Revert "Slight Performance Improvement"

This reverts commit 9a472e2435.

README.md

@@ -1,12 +1,12 @@
-<h1 align="center">Deep Live Cam</h1>
+<h1 align="center">Deep-Live-Cam</h1>
 
 <p align="center">
   Real-time face swap and video deepfake with a single click and only a single image.
 </p>
 
 <p align="center">
-  <img src="demo.gif" alt="Demo GIF">
-  <img src="avgpcperformancedemo.gif" alt="Performance Demo GIF">
+  <img src="media/demo.gif" alt="Demo GIF">
+  <img src="media/avgpcperformancedemo.gif" alt="Performance Demo GIF">
 </p>
 
 ## Disclaimer
@@ -20,11 +20,7 @@ Users are expected to use this software responsibly and legally. If using a real
 
 ## Quick Start (Windows / Nvidia)
 
-[![Download](https://github.com/user-attachments/assets/3e3e252a-4bfa-41fb-a88c-84557402a7c7)](https://hacksider.gumroad.com/l/vccdmm) 
-
-
-
-
+[![Download](media/download.png)](https://hacksider.gumroad.com/l/vccdmm) 
 
 [Download latest pre-built version with CUDA support](https://hacksider.gumroad.com/l/vccdmm) - No Manual Installation/Downloading required.
 
@@ -159,7 +155,7 @@ python run.py --execution-provider openvino
 - Use a screen capture tool like OBS to stream.
 - To change the face, select a new source image.
 
-![demo-gif](demo.gif)
+![demo-gif](media/demo.gif)
 
 ## Features
 
@@ -167,28 +163,35 @@ python run.py --execution-provider openvino
 
 Dynamically improve performance using the `--live-resizable` parameter.
 
-![resizable-gif](resizable.gif)
+![resizable-gif](media/resizable.gif)
 
 ### Face Mapping
 
 Track and change faces on the fly.
 
-![face_mapping_source](face_mapping_source.gif)
+![face_mapping_source](media/face_mapping_source.gif)
 
 **Source Video:**
 
-![face-mapping](face_mapping.png)
+![face-mapping](media/face_mapping.png)
 
 **Enable Face Mapping:**
 
-![face-mapping2](face_mapping2.png)
+![face-mapping2](media/face_mapping2.png)
 
 **Map the Faces:**
 
-![face_mapping_result](face_mapping_result.gif)
+![face_mapping_result](media/face_mapping_result.gif)
 
 **See the Magic!**
 
+![movie](media/movie.gif)
+
+**Watch movies in realtime:**
+
+It's as simple as opening a movie on the screen, and selecting OBS as your camera!
+![image](media/movie_img.png)
+
 
 ## Command Line Arguments
 
@@ -379,6 +382,10 @@ For the latest experimental builds and features, see the [experimental branch](h
 
 This is an open-source project developed in our free time. Updates may be delayed.
 
+**Tips and Links:**
+- [How to make the most of Deep-Live-Cam](https://hacksider.gumroad.com/p/how-to-make-the-most-on-deep-live-cam)
+- Face enhancer is good, but still very slow for any live streaming purpose.
+
 
 ## Credits
 
@@ -392,9 +399,14 @@ This is an open-source project developed in our free time. Updates may be delaye
 - and [all developers](https://github.com/hacksider/Deep-Live-Cam/graphs/contributors) behind libraries used in this project.
 - Foot Note: [This is originally roop-cam, see the full history of the code here.](https://github.com/hacksider/roop-cam) Please be informed that the base author of the code is [s0md3v](https://github.com/s0md3v/roop)
 
-## Thanks to all the contributors
-<a href="https://github.com/hacksider/Deep-Live-Cam/graphs/contributors" target="_blank">
-  <img src="https://contrib.rocks/image?repo=hacksider/Deep-Live-Cam" />
-</a>
-
+## Contributions
 ![Alt](https://repobeats.axiom.co/api/embed/fec8e29c45dfdb9c5916f3a7830e1249308d20e1.svg "Repobeats analytics image")
+## Star History
+
+<a href="https://star-history.com/#hacksider/deep-live-cam&Date">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=hacksider/deep-live-cam&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=hacksider/deep-live-cam&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=hacksider/deep-live-cam&type=Date" />
+ </picture>
+</a>

models/instructions.txt

@@ -1 +1,4 @@
-just put the models in this folder
+just put the models in this folder -
+
+https://huggingface.co/hacksider/deep-live-cam/resolve/main/inswapper_128_fp16.onnx?download=true
+https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth

modules/globals.py

@@ -2,11 +2,11 @@ import os
 from typing import List, Dict, Any
 
 ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
-WORKFLOW_DIR = os.path.join(ROOT_DIR, 'workflow')
+WORKFLOW_DIR = os.path.join(ROOT_DIR, "workflow")
 
 file_types = [
-    ('Image', ('*.png','*.jpg','*.jpeg','*.gif','*.bmp')),
-    ('Video', ('*.mp4','*.mkv'))
+    ("Image", ("*.png", "*.jpg", "*.jpeg", "*.gif", "*.bmp")),
+    ("Video", ("*.mp4", "*.mkv")),
 ]
 
 souce_target_map = []
@@ -16,23 +16,31 @@ 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
-map_faces = None
-color_correction = None  # New global variable for color correction toggle
-nsfw_filter = None
+keep_fps = True  # Initialize with default value
+keep_audio = True  # Initialize with default value
+keep_frames = False  # Initialize with default value
+many_faces = False  # Initialize with default value
+map_faces = False  # Initialize with default value
+color_correction = False  # Initialize with default value
+nsfw_filter = False  # Initialize with default value
 video_encoder = None
 video_quality = None
-live_mirror = None
-live_resizable = None
+live_mirror = False  # Initialize with default value
+live_resizable = False  # Initialize with default value
 max_memory = None
 execution_providers: List[str] = []
 execution_threads = None
 headless = None
-log_level = 'error'
-fp_ui: Dict[str, bool] = {}
+log_level = "error"
+fp_ui: Dict[str, bool] = {"face_enhancer": False}  # Initialize with default value
 camera_input_combobox = None
 webcam_preview_running = False
-opacity = 100 
+show_fps = False  # Initialize with default value
+mouth_mask = False
+show_mouth_mask_box = False
+mask_down_size = 0.5
+mask_size = 1.0
+mask_feather_ratio = 8
+opacity_switch = False
+face_opacity = 100
+selected_camera = None

modules/metadata.py

@@ -1,3 +1,3 @@
 name = 'Deep Live Cam'
-version = '1.5.0'
+version = '1.6.0'
 edition = 'Portable'

modules/processors/frame/face_swapper.py

@@ -2,35 +2,49 @@ from typing import Any, List
 import cv2
 import insightface
 import threading
-
+import numpy as np
 import modules.globals
 import modules.processors.frame.core
 from modules.core import update_status
 from modules.face_analyser import get_one_face, get_many_faces, default_source_face
 from modules.typing import Face, Frame
-from modules.utilities import conditional_download, resolve_relative_path, is_image, is_video
+from modules.utilities import (
+    conditional_download,
+    resolve_relative_path,
+    is_image,
+    is_video,
+)
 from modules.cluster_analysis import find_closest_centroid
 
 FACE_SWAPPER = None
 THREAD_LOCK = threading.Lock()
-NAME = 'DLC.FACE-SWAPPER'
+NAME = "DLC.FACE-SWAPPER"
 
 
 def pre_check() -> bool:
-    download_directory_path = resolve_relative_path('../models')
-    conditional_download(download_directory_path, ['https://huggingface.co/hacksider/deep-live-cam/blob/main/inswapper_128.onnx'])
+    download_directory_path = resolve_relative_path("../models")
+    conditional_download(
+        download_directory_path,
+        [
+            "https://huggingface.co/hacksider/deep-live-cam/blob/main/inswapper_128_fp16.onnx"
+        ],
+    )
     return True
 
 
 def pre_start() -> bool:
     if not modules.globals.map_faces and not is_image(modules.globals.source_path):
-        update_status('Select an image for source path.', NAME)
+        update_status("Select an image for source path.", NAME)
         return False
-    elif not modules.globals.map_faces and not get_one_face(cv2.imread(modules.globals.source_path)):
-        update_status('No face in source path detected.', NAME)
+    elif not modules.globals.map_faces and not get_one_face(
+        cv2.imread(modules.globals.source_path)
+    ):
+        update_status("No face in source path detected.", NAME)
         return False
-    if not is_image(modules.globals.target_path) and not is_video(modules.globals.target_path):
-        update_status('Select an image or video for target path.', NAME)
+    if not is_image(modules.globals.target_path) and not is_video(
+        modules.globals.target_path
+    ):
+        update_status("Select an image or video for target path.", NAME)
         return False
     return True
 
@@ -40,20 +54,49 @@ def get_face_swapper() -> Any:
 
     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=modules.globals.execution_providers)
+            model_path = resolve_relative_path("../models/inswapper_128_fp16.onnx")
+            FACE_SWAPPER = insightface.model_zoo.get_model(
+                model_path, providers=modules.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)
+    swapped_frame = get_face_swapper().get(
+        temp_frame, target_face, source_face, paste_back=True
+    )
+
+    # Apply opacity if enabled
+    if modules.globals.opacity_switch:
+        opacity = modules.globals.face_opacity / 100
+        swapped_frame = cv2.addWeighted(
+            swapped_frame, opacity, temp_frame, 1 - opacity, 0
+        )
+
+    # Apply mouth mask if enabled
+    if modules.globals.mouth_mask:
+        face_mask = create_face_mask(target_face, temp_frame)
+        mouth_mask_data = create_lower_mouth_mask(target_face, temp_frame)
+        mouth_mask, mouth_cutout, mouth_box, lower_lip_polygon = mouth_mask_data
+
+        if mouth_box is not None:
+            swapped_frame = apply_mouth_area(
+                swapped_frame, mouth_cutout, mouth_box, face_mask, lower_lip_polygon
+            )
+
+            if modules.globals.show_mouth_mask_box:
+                swapped_frame = draw_mouth_mask_visualization(
+                    swapped_frame, target_face, mouth_mask_data
+                )
+
+    return swapped_frame
 
 
 def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
     # Ensure the frame is in RGB format if color correction is enabled
     if modules.globals.color_correction:
         temp_frame = cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB)
-        
+
     if modules.globals.many_faces:
         many_faces = get_many_faces(temp_frame)
         if many_faces:
@@ -71,34 +114,42 @@ def process_frame_v2(temp_frame: Frame, temp_frame_path: str = "") -> Frame:
         if modules.globals.many_faces:
             source_face = default_source_face()
             for map in modules.globals.souce_target_map:
-                target_face = map['target']['face']
+                target_face = map["target"]["face"]
                 temp_frame = swap_face(source_face, target_face, temp_frame)
 
         elif not modules.globals.many_faces:
             for map in modules.globals.souce_target_map:
                 if "source" in map:
-                    source_face = map['source']['face']
-                    target_face = map['target']['face']               
+                    source_face = map["source"]["face"]
+                    target_face = map["target"]["face"]
                     temp_frame = swap_face(source_face, target_face, temp_frame)
 
     elif is_video(modules.globals.target_path):
         if modules.globals.many_faces:
             source_face = default_source_face()
             for map in modules.globals.souce_target_map:
-                target_frame = [f for f in map['target_faces_in_frame'] if f['location'] == temp_frame_path]
+                target_frame = [
+                    f
+                    for f in map["target_faces_in_frame"]
+                    if f["location"] == temp_frame_path
+                ]
 
                 for frame in target_frame:
-                    for target_face in frame['faces']:
+                    for target_face in frame["faces"]:
                         temp_frame = swap_face(source_face, target_face, temp_frame)
 
         elif not modules.globals.many_faces:
             for map in modules.globals.souce_target_map:
                 if "source" in map:
-                    target_frame = [f for f in map['target_faces_in_frame'] if f['location'] == temp_frame_path]
-                    source_face = map['source']['face']
+                    target_frame = [
+                        f
+                        for f in map["target_faces_in_frame"]
+                        if f["location"] == temp_frame_path
+                    ]
+                    source_face = map["source"]["face"]
 
                     for frame in target_frame:
-                        for target_face in frame['faces']:
+                        for target_face in frame["faces"]:
                             temp_frame = swap_face(source_face, target_face, temp_frame)
     else:
         detected_faces = get_many_faces(temp_frame)
@@ -110,25 +161,46 @@ def process_frame_v2(temp_frame: Frame, temp_frame_path: str = "") -> Frame:
 
         elif not modules.globals.many_faces:
             if detected_faces:
-                if len(detected_faces) <= len(modules.globals.simple_map['target_embeddings']):
+                if len(detected_faces) <= len(
+                    modules.globals.simple_map["target_embeddings"]
+                ):
                     for detected_face in detected_faces:
-                        closest_centroid_index, _ = find_closest_centroid(modules.globals.simple_map['target_embeddings'], detected_face.normed_embedding)
+                        closest_centroid_index, _ = find_closest_centroid(
+                            modules.globals.simple_map["target_embeddings"],
+                            detected_face.normed_embedding,
+                        )
 
-                        temp_frame = swap_face(modules.globals.simple_map['source_faces'][closest_centroid_index], detected_face, temp_frame)
+                        temp_frame = swap_face(
+                            modules.globals.simple_map["source_faces"][
+                                closest_centroid_index
+                            ],
+                            detected_face,
+                            temp_frame,
+                        )
                 else:
                     detected_faces_centroids = []
                     for face in detected_faces:
-                            detected_faces_centroids.append(face.normed_embedding)
+                        detected_faces_centroids.append(face.normed_embedding)
                     i = 0
-                    for target_embedding in modules.globals.simple_map['target_embeddings']:
-                        closest_centroid_index, _ = find_closest_centroid(detected_faces_centroids, target_embedding)
+                    for target_embedding in modules.globals.simple_map[
+                        "target_embeddings"
+                    ]:
+                        closest_centroid_index, _ = find_closest_centroid(
+                            detected_faces_centroids, target_embedding
+                        )
 
-                        temp_frame = swap_face(modules.globals.simple_map['source_faces'][i], detected_faces[closest_centroid_index], temp_frame)
+                        temp_frame = swap_face(
+                            modules.globals.simple_map["source_faces"][i],
+                            detected_faces[closest_centroid_index],
+                            temp_frame,
+                        )
                         i += 1
     return temp_frame
 
 
-def process_frames(source_path: str, temp_frame_paths: List[str], progress: Any = None) -> None:
+def process_frames(
+    source_path: str, temp_frame_paths: List[str], progress: Any = None
+) -> None:
     if not modules.globals.map_faces:
         source_face = get_one_face(cv2.imread(source_path))
         for temp_frame_path in temp_frame_paths:
@@ -162,7 +234,9 @@ def process_image(source_path: str, target_path: str, output_path: str) -> None:
         cv2.imwrite(output_path, result)
     else:
         if modules.globals.many_faces:
-            update_status('Many faces enabled. Using first source image. Progressing...', NAME)
+            update_status(
+                "Many faces enabled. Using first source image. Progressing...", NAME
+            )
         target_frame = cv2.imread(output_path)
         result = process_frame_v2(target_frame)
         cv2.imwrite(output_path, result)
@@ -170,5 +244,250 @@ def process_image(source_path: str, target_path: str, output_path: str) -> None:
 
 def process_video(source_path: str, temp_frame_paths: List[str]) -> None:
     if modules.globals.map_faces and modules.globals.many_faces:
-        update_status('Many faces enabled. Using first source image. Progressing...', NAME)
-    modules.processors.frame.core.process_video(source_path, temp_frame_paths, process_frames)
+        update_status(
+            "Many faces enabled. Using first source image. Progressing...", NAME
+        )
+    modules.processors.frame.core.process_video(
+        source_path, temp_frame_paths, process_frames
+    )
+
+
+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:
+        landmarks = landmarks.astype(np.int32)
+
+        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]
+
+        right_eyebrow_top = np.min(right_eye_brow[:, 1])
+        left_eyebrow_top = np.min(left_eye_brow[:, 1])
+        eyebrow_top = min(right_eyebrow_top, left_eyebrow_top)
+
+        face_top = np.min([right_side_face[0, 1], left_side_face[-1, 1]])
+        forehead_height = face_top - eyebrow_top
+        extended_forehead_height = int(forehead_height * 5.0)
+
+        forehead_left = right_side_face[0].copy()
+        forehead_right = left_side_face[-1].copy()
+        forehead_left[1] -= extended_forehead_height
+        forehead_right[1] -= extended_forehead_height
+
+        face_outline = np.vstack(
+            [
+                [forehead_left],
+                right_side_face,
+                left_side_face[::-1],
+                [forehead_right],
+            ]
+        )
+
+        padding = int(np.linalg.norm(right_side_face[0] - left_side_face[-1]) * 0.05)
+
+        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)
+        cv2.fillConvexPoly(mask, hull_padded, 255)
+        mask = cv2.GaussianBlur(mask, (5, 5), 3)
+
+    return mask
+
+
+def create_lower_mouth_mask(face: Face, frame: Frame) -> tuple:
+    mask = np.zeros(frame.shape[:2], dtype=np.uint8)
+    mouth_cutout = None
+    landmarks = face.landmark_2d_106
+    if landmarks is not None:
+        lower_lip_order = [
+            65,
+            66,
+            62,
+            70,
+            69,
+            18,
+            19,
+            20,
+            21,
+            22,
+            23,
+            24,
+            0,
+            8,
+            7,
+            6,
+            5,
+            4,
+            3,
+            2,
+            65,
+        ]
+        lower_lip_landmarks = landmarks[lower_lip_order].astype(np.float32)
+
+        center = np.mean(lower_lip_landmarks, axis=0)
+        expansion_factor = 1 + modules.globals.mask_down_size
+        expanded_landmarks = (lower_lip_landmarks - center) * expansion_factor + center
+
+        toplip_indices = [20, 0, 1, 2, 3, 4, 5]
+        toplip_extension = modules.globals.mask_size * 0.5
+        for idx in toplip_indices:
+            direction = expanded_landmarks[idx] - center
+            direction = direction / np.linalg.norm(direction)
+            expanded_landmarks[idx] += direction * toplip_extension
+
+        chin_indices = [11, 12, 13, 14, 15, 16]
+        chin_extension = 2 * 0.2
+        for idx in chin_indices:
+            expanded_landmarks[idx][1] += (
+                expanded_landmarks[idx][1] - center[1]
+            ) * chin_extension
+
+        expanded_landmarks = expanded_landmarks.astype(np.int32)
+
+        min_x, min_y = np.min(expanded_landmarks, axis=0)
+        max_x, max_y = np.max(expanded_landmarks, axis=0)
+
+        padding = int((max_x - min_x) * 0.1)
+        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)
+
+        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
+
+        mask_roi = np.zeros((max_y - min_y, max_x - min_x), dtype=np.uint8)
+        cv2.fillPoly(mask_roi, [expanded_landmarks - [min_x, min_y]], 255)
+        mask_roi = cv2.GaussianBlur(mask_roi, (15, 15), 5)
+        mask[min_y:max_y, min_x:max_x] = mask_roi
+        mouth_cutout = frame[min_y:max_y, min_x:max_x].copy()
+
+        return mask, mouth_cutout, (min_x, min_y, max_x, max_y), expanded_landmarks
+
+    return mask, mouth_cutout, None, None
+
+
+def apply_mouth_area(
+    frame: Frame,
+    mouth_cutout: np.ndarray,
+    mouth_box: tuple,
+    face_mask: np.ndarray,
+    mouth_polygon: np.ndarray,
+) -> Frame:
+    min_x, min_y, max_x, max_y = mouth_box
+    box_width = max_x - min_x
+    box_height = max_y - min_y
+
+    if (
+        mouth_cutout is None
+        or box_width is None
+        or box_height is None
+        or face_mask is None
+        or mouth_polygon is None
+    ):
+        return frame
+
+    try:
+        resized_mouth_cutout = cv2.resize(mouth_cutout, (box_width, box_height))
+        roi = frame[min_y:max_y, min_x:max_x]
+
+        if roi.shape != resized_mouth_cutout.shape:
+            resized_mouth_cutout = cv2.resize(
+                resized_mouth_cutout, (roi.shape[1], roi.shape[0])
+            )
+
+        color_corrected_mouth = apply_color_transfer(resized_mouth_cutout, roi)
+
+        polygon_mask = np.zeros(roi.shape[:2], dtype=np.uint8)
+        adjusted_polygon = mouth_polygon - [min_x, min_y]
+        cv2.fillPoly(polygon_mask, [adjusted_polygon], 255)
+
+        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()
+
+        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_mouth * combined_mask + roi * (1 - combined_mask)
+        ).astype(np.uint8)
+
+        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 apply_color_transfer(source: np.ndarray, target: np.ndarray) -> np.ndarray:
+    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)
+
+    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)
+
+    source = (source - source_mean) * (target_std / source_std) + target_mean
+
+    return cv2.cvtColor(np.clip(source, 0, 255).astype("uint8"), cv2.COLOR_LAB2BGR)
+
+
+def draw_mouth_mask_visualization(
+    frame: Frame, face: Face, mouth_mask_data: tuple
+) -> Frame:
+    landmarks = face.landmark_2d_106
+    if landmarks is not None and mouth_mask_data is not None:
+        mask, mouth_cutout, (min_x, min_y, max_x, max_y), lower_lip_polygon = (
+            mouth_mask_data
+        )
+
+        vis_frame = frame.copy()
+
+        # Draw the lower lip polygon
+        cv2.polylines(vis_frame, [lower_lip_polygon], True, (0, 255, 0), 2)
+
+        # Add labels
+        cv2.putText(
+            vis_frame,
+            "Mouth Mask",
+            (min_x, min_y - 10),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.5,
+            (255, 255, 255),
+            1,
+        )
+
+        return vis_frame
+    return frame

modules/ui.py

@@ -7,6 +7,8 @@ from cv2_enumerate_cameras import enumerate_cameras
 from PIL import Image, ImageOps
 import tkinterdnd2 as tkdnd
 import time
+import json
+
 import modules.globals
 import modules.metadata
 from modules.face_analyser import (
@@ -26,7 +28,6 @@ from modules.utilities import (
     has_image_extension,
 )
 
-modules.globals.face_opacity = 100
 os.environ["QT_AUTO_SCREEN_SCALE_FACTOR"] = "1"
 os.environ["QT_SCREEN_SCALE_FACTORS"] = "1"
 os.environ["QT_SCALE_FACTOR"] = "1"
@@ -201,8 +202,193 @@ class TargetLabel(DragDropLabel):
                 target_label.configure(text="")
 
 
+class ModernOptionMenu(ctk.CTkFrame):
+    def __init__(self, master, values, command=None, **kwargs):
+        super().__init__(master, fg_color="transparent")
+
+        self.values = values
+        self.command = command
+
+        # Set initial value based on saved camera or first available
+        self.current_value = (
+            modules.globals.selected_camera
+            if modules.globals.selected_camera in values
+            else (values[0] if values else "No cameras found")
+        )
+
+        # Main button
+        self.main_button = ctk.CTkButton(
+            self,
+            text=self.current_value,
+            command=self.show_dropdown,
+            width=300,
+            height=40,
+            corner_radius=8,
+            fg_color="#1f538d",
+            hover_color="#1a4572",
+            text_color="white",
+            font=("Roboto", 13, "bold"),
+            border_width=2,
+            border_color="#3d7ab8",
+        )
+        self.main_button.pack(expand=True, fill="both")
+
+        # Dropdown frame (initially hidden)
+        self.dropdown_frame = None
+        self.is_dropdown_visible = False
+        self.click_binding = None
+
+    def show_dropdown(self):
+        if self.is_dropdown_visible:
+            self.hide_dropdown()
+            return
+
+        # Calculate position and size
+        button_width = self.main_button.winfo_width()
+        dropdown_height = min(len(self.values) * 35, 200)  # Limit max height
+
+        # Create and show dropdown with fixed size
+        self.dropdown_frame = ctk.CTkFrame(
+            self.winfo_toplevel(),
+            width=button_width,
+            height=dropdown_height,
+            fg_color="#1f538d",
+            corner_radius=8,
+            border_width=2,
+            border_color="#3d7ab8",
+        )
+
+        # Get the absolute coordinates of the button relative to the screen
+        button_x = self.winfo_rootx()
+        button_y = self.winfo_rooty()
+
+        # Position the dropdown above the button, using relative coordinates
+        relative_x = button_x - self.winfo_toplevel().winfo_rootx()
+        relative_y = button_y - self.winfo_toplevel().winfo_rooty() - dropdown_height
+
+        self.dropdown_frame.place(in_=self.winfo_toplevel(), x=relative_x, y=relative_y)
+
+        # Prevent frame from resizing
+        self.dropdown_frame.pack_propagate(False)
+
+        # Create scrollable frame if needed
+        if len(self.values) * 35 > 200:
+            scrollable_frame = ctk.CTkScrollableFrame(
+                self.dropdown_frame,
+                width=button_width - 20,
+                height=dropdown_height - 10,
+                fg_color="#1f538d",
+                scrollbar_button_color="#3d7ab8",
+                scrollbar_button_hover_color="#2b5d8b",
+            )
+            scrollable_frame.pack(expand=True, fill="both", padx=5, pady=5)
+
+            container = scrollable_frame
+        else:
+            container = self.dropdown_frame
+
+        # Add options
+        for value in self.values:
+            option_button = ctk.CTkButton(
+                container,
+                text=value,
+                fg_color="transparent",
+                hover_color="#233d54",
+                text_color="white",
+                height=35,
+                corner_radius=4,
+                font=("Roboto", 13),
+                command=lambda v=value: self.select_value(v),
+            )
+            option_button.pack(padx=2, pady=1, fill="x")
+
+        self.is_dropdown_visible = True
+        self.click_binding = self.winfo_toplevel().bind(
+            "<Button-1>", self.on_click_outside, add="+"
+        )
+
+    def on_click_outside(self, event):
+        if self.is_dropdown_visible:
+            widget_under_cursor = event.widget.winfo_containing(
+                event.x_root, event.y_root
+            )
+            if widget_under_cursor not in [self.main_button] + (
+                self.dropdown_frame.winfo_children() if self.dropdown_frame else []
+            ):
+                self.hide_dropdown()
+
+    def hide_dropdown(self):
+        if self.dropdown_frame:
+            if self.click_binding:
+                self.winfo_toplevel().unbind("<Button-1>", self.click_binding)
+                self.click_binding = None
+            self.dropdown_frame.destroy()
+            self.dropdown_frame = None
+            self.is_dropdown_visible = False
+
+    def select_value(self, value):
+        self.current_value = value
+        self.main_button.configure(text=value)
+        self.hide_dropdown()
+        if self.command:
+            self.command(value)
+
+    def get(self):
+        return self.current_value
+
+
+def save_switch_states():
+    switch_states = {
+        "keep_fps": modules.globals.keep_fps,
+        "keep_audio": modules.globals.keep_audio,
+        "keep_frames": modules.globals.keep_frames,
+        "many_faces": modules.globals.many_faces,
+        "map_faces": modules.globals.map_faces,
+        "color_correction": modules.globals.color_correction,
+        "nsfw_filter": modules.globals.nsfw_filter,
+        "live_mirror": modules.globals.live_mirror,
+        "live_resizable": modules.globals.live_resizable,
+        "fp_ui": modules.globals.fp_ui,
+        "show_fps": modules.globals.show_fps,
+        "mouth_mask": modules.globals.mouth_mask,
+        "show_mouth_mask_box": modules.globals.show_mouth_mask_box,
+        "mask_down_size": modules.globals.mask_down_size,
+        "mask_feather_ratio": modules.globals.mask_feather_ratio,
+        "selected_camera": modules.globals.selected_camera,
+    }
+    with open("switch_states.json", "w") as f:
+        json.dump(switch_states, f)
+
+
+def load_switch_states():
+    try:
+        with open("switch_states.json", "r") as f:
+            switch_states = json.load(f)
+        modules.globals.keep_fps = switch_states.get("keep_fps", True)
+        modules.globals.keep_audio = switch_states.get("keep_audio", True)
+        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.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)
+        modules.globals.live_resizable = switch_states.get("live_resizable", False)
+        modules.globals.fp_ui = switch_states.get("fp_ui", {"face_enhancer": False})
+        modules.globals.show_fps = switch_states.get("show_fps", False)
+        modules.globals.mouth_mask = switch_states.get("mouth_mask", False)
+        modules.globals.show_mouth_mask_box = switch_states.get(
+            "show_mouth_mask_box", False
+        )
+        modules.globals.mask_down_size = switch_states.get("mask_down_size", 0.5)
+        modules.globals.mask_feather_ratio = switch_states.get("mask_feather_ratio", 8)
+        modules.globals.selected_camera = switch_states.get("selected_camera", None)
+    except FileNotFoundError:
+        # If the file doesn't exist, use default values
+        pass
+
+
 def init(start: Callable[[], None], destroy: Callable[[], None]) -> tkdnd.TkinterDnD.Tk:
-    global ROOT, PREVIEW
+    global ROOT, PREVIEW, donate_frame
 
     ROOT = create_root(start, destroy)
     PREVIEW = create_preview(ROOT)
@@ -213,7 +399,9 @@ def init(start: Callable[[], None], destroy: Callable[[], None]) -> tkdnd.Tkinte
 def create_root(
     start: Callable[[], None], destroy: Callable[[], None]
 ) -> tkdnd.TkinterDnD.Tk:
-    global source_label, target_label, status_label
+    global source_label, target_label, status_label, donate_frame, show_fps_switch
+
+    load_switch_states()
 
     ctk.set_appearance_mode("dark")
     ctk.set_default_color_theme("blue")
@@ -225,7 +413,8 @@ def create_root(
     root.configure(bg="#1a1a1a")
     root.protocol("WM_DELETE_WINDOW", lambda: destroy())
     root.resizable(True, True)
-    root.attributes("-alpha", 1.0)  # Set window opacity to fully opaque
+    root.attributes("-alpha", 1.0)
+    root.minsize(650, 870)
 
     main_frame = ctk.CTkFrame(root, fg_color="#1a1a1a")
     main_frame.pack(fill="both", expand=True, padx=20, pady=20)
@@ -288,83 +477,100 @@ def create_root(
     options_frame = ctk.CTkFrame(main_frame, fg_color="#2a2d2e", corner_radius=15)
     options_frame.grid(row=1, column=0, columnspan=3, padx=10, pady=10, sticky="nsew")
 
-    # Create a single column for options, centered
-    options_column = ctk.CTkFrame(options_frame, fg_color="#2a2d2e")
-    options_column.pack(expand=True)
+    # Create two columns for options
+    left_column = ctk.CTkFrame(options_frame, fg_color="#2a2d2e")
+    left_column.pack(side="left", padx=20, expand=True)
 
-    # Switches
+    right_column = ctk.CTkFrame(options_frame, fg_color="#2a2d2e")
+    right_column.pack(side="right", padx=20, expand=True)
+
+    # Left column - Video/Processing Options
     keep_fps_value = ctk.BooleanVar(value=modules.globals.keep_fps)
     keep_fps_checkbox = ctk.CTkSwitch(
-        options_column,
+        left_column,
         text="Keep fps",
         variable=keep_fps_value,
         cursor="hand2",
-        command=lambda: setattr(
-            modules.globals, "keep_fps", not modules.globals.keep_fps
+        command=lambda: (
+            setattr(modules.globals, "keep_fps", keep_fps_value.get()),
+            save_switch_states(),
         ),
         progress_color="#3a7ebf",
         font=("Roboto", 14, "bold"),
     )
     keep_fps_checkbox.pack(pady=5, anchor="w")
 
+    # Move many faces switch to left column
+    many_faces_value = ctk.BooleanVar(value=modules.globals.many_faces)
+    many_faces_switch = ctk.CTkSwitch(
+        left_column,
+        text="Many faces",
+        variable=many_faces_value,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "many_faces", many_faces_value.get()),
+            save_switch_states(),
+        ),
+        progress_color="#3a7ebf",
+        font=("Roboto", 14, "bold"),
+    )
+    many_faces_switch.pack(pady=5, anchor="w")
+
+    keep_audio_value = ctk.BooleanVar(value=modules.globals.keep_audio)
+    keep_audio_switch = ctk.CTkSwitch(
+        left_column,
+        text="Keep audio",
+        variable=keep_audio_value,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "keep_audio", keep_audio_value.get()),
+            save_switch_states(),
+        ),
+        progress_color="#3a7ebf",
+        font=("Roboto", 14, "bold"),
+    )
+    keep_audio_switch.pack(pady=5, anchor="w")
+
     keep_frames_value = ctk.BooleanVar(value=modules.globals.keep_frames)
     keep_frames_switch = ctk.CTkSwitch(
-        options_column,
+        left_column,
         text="Keep frames",
         variable=keep_frames_value,
         cursor="hand2",
-        command=lambda: setattr(
-            modules.globals, "keep_frames", keep_frames_value.get()
+        command=lambda: (
+            setattr(modules.globals, "keep_frames", keep_frames_value.get()),
+            save_switch_states(),
         ),
         progress_color="#3a7ebf",
         font=("Roboto", 14, "bold"),
     )
     keep_frames_switch.pack(pady=5, anchor="w")
 
+    # Face Processing Options
     enhancer_value = ctk.BooleanVar(value=modules.globals.fp_ui["face_enhancer"])
     enhancer_switch = ctk.CTkSwitch(
-        options_column,
+        left_column,
         text="Face Enhancer",
         variable=enhancer_value,
         cursor="hand2",
-        command=lambda: update_tumbler("face_enhancer", enhancer_value.get()),
+        command=lambda: (
+            update_tumbler("face_enhancer", enhancer_value.get()),
+            save_switch_states(),
+        ),
         progress_color="#3a7ebf",
         font=("Roboto", 14, "bold"),
     )
     enhancer_switch.pack(pady=5, anchor="w")
 
-    keep_audio_value = ctk.BooleanVar(value=modules.globals.keep_audio)
-    keep_audio_switch = ctk.CTkSwitch(
-        options_column,
-        text="Keep audio",
-        variable=keep_audio_value,
-        cursor="hand2",
-        command=lambda: setattr(modules.globals, "keep_audio", keep_audio_value.get()),
-        progress_color="#3a7ebf",
-        font=("Roboto", 14, "bold"),
-    )
-    keep_audio_switch.pack(pady=5, anchor="w")
-
-    many_faces_value = ctk.BooleanVar(value=modules.globals.many_faces)
-    many_faces_switch = ctk.CTkSwitch(
-        options_column,
-        text="Many faces",
-        variable=many_faces_value,
-        cursor="hand2",
-        command=lambda: setattr(modules.globals, "many_faces", many_faces_value.get()),
-        progress_color="#3a7ebf",
-        font=("Roboto", 14, "bold"),
-    )
-    many_faces_switch.pack(pady=5, anchor="w")
-
     color_correction_value = ctk.BooleanVar(value=modules.globals.color_correction)
     color_correction_switch = ctk.CTkSwitch(
-        options_column,
+        left_column,
         text="Fix Blueish Cam",
         variable=color_correction_value,
         cursor="hand2",
-        command=lambda: setattr(
-            modules.globals, "color_correction", color_correction_value.get()
+        command=lambda: (
+            setattr(modules.globals, "color_correction", color_correction_value.get()),
+            save_switch_states(),
         ),
         progress_color="#3a7ebf",
         font=("Roboto", 14, "bold"),
@@ -373,16 +579,137 @@ def create_root(
 
     map_faces = ctk.BooleanVar(value=modules.globals.map_faces)
     map_faces_switch = ctk.CTkSwitch(
-        options_column,
+        left_column,
         text="Map faces",
         variable=map_faces,
         cursor="hand2",
-        command=lambda: setattr(modules.globals, "map_faces", map_faces.get()),
+        command=lambda: (
+            setattr(modules.globals, "map_faces", map_faces.get()),
+            save_switch_states(),
+        ),
         progress_color="#3a7ebf",
         font=("Roboto", 14, "bold"),
     )
     map_faces_switch.pack(pady=5, anchor="w")
 
+    # Right column - Face Detection & Masking Options
+    show_fps_value = ctk.BooleanVar(value=modules.globals.show_fps)
+    show_fps_switch = ctk.CTkSwitch(
+        right_column,
+        text="Show FPS",
+        variable=show_fps_value,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "show_fps", show_fps_value.get()),
+            save_switch_states(),
+        ),
+        progress_color="#3a7ebf",
+        font=("Roboto", 14, "bold"),
+    )
+    show_fps_switch.pack(pady=5, anchor="w")
+
+    # Mouth Mask Controls
+    mouth_mask_var = ctk.BooleanVar(value=modules.globals.mouth_mask)
+    mouth_mask_switch = ctk.CTkSwitch(
+        right_column,
+        text="Mouth Mask",
+        variable=mouth_mask_var,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "mouth_mask", mouth_mask_var.get()),
+            save_switch_states(),
+        ),
+        progress_color="#3a7ebf",
+        font=("Roboto", 14, "bold"),
+    )
+    mouth_mask_switch.pack(pady=5, anchor="w")
+
+    show_mouth_mask_box_var = ctk.BooleanVar(value=modules.globals.show_mouth_mask_box)
+    show_mouth_mask_box_switch = ctk.CTkSwitch(
+        right_column,
+        text="Show Mouth Box",
+        variable=show_mouth_mask_box_var,
+        cursor="hand2",
+        command=lambda: (
+            setattr(
+                modules.globals, "show_mouth_mask_box", show_mouth_mask_box_var.get()
+            ),
+            save_switch_states(),
+        ),
+        progress_color="#3a7ebf",
+        font=("Roboto", 14, "bold"),
+    )
+    show_mouth_mask_box_switch.pack(pady=5, anchor="w")
+
+    # Face Opacity Controls - Moved under Show Mouth Box
+    opacity_frame = ctk.CTkFrame(right_column, fg_color="#2a2d2e")
+    opacity_frame.pack(pady=5, anchor="w", fill="x")
+
+    opacity_switch = ctk.CTkSwitch(
+        opacity_frame,
+        text="Face Opacity",
+        variable=ctk.BooleanVar(value=modules.globals.opacity_switch),
+        cursor="hand2",
+        command=lambda: setattr(
+            modules.globals, "opacity_switch", not modules.globals.opacity_switch
+        ),
+        progress_color="#3a7ebf",
+        font=("Roboto", 14, "bold"),
+    )
+    opacity_switch.pack(side="left", padx=(0, 10))
+
+    opacity_slider = ctk.CTkSlider(
+        opacity_frame,
+        from_=0,
+        to=100,
+        number_of_steps=100,
+        command=update_opacity,
+        fg_color=("gray75", "gray25"),
+        progress_color="#3a7ebf",
+        button_color="#3a7ebf",
+        button_hover_color="#2b5d8b",
+    )
+    opacity_slider.pack(side="left", fill="x", expand=True)
+    opacity_slider.set(modules.globals.face_opacity)
+
+    # Mask Size Controls
+    mask_down_size_label = ctk.CTkLabel(
+        right_column, text="Mask Size:", font=("Roboto", 12)
+    )
+    mask_down_size_label.pack(pady=(5, 0), anchor="w")
+
+    mask_down_size_slider = ctk.CTkSlider(
+        right_column,
+        from_=0.1,
+        to=1.0,
+        number_of_steps=9,
+        command=lambda value: [
+            setattr(modules.globals, "mask_down_size", value),
+            save_switch_states(),
+        ],
+    )
+    mask_down_size_slider.set(modules.globals.mask_down_size)
+    mask_down_size_slider.pack(pady=(0, 5), fill="x")
+
+    # Mask Feather Controls
+    mask_feather_label = ctk.CTkLabel(
+        right_column, text="Mask Feather:", font=("Roboto", 12)
+    )
+    mask_feather_label.pack(pady=(5, 0), anchor="w")
+
+    mask_feather_slider = ctk.CTkSlider(
+        right_column,
+        from_=4,
+        to=16,
+        number_of_steps=12,
+        command=lambda value: [
+            setattr(modules.globals, "mask_feather_ratio", int(value)),
+            save_switch_states(),
+        ],
+    )
+    mask_feather_slider.set(modules.globals.mask_feather_ratio)
+    mask_feather_slider.pack(pady=(0, 5), fill="x")
+
     button_frame = ctk.CTkFrame(main_frame, fg_color="#1a1a1a")
     button_frame.grid(row=2, column=0, columnspan=3, padx=10, pady=10, sticky="nsew")
 
@@ -390,52 +717,24 @@ def create_root(
         button_frame,
         text="Start",
         cursor="hand2",
-        command=lambda: analyze_target(start, root),
+        command=lambda: [
+            (
+                donate_frame.destroy()
+                if "donate_frame" in globals() and donate_frame.winfo_exists()
+                else None
+            ),
+            analyze_target(start, root),
+        ],
         fg_color="#4CAF50",
         hover_color="#45a049",
     )
     start_button.pack(side="left", padx=10, expand=True)
 
     preview_button = ModernButton(
-        button_frame,
-        text="Preview",
-        cursor="hand2",
-        command=lambda: toggle_preview(),
+        button_frame, text="Preview", cursor="hand2", command=lambda: toggle_preview()
     )
     preview_button.pack(side="left", padx=10, expand=True)
 
-    # --- Camera Selection ---
-    camera_label = ctk.CTkLabel(root, text="Select Camera:")
-    camera_label.place(relx=0.4, rely=0.86, relwidth=0.2, relheight=0.05)
-    available_cameras = get_available_cameras()
-    # Convert camera indices to strings for CTkOptionMenu
-    available_camera_indices, available_camera_strings = available_cameras
-    camera_variable = ctk.StringVar(
-        value=(
-            available_camera_strings[0]
-            if available_camera_strings
-            else "No cameras found"
-        )
-    )
-    camera_optionmenu = ctk.CTkOptionMenu(
-        root, variable=camera_variable, values=available_camera_strings
-    )
-    camera_optionmenu.place(relx=0.65, rely=0.86, relwidth=0.2, relheight=0.05)
-    # --- End Camera Selection ---
-
-    live_button = ModernButton(
-        button_frame,
-        text="Live",
-        cursor="hand2",
-        command=lambda: webcam_preview(
-            root,
-            available_camera_indices[
-                available_camera_strings.index(camera_variable.get())
-            ],
-        ),
-    )
-    live_button.pack(side="left", padx=10, expand=True)
-
     stop_button = ModernButton(
         button_frame,
         text="Destroy",
@@ -446,10 +745,55 @@ def create_root(
     )
     stop_button.pack(side="left", padx=10, expand=True)
 
+    # Camera Selection
+    camera_frame = ctk.CTkFrame(main_frame, fg_color="#2a2d2e", corner_radius=15)
+    camera_frame.grid(row=3, column=0, columnspan=3, padx=10, pady=(0, 10), sticky="ew")
+
+    camera_label = ctk.CTkLabel(
+        camera_frame, text="Select Camera:", font=("Roboto", 14)
+    )
+    camera_label.pack(side="left", padx=(20, 10), pady=10)
+
+    available_cameras = get_available_cameras()
+    available_camera_indices, available_camera_strings = available_cameras
+    camera_variable = ctk.StringVar(
+        value=(
+            available_camera_strings[0]
+            if available_camera_strings
+            else "No cameras found"
+        )
+    )
+    camera_optionmenu = ModernOptionMenu(
+        camera_frame,
+        values=available_camera_strings,
+        command=lambda value: print(f"Selected: {value}"),  # Add your command here
+    )
+    camera_optionmenu.pack(side="left", padx=(10, 20), pady=10, fill="x", expand=True)
+
+    live_button = ModernButton(
+        camera_frame,
+        text="Live",
+        cursor="hand2",
+        command=lambda: [
+            (
+                donate_frame.destroy()
+                if "donate_frame" in globals() and donate_frame.winfo_exists()
+                else None
+            ),
+            webcam_preview(
+                root,
+                available_camera_indices[
+                    available_camera_strings.index(camera_optionmenu.get())
+                ],
+            ),
+        ],
+    )
+    live_button.pack(side="left", padx=10, pady=10)
+
     status_label = ModernLabel(
         main_frame, text=None, justify="center", fg_color="#1a1a1a"
     )
-    status_label.grid(row=3, column=0, columnspan=3, pady=10, sticky="ew")
+    status_label.grid(row=4, column=0, columnspan=3, pady=10, sticky="ew")
 
     donate_frame = ctk.CTkFrame(main_frame, fg_color="#1a1a1a")
     donate_frame.grid(row=4, column=0, columnspan=3, pady=5, sticky="ew")
@@ -463,7 +807,6 @@ def create_root(
         text_color="#1870c4",
     )
     donate_label.pack(side="left", expand=True)
-
     donate_label.bind(
         "<Button>", lambda event: webbrowser.open("https://paypal.me/hacksider")
     )
@@ -708,6 +1051,10 @@ def create_preview(parent: ctk.CTkToplevel) -> ctk.CTkToplevel:
     )
     preview_slider.pack(fill="x", padx=20, pady=10)
 
+    # Add keyboard bindings for left and right arrow keys
+    preview.bind("<Left>", lambda event: navigate_frames(-1))
+    preview.bind("<Right>", lambda event: navigate_frames(1))
+
     return preview
 
 
@@ -746,7 +1093,7 @@ def select_source_path() -> None:
     else:
         modules.globals.source_path = None
         source_label.configure(image=None)
-        source_label.configure(text="Drag & Drop Source Image Here")
+        source_label.configure(text="Drag & Drop\nSource Image Here")
 
 
 def swap_faces_paths() -> None:
@@ -893,36 +1240,77 @@ def toggle_preview() -> None:
     if PREVIEW.state() == "normal":
         PREVIEW.withdraw()
     elif modules.globals.source_path and modules.globals.target_path:
-        init_preview()
-        update_preview()
+        try:
+            init_preview()
+            update_preview()
+        except Exception as e:
+            print(f"Error initializing preview: {str(e)}")
+            # Optionally, show an error message to the user
+            update_status(f"Error initializing preview: {str(e)}")
 
 
 def init_preview() -> None:
+    global preview_slider
+
     if is_image(modules.globals.target_path):
-        preview_slider.pack_forget()
-    if is_video(modules.globals.target_path):
+        if hasattr(preview_slider, "pack_forget"):
+            preview_slider.pack_forget()
+    elif is_video(modules.globals.target_path):
         video_frame_total = get_video_frame_total(modules.globals.target_path)
-        preview_slider.configure(to=video_frame_total)
-        preview_slider.pack(fill="x")
-        preview_slider.set(0)
+
+        # Check if preview_slider exists and is a valid widget
+        if hasattr(preview_slider, "winfo_exists") and preview_slider.winfo_exists():
+            try:
+                preview_slider.configure(to=video_frame_total)
+                preview_slider.pack(fill="x")
+                preview_slider.set(0)
+            except tk.TclError:
+                print("Error: Preview slider widget not available. Recreating it.")
+                create_preview_slider()
+        else:
+            print("Preview slider not found. Creating a new one.")
+            create_preview_slider()
+
+
+def create_preview_slider():
+    global preview_slider, PREVIEW
+
+    # Ensure PREVIEW window exists
+    if not hasattr(PREVIEW, "winfo_exists") or not PREVIEW.winfo_exists():
+        print("Error: Preview window does not exist.")
+        return
+
+    # Create a new slider
+    preview_slider = ctk.CTkSlider(
+        PREVIEW,
+        from_=0,
+        to=get_video_frame_total(modules.globals.target_path),
+        command=lambda frame_value: update_preview(int(frame_value)),
+        fg_color=("gray75", "gray25"),
+        progress_color=("DodgerBlue", "DodgerBlue"),
+        button_color=("DodgerBlue", "DodgerBlue"),
+        button_hover_color=("RoyalBlue", "RoyalBlue"),
+    )
+    preview_slider.pack(fill="x", padx=20, pady=10)
+
+
+def navigate_frames(direction: int) -> None:
+    current_frame = int(preview_slider.get())
+    new_frame = max(0, min(current_frame + direction, int(preview_slider.cget("to"))))
+    preview_slider.set(new_frame)
+    update_preview(new_frame)
 
 
 def update_preview(frame_number: int = 0) -> None:
     if modules.globals.source_path and modules.globals.target_path:
         update_status("Processing...")
 
-        # Debug: Print the target path and frame number
-        print(
-            f"Target path: {modules.globals.target_path}, Frame number: {frame_number}"
-        )
-
         temp_frame = None
         if is_video(modules.globals.target_path):
             temp_frame = get_video_frame(modules.globals.target_path, frame_number)
         elif is_image(modules.globals.target_path):
             temp_frame = cv2.imread(modules.globals.target_path)
 
-        # Debug: Check if temp_frame is None
         if temp_frame is None:
             print("Error: temp_frame is None")
             update_status("Error: Could not read frame from video or image.")
@@ -934,19 +1322,10 @@ def update_preview(frame_number: int = 0) -> None:
         for frame_processor in get_frame_processors_modules(
             modules.globals.frame_processors
         ):
-            # Debug: Print the type of frame_processor
-            print(f"Processing frame with: {type(frame_processor).__name__}")
-
             temp_frame = frame_processor.process_frame(
                 get_one_face(cv2.imread(modules.globals.source_path)), temp_frame
             )
 
-            # Debug: Check if temp_frame is None after processing
-            if temp_frame is None:
-                print("Error: temp_frame is None after processing")
-                update_status("Error: Frame processing failed.")
-                return
-
         image = Image.fromarray(cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB))
         image = ImageOps.contain(
             image, (PREVIEW_MAX_WIDTH, PREVIEW_MAX_HEIGHT), Image.LANCZOS
@@ -987,25 +1366,25 @@ def update_opacity(value):
     modules.globals.face_opacity = int(value)
 
 
-# Modify the create_webcam_preview function to include the slider
-def create_webcam_preview(camera_index):
+def create_webcam_preview(camera_index: int):
     global preview_label, PREVIEW
 
     camera = cv2.VideoCapture(camera_index)
     if not camera.isOpened():
         update_status(f"Error: Could not open camera with index {camera_index}")
         return
+
     camera.set(cv2.CAP_PROP_FRAME_WIDTH, PREVIEW_DEFAULT_WIDTH)
     camera.set(cv2.CAP_PROP_FRAME_HEIGHT, PREVIEW_DEFAULT_HEIGHT)
     camera.set(cv2.CAP_PROP_FPS, 60)
 
     PREVIEW.deiconify()
 
-    # Remove any existing widgets in PREVIEW window
+    # Clear any existing widgets in the PREVIEW window
     for widget in PREVIEW.winfo_children():
         widget.destroy()
 
-    # Create a main frame to hold all widgets
+    # Create a main frame to contain all widgets
     main_frame = ctk.CTkFrame(PREVIEW)
     main_frame.pack(fill="both", expand=True)
 
@@ -1016,10 +1395,17 @@ def create_webcam_preview(camera_index):
     preview_label = ctk.CTkLabel(preview_frame, text="")
     preview_label.pack(fill="both", expand=True)
 
+    # Initialize frame processors
     frame_processors = get_frame_processors_modules(modules.globals.frame_processors)
 
+    # Variables for source image and FPS calculation
     source_image = None
+    prev_time = time.time()
+    fps_update_interval = 0.5
+    frame_count = 0
+    fps = 0
 
+    # Function to update frame size when the window is resized
     def update_frame_size(event):
         nonlocal temp_frame
         if modules.globals.live_resizable:
@@ -1027,44 +1413,63 @@ def create_webcam_preview(camera_index):
 
     preview_frame.bind("<Configure>", update_frame_size)
 
-    while camera:
+    # Main loop for capturing and processing frames
+    while camera.isOpened() and PREVIEW.state() != "withdrawn":
         ret, frame = camera.read()
         if not ret:
             break
 
-        temp_frame = frame.copy()  # Create a copy of the frame
+        temp_frame = frame.copy()
 
+        # Apply mirroring if enabled
         if modules.globals.live_mirror:
-            temp_frame = cv2.flip(temp_frame, 1)  # horizontal flipping
+            temp_frame = cv2.flip(temp_frame, 1)
 
+        # Resize frame if enabled
         if modules.globals.live_resizable:
             temp_frame = fit_image_to_size(
                 temp_frame, PREVIEW.winfo_width(), PREVIEW.winfo_height()
             )
 
+        # Process frame based on face mapping mode
         if not modules.globals.map_faces:
-            # Check if source_path has changed and update source_image if necessary
+            # Update source image if path has changed
             if modules.globals.source_path and (
                 source_image is None
                 or modules.globals.source_path != source_image["location"]
             ):
                 source_image = get_one_face(cv2.imread(modules.globals.source_path))
-                source_image["location"] = (
-                    modules.globals.source_path
-                )  # Store location for comparison
+                source_image["location"] = modules.globals.source_path
 
+            # Apply frame processors (e.g., face swapping, enhancement)
             for frame_processor in frame_processors:
                 temp_frame = frame_processor.process_frame(source_image, temp_frame)
-
         else:
             modules.globals.target_path = None
-
             for frame_processor in frame_processors:
                 temp_frame = frame_processor.process_frame_v2(temp_frame)
 
-        image = cv2.cvtColor(
-            temp_frame, cv2.COLOR_BGR2RGB
-        )  # Convert the image to RGB format to display it with Tkinter
+        # Calculate and display FPS
+        current_time = time.time()
+        frame_count += 1
+        if current_time - prev_time >= fps_update_interval:
+            fps = frame_count / (current_time - prev_time)
+            frame_count = 0
+            prev_time = current_time
+
+        if modules.globals.show_fps:
+            cv2.putText(
+                temp_frame,
+                f"FPS: {fps:.1f}",
+                (10, 30),
+                cv2.FONT_HERSHEY_SIMPLEX,
+                1,
+                (0, 255, 0),
+                2,
+            )
+
+        # Convert frame to RGB and display in preview label
+        image = cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB)
         image = Image.fromarray(image)
         image = ImageOps.contain(
             image, (temp_frame.shape[1], temp_frame.shape[0]), Image.LANCZOS
@@ -1073,11 +1478,9 @@ def create_webcam_preview(camera_index):
         preview_label.configure(image=image)
         ROOT.update()
 
-        if PREVIEW.state() == "withdrawn":
-            break
-
+    # Release camera and close preview window
     camera.release()
-    PREVIEW.withdraw()  # Close preview window when loop is finished
+    PREVIEW.withdraw()
 
 
 def create_source_target_popup_for_webcam(root: ctk.CTk, map: list) -> None:
@@ -1092,7 +1495,12 @@ def create_source_target_popup_for_webcam(root: ctk.CTk, map: list) -> None:
         if has_valid_map():
             POPUP_LIVE.destroy()
             simplify_maps()
-            create_webcam_preview()
+            # Get the selected camera index
+            selected_camera = camera_optionmenu.get()
+            camera_index = available_camera_indices[
+                available_camera_strings.index(selected_camera)
+            ]
+            create_webcam_preview(camera_index)
         else:
             update_pop_live_status("At least 1 source with target is required!")
 
@@ -1101,7 +1509,10 @@ def create_source_target_popup_for_webcam(root: ctk.CTk, map: list) -> None:
         refresh_data(map)
         update_pop_live_status("Please provide mapping!")
 
-    popup_status_label_live = ctk.CTkLabel(POPUP_LIVE, text=None, justify="center")
+    # Rest of the popup content
+    popup_status_label_live = ctk.CTkLabel(
+        POPUP_LIVE, text=None, justify="center", font=("Roboto", 14)
+    )
     popup_status_label_live.grid(row=1, column=0, pady=15)
 
     add_button = ctk.CTkButton(
@@ -1124,6 +1535,29 @@ def create_source_target_popup_for_webcam(root: ctk.CTk, map: list) -> None:
     )
     close_button.place(relx=0.6, rely=0.92, relwidth=0.2, relheight=0.05)
 
+    # Create a better styled camera selection frame
+    camera_frame = ctk.CTkFrame(POPUP_LIVE, fg_color="#2a2d2e", corner_radius=15)
+    camera_frame.grid(row=2, column=0, pady=15, padx=20, sticky="ew")
+    POPUP_LIVE.grid_columnconfigure(0, weight=1)
+
+    camera_label = ctk.CTkLabel(
+        camera_frame,
+        text="Select Camera:",
+        font=("Roboto", 14, "bold"),
+        text_color="#DCE4EE",
+    )
+    camera_label.pack(side="left", padx=20, pady=10)
+
+    available_cameras = get_available_cameras()
+    available_camera_indices, available_camera_strings = available_cameras
+
+    camera_optionmenu = ModernOptionMenu(
+        camera_frame,
+        values=available_camera_strings,
+        command=lambda value: print(f"Selected: {value}"),  # Add your command here
+    )
+    camera_optionmenu.pack(side="left", padx=(10, 20), pady=10, fill="x", expand=True)
+
     refresh_data(map)  # Initial data refresh
 
 

requirements.txt

@@ -7,7 +7,6 @@ onnx==1.16.0
 insightface==0.7.3
 psutil==5.9.8
 tk==0.1.0
-customtkinter==5.2.2
 pillow==9.5.0
 torch==2.0.1+cu118; sys_platform != 'darwin'
 torch==2.0.1; sys_platform == 'darwin'