None
+
+
+def get_many_faces(frame: Frame) -> Any:
+    try:
+        return get_face_analyser().get(frame)
+    except IndexError:
+        return None
@@ -1,11 +1,17 @@
-import onnxruntime
+from typing import List
 
-all_faces = None
+source_path = None
+target_path = None
+output_path = None
+frame_processors: List[str] = []
+keep_fps = None
+keep_audio = None
+keep_frames = None
+many_faces = None
+video_encoder = None
+video_quality = None
+max_memory = None
+execution_providers: List[str] = []
+execution_threads = None
+headless = None
 log_level = 'error'
-cpu_cores = None
-gpu_threads = None
-gpu_vendor = None
-providers = onnxruntime.get_available_providers()
-
-if 'TensorrtExecutionProvider' in providers:
-    providers.remove('TensorrtExecutionProvider')
 
@@ -0,0 +1,2 @@
+name = 'roop'
+version = '1.0.0'
@@ -0,0 +1,25 @@
+import numpy
+import opennsfw2
+from PIL import Image
+
+from roop.typing import Frame
+
+MAX_PROBABILITY = 0.85
+
+
+def predict_frame(target_frame: Frame) -> bool:
+    image = Image.fromarray(target_frame)
+    image = opennsfw2.preprocess_image(image, opennsfw2.Preprocessing.YAHOO)
+    model = opennsfw2.make_open_nsfw_model()
+    views = numpy.expand_dims(image, axis=0)
+    _, probability = model.predict(views)[0]
+    return probability > MAX_PROBABILITY
+
+
+def predict_image(target_path: str) -> bool:
+    return opennsfw2.predict_image(target_path) > MAX_PROBABILITY
+
+
+def predict_video(target_path: str) -> bool:
+    _, probabilities = opennsfw2.predict_video_frames(video_path=target_path, frame_interval=100)
+    return any(probability > MAX_PROBABILITY for probability in probabilities)
@@ -0,0 +1,56 @@
+import sys
+import importlib
+from concurrent.futures import ThreadPoolExecutor
+from types import ModuleType
+from typing import Any, List, Callable
+from tqdm import tqdm
+
+import roop
+
+FRAME_PROCESSORS_MODULES: List[ModuleType] = []
+FRAME_PROCESSORS_INTERFACE = [
+    'pre_check',
+    'pre_start',
+    'process_frame',
+    'process_image',
+    'process_video'
+]
+
+
+def load_frame_processor_module(frame_processor: str) -> Any:
+    try:
+        frame_processor_module = importlib.import_module(f'roop.processors.frame.{frame_processor}')
+        for method_name in FRAME_PROCESSORS_INTERFACE:
+            if not hasattr(frame_processor_module, method_name):
+                sys.exit()
+    except ImportError:
+        sys.exit()
+    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 multi_process_frame(source_path: str, temp_frame_paths: List[str], process_frames: Callable[[str, List[str], Any], None], progress: Any = None) -> None:
+    with ThreadPoolExecutor(max_workers=roop.globals.execution_threads) as executor:
+        futures = []
+        for path in temp_frame_paths:
+            future = executor.submit(process_frames, source_path, [path], progress)
+            futures.append(future)
+        for future in futures:
+            future.result()
+
+
+def process_video(source_path: str, frame_paths: list[str], process_frames: Callable[[str, List[str], Any], None]) -> None:
+    progress_bar_format = '{l_bar}{bar}| {n_fmt}/{total_fmt} [{elapsed}<{remaining}, {rate_fmt}{postfix}]'
+    total = len(frame_paths)
+    with tqdm(total=total, desc='Processing', unit='frame', dynamic_ncols=True, bar_format=progress_bar_format) as progress:
+        progress.set_postfix({'execution_providers': roop.globals.execution_providers, 'threads': roop.globals.execution_threads, 'memory': roop.globals.max_memory})
+        multi_process_frame(source_path, frame_paths, process_frames, progress)
@@ -0,0 +1,75 @@
+from typing import Any, List
+import cv2
+import threading
+import gfpgan
+
+import roop.globals
+import roop.processors.frame.core
+from roop.core import update_status
+from roop.face_analyser import get_one_face
+from roop.typing import Frame, Face
+from roop.utilities import conditional_download, resolve_relative_path, is_image, is_video
+
+FACE_ENHANCER = None
+THREAD_SEMAPHORE = threading.Semaphore()
+THREAD_LOCK = threading.Lock()
+NAME = 'ROOP.FACE-ENHANCER'
+
+
+def pre_check() -> bool:
+    download_directory_path = resolve_relative_path('../models')
+    conditional_download(download_directory_path, ['https://huggingface.co/henryruhs/roop/resolve/main/GFPGANv1.4.pth'])
+    return True
+
+
+def pre_start() -> bool:
+    if not is_image(roop.globals.target_path) and not is_video(roop.globals.target_path):
+        update_status('Select an image or video for target path.', NAME)
+        return False
+    return True
+
+
+def get_face_enhancer() -> Any:
+    global FACE_ENHANCER
+
+    with THREAD_LOCK:
+        if FACE_ENHANCER is None:
+            model_path = resolve_relative_path('../models/GFPGANv1.4.pth')
+            # todo: set models path https://github.com/TencentARC/GFPGAN/issues/399
+            FACE_ENHANCER = gfpgan.GFPGANer(model_path=model_path, upscale=1) # type: ignore[attr-defined]
+    return FACE_ENHANCER
+
+
+def enhance_face(temp_frame: Frame) -> Frame:
+    with THREAD_SEMAPHORE:
+        _, _, temp_frame = get_face_enhancer().enhance(
+            temp_frame,
+            paste_back=True
+        )
+    return temp_frame
+
+
+def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
+    target_face = get_one_face(temp_frame)
+    if target_face:
+        temp_frame = enhance_face(temp_frame)
+    return temp_frame
+
+
+def process_frames(source_path: str, temp_frame_paths: List[str], progress: Any = None) -> None:
+    for temp_frame_path in temp_frame_paths:
+        temp_frame = cv2.imread(temp_frame_path)
+        result = process_frame(None, temp_frame)
+        cv2.imwrite(temp_frame_path, result)
+        if progress:
+            progress.update(1)
+
+
+def process_image(source_path: str, target_path: str, output_path: str) -> None:
+    target_frame = cv2.imread(target_path)
+    result = process_frame(None, target_frame)
+    cv2.imwrite(output_path, result)
+
+
+def process_video(source_path: str, temp_frame_paths: List[str]) -> None:
+    roop.processors.frame.core.process_video(None, temp_frame_paths, process_frames)
@@ -0,0 +1,86 @@
+from typing import Any, List
+import cv2
+import insightface
+import threading
+
+import roop.globals
+import roop.processors.frame.core
+from roop.core import update_status
+from roop.face_analyser import get_one_face, get_many_faces
+from roop.typing import Face, Frame
+from roop.utilities import conditional_download, resolve_relative_path, is_image, is_video
+
+FACE_SWAPPER = None
+THREAD_LOCK = threading.Lock()
+NAME = 'ROOP.FACE-SWAPPER'
+
+
+def pre_check() -> bool:
+    download_directory_path = resolve_relative_path('../models')
+    conditional_download(download_directory_path, ['https://huggingface.co/henryruhs/roop/resolve/main/inswapper_128.onnx'])
+    return True
+
+
+def pre_start() -> bool:
+    if not is_image(roop.globals.source_path):
+        update_status('Select an image for source path.', NAME)
+        return False
+    elif not get_one_face(cv2.imread(roop.globals.source_path)):
+        update_status('No face in source path detected.', NAME)
+        return False
+    if not is_image(roop.globals.target_path) and not is_video(roop.globals.target_path):
+        update_status('Select an image or video for target path.', NAME)
+        return False
+    return True
+
+
+def get_face_swapper() -> Any:
+    global FACE_SWAPPER
+
+    with THREAD_LOCK:
+        if FACE_SWAPPER is None:
+            model_path = resolve_relative_path('../models/inswapper_128.onnx')
+            FACE_SWAPPER = insightface.model_zoo.get_model(model_path, providers=roop.globals.execution_providers)
+    return FACE_SWAPPER
+
+
+def swap_face(source_face: Face, target_face: Face, temp_frame: Frame) -> Frame:
+    return get_face_swapper().get(temp_frame, target_face, source_face, paste_back=True)
+
+
+def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
+    if roop.globals.many_faces:
+        many_faces = get_many_faces(temp_frame)
+        if many_faces:
+            for target_face in many_faces:
+                temp_frame = swap_face(source_face, target_face, temp_frame)
+    else:
+        target_face = get_one_face(temp_frame)
+        if target_face:
+            temp_frame = swap_face(source_face, target_face, temp_frame)
+    return temp_frame
+
+
+def process_frames(source_path: str, temp_frame_paths: List[str], progress: Any = None) -> None:
+    source_face = get_one_face(cv2.imread(source_path))
+    for temp_frame_path in temp_frame_paths:
+        temp_frame = cv2.imread(temp_frame_path)
+        try:
+            result = process_frame(source_face, temp_frame)
+            cv2.imwrite(temp_frame_path, result)
+        except Exception as exception:
+            print(exception)
+            pass
+        if progress:
+            progress.update(1)
+
+
+def process_image(source_path: str, target_path: str, output_path: str) -> None:
+    source_face = get_one_face(cv2.imread(source_path))
+    target_frame = cv2.imread(target_path)
+    result = process_frame(source_face, target_frame)
+    cv2.imwrite(output_path, result)
+
+
+def process_video(source_path: str, temp_frame_paths: List[str]) -> None:
+    roop.processors.frame.core.process_video(source_path, temp_frame_paths, process_frames)
@@ -0,0 +1,7 @@
+from typing import Any
+
+from insightface.app.common import Face
+import numpy
+
+Face = Face
+Frame = numpy.ndarray[Any, Any]
@@ -0,0 +1,155 @@
+{
+  "CTk": {
+    "fg_color": ["gray95", "gray10"]
+  },
+  "CTkToplevel": {
+    "fg_color": ["gray95", "gray10"]
+  },
+  "CTkFrame": {
+    "corner_radius": 6,
+    "border_width": 0,
+    "fg_color": ["gray90", "gray13"],
+    "top_fg_color": ["gray85", "gray16"],
+    "border_color": ["gray65", "gray28"]
+  },
+  "CTkButton": {
+    "corner_radius": 6,
+    "border_width": 0,
+    "fg_color": ["#3a7ebf", "#1f538d"],
+    "hover_color": ["#325882", "#14375e"],
+    "border_color": ["#3E454A", "#949A9F"],
+    "text_color": ["#DCE4EE", "#DCE4EE"],
+    "text_color_disabled": ["gray74", "gray60"]
+  },
+  "CTkLabel": {
+    "corner_radius": 0,
+    "fg_color": "transparent",
+    "text_color": ["gray14", "gray84"]
+  },
+  "CTkEntry": {
+    "corner_radius": 6,
+    "border_width": 2,
+    "fg_color": ["#F9F9FA", "#343638"],
+    "border_color": ["#979DA2", "#565B5E"],
+    "text_color": ["gray14", "gray84"],
+    "placeholder_text_color": ["gray52", "gray62"]
+  },
+  "CTkCheckbox": {
+    "corner_radius": 6,
+    "border_width": 3,
+    "fg_color": ["#3a7ebf", "#1f538d"],
+    "border_color": ["#3E454A", "#949A9F"],
+    "hover_color": ["#325882", "#14375e"],
+    "checkmark_color": ["#DCE4EE", "gray90"],
+    "text_color": ["gray14", "gray84"],
+    "text_color_disabled": ["gray60", "gray45"]
+  },
+  "CTkSwitch": {
+    "corner_radius": 1000,
+    "border_width": 3,
+    "button_length": 0,
+    "fg_color": ["#939BA2", "#4A4D50"],
+    "progress_color": ["#3a7ebf", "#1f538d"],
+    "button_color": ["gray36", "#D5D9DE"],
+    "button_hover_color": ["gray20", "gray100"],
+    "text_color": ["gray14", "gray84"],
+    "text_color_disabled": ["gray60", "gray45"]
+  },
+  "CTkRadiobutton": {
+    "corner_radius": 1000,
+    "border_width_checked": 6,
+    "border_width_unchecked": 3,
+    "fg_color": ["#3a7ebf", "#1f538d"],
+    "border_color": ["#3E454A", "#949A9F"],
+    "hover_color": ["#325882", "#14375e"],
+    "text_color": ["gray14", "gray84"],
+    "text_color_disabled": ["gray60", "gray45"]
+  },
+  "CTkProgressBar": {
+    "corner_radius": 1000,
+    "border_width": 0,
+    "fg_color": ["#939BA2", "#4A4D50"],
+    "progress_color": ["#3a7ebf", "#1f538d"],
+    "border_color": ["gray", "gray"]
+  },
+  "CTkSlider": {
+    "corner_radius": 1000,
+    "button_corner_radius": 1000,
+    "border_width": 6,
+    "button_length": 0,
+    "fg_color": ["#939BA2", "#4A4D50"],
+    "progress_color": ["gray40", "#AAB0B5"],
+    "button_color": ["#3a7ebf", "#1f538d"],
+    "button_hover_color": ["#325882", "#14375e"]
+  },
+  "CTkOptionMenu": {
+    "corner_radius": 6,
+    "fg_color": ["#3a7ebf", "#1f538d"],
+    "button_color": ["#325882", "#14375e"],
+    "button_hover_color": ["#234567", "#1e2c40"],
+    "text_color": ["#DCE4EE", "#DCE4EE"],
+    "text_color_disabled": ["gray74", "gray60"]
+  },
+  "CTkComboBox": {
+    "corner_radius": 6,
+    "border_width": 2,
+    "fg_color": ["#F9F9FA", "#343638"],
+    "border_color": ["#979DA2", "#565B5E"],
+    "button_color": ["#979DA2", "#565B5E"],
+    "button_hover_color": ["#6E7174", "#7A848D"],
+    "text_color": ["gray14", "gray84"],
+    "text_color_disabled": ["gray50", "gray45"]
+  },
+  "CTkScrollbar": {
+    "corner_radius": 1000,
+    "border_spacing": 4,
+    "fg_color": "transparent",
+    "button_color": ["gray55", "gray41"],
+    "button_hover_color": ["gray40", "gray53"]
+  },
+  "CTkSegmentedButton": {
+    "corner_radius": 6,
+    "border_width": 2,
+    "fg_color": ["#979DA2", "gray29"],
+    "selected_color": ["#3a7ebf", "#1f538d"],
+    "selected_hover_color": ["#325882", "#14375e"],
+    "unselected_color": ["#979DA2", "gray29"],
+    "unselected_hover_color": ["gray70", "gray41"],
+    "text_color": ["#DCE4EE", "#DCE4EE"],
+    "text_color_disabled": ["gray74", "gray60"]
+  },
+  "CTkTextbox": {
+    "corner_radius": 6,
+    "border_width": 0,
+    "fg_color": ["gray100", "gray20"],
+    "border_color": ["#979DA2", "#565B5E"],
+    "text_color": ["gray14", "gray84"],
+    "scrollbar_button_color": ["gray55", "gray41"],
+    "scrollbar_button_hover_color": ["gray40", "gray53"]
+  },
+  "CTkScrollableFrame": {
+    "label_fg_color": ["gray80", "gray21"]
+  },
+  "DropdownMenu": {
+    "fg_color": ["gray90", "gray20"],
+    "hover_color": ["gray75", "gray28"],
+    "text_color": ["gray14", "gray84"]
+  },
+  "CTkFont": {
+    "macOS": {
+      "family": "Avenir",
+      "size": 12,
+      "weight": "normal"
+    },
+    "Windows": {
+      "family": "Corbel",
+      "size": 12,
+      "weight": "normal"
+    },
+    "Linux": {
+      "family": "Montserrat",
+      "size": 12,
+      "weight": "normal"
+    }
+  }
+}
@@ -0,0 +1,141 @@
+import glob
+import mimetypes
+import os
+import platform
+import shutil
+import ssl
+import subprocess
+import urllib
+from pathlib import Path
+from typing import List, Any
+from tqdm import tqdm
+
+import roop.globals
+
+TEMP_FILE = 'temp.mp4'
+TEMP_DIRECTORY = 'temp'
+
+# monkey patch ssl for mac
+if platform.system().lower() == 'darwin':
+    ssl._create_default_https_context = ssl._create_unverified_context
+
+
+def run_ffmpeg(args: List[str]) -> bool:
+    commands = ['ffmpeg', '-hide_banner', '-hwaccel', 'auto', '-loglevel', roop.globals.log_level]
+    commands.extend(args)
+    try:
+        subprocess.check_output(commands, stderr=subprocess.STDOUT)
+        return True
+    except Exception:
+        pass
+    return False
+
+
+def detect_fps(target_path: str) -> float:
+    command = ['ffprobe', '-v', 'error', '-select_streams', 'v:0', '-show_entries', 'stream=r_frame_rate', '-of', 'default=noprint_wrappers=1:nokey=1', target_path]
+    output = subprocess.check_output(command).decode().strip().split('/')
+    try:
+        numerator, denominator = map(int, output)
+        return numerator / denominator
+    except Exception:
+        pass
+    return 30.0
+
+
+def extract_frames(target_path: str) -> None:
+    temp_directory_path = get_temp_directory_path(target_path)
+    run_ffmpeg(['-i', target_path, '-pix_fmt', 'rgb24', os.path.join(temp_directory_path, '%04d.png')])
+
+
+def create_video(target_path: str, fps: float = 30.0) -> None:
+    temp_output_path = get_temp_output_path(target_path)
+    temp_directory_path = get_temp_directory_path(target_path)
+    run_ffmpeg(['-r', str(fps), '-i', os.path.join(temp_directory_path, '%04d.png'), '-c:v', roop.globals.video_encoder, '-crf', str(roop.globals.video_quality), '-pix_fmt', 'yuv420p', '-vf', 'colorspace=bt709:iall=bt601-6-625:fast=1', '-y', temp_output_path])
+
+
+def restore_audio(target_path: str, output_path: str) -> None:
+    temp_output_path = get_temp_output_path(target_path)
+    done = run_ffmpeg(['-i', temp_output_path, '-i', target_path, '-c:v', 'copy', '-map', '0:v:0', '-map', '1:a:0', '-y', output_path])
+    if not done:
+        move_temp(target_path, output_path)
+
+
+def get_temp_frame_paths(target_path: str) -> List[str]:
+    temp_directory_path = get_temp_directory_path(target_path)
+    return glob.glob((os.path.join(glob.escape(temp_directory_path), '*.png')))
+
+
+def get_temp_directory_path(target_path: str) -> str:
+    target_name, _ = os.path.splitext(os.path.basename(target_path))
+    target_directory_path = os.path.dirname(target_path)
+    return os.path.join(target_directory_path, TEMP_DIRECTORY, target_name)
+
+
+def get_temp_output_path(target_path: str) -> str:
+    temp_directory_path = get_temp_directory_path(target_path)
+    return os.path.join(temp_directory_path, TEMP_FILE)
+
+
+def normalize_output_path(source_path: str, target_path: str, output_path: str) -> Any:
+    if source_path and target_path:
+        source_name, _ = os.path.splitext(os.path.basename(source_path))
+        target_name, target_extension = os.path.splitext(os.path.basename(target_path))
+        if os.path.isdir(output_path):
+            return os.path.join(output_path, source_name + '-' + target_name + target_extension)
+    return output_path
+
+
+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_path = get_temp_output_path(target_path)
+    if os.path.isfile(temp_output_path):
+        if os.path.isfile(output_path):
+            os.remove(output_path)
+        shutil.move(temp_output_path, output_path)
+
+
+def clean_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 roop.globals.keep_frames and os.path.isdir(temp_directory_path):
+        shutil.rmtree(temp_directory_path)
+    if os.path.exists(parent_directory_path) and not os.listdir(parent_directory_path):
+        os.rmdir(parent_directory_path)
+
+
+def has_image_extension(image_path: str) -> bool:
+    return image_path.lower().endswith(('png', 'jpg', 'jpeg'))
+
+
+def is_image(image_path: str) -> bool:
+    if image_path and os.path.isfile(image_path):
+        mimetype, _ = mimetypes.guess_type(image_path)
+        return bool(mimetype and mimetype.startswith('image/'))
+    return False
+
+
+def is_video(video_path: str) -> bool:
+    if video_path and os.path.isfile(video_path):
+        mimetype, _ = mimetypes.guess_type(video_path)
+        return bool(mimetype and mimetype.startswith('video/'))
+    return False
+
+
+def conditional_download(download_directory_path: str, urls: List[str]) -> None:
+    if not os.path.exists(download_directory_path):
+        os.makedirs(download_directory_path)
+    for url in urls:
+        download_file_path = os.path.join(download_directory_path, os.path.basename(url))
+        if not os.path.exists(download_file_path):
+            request = urllib.request.urlopen(url) # type: ignore[attr-defined]
+            total = int(request.headers.get('Content-Length', 0))
+            with tqdm(total=total, desc='Downloading', unit='B', unit_scale=True, unit_divisor=1024) as progress:
+                urllib.request.urlretrieve(url, download_file_path, reporthook=lambda count, block_size, total_size: progress.update(block_size)) # type: ignore[attr-defined]
+
+
+def resolve_relative_path(path: str) -> str:
+    return os.path.abspath(os.path.join(os.path.dirname(__file__), path))
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,4 @@`
`1`	`1`	`.idea`
	`2`	`+models`
	`3`	`+temp`
`2`	`4`	`__pycache__`
`3`		`-*.onnx`