Update metadata.py

better mouth mask showing and tracking the lips part only.

README.md

@@ -1,4 +1,4 @@
-<h1 align="center">Deep-Live-Cam</h1>
+<h1 align="center">Deep-Live-Cam 2.0.2c</h1>
 
 <p align="center">
   Real-time face swap and video deepfake with a single click and only a single image.
@@ -30,7 +30,7 @@ By using this software, you agree to these terms and commit to using it in a man
 
 Users are expected to use this software responsibly and legally. If using a real person's face, obtain their consent and clearly label any output as a deepfake when sharing online. We are not responsible for end-user actions.
 
-## Exclusive v2.1 Quick Start - Pre-built (Windows/Mac Silicon)
+## Exclusive v2.4 Quick Start - Pre-built (Windows/Mac Silicon)
 
   <a href="https://deeplivecam.net/index.php/quickstart"> <img src="media/Download.png" width="285" height="77" />
 
@@ -179,6 +179,11 @@ source venv/bin/activate
 
 # install the dependencies again
 pip install -r requirements.txt
+
+# gfpgan and basicsrs issue fix
+pip install git+https://github.com/xinntao/BasicSR.git@master
+pip uninstall gfpgan -y
+pip install git+https://github.com/TencentARC/GFPGAN.git@master
 ```
 
 **Run:** If you don't have a GPU, you can run Deep-Live-Cam using `python run.py`. Note that initial execution will download models (~300MB).
@@ -348,11 +353,14 @@ Looking for a CLI mode? Using the -s/--source argument will make the run program
  - [*"That's Crazy, Oh God. That's Fucking Freaky Dude... That's So Wild Dude"*](https://www.youtube.com/watch?time_continue=1074&v=py4Tc-Y8BcY) - SomeOrdinaryGamers
  - [*"Alright look look look, now look chat, we can do any face we want to look like chat"*](https://www.youtube.com/live/mFsCe7AIxq8?feature=shared&t=2686) - IShowSpeed
  - [*"They do a pretty good job matching poses, expression and even the lighting"*](https://www.youtube.com/watch?v=wnCghLjqv3s&t=551s) - TechLinked (LTT)
+ - [*"Als Sean Connery an der Redaktionskonferenz teilnahm"*](https://www.golem.de/news/deepfakes-als-sean-connery-an-der-redaktionskonferenz-teilnahm-2408-188172.html) - Golem.de (German)
+ - [*"What the F***! Why do I look like Vinny Jr? I look exactly like Vinny Jr!? No, this shit is crazy! Bro This is F*** Crazy! "*](https://youtu.be/JbUPRmXRUtE?t=3964) - IShowSpeed
 
 
 ## Credits
 
 -   [ffmpeg](https://ffmpeg.org/): for making video-related operations easy
+-   [Henry](https://github.com/henryruhs): One of the major contributor in this repo
 -   [deepinsight](https://github.com/deepinsight): for their [insightface](https://github.com/deepinsight/insightface) project which provided a well-made library and models. Please be reminded that the [use of the model is for non-commercial research purposes only](https://github.com/deepinsight/insightface?tab=readme-ov-file#license).
 -   [havok2-htwo](https://github.com/havok2-htwo): for sharing the code for webcam
 -   [GosuDRM](https://github.com/GosuDRM): for the open version of roop

locales/id.json

@@ -0,0 +1,45 @@
+{
+    "Source x Target Mapper": "Pemetaan Sumber x Target",
+    "select a source image": "Pilih gambar sumber",
+    "Preview": "Pratinjau",
+    "select a target image or video": "Pilih gambar atau video target",
+    "save image output file": "Simpan file keluaran gambar",
+    "save video output file": "Simpan file keluaran video",
+    "select a target image": "Pilih gambar target",
+    "source": "Sumber",
+    "Select a target": "Pilih target",
+    "Select a face": "Pilih wajah",
+    "Keep audio": "Pertahankan audio",
+    "Face Enhancer": "Peningkat wajah",
+    "Many faces": "Banyak wajah",
+    "Show FPS": "Tampilkan FPS",
+    "Keep fps": "Pertahankan FPS",
+    "Keep frames": "Pertahankan frame",
+    "Fix Blueish Cam": "Perbaiki kamera kebiruan",
+    "Mouth Mask": "Masker mulut",
+    "Show Mouth Mask Box": "Tampilkan kotak masker mulut",
+    "Start": "Mulai",
+    "Live": "Langsung",
+    "Destroy": "Hentikan",
+    "Map faces": "Petakan wajah",
+    "Processing...": "Sedang memproses...",
+    "Processing succeed!": "Pemrosesan berhasil!",
+    "Processing ignored!": "Pemrosesan diabaikan!",
+    "Failed to start camera": "Gagal memulai kamera",
+    "Please complete pop-up or close it.": "Harap selesaikan atau tutup pop-up.",
+    "Getting unique faces": "Mengambil wajah unik",
+    "Please select a source image first": "Silakan pilih gambar sumber terlebih dahulu",
+    "No faces found in target": "Tidak ada wajah ditemukan pada target",
+    "Add": "Tambah",
+    "Clear": "Bersihkan",
+    "Submit": "Kirim",
+    "Select source image": "Pilih gambar sumber",
+    "Select target image": "Pilih gambar target",
+    "Please provide mapping!": "Harap tentukan pemetaan!",
+    "At least 1 source with target is required!": "Minimal 1 sumber dengan target diperlukan!",
+    "Face could not be detected in last upload!": "Wajah tidak dapat terdeteksi pada unggahan terakhir!",
+    "Select Camera:": "Pilih Kamera:",
+    "All mappings cleared!": "Semua pemetaan telah dibersihkan!",
+    "Mappings successfully submitted!": "Pemetaan berhasil dikirim!",
+    "Source x Target Mapper is already open.": "Pemetaan Sumber x Target sudah terbuka."
+}

modules/core.py

@@ -129,11 +129,22 @@ def suggest_execution_providers() -> List[str]:
 
 
 def suggest_execution_threads() -> int:
+    """Suggest optimal thread count based on hardware and execution provider."""
+    import os
+    
+    # Get CPU count
+    cpu_count = os.cpu_count() or 4
+    
     if 'DmlExecutionProvider' in modules.globals.execution_providers:
         return 1
     if 'ROCMExecutionProvider' in modules.globals.execution_providers:
         return 1
-    return 8
+    if 'CUDAExecutionProvider' in modules.globals.execution_providers:
+        # For CUDA, use more threads for parallel frame processing
+        return min(cpu_count, 16)
+    
+    # For CPU execution, use most cores but leave some for system
+    return max(4, min(cpu_count - 2, 16))
 
 
 def limit_resources() -> None:
@@ -176,10 +187,16 @@ def update_status(message: str, scope: str = 'DLC.CORE') -> None:
         ui.update_status(message)
 
 def start() -> None:
+    """Start processing with performance monitoring."""
+    import time
+    
+    start_time = time.time()
+    
     for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
         if not frame_processor.pre_start():
             return
     update_status('Processing...')
+    
     # process image to image
     if has_image_extension(modules.globals.target_path):
         if modules.globals.nsfw_filter and ui.check_and_ignore_nsfw(modules.globals.target_path, destroy):
@@ -193,26 +210,40 @@ def start() -> None:
             frame_processor.process_image(modules.globals.source_path, modules.globals.output_path, modules.globals.output_path)
             release_resources()
         if is_image(modules.globals.target_path):
-            update_status('Processing to image succeed!')
+            elapsed = time.time() - start_time
+            update_status(f'Processing to image succeed! (Time: {elapsed:.2f}s)')
         else:
             update_status('Processing to image failed!')
         return
+    
     # process image to videos
     if modules.globals.nsfw_filter and ui.check_and_ignore_nsfw(modules.globals.target_path, destroy):
         return
 
+    extraction_start = time.time()
     if not modules.globals.map_faces:
         update_status('Creating temp resources...')
         create_temp(modules.globals.target_path)
         update_status('Extracting frames...')
         extract_frames(modules.globals.target_path)
+    extraction_time = time.time() - extraction_start
+    update_status(f'Frame extraction completed in {extraction_time:.2f}s')
 
     temp_frame_paths = get_temp_frame_paths(modules.globals.target_path)
+    total_frames = len(temp_frame_paths)
+    update_status(f'Processing {total_frames} frames with {modules.globals.execution_threads} threads...')
+    
+    processing_start = time.time()
     for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
         update_status('Progressing...', frame_processor.NAME)
         frame_processor.process_video(modules.globals.source_path, temp_frame_paths)
         release_resources()
+    processing_time = time.time() - processing_start
+    fps_processing = total_frames / processing_time if processing_time > 0 else 0
+    update_status(f'Frame processing completed in {processing_time:.2f}s ({fps_processing:.2f} fps)')
+    
     # handles fps
+    encoding_start = time.time()
     if modules.globals.keep_fps:
         update_status('Detecting fps...')
         fps = detect_fps(modules.globals.target_path)
@@ -221,6 +252,9 @@ def start() -> None:
     else:
         update_status('Creating video with 30.0 fps...')
         create_video(modules.globals.target_path)
+    encoding_time = time.time() - encoding_start
+    update_status(f'Video encoding completed in {encoding_time:.2f}s')
+    
     # handle audio
     if modules.globals.keep_audio:
         if modules.globals.keep_fps:
@@ -230,10 +264,13 @@ def start() -> None:
         restore_audio(modules.globals.target_path, modules.globals.output_path)
     else:
         move_temp(modules.globals.target_path, modules.globals.output_path)
+    
     # clean and validate
     clean_temp(modules.globals.target_path)
+    
+    total_time = time.time() - start_time
     if is_video(modules.globals.target_path):
-        update_status('Processing to video succeed!')
+        update_status(f'Processing to video succeed! Total time: {total_time:.2f}s')
     else:
         update_status('Processing to video failed!')
 

modules/custom_types.py

@@ -0,0 +1,7 @@
+from typing import Any
+
+from insightface.app.common import Face
+import numpy
+ 
+Face = Face
+Frame = numpy.ndarray[Any, Any] 

modules/face_analyser.py

@@ -2,6 +2,7 @@ import os
 import shutil
 from typing import Any
 import insightface
+import threading
 
 import cv2
 import numpy as np
@@ -13,14 +14,22 @@ from modules.utilities import get_temp_directory_path, create_temp, extract_fram
 from pathlib import Path
 
 FACE_ANALYSER = None
+FACE_ANALYSER_LOCK = threading.Lock()
 
 
 def get_face_analyser() -> Any:
+    """Get face analyser with thread-safe initialization."""
     global FACE_ANALYSER
 
     if FACE_ANALYSER is None:
-        FACE_ANALYSER = insightface.app.FaceAnalysis(name='buffalo_l', providers=modules.globals.execution_providers)
+        with FACE_ANALYSER_LOCK:
-        FACE_ANALYSER.prepare(ctx_id=0, det_size=(640, 640))
+            # Double-check after acquiring lock
+            if FACE_ANALYSER is None:
+                FACE_ANALYSER = insightface.app.FaceAnalysis(
+                    name='buffalo_l',
+                    providers=modules.globals.execution_providers
+                )
+                FACE_ANALYSER.prepare(ctx_id=0, det_size=(640, 640))
     return FACE_ANALYSER
 
 

modules/globals.py

@@ -1,3 +1,5 @@
+# --- START OF FILE globals.py ---
+
 import os
 from typing import List, Dict, Any
 
@@ -9,35 +11,62 @@ file_types = [
     ("Video", ("*.mp4", "*.mkv")),
 ]
 
-source_target_map = []
+# Face Mapping Data
-simple_map = {}
+source_target_map: List[Dict[str, Any]] = [] # Stores detailed map for image/video processing
+simple_map: Dict[str, Any] = {}             # Stores simplified map (embeddings/faces) for live/simple mode
 
-source_path = None
+# Paths
-target_path = None
+source_path: str | None = None
-output_path = None
+target_path: str | None = None
+output_path: str | None = None
+
+# Processing Options
 frame_processors: List[str] = []
-keep_fps = True
+keep_fps: bool = True
-keep_audio = True
+keep_audio: bool = True
-keep_frames = False
+keep_frames: bool = False
-many_faces = False
+many_faces: bool = False         # Process all detected faces with default source
-map_faces = False
+map_faces: bool = False          # Use source_target_map or simple_map for specific swaps
-color_correction = False  # New global variable for color correction toggle
+poisson_blend: bool = False      # Enable Poisson Blending for smoother face swaps
-nsfw_filter = False
+color_correction: bool = False   # Enable color correction (implementation specific)
-video_encoder = None
+nsfw_filter: bool = False
-video_quality = None
+
-live_mirror = False
+# Video Output Options
-live_resizable = True
+video_encoder: str | None = None
-max_memory = None
+video_quality: int | None = None # Typically a CRF value or bitrate
-execution_providers: List[str] = []
+
-execution_threads = None
+# Live Mode Options
-headless = None
+live_mirror: bool = False
-log_level = "error"
+live_resizable: bool = True
+camera_input_combobox: Any | None = None # Placeholder for UI element if needed
+webcam_preview_running: bool = False
+show_fps: bool = False
+
+# System Configuration
+max_memory: int | None = None        # Memory limit in GB? (Needs clarification)
+execution_providers: List[str] = []  # e.g., ['CUDAExecutionProvider', 'CPUExecutionProvider']
+execution_threads: int | None = None # Number of threads for CPU execution
+headless: bool | None = None         # Run without UI?
+log_level: str = "error"             # Logging level (e.g., 'debug', 'info', 'warning', 'error')
+
+# Face Processor UI Toggles (Example)
 fp_ui: Dict[str, bool] = {"face_enhancer": False}
-camera_input_combobox = None
+
-webcam_preview_running = False
+# Face Swapper Specific Options
-show_fps = False
+face_swapper_enabled: bool = True # General toggle for the swapper processor
-mouth_mask = False
+opacity: float = 1.0              # Blend factor for the swapped face (0.0-1.0)
-show_mouth_mask_box = False
+sharpness: float = 0.0            # Sharpness enhancement for swapped face (0.0-1.0+)
-mask_feather_ratio = 8
+
-mask_down_size = 0.50
+# Mouth Mask Options
-mask_size = 1
+mouth_mask: bool = False           # Enable mouth area masking/pasting
+show_mouth_mask_box: bool = False  # Visualize the mouth mask area (for debugging)
+mask_feather_ratio: int = 12       # Denominator for feathering calculation (higher = smaller feather)
+mask_down_size: float = 0.1        # Expansion factor for lower lip mask (relative)
+mask_size: float = 1.0             # Expansion factor for upper lip mask (relative)
+
+# --- START: Added for Frame Interpolation ---
+enable_interpolation: bool = True # Toggle temporal smoothing
+interpolation_weight: float = 0  # Blend weight for current frame (0.0-1.0). Lower=smoother.
+# --- END: Added for Frame Interpolation ---
+
+# --- END OF FILE globals.py ---

modules/metadata.py

@@ -1,3 +1,3 @@
 name = 'Deep-Live-Cam'
-version = '1.8.1'
+version = '2.0.3c'
-edition = 'GitHub Edition'
+edition = 'GitHub Edition'

modules/processors/frame/core.py

@@ -67,13 +67,29 @@ def set_frame_processors_modules_from_ui(frame_processors: List[str]) -> None:
                  print(f"Warning: Error removing frame processor {frame_processor}: {e}")
 
 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=modules.globals.execution_threads) as executor:
+    """Process frames in parallel with optimized batching and memory management."""
-        futures = []
+    max_workers = modules.globals.execution_threads
-        for path in temp_frame_paths:
+    
-            future = executor.submit(process_frames, source_path, [path], progress)
+    # Determine optimal batch size based on available memory and thread count
-            futures.append(future)
+    # Process frames in batches to avoid memory overflow
-        for future in futures:
+    batch_size = max(1, min(32, len(temp_frame_paths) // max(1, max_workers)))
-            future.result()
+    
+    with ThreadPoolExecutor(max_workers=max_workers) as executor:
+        # Process in batches to manage memory better
+        for i in range(0, len(temp_frame_paths), batch_size):
+            batch = temp_frame_paths[i:i + batch_size]
+            futures = []
+            
+            for path in batch:
+                future = executor.submit(process_frames, source_path, [path], progress)
+                futures.append(future)
+            
+            # Wait for batch to complete before starting next batch
+            for future in futures:
+                try:
+                    future.result()
+                except Exception as e:
+                    print(f"Error processing frame: {e}")
 
 
 def process_video(source_path: str, frame_paths: list[str], process_frames: Callable[[str, List[str], Any], None]) -> None:

modules/processors/frame/face_enhancer.py

@@ -1,16 +1,18 @@
+# --- START OF FILE face_enhancer.py ---
+
 from typing import Any, List
 import cv2
 import threading
 import gfpgan
 import os
+import platform
+import torch # Make sure torch is imported
 
 import modules.globals
 import modules.processors.frame.core
 from modules.core import update_status
 from modules.face_analyser import get_one_face
 from modules.typing import Frame, Face
-import platform
-import torch
 from modules.utilities import (
     conditional_download,
     is_image,
@@ -48,83 +50,157 @@ def pre_start() -> bool:
     return True
 
 
-TENSORRT_AVAILABLE = False
-try:
-    import torch_tensorrt
-    TENSORRT_AVAILABLE = True
-except ImportError as im:
-    print(f"TensorRT is not available: {im}")
-    pass
-except Exception as e:
-    print(f"TensorRT is not available: {e}")
-    pass
-
 def get_face_enhancer() -> Any:
+    """
+    Initializes and returns the GFPGAN face enhancer instance,
+    prioritizing CUDA, then MPS (Mac), then CPU.
+    """
     global FACE_ENHANCER
 
     with THREAD_LOCK:
         if FACE_ENHANCER is None:
             model_path = os.path.join(models_dir, "GFPGANv1.4.pth")
-            
+            device = None
-            selected_device = None
+            try:
-            device_priority = []
+                # Priority 1: CUDA
+                if torch.cuda.is_available():
+                    device = torch.device("cuda")
+                    print(f"{NAME}: Using CUDA device.")
+                # Priority 2: MPS (Mac Silicon)
+                elif platform.system() == "Darwin" and torch.backends.mps.is_available():
+                    device = torch.device("mps")
+                    print(f"{NAME}: Using MPS device.")
+                # Priority 3: CPU
+                else:
+                    device = torch.device("cpu")
+                    print(f"{NAME}: Using CPU device.")
 
-            if TENSORRT_AVAILABLE and torch.cuda.is_available():
+                FACE_ENHANCER = gfpgan.GFPGANer(
-                selected_device = torch.device("cuda")
+                    model_path=model_path,
-                device_priority.append("TensorRT+CUDA")
+                    upscale=1,  # upscale=1 means enhancement only, no resizing
-            elif torch.cuda.is_available():
+                    arch='clean',
-                selected_device = torch.device("cuda")
+                    channel_multiplier=2,
-                device_priority.append("CUDA")
+                    bg_upsampler=None,
-            elif torch.backends.mps.is_available() and platform.system() == "Darwin":
+                    device=device
-                selected_device = torch.device("mps")
+                )
-                device_priority.append("MPS")
+                print(f"{NAME}: GFPGANer initialized successfully on {device}.")
-            elif not torch.cuda.is_available():
+
-                selected_device = torch.device("cpu")
+            except Exception as e:
-                device_priority.append("CPU")
+                print(f"{NAME}: Error initializing GFPGANer: {e}")
-            
+                # Fallback to CPU if initialization with GPU fails for some reason
-            FACE_ENHANCER = gfpgan.GFPGANer(model_path=model_path, upscale=1, device=selected_device)
+                if device is not None and device.type != 'cpu':
+                    print(f"{NAME}: Falling back to CPU due to error.")
+                    try:
+                        device = torch.device("cpu")
+                        FACE_ENHANCER = gfpgan.GFPGANer(
+                            model_path=model_path,
+                            upscale=1,
+                            arch='clean',
+                            channel_multiplier=2,
+                            bg_upsampler=None,
+                            device=device
+                        )
+                        print(f"{NAME}: GFPGANer initialized successfully on CPU after fallback.")
+                    except Exception as fallback_e:
+                         print(f"{NAME}: FATAL: Could not initialize GFPGANer even on CPU: {fallback_e}")
+                         FACE_ENHANCER = None # Ensure it's None if totally failed
+                else:
+                    # If it failed even on the first CPU attempt or device was already CPU
+                     print(f"{NAME}: FATAL: Could not initialize GFPGANer on CPU: {e}")
+                     FACE_ENHANCER = None # Ensure it's None if totally failed
+
+
+    # Check if enhancer is still None after attempting initialization
+    if FACE_ENHANCER is None:
+        raise RuntimeError(f"{NAME}: Failed to initialize GFPGANer. Check logs for errors.")
 
-            # for debug:
-            print(f"Selected device: {selected_device} and device priority: {device_priority}")
     return FACE_ENHANCER
 
 
 def enhance_face(temp_frame: Frame) -> Frame:
-    with THREAD_SEMAPHORE:
+    """Enhances faces in a single frame using the global GFPGANer instance."""
-        _, _, temp_frame = get_face_enhancer().enhance(temp_frame, paste_back=True)
+    # Ensure enhancer is ready
-    return temp_frame
+    enhancer = get_face_enhancer()
+    try:
+        with THREAD_SEMAPHORE:
+            # The enhance method returns: _, restored_faces, restored_img
+            _, _, restored_img = enhancer.enhance(
+                temp_frame,
+                has_aligned=False, # Assume faces are not pre-aligned
+                only_center_face=False, # Enhance all detected faces
+                paste_back=True # Paste enhanced faces back onto the original image
+            )
+        # GFPGAN might return None if no face is detected or an error occurs
+        if restored_img is None:
+            # print(f"{NAME}: Warning: GFPGAN enhancement returned None. Returning original frame.")
+            return temp_frame
+        return restored_img
+    except Exception as e:
+        print(f"{NAME}: Error during face enhancement: {e}")
+        # Return the original frame in case of error during enhancement
+        return temp_frame
 
 
-def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
+def process_frame(source_face: Face | None, temp_frame: Frame) -> Frame:
-    target_face = get_one_face(temp_frame)
+    """Processes a frame: enhances face if detected."""
-    if target_face:
+    # We don't strictly need source_face for enhancement only
-        temp_frame = enhance_face(temp_frame)
+    # Check if any face exists to potentially save processing time, though GFPGAN also does detection.
+    # For simplicity and ensuring enhancement is attempted if possible, we can rely on enhance_face.
+    # target_face = get_one_face(temp_frame) # This gets only ONE face
+    # If you want to enhance ONLY if a face is detected by your *own* analyser first:
+    # has_face = get_one_face(temp_frame) is not None # Or use get_many_faces
+    # if has_face:
+    #     temp_frame = enhance_face(temp_frame)
+    # else: # Enhance regardless, let GFPGAN handle detection
+    temp_frame = enhance_face(temp_frame)
     return temp_frame
 
 
 def process_frames(
-    source_path: str, temp_frame_paths: List[str], progress: Any = None
+    source_path: str | None, temp_frame_paths: List[str], progress: Any = None
 ) -> None:
+    """Processes multiple frames from file paths."""
     for temp_frame_path in temp_frame_paths:
+        if not os.path.exists(temp_frame_path):
+            print(f"{NAME}: Warning: Frame path not found {temp_frame_path}, skipping.")
+            if progress:
+                progress.update(1)
+            continue
+
         temp_frame = cv2.imread(temp_frame_path)
-        result = process_frame(None, temp_frame)
+        if temp_frame is None:
-        cv2.imwrite(temp_frame_path, result)
+            print(f"{NAME}: Warning: Failed to read frame {temp_frame_path}, skipping.")
+            if progress:
+                progress.update(1)
+            continue
+
+        result_frame = process_frame(None, temp_frame)
+        cv2.imwrite(temp_frame_path, result_frame)
         if progress:
             progress.update(1)
 
 
-def process_image(source_path: str, target_path: str, output_path: str) -> None:
+def process_image(source_path: str | None, target_path: str, output_path: str) -> None:
+    """Processes a single image file."""
     target_frame = cv2.imread(target_path)
-    result = process_frame(None, target_frame)
+    if target_frame is None:
-    cv2.imwrite(output_path, result)
+        print(f"{NAME}: Error: Failed to read target image {target_path}")
+        return
+    result_frame = process_frame(None, target_frame)
+    cv2.imwrite(output_path, result_frame)
+    print(f"{NAME}: Enhanced image saved to {output_path}")
 
 
-def process_video(source_path: str, temp_frame_paths: List[str]) -> None:
+def process_video(source_path: str | None, temp_frame_paths: List[str]) -> None:
-    modules.processors.frame.core.process_video(None, temp_frame_paths, process_frames)
+    """Processes video frames using the frame processor core."""
+    # source_path might be optional depending on how process_video is called
+    modules.processors.frame.core.process_video(source_path, temp_frame_paths, process_frames)
 
+# Optional: Keep process_frame_v2 if it's used elsewhere, otherwise it's redundant
+# def process_frame_v2(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_frame_v2(temp_frame: Frame) -> Frame:
+# --- END OF FILE face_enhancer.py ---
-    target_face = get_one_face(temp_frame)
-    if target_face:
-        temp_frame = enhance_face(temp_frame)
-    return temp_frame

modules/processors/frame/face_masking.py

@@ -0,0 +1,566 @@
+import cv2
+import numpy as np
+from modules.typing import Face, Frame
+import modules.globals
+
+def apply_color_transfer(source, target):
+    """
+    Apply color transfer from target to source image
+    """
+    source = cv2.cvtColor(source, cv2.COLOR_BGR2LAB).astype("float32")
+    target = cv2.cvtColor(target, cv2.COLOR_BGR2LAB).astype("float32")
+
+    source_mean, source_std = cv2.meanStdDev(source)
+    target_mean, target_std = cv2.meanStdDev(target)
+
+    # Reshape mean and std to be broadcastable
+    source_mean = source_mean.reshape(1, 1, 3)
+    source_std = source_std.reshape(1, 1, 3)
+    target_mean = target_mean.reshape(1, 1, 3)
+    target_std = target_std.reshape(1, 1, 3)
+
+    # Perform the color transfer
+    source = (source - source_mean) * (target_std / source_std) + target_mean
+
+    return cv2.cvtColor(np.clip(source, 0, 255).astype("uint8"), cv2.COLOR_LAB2BGR)
+
+def create_face_mask(face: Face, frame: Frame) -> np.ndarray:
+    mask = np.zeros(frame.shape[:2], dtype=np.uint8)
+    landmarks = face.landmark_2d_106
+    if landmarks is not None:
+        # Convert landmarks to int32
+        landmarks = landmarks.astype(np.int32)
+
+        # Extract facial features
+        right_side_face = landmarks[0:16]
+        left_side_face = landmarks[17:32]
+        right_eye = landmarks[33:42]
+        right_eye_brow = landmarks[43:51]
+        left_eye = landmarks[87:96]
+        left_eye_brow = landmarks[97:105]
+
+        # Calculate padding
+        padding = int(
+            np.linalg.norm(right_side_face[0] - left_side_face[-1]) * 0.05
+        )  # 5% of face width
+
+        # Create a slightly larger convex hull for padding
+        face_outline = landmarks[0:33]
+        hull = cv2.convexHull(face_outline)
+        hull_padded = []
+        for point in hull:
+            x, y = point[0]
+            center = np.mean(face_outline, axis=0)
+            direction = np.array([x, y]) - center
+            direction = direction / np.linalg.norm(direction)
+            padded_point = np.array([x, y]) + direction * padding
+            hull_padded.append(padded_point)
+
+        hull_padded = np.array(hull_padded, dtype=np.int32)
+
+        # Fill the padded convex hull
+        cv2.fillConvexPoly(mask, hull_padded, 255)
+
+        # Smooth the mask edges
+        mask = cv2.GaussianBlur(mask, (5, 5), 3)
+
+    return mask
+
+def create_lower_mouth_mask(
+    face: Face, frame: Frame
+) -> (np.ndarray, np.ndarray, tuple, np.ndarray):
+    mask = np.zeros(frame.shape[:2], dtype=np.uint8)
+    mouth_cutout = None
+    lower_lip_polygon = None
+    mouth_box = (0,0,0,0)
+
+    landmarks = face.landmark_2d_106
+    if landmarks is not None:
+        # Use outer mouth landmarks (52-63) to capture the lips only
+        lower_lip_order = list(range(52, 64))
+        
+        if max(lower_lip_order) >= landmarks.shape[0]:
+            return mask, mouth_cutout, mouth_box, lower_lip_polygon
+
+        lower_lip_landmarks = landmarks[lower_lip_order].astype(np.float32)
+
+        # Calculate the center of the landmarks
+        center = np.mean(lower_lip_landmarks, axis=0)
+
+        # Expand the landmarks outward using the mouth_mask_size
+        # Use a more conservative expansion to avoid affecting face shape
+        expansion_factor = (
+            1 + modules.globals.mask_down_size * modules.globals.mouth_mask_size
+        )
+        expanded_landmarks = (lower_lip_landmarks - center) * expansion_factor + center
+
+        # Removed specific top/chin extensions to preserve face shape
+
+        # Convert back to integer coordinates
+        expanded_landmarks = expanded_landmarks.astype(np.int32)
+
+        # Calculate bounding box for the expanded lower mouth
+        min_x, min_y = np.min(expanded_landmarks, axis=0)
+        max_x, max_y = np.max(expanded_landmarks, axis=0)
+
+        # Add some padding to the bounding box
+        padding = int((max_x - min_x) * 0.1)  # 10% padding
+        min_x = max(0, min_x - padding)
+        min_y = max(0, min_y - padding)
+        max_x = min(frame.shape[1], max_x + padding)
+        max_y = min(frame.shape[0], max_y + padding)
+
+        # Ensure the bounding box dimensions are valid
+        if max_x <= min_x or max_y <= min_y:
+            if (max_x - min_x) <= 1:
+                max_x = min_x + 1
+            if (max_y - min_y) <= 1:
+                max_y = min_y + 1
+
+        # Create the mask
+        mask_roi = np.zeros((max_y - min_y, max_x - min_x), dtype=np.uint8)
+        # Shift polygon coordinates relative to the ROI's top-left corner
+        polygon_relative_to_roi = expanded_landmarks - [min_x, min_y]
+        cv2.fillPoly(mask_roi, [polygon_relative_to_roi], 255)
+
+        # Apply Gaussian blur to soften the mask edges
+        mask_roi = cv2.GaussianBlur(mask_roi, (15, 15), 5)
+
+        # Place the mask ROI in the full-sized mask
+        mask[min_y:max_y, min_x:max_x] = mask_roi
+
+        # Extract the masked area from the frame
+        mouth_cutout = frame[min_y:max_y, min_x:max_x].copy()
+
+        # Return the expanded lower lip polygon in original frame coordinates
+        lower_lip_polygon = expanded_landmarks
+        mouth_box = (min_x, min_y, max_x, max_y)
+
+    return mask, mouth_cutout, mouth_box, lower_lip_polygon
+
+def create_eyes_mask(face: Face, frame: Frame) -> (np.ndarray, np.ndarray, tuple, np.ndarray):
+    mask = np.zeros(frame.shape[:2], dtype=np.uint8)
+    eyes_cutout = None
+    landmarks = face.landmark_2d_106
+    if landmarks is not None:
+        # Left eye landmarks (87-96) and right eye landmarks (33-42)
+        left_eye = landmarks[87:96]
+        right_eye = landmarks[33:42]
+        
+        # Calculate centers and dimensions for each eye
+        left_eye_center = np.mean(left_eye, axis=0).astype(np.int32)
+        right_eye_center = np.mean(right_eye, axis=0).astype(np.int32)
+        
+        # Calculate eye dimensions with size adjustment
+        def get_eye_dimensions(eye_points):
+            x_coords = eye_points[:, 0]
+            y_coords = eye_points[:, 1]
+            width = int((np.max(x_coords) - np.min(x_coords)) * (1 + modules.globals.mask_down_size * modules.globals.eyes_mask_size))
+            height = int((np.max(y_coords) - np.min(y_coords)) * (1 + modules.globals.mask_down_size * modules.globals.eyes_mask_size))
+            return width, height
+        
+        left_width, left_height = get_eye_dimensions(left_eye)
+        right_width, right_height = get_eye_dimensions(right_eye)
+        
+        # Add extra padding
+        padding = int(max(left_width, right_width) * 0.2)
+        
+        # Calculate bounding box for both eyes
+        min_x = min(left_eye_center[0] - left_width//2, right_eye_center[0] - right_width//2) - padding
+        max_x = max(left_eye_center[0] + left_width//2, right_eye_center[0] + right_width//2) + padding
+        min_y = min(left_eye_center[1] - left_height//2, right_eye_center[1] - right_height//2) - padding
+        max_y = max(left_eye_center[1] + left_height//2, right_eye_center[1] + right_height//2) + padding
+        
+        # Ensure coordinates are within frame bounds
+        min_x = max(0, min_x)
+        min_y = max(0, min_y)
+        max_x = min(frame.shape[1], max_x)
+        max_y = min(frame.shape[0], max_y)
+        
+        # Create mask for the eyes region
+        mask_roi = np.zeros((max_y - min_y, max_x - min_x), dtype=np.uint8)
+        
+        # Draw ellipses for both eyes
+        left_center = (left_eye_center[0] - min_x, left_eye_center[1] - min_y)
+        right_center = (right_eye_center[0] - min_x, right_eye_center[1] - min_y)
+        
+        # Calculate axes lengths (half of width and height)
+        left_axes = (left_width//2, left_height//2)
+        right_axes = (right_width//2, right_height//2)
+        
+        # Draw filled ellipses
+        cv2.ellipse(mask_roi, left_center, left_axes, 0, 0, 360, 255, -1)
+        cv2.ellipse(mask_roi, right_center, right_axes, 0, 0, 360, 255, -1)
+        
+        # Apply Gaussian blur to soften mask edges
+        mask_roi = cv2.GaussianBlur(mask_roi, (15, 15), 5)
+        
+        # Place the mask ROI in the full-sized mask
+        mask[min_y:max_y, min_x:max_x] = mask_roi
+        
+        # Extract the masked area from the frame
+        eyes_cutout = frame[min_y:max_y, min_x:max_x].copy()
+        
+        # Create polygon points for visualization
+        def create_ellipse_points(center, axes):
+            t = np.linspace(0, 2*np.pi, 32)
+            x = center[0] + axes[0] * np.cos(t)
+            y = center[1] + axes[1] * np.sin(t)
+            return np.column_stack((x, y)).astype(np.int32)
+        
+        # Generate points for both ellipses
+        left_points = create_ellipse_points((left_eye_center[0], left_eye_center[1]), (left_width//2, left_height//2))
+        right_points = create_ellipse_points((right_eye_center[0], right_eye_center[1]), (right_width//2, right_height//2))
+        
+        # Combine points for both eyes
+        eyes_polygon = np.vstack([left_points, right_points])
+        
+    return mask, eyes_cutout, (min_x, min_y, max_x, max_y), eyes_polygon
+
+def create_curved_eyebrow(points):
+    if len(points) >= 5:
+        # Sort points by x-coordinate
+        sorted_idx = np.argsort(points[:, 0])
+        sorted_points = points[sorted_idx]
+        
+        # Calculate dimensions
+        x_min, y_min = np.min(sorted_points, axis=0)
+        x_max, y_max = np.max(sorted_points, axis=0)
+        width = x_max - x_min
+        height = y_max - y_min
+        
+        # Create more points for smoother curve
+        num_points = 50
+        x = np.linspace(x_min, x_max, num_points)
+        
+        # Fit quadratic curve through points for more natural arch
+        coeffs = np.polyfit(sorted_points[:, 0], sorted_points[:, 1], 2)
+        y = np.polyval(coeffs, x)
+        
+        # Increased offsets to create more separation
+        top_offset = height * 0.5  # Increased from 0.3 to shift up more
+        bottom_offset = height * 0.2  # Increased from 0.1 to shift down more
+        
+        # Create smooth curves
+        top_curve = y - top_offset
+        bottom_curve = y + bottom_offset
+        
+        # Create curved endpoints with more pronounced taper
+        end_points = 5
+        start_x = np.linspace(x[0] - width * 0.15, x[0], end_points)  # Increased taper
+        end_x = np.linspace(x[-1], x[-1] + width * 0.15, end_points)  # Increased taper
+        
+        # Create tapered ends
+        start_curve = np.column_stack((
+            start_x,
+            np.linspace(bottom_curve[0], top_curve[0], end_points)
+        ))
+        end_curve = np.column_stack((
+            end_x,
+            np.linspace(bottom_curve[-1], top_curve[-1], end_points)
+        ))
+        
+        # Combine all points to form a smooth contour
+        contour_points = np.vstack([
+            start_curve,
+            np.column_stack((x, top_curve)),
+            end_curve,
+            np.column_stack((x[::-1], bottom_curve[::-1]))
+        ])
+        
+        # Add slight padding for better coverage
+        center = np.mean(contour_points, axis=0)
+        vectors = contour_points - center
+        padded_points = center + vectors * 1.2  # Increased padding slightly
+        
+        return padded_points
+    return points
+
+def create_eyebrows_mask(face: Face, frame: Frame) -> (np.ndarray, np.ndarray, tuple, np.ndarray):
+    mask = np.zeros(frame.shape[:2], dtype=np.uint8)
+    eyebrows_cutout = None
+    landmarks = face.landmark_2d_106
+    if landmarks is not None:
+        # Left eyebrow landmarks (97-105) and right eyebrow landmarks (43-51)
+        left_eyebrow = landmarks[97:105].astype(np.float32)
+        right_eyebrow = landmarks[43:51].astype(np.float32)
+        
+        # Calculate centers and dimensions for each eyebrow
+        left_center = np.mean(left_eyebrow, axis=0)
+        right_center = np.mean(right_eyebrow, axis=0)
+        
+        # Calculate bounding box with padding adjusted by size
+        all_points = np.vstack([left_eyebrow, right_eyebrow])
+        padding_factor = modules.globals.eyebrows_mask_size
+        min_x = np.min(all_points[:, 0]) - 25 * padding_factor
+        max_x = np.max(all_points[:, 0]) + 25 * padding_factor
+        min_y = np.min(all_points[:, 1]) - 20 * padding_factor
+        max_y = np.max(all_points[:, 1]) + 15 * padding_factor
+        
+        # Ensure coordinates are within frame bounds
+        min_x = max(0, int(min_x))
+        min_y = max(0, int(min_y))
+        max_x = min(frame.shape[1], int(max_x))
+        max_y = min(frame.shape[0], int(max_y))
+        
+        # Create mask for the eyebrows region
+        mask_roi = np.zeros((max_y - min_y, max_x - min_x), dtype=np.uint8)
+        
+        try:
+            # Convert points to local coordinates
+            left_local = left_eyebrow - [min_x, min_y]
+            right_local = right_eyebrow - [min_x, min_y]
+            
+            def create_curved_eyebrow(points):
+                if len(points) >= 5:
+                    # Sort points by x-coordinate
+                    sorted_idx = np.argsort(points[:, 0])
+                    sorted_points = points[sorted_idx]
+                    
+                    # Calculate dimensions
+                    x_min, y_min = np.min(sorted_points, axis=0)
+                    x_max, y_max = np.max(sorted_points, axis=0)
+                    width = x_max - x_min
+                    height = y_max - y_min
+                    
+                    # Create more points for smoother curve
+                    num_points = 50
+                    x = np.linspace(x_min, x_max, num_points)
+                    
+                    # Fit quadratic curve through points for more natural arch
+                    coeffs = np.polyfit(sorted_points[:, 0], sorted_points[:, 1], 2)
+                    y = np.polyval(coeffs, x)
+                    
+                    # Increased offsets to create more separation
+                    top_offset = height * 0.5  # Increased from 0.3 to shift up more
+                    bottom_offset = height * 0.2  # Increased from 0.1 to shift down more
+                    
+                    # Create smooth curves
+                    top_curve = y - top_offset
+                    bottom_curve = y + bottom_offset
+                    
+                    # Create curved endpoints with more pronounced taper
+                    end_points = 5
+                    start_x = np.linspace(x[0] - width * 0.15, x[0], end_points)  # Increased taper
+                    end_x = np.linspace(x[-1], x[-1] + width * 0.15, end_points)  # Increased taper
+                    
+                    # Create tapered ends
+                    start_curve = np.column_stack((
+                        start_x,
+                        np.linspace(bottom_curve[0], top_curve[0], end_points)
+                    ))
+                    end_curve = np.column_stack((
+                        end_x,
+                        np.linspace(bottom_curve[-1], top_curve[-1], end_points)
+                    ))
+                    
+                    # Combine all points to form a smooth contour
+                    contour_points = np.vstack([
+                        start_curve,
+                        np.column_stack((x, top_curve)),
+                        end_curve,
+                        np.column_stack((x[::-1], bottom_curve[::-1]))
+                    ])
+                    
+                    # Add slight padding for better coverage
+                    center = np.mean(contour_points, axis=0)
+                    vectors = contour_points - center
+                    padded_points = center + vectors * 1.2  # Increased padding slightly
+                    
+                    return padded_points
+                return points
+            
+            # Generate and draw eyebrow shapes
+            left_shape = create_curved_eyebrow(left_local)
+            right_shape = create_curved_eyebrow(right_local)
+            
+            # Apply multi-stage blurring for natural feathering
+            # First, strong Gaussian blur for initial softening
+            mask_roi = cv2.GaussianBlur(mask_roi, (21, 21), 7)
+            
+            # Second, medium blur for transition areas
+            mask_roi = cv2.GaussianBlur(mask_roi, (11, 11), 3)
+            
+            # Finally, light blur for fine details
+            mask_roi = cv2.GaussianBlur(mask_roi, (5, 5), 1)
+            
+            # Normalize mask values
+            mask_roi = cv2.normalize(mask_roi, None, 0, 255, cv2.NORM_MINMAX)
+            
+            # Place the mask ROI in the full-sized mask
+            mask[min_y:max_y, min_x:max_x] = mask_roi
+            
+            # Extract the masked area from the frame
+            eyebrows_cutout = frame[min_y:max_y, min_x:max_x].copy()
+            
+            # Combine points for visualization
+            eyebrows_polygon = np.vstack([
+                left_shape + [min_x, min_y],
+                right_shape + [min_x, min_y]
+            ]).astype(np.int32)
+            
+        except Exception as e:
+            # Fallback to simple polygons if curve fitting fails
+            left_local = left_eyebrow - [min_x, min_y]
+            right_local = right_eyebrow - [min_x, min_y]
+            cv2.fillPoly(mask_roi, [left_local.astype(np.int32)], 255)
+            cv2.fillPoly(mask_roi, [right_local.astype(np.int32)], 255)
+            mask_roi = cv2.GaussianBlur(mask_roi, (21, 21), 7)
+            mask[min_y:max_y, min_x:max_x] = mask_roi
+            eyebrows_cutout = frame[min_y:max_y, min_x:max_x].copy()
+            eyebrows_polygon = np.vstack([left_eyebrow, right_eyebrow]).astype(np.int32)
+        
+    return mask, eyebrows_cutout, (min_x, min_y, max_x, max_y), eyebrows_polygon
+
+def apply_mask_area(
+    frame: np.ndarray,
+    cutout: np.ndarray,
+    box: tuple,
+    face_mask: np.ndarray,
+    polygon: np.ndarray,
+) -> np.ndarray:
+    min_x, min_y, max_x, max_y = box
+    box_width = max_x - min_x
+    box_height = max_y - min_y
+
+    if (
+        cutout is None
+        or box_width is None
+        or box_height is None
+        or face_mask is None
+        or polygon is None
+    ):
+        return frame
+
+    try:
+        resized_cutout = cv2.resize(cutout, (box_width, box_height))
+        roi = frame[min_y:max_y, min_x:max_x]
+
+        if roi.shape != resized_cutout.shape:
+            resized_cutout = cv2.resize(
+                resized_cutout, (roi.shape[1], roi.shape[0])
+            )
+
+        color_corrected_area = apply_color_transfer(resized_cutout, roi)
+
+        # Create mask for the area
+        polygon_mask = np.zeros(roi.shape[:2], dtype=np.uint8)
+        
+        # Split points for left and right parts if needed
+        if len(polygon) > 50:  # Arbitrary threshold to detect if we have multiple parts
+            mid_point = len(polygon) // 2
+            left_points = polygon[:mid_point] - [min_x, min_y]
+            right_points = polygon[mid_point:] - [min_x, min_y]
+            cv2.fillPoly(polygon_mask, [left_points], 255)
+            cv2.fillPoly(polygon_mask, [right_points], 255)
+        else:
+            adjusted_polygon = polygon - [min_x, min_y]
+            cv2.fillPoly(polygon_mask, [adjusted_polygon], 255)
+
+        # Apply strong initial feathering
+        polygon_mask = cv2.GaussianBlur(polygon_mask, (21, 21), 7)
+
+        # Apply additional feathering
+        feather_amount = min(
+            30,
+            box_width // modules.globals.mask_feather_ratio,
+            box_height // modules.globals.mask_feather_ratio,
+        )
+        feathered_mask = cv2.GaussianBlur(
+            polygon_mask.astype(float), (0, 0), feather_amount
+        )
+        feathered_mask = feathered_mask / feathered_mask.max()
+
+        # Apply additional smoothing to the mask edges
+        feathered_mask = cv2.GaussianBlur(feathered_mask, (5, 5), 1)
+
+        face_mask_roi = face_mask[min_y:max_y, min_x:max_x]
+        combined_mask = feathered_mask * (face_mask_roi / 255.0)
+
+        combined_mask = combined_mask[:, :, np.newaxis]
+        blended = (
+            color_corrected_area * combined_mask + roi * (1 - combined_mask)
+        ).astype(np.uint8)
+
+        # Apply face mask to blended result
+        face_mask_3channel = (
+            np.repeat(face_mask_roi[:, :, np.newaxis], 3, axis=2) / 255.0
+        )
+        final_blend = blended * face_mask_3channel + roi * (1 - face_mask_3channel)
+
+        frame[min_y:max_y, min_x:max_x] = final_blend.astype(np.uint8)
+    except Exception as e:
+        pass
+
+    return frame
+
+def draw_mask_visualization(
+    frame: Frame,
+    mask_data: tuple,
+    label: str,
+    draw_method: str = "polygon"
+) -> Frame:
+    mask, cutout, (min_x, min_y, max_x, max_y), polygon = mask_data
+
+    vis_frame = frame.copy()
+
+    # Ensure coordinates are within frame bounds
+    height, width = vis_frame.shape[:2]
+    min_x, min_y = max(0, min_x), max(0, min_y)
+    max_x, max_y = min(width, max_x), min(height, max_y)
+
+    if draw_method == "ellipse" and len(polygon) > 50:  # For eyes
+        # Split points for left and right parts
+        mid_point = len(polygon) // 2
+        left_points = polygon[:mid_point]
+        right_points = polygon[mid_point:]
+        
+        try:
+            # Fit ellipses to points - need at least 5 points
+            if len(left_points) >= 5 and len(right_points) >= 5:
+                # Convert points to the correct format for ellipse fitting
+                left_points = left_points.astype(np.float32)
+                right_points = right_points.astype(np.float32)
+                
+                # Fit ellipses
+                left_ellipse = cv2.fitEllipse(left_points)
+                right_ellipse = cv2.fitEllipse(right_points)
+                
+                # Draw the ellipses
+                cv2.ellipse(vis_frame, left_ellipse, (0, 255, 0), 2)
+                cv2.ellipse(vis_frame, right_ellipse, (0, 255, 0), 2)
+        except Exception as e:
+            # If ellipse fitting fails, draw simple rectangles as fallback
+            left_rect = cv2.boundingRect(left_points)
+            right_rect = cv2.boundingRect(right_points)
+            cv2.rectangle(vis_frame, 
+                        (left_rect[0], left_rect[1]), 
+                        (left_rect[0] + left_rect[2], left_rect[1] + left_rect[3]), 
+                        (0, 255, 0), 2)
+            cv2.rectangle(vis_frame,
+                        (right_rect[0], right_rect[1]),
+                        (right_rect[0] + right_rect[2], right_rect[1] + right_rect[3]),
+                        (0, 255, 0), 2)
+    else:  # For mouth and eyebrows
+        # Draw the polygon
+        if len(polygon) > 50:  # If we have multiple parts
+            mid_point = len(polygon) // 2
+            left_points = polygon[:mid_point]
+            right_points = polygon[mid_point:]
+            cv2.polylines(vis_frame, [left_points], True, (0, 255, 0), 2, cv2.LINE_AA)
+            cv2.polylines(vis_frame, [right_points], True, (0, 255, 0), 2, cv2.LINE_AA)
+        else:
+            cv2.polylines(vis_frame, [polygon], True, (0, 255, 0), 2, cv2.LINE_AA)
+
+    # Add label
+    cv2.putText(
+        vis_frame,
+        label,
+        (min_x, min_y - 10),
+        cv2.FONT_HERSHEY_SIMPLEX,
+        0.5,
+        (255, 255, 255),
+        1,
+    )
+
+    return vis_frame

modules/run.py

@@ -0,0 +1,9 @@
+#!/usr/bin/env python3
+
+# Import the tkinter fix to patch the ScreenChanged error
+import tkinter_fix
+
+import core
+
+if __name__ == '__main__':
+    core.run()

modules/tkinter_fix.py

@@ -0,0 +1,26 @@
+import tkinter
+
+# Only needs to be imported once at the beginning of the application
+def apply_patch():
+    # Create a monkey patch for the internal _tkinter module
+    original_init = tkinter.Tk.__init__
+    
+    def patched_init(self, *args, **kwargs):
+        # Call the original init
+        original_init(self, *args, **kwargs)
+        
+        # Define the missing ::tk::ScreenChanged procedure
+        self.tk.eval("""
+        if {[info commands ::tk::ScreenChanged] == ""} {
+            proc ::tk::ScreenChanged {args} {
+                # Do nothing
+                return
+            }
+        }
+        """)
+    
+    # Apply the monkey patch
+    tkinter.Tk.__init__ = patched_init
+
+# Apply the patch automatically when this module is imported
+apply_patch() 

modules/ui.py

@@ -27,6 +27,7 @@ from modules.utilities import (
 )
 from modules.video_capture import VideoCapturer
 from modules.gettext import LanguageManager
+from modules import globals
 import platform
 
 if platform.system() == "Windows":
@@ -35,7 +36,7 @@ if platform.system() == "Windows":
 ROOT = None
 POPUP = None
 POPUP_LIVE = None
-ROOT_HEIGHT = 700
+ROOT_HEIGHT = 800
 ROOT_WIDTH = 600
 
 PREVIEW = None
@@ -97,6 +98,7 @@ def save_switch_states():
         "keep_frames": modules.globals.keep_frames,
         "many_faces": modules.globals.many_faces,
         "map_faces": modules.globals.map_faces,
+        "poisson_blend": modules.globals.poisson_blend,
         "color_correction": modules.globals.color_correction,
         "nsfw_filter": modules.globals.nsfw_filter,
         "live_mirror": modules.globals.live_mirror,
@@ -119,6 +121,7 @@ def load_switch_states():
         modules.globals.keep_frames = switch_states.get("keep_frames", False)
         modules.globals.many_faces = switch_states.get("many_faces", False)
         modules.globals.map_faces = switch_states.get("map_faces", False)
+        modules.globals.poisson_blend = switch_states.get("poisson_blend", False)
         modules.globals.color_correction = switch_states.get("color_correction", False)
         modules.globals.nsfw_filter = switch_states.get("nsfw_filter", False)
         modules.globals.live_mirror = switch_states.get("live_mirror", False)
@@ -152,20 +155,20 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
     root.protocol("WM_DELETE_WINDOW", lambda: destroy())
 
     source_label = ctk.CTkLabel(root, text=None)
-    source_label.place(relx=0.1, rely=0.1, relwidth=0.3, relheight=0.25)
+    source_label.place(relx=0.1, rely=0.05, relwidth=0.275, relheight=0.225)
 
     target_label = ctk.CTkLabel(root, text=None)
-    target_label.place(relx=0.6, rely=0.1, relwidth=0.3, relheight=0.25)
+    target_label.place(relx=0.6, rely=0.05, relwidth=0.275, relheight=0.225)
 
     select_face_button = ctk.CTkButton(
         root, text=_("Select a face"), cursor="hand2", command=lambda: select_source_path()
     )
-    select_face_button.place(relx=0.1, rely=0.4, relwidth=0.3, relheight=0.1)
+    select_face_button.place(relx=0.1, rely=0.30, relwidth=0.3, relheight=0.1)
 
     swap_faces_button = ctk.CTkButton(
         root, text="↔", cursor="hand2", command=lambda: swap_faces_paths()
     )
-    swap_faces_button.place(relx=0.45, rely=0.4, relwidth=0.1, relheight=0.1)
+    swap_faces_button.place(relx=0.45, rely=0.30, relwidth=0.1, relheight=0.1)
 
     select_target_button = ctk.CTkButton(
         root,
@@ -173,7 +176,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
         cursor="hand2",
         command=lambda: select_target_path(),
     )
-    select_target_button.place(relx=0.6, rely=0.4, relwidth=0.3, relheight=0.1)
+    select_target_button.place(relx=0.6, rely=0.30, relwidth=0.3, relheight=0.1)
 
     keep_fps_value = ctk.BooleanVar(value=modules.globals.keep_fps)
     keep_fps_checkbox = ctk.CTkSwitch(
@@ -186,7 +189,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
             save_switch_states(),
         ),
     )
-    keep_fps_checkbox.place(relx=0.1, rely=0.6)
+    keep_fps_checkbox.place(relx=0.1, rely=0.5)
 
     keep_frames_value = ctk.BooleanVar(value=modules.globals.keep_frames)
     keep_frames_switch = ctk.CTkSwitch(
@@ -199,7 +202,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
             save_switch_states(),
         ),
     )
-    keep_frames_switch.place(relx=0.1, rely=0.65)
+    keep_frames_switch.place(relx=0.1, rely=0.55)
 
     enhancer_value = ctk.BooleanVar(value=modules.globals.fp_ui["face_enhancer"])
     enhancer_switch = ctk.CTkSwitch(
@@ -212,7 +215,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
             save_switch_states(),
         ),
     )
-    enhancer_switch.place(relx=0.1, rely=0.7)
+    enhancer_switch.place(relx=0.1, rely=0.6)
 
     keep_audio_value = ctk.BooleanVar(value=modules.globals.keep_audio)
     keep_audio_switch = ctk.CTkSwitch(
@@ -225,7 +228,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
             save_switch_states(),
         ),
     )
-    keep_audio_switch.place(relx=0.6, rely=0.6)
+    keep_audio_switch.place(relx=0.6, rely=0.5)
 
     many_faces_value = ctk.BooleanVar(value=modules.globals.many_faces)
     many_faces_switch = ctk.CTkSwitch(
@@ -238,7 +241,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
             save_switch_states(),
         ),
     )
-    many_faces_switch.place(relx=0.6, rely=0.65)
+    many_faces_switch.place(relx=0.6, rely=0.55)
 
     color_correction_value = ctk.BooleanVar(value=modules.globals.color_correction)
     color_correction_switch = ctk.CTkSwitch(
@@ -251,7 +254,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
             save_switch_states(),
         ),
     )
-    color_correction_switch.place(relx=0.6, rely=0.70)
+    color_correction_switch.place(relx=0.6, rely=0.6)
 
     #    nsfw_value = ctk.BooleanVar(value=modules.globals.nsfw_filter)
     #    nsfw_switch = ctk.CTkSwitch(root, text='NSFW filter', variable=nsfw_value, cursor='hand2', command=lambda: setattr(modules.globals, 'nsfw_filter', nsfw_value.get()))
@@ -269,7 +272,20 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
             close_mapper_window() if not map_faces.get() else None
         ),
     )
-    map_faces_switch.place(relx=0.1, rely=0.75)
+    map_faces_switch.place(relx=0.1, rely=0.65)
+
+    poisson_blend_value = ctk.BooleanVar(value=modules.globals.poisson_blend)
+    poisson_blend_switch = ctk.CTkSwitch(
+        root,
+        text=_("Poisson Blend"),
+        variable=poisson_blend_value,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "poisson_blend", poisson_blend_value.get()),
+            save_switch_states(),
+        ),
+    )
+    poisson_blend_switch.place(relx=0.1, rely=0.7)
 
     show_fps_value = ctk.BooleanVar(value=modules.globals.show_fps)
     show_fps_switch = ctk.CTkSwitch(
@@ -282,7 +298,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
             save_switch_states(),
         ),
     )
-    show_fps_switch.place(relx=0.6, rely=0.75)
+    show_fps_switch.place(relx=0.6, rely=0.65)
 
     mouth_mask_var = ctk.BooleanVar(value=modules.globals.mouth_mask)
     mouth_mask_switch = ctk.CTkSwitch(
@@ -292,7 +308,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
         cursor="hand2",
         command=lambda: setattr(modules.globals, "mouth_mask", mouth_mask_var.get()),
     )
-    mouth_mask_switch.place(relx=0.1, rely=0.55)
+    mouth_mask_switch.place(relx=0.1, rely=0.45)
 
     show_mouth_mask_box_var = ctk.BooleanVar(value=modules.globals.show_mouth_mask_box)
     show_mouth_mask_box_switch = ctk.CTkSwitch(
@@ -304,26 +320,26 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
             modules.globals, "show_mouth_mask_box", show_mouth_mask_box_var.get()
         ),
     )
-    show_mouth_mask_box_switch.place(relx=0.6, rely=0.55)
+    show_mouth_mask_box_switch.place(relx=0.6, rely=0.45)
 
     start_button = ctk.CTkButton(
         root, text=_("Start"), cursor="hand2", command=lambda: analyze_target(start, root)
     )
-    start_button.place(relx=0.15, rely=0.80, relwidth=0.2, relheight=0.05)
+    start_button.place(relx=0.15, rely=0.86, relwidth=0.2, relheight=0.05)
 
     stop_button = ctk.CTkButton(
         root, text=_("Destroy"), cursor="hand2", command=lambda: destroy()
     )
-    stop_button.place(relx=0.4, rely=0.80, relwidth=0.2, relheight=0.05)
+    stop_button.place(relx=0.4, rely=0.86, relwidth=0.2, relheight=0.05)
 
     preview_button = ctk.CTkButton(
         root, text=_("Preview"), cursor="hand2", command=lambda: toggle_preview()
     )
-    preview_button.place(relx=0.65, rely=0.80, relwidth=0.2, relheight=0.05)
+    preview_button.place(relx=0.65, rely=0.86, relwidth=0.2, relheight=0.05)
 
     # --- Camera Selection ---
     camera_label = ctk.CTkLabel(root, text=_("Select Camera:"))
-    camera_label.place(relx=0.1, rely=0.86, relwidth=0.2, relheight=0.05)
+    camera_label.place(relx=0.1, rely=0.92, relwidth=0.2, relheight=0.05)
 
     available_cameras = get_available_cameras()
     camera_indices, camera_names = available_cameras
@@ -342,7 +358,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
             root, variable=camera_variable, values=camera_names
         )
 
-    camera_optionmenu.place(relx=0.35, rely=0.86, relwidth=0.25, relheight=0.05)
+    camera_optionmenu.place(relx=0.35, rely=0.92, relwidth=0.25, relheight=0.05)
 
     live_button = ctk.CTkButton(
         root,
@@ -362,16 +378,82 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
             else "disabled"
         ),
     )
-    live_button.place(relx=0.65, rely=0.86, relwidth=0.2, relheight=0.05)
+    live_button.place(relx=0.65, rely=0.92, relwidth=0.2, relheight=0.05)
     # --- End Camera Selection ---
 
+    # 1) Define a DoubleVar for transparency (0 = fully transparent, 1 = fully opaque)
+    transparency_var = ctk.DoubleVar(value=1.0)
+
+    def on_transparency_change(value: float):
+        # Convert slider value to float
+        val = float(value)
+        modules.globals.opacity = val  # Set global opacity
+        percentage = int(val * 100)
+
+        if percentage == 0:
+            modules.globals.fp_ui["face_enhancer"] = False
+            update_status("Transparency set to 0% - Face swapping disabled.")
+        elif percentage == 100:
+            modules.globals.face_swapper_enabled = True
+            update_status("Transparency set to 100%.")
+        else:
+            modules.globals.face_swapper_enabled = True
+            update_status(f"Transparency set to {percentage}%")
+
+    # 2) Transparency label and slider (placed ABOVE sharpness)
+    transparency_label = ctk.CTkLabel(root, text="Transparency:")
+    transparency_label.place(relx=0.15, rely=0.75, relwidth=0.2, relheight=0.05)
+
+    transparency_slider = ctk.CTkSlider(
+        root,
+        from_=0.0,
+        to=1.0,
+        variable=transparency_var,
+        command=on_transparency_change,
+        fg_color="#E0E0E0",
+        progress_color="#007BFF",
+        button_color="#FFFFFF",
+        button_hover_color="#CCCCCC",
+        height=5,
+        border_width=1,
+        corner_radius=3,
+    )
+    transparency_slider.place(relx=0.35, rely=0.77, relwidth=0.5, relheight=0.02)
+
+    # 3) Sharpness label & slider
+    sharpness_var = ctk.DoubleVar(value=0.0)  # start at 0.0
+    def on_sharpness_change(value: float):
+        modules.globals.sharpness = float(value)
+        update_status(f"Sharpness set to {value:.1f}")
+
+    sharpness_label = ctk.CTkLabel(root, text="Sharpness:")
+    sharpness_label.place(relx=0.15, rely=0.80, relwidth=0.2, relheight=0.05)
+
+    sharpness_slider = ctk.CTkSlider(
+        root,
+        from_=0.0,
+        to=5.0,
+        variable=sharpness_var,
+        command=on_sharpness_change,
+        fg_color="#E0E0E0",
+        progress_color="#007BFF",
+        button_color="#FFFFFF",
+        button_hover_color="#CCCCCC",
+        height=5,
+        border_width=1,
+        corner_radius=3,
+    )
+    sharpness_slider.place(relx=0.35, rely=0.82, relwidth=0.5, relheight=0.02)
+
+    # Status and link at the bottom
+    global status_label
     status_label = ctk.CTkLabel(root, text=None, justify="center")
-    status_label.place(relx=0.1, rely=0.9, relwidth=0.8)
+    status_label.place(relx=0.1, rely=0.96, relwidth=0.8)
 
     donate_label = ctk.CTkLabel(
         root, text="Deep Live Cam", justify="center", cursor="hand2"
     )
-    donate_label.place(relx=0.1, rely=0.95, relwidth=0.8)
+    donate_label.place(relx=0.1, rely=0.98, relwidth=0.8)
     donate_label.configure(
         text_color=ctk.ThemeManager.theme.get("URL").get("text_color")
     )
@@ -381,6 +463,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
 
     return root
 
+
 def close_mapper_window():
     global POPUP, POPUP_LIVE
     if POPUP and POPUP.winfo_exists():
@@ -429,7 +512,7 @@ def create_source_target_popup(
             POPUP.destroy()
             select_output_path(start)
         else:
-            update_pop_status("At least 1 source with target is required!")
+            update_pop_status("Atleast 1 source with target is required!")
 
     scrollable_frame = ctk.CTkScrollableFrame(
         POPUP, width=POPUP_SCROLL_WIDTH, height=POPUP_SCROLL_HEIGHT
@@ -489,7 +572,7 @@ def update_popup_source(
     global source_label_dict
 
     source_path = ctk.filedialog.askopenfilename(
-        title=_("select a source image"),
+        title=_("select an source image"),
         initialdir=RECENT_DIRECTORY_SOURCE,
         filetypes=[img_ft],
     )
@@ -584,7 +667,7 @@ def select_source_path() -> None:
 
     PREVIEW.withdraw()
     source_path = ctk.filedialog.askopenfilename(
-        title=_("select a source image"),
+        title=_("select an source image"),
         initialdir=RECENT_DIRECTORY_SOURCE,
         filetypes=[img_ft],
     )
@@ -627,7 +710,7 @@ def select_target_path() -> None:
 
     PREVIEW.withdraw()
     target_path = ctk.filedialog.askopenfilename(
-        title=_("select a target image or video"),
+        title=_("select an target image or video"),
         initialdir=RECENT_DIRECTORY_TARGET,
         filetypes=[img_ft, vid_ft],
     )
@@ -696,21 +779,17 @@ def check_and_ignore_nsfw(target, destroy: Callable = None) -> bool:
 
 
 def fit_image_to_size(image, width: int, height: int):
-    if width is None or height is None or width <= 0 or height <= 0:
+    if width is None and height is None:
         return image
     h, w, _ = image.shape
     ratio_h = 0.0
     ratio_w = 0.0
-    ratio_w = width / w
+    if width > height:
-    ratio_h = height / h
+        ratio_h = height / h
-    # Use the smaller ratio to ensure the image fits within the given dimensions
+    else:
-    ratio = min(ratio_w, ratio_h)
+        ratio_w = width / w
-    
+    ratio = max(ratio_w, ratio_h)
-    # Compute new dimensions, ensuring they're at least 1 pixel
+    new_size = (int(ratio * w), int(ratio * h))
-    new_width = max(1, int(ratio * w))
-    new_height = max(1, int(ratio * h))
-    new_size = (new_width, new_height)
-
     return cv2.resize(image, dsize=new_size)
 
 
@@ -1108,7 +1187,7 @@ def update_webcam_source(
     global source_label_dict_live
 
     source_path = ctk.filedialog.askopenfilename(
-        title=_("select a source image"),
+        title=_("select an source image"),
         initialdir=RECENT_DIRECTORY_SOURCE,
         filetypes=[img_ft],
     )
@@ -1160,7 +1239,7 @@ def update_webcam_target(
     global target_label_dict_live
 
     target_path = ctk.filedialog.askopenfilename(
-        title=_("select a target image"),
+        title=_("select an target image"),
         initialdir=RECENT_DIRECTORY_SOURCE,
         filetypes=[img_ft],
     )
@@ -1203,4 +1282,4 @@ def update_webcam_target(
             target_label_dict_live[button_num] = target_image
         else:
             update_pop_live_status("Face could not be detected in last upload!")
-        return map
+        return map

modules/utilities.py

@@ -21,13 +21,14 @@ if platform.system().lower() == "darwin":
 
 
 def run_ffmpeg(args: List[str]) -> bool:
+    """Run ffmpeg with hardware acceleration and optimized settings."""
     commands = [
         "ffmpeg",
         "-hide_banner",
-        "-hwaccel",
+        "-hwaccel", "auto",  # Auto-detect hardware acceleration
-        "auto",
+        "-hwaccel_output_format", "auto",  # Use hardware format when possible
-        "-loglevel",
+        "-threads", str(modules.globals.execution_threads or 0),  # 0 = auto-detect optimal thread count
-        modules.globals.log_level,
+        "-loglevel", modules.globals.log_level,
     ]
     commands.extend(args)
     try:
@@ -61,39 +62,131 @@ def detect_fps(target_path: str) -> float:
 
 
 def extract_frames(target_path: str) -> None:
+    """Extract frames with hardware acceleration and optimized settings."""
     temp_directory_path = get_temp_directory_path(target_path)
+    
+    # Use hardware-accelerated decoding and optimized pixel format
     run_ffmpeg(
         [
-            "-i",
+            "-i", target_path,
-            target_path,
+            "-vf", "format=rgb24",  # Use video filter for format conversion (faster)
-            "-pix_fmt",
+            "-vsync", "0",  # Prevent frame duplication
-            "rgb24",
+            "-frame_pts", "1",  # Preserve frame timing
             os.path.join(temp_directory_path, "%04d.png"),
         ]
     )
 
 
 def create_video(target_path: str, fps: float = 30.0) -> None:
+    """Create video with hardware-accelerated encoding and optimized settings."""
     temp_output_path = get_temp_output_path(target_path)
     temp_directory_path = get_temp_directory_path(target_path)
-    run_ffmpeg(
+    
-        [
+    # Determine optimal encoder based on available hardware
-            "-r",
+    encoder = modules.globals.video_encoder
-            str(fps),
+    encoder_options = []
-            "-i",
+    
-            os.path.join(temp_directory_path, "%04d.png"),
+    # GPU-accelerated encoding options
-            "-c:v",
+    if 'CUDAExecutionProvider' in modules.globals.execution_providers:
-            modules.globals.video_encoder,
+        # NVIDIA GPU encoding
-            "-crf",
+        if encoder == 'libx264':
-            str(modules.globals.video_quality),
+            encoder = 'h264_nvenc'
-            "-pix_fmt",
+            encoder_options = [
-            "yuv420p",
+                "-preset", "p7",  # Highest quality preset for NVENC
-            "-vf",
+                "-tune", "hq",  # High quality tuning
-            "colorspace=bt709:iall=bt601-6-625:fast=1",
+                "-rc", "vbr",  # Variable bitrate
+                "-cq", str(modules.globals.video_quality),  # Quality level
+                "-b:v", "0",  # Let CQ control bitrate
+                "-multipass", "fullres",  # Two-pass encoding for better quality
+            ]
+        elif encoder == 'libx265':
+            encoder = 'hevc_nvenc'
+            encoder_options = [
+                "-preset", "p7",
+                "-tune", "hq",
+                "-rc", "vbr",
+                "-cq", str(modules.globals.video_quality),
+                "-b:v", "0",
+            ]
+    elif 'DmlExecutionProvider' in modules.globals.execution_providers:
+        # AMD/Intel GPU encoding (DirectML on Windows)
+        if encoder == 'libx264':
+            # Try AMD AMF encoder
+            encoder = 'h264_amf'
+            encoder_options = [
+                "-quality", "quality",  # Quality mode
+                "-rc", "vbr_latency",
+                "-qp_i", str(modules.globals.video_quality),
+                "-qp_p", str(modules.globals.video_quality),
+            ]
+        elif encoder == 'libx265':
+            encoder = 'hevc_amf'
+            encoder_options = [
+                "-quality", "quality",
+                "-rc", "vbr_latency",
+                "-qp_i", str(modules.globals.video_quality),
+                "-qp_p", str(modules.globals.video_quality),
+            ]
+    else:
+        # CPU encoding with optimized settings
+        if encoder == 'libx264':
+            encoder_options = [
+                "-preset", "medium",  # Balance speed/quality
+                "-crf", str(modules.globals.video_quality),
+                "-tune", "film",  # Optimize for film content
+            ]
+        elif encoder == 'libx265':
+            encoder_options = [
+                "-preset", "medium",
+                "-crf", str(modules.globals.video_quality),
+                "-x265-params", "log-level=error",
+            ]
+        elif encoder == 'libvpx-vp9':
+            encoder_options = [
+                "-crf", str(modules.globals.video_quality),
+                "-b:v", "0",  # Constant quality mode
+                "-cpu-used", "2",  # Speed vs quality (0-5, lower=slower/better)
+            ]
+    
+    # Build ffmpeg command
+    ffmpeg_args = [
+        "-r", str(fps),
+        "-i", os.path.join(temp_directory_path, "%04d.png"),
+        "-c:v", encoder,
+    ]
+    
+    # Add encoder-specific options
+    ffmpeg_args.extend(encoder_options)
+    
+    # Add common options
+    ffmpeg_args.extend([
+        "-pix_fmt", "yuv420p",
+        "-movflags", "+faststart",  # Enable fast start for web playback
+        "-vf", "colorspace=bt709:iall=bt601-6-625:fast=1",
+        "-y",
+        temp_output_path,
+    ])
+    
+    # Try with hardware encoder first, fallback to software if it fails
+    success = run_ffmpeg(ffmpeg_args)
+    
+    if not success and encoder in ['h264_nvenc', 'hevc_nvenc', 'h264_amf', 'hevc_amf']:
+        # Fallback to software encoding
+        print(f"Hardware encoding with {encoder} failed, falling back to software encoding...")
+        fallback_encoder = 'libx264' if 'h264' in encoder else 'libx265'
+        ffmpeg_args_fallback = [
+            "-r", str(fps),
+            "-i", os.path.join(temp_directory_path, "%04d.png"),
+            "-c:v", fallback_encoder,
+            "-preset", "medium",
+            "-crf", str(modules.globals.video_quality),
+            "-pix_fmt", "yuv420p",
+            "-movflags", "+faststart",
+            "-vf", "colorspace=bt709:iall=bt601-6-625:fast=1",
             "-y",
             temp_output_path,
         ]
-    )
+        run_ffmpeg(ffmpeg_args_fallback)
 
 
 def restore_audio(target_path: str, output_path: str) -> None:

requirements.txt

@@ -11,7 +11,7 @@ tk==0.1.0
 customtkinter==5.2.2
 pillow==11.1.0
 torch; sys_platform != 'darwin'
-torch==2.5.1; sys_platform == 'darwin'
+torch==2.8.0+cu128; sys_platform == 'darwin'
 torchvision; sys_platform != 'darwin'
 torchvision==0.20.1; sys_platform == 'darwin'
 onnxruntime-silicon==1.16.3; sys_platform == 'darwin' and platform_machine == 'arm64'
@@ -19,3 +19,6 @@ onnxruntime-gpu==1.22.0; sys_platform != 'darwin'
 tensorflow; sys_platform != 'darwin'
 opennsfw2==0.10.2
 protobuf==4.25.1
+git+https://github.com/xinntao/BasicSR.git@master
+git+https://github.com/TencentARC/GFPGAN.git@master
+pygrabber

run.py

@@ -1,5 +1,8 @@
 #!/usr/bin/env python3
 
+# Import the tkinter fix to patch the ScreenChanged error
+import tkinter_fix
+
 from modules import core
 
 if __name__ == '__main__':

tkinter_fix.py

@@ -0,0 +1,26 @@
+import tkinter
+
+# Only needs to be imported once at the beginning of the application
+def apply_patch():
+    # Create a monkey patch for the internal _tkinter module
+    original_init = tkinter.Tk.__init__
+    
+    def patched_init(self, *args, **kwargs):
+        # Call the original init
+        original_init(self, *args, **kwargs)
+        
+        # Define the missing ::tk::ScreenChanged procedure
+        self.tk.eval("""
+        if {[info commands ::tk::ScreenChanged] == ""} {
+            proc ::tk::ScreenChanged {args} {
+                # Do nothing
+                return
+            }
+        }
+        """)
+    
+    # Apply the monkey patch
+    tkinter.Tk.__init__ = patched_init
+
+# Apply the patch automatically when this module is imported
+apply_patch()