import os import webbrowser import customtkinter as ctk from typing import Callable, Tuple import cv2 from PIL import Image, ImageOps import modules.globals import modules.metadata from modules.face_analyser import get_one_face from modules.capturer import get_video_frame, get_video_frame_total from modules.processors.frame.core import get_frame_processors_modules from modules.utilities import is_image, is_video, resolve_relative_path, has_image_extension ROOT = None ROOT_HEIGHT = 700 ROOT_WIDTH = 600 PREVIEW = None PREVIEW_MAX_HEIGHT = 700 PREVIEW_MAX_WIDTH = 1200 PREVIEW_DEFAULT_WIDTH = 960 PREVIEW_DEFAULT_HEIGHT = 540 RECENT_DIRECTORY_SOURCE = None RECENT_DIRECTORY_TARGET = None RECENT_DIRECTORY_OUTPUT = None preview_label = None preview_slider = None source_label = None target_label = None status_label = None img_ft, vid_ft = modules.globals.file_types def init(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.CTk: global ROOT, PREVIEW ROOT = create_root(start, destroy) PREVIEW = create_preview(ROOT) return ROOT def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.CTk: global source_label, target_label, status_label ctk.deactivate_automatic_dpi_awareness() ctk.set_appearance_mode('system') ctk.set_default_color_theme(resolve_relative_path('ui.json')) root = ctk.CTk() root.minsize(ROOT_WIDTH, ROOT_HEIGHT) root.title(f'{modules.metadata.name} {modules.metadata.version} {modules.metadata.edition}') root.configure() 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) target_label = ctk.CTkLabel(root, text=None) target_label.place(relx=0.6, rely=0.1, relwidth=0.3, relheight=0.25) 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_target_button = ctk.CTkButton(root, text='Select a target', cursor='hand2', command=lambda: select_target_path()) select_target_button.place(relx=0.6, rely=0.4, relwidth=0.3, relheight=0.1) keep_fps_value = ctk.BooleanVar(value=modules.globals.keep_fps) keep_fps_checkbox = ctk.CTkSwitch(root, text='Keep fps', variable=keep_fps_value, cursor='hand2', command=lambda: setattr(modules.globals, 'keep_fps', not modules.globals.keep_fps)) keep_fps_checkbox.place(relx=0.1, rely=0.6) keep_frames_value = ctk.BooleanVar(value=modules.globals.keep_frames) keep_frames_switch = ctk.CTkSwitch(root, text='Keep frames', variable=keep_frames_value, cursor='hand2', command=lambda: setattr(modules.globals, 'keep_frames', keep_frames_value.get())) keep_frames_switch.place(relx=0.1, rely=0.65) # for FRAME PROCESSOR ENHANCER tumbler: enhancer_value = ctk.BooleanVar(value=modules.globals.fp_ui['face_enhancer']) enhancer_switch = ctk.CTkSwitch(root, text='Face Enhancer', variable=enhancer_value, cursor='hand2', command=lambda: update_tumbler('face_enhancer',enhancer_value.get())) enhancer_switch.place(relx=0.1, rely=0.7) keep_audio_value = ctk.BooleanVar(value=modules.globals.keep_audio) keep_audio_switch = ctk.CTkSwitch(root, text='Keep audio', variable=keep_audio_value, cursor='hand2', command=lambda: setattr(modules.globals, 'keep_audio', keep_audio_value.get())) keep_audio_switch.place(relx=0.6, rely=0.6) many_faces_value = ctk.BooleanVar(value=modules.globals.many_faces) many_faces_switch = ctk.CTkSwitch(root, text='Many faces', variable=many_faces_value, cursor='hand2', command=lambda: setattr(modules.globals, 'many_faces', many_faces_value.get())) many_faces_switch.place(relx=0.6, rely=0.65) 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())) nsfw_switch.place(relx=0.6, rely=0.7) start_button = ctk.CTkButton(root, text='Start', cursor='hand2', command=lambda: select_output_path(start)) start_button.place(relx=0.15, rely=0.80, 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) 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) live_button = ctk.CTkButton(root, text='Live', cursor='hand2', command=lambda: webcam_preview()) live_button.place(relx=0.40, rely=0.86, relwidth=0.2, relheight=0.05) status_label = ctk.CTkLabel(root, text=None, justify='center') status_label.place(relx=0.1, rely=0.9, 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.configure(text_color=ctk.ThemeManager.theme.get('URL').get('text_color')) donate_label.bind('<Button>', lambda event: webbrowser.open('https://paypal.me/hacksider')) return root def create_preview(parent: ctk.CTkToplevel) -> ctk.CTkToplevel: global preview_label, preview_slider preview = ctk.CTkToplevel(parent) preview.withdraw() preview.title('Preview') preview.configure() preview.protocol('WM_DELETE_WINDOW', lambda: toggle_preview()) preview.resizable(width=True, height=True) preview_label = ctk.CTkLabel(preview, text=None) preview_label.pack(fill='both', expand=True) preview_slider = ctk.CTkSlider(preview, from_=0, to=0, command=lambda frame_value: update_preview(frame_value)) return preview def update_status(text: str) -> None: status_label.configure(text=text) ROOT.update() def update_tumbler(var: str, value: bool) -> None: modules.globals.fp_ui[var] = value def select_source_path() -> None: global RECENT_DIRECTORY_SOURCE, img_ft, vid_ft PREVIEW.withdraw() source_path = ctk.filedialog.askopenfilename(title='select an source image', initialdir=RECENT_DIRECTORY_SOURCE, filetypes=[img_ft]) if is_image(source_path): modules.globals.source_path = source_path RECENT_DIRECTORY_SOURCE = os.path.dirname(modules.globals.source_path) image = render_image_preview(modules.globals.source_path, (200, 200)) source_label.configure(image=image) else: modules.globals.source_path = None source_label.configure(image=None) def select_target_path() -> None: global RECENT_DIRECTORY_TARGET, img_ft, vid_ft PREVIEW.withdraw() target_path = ctk.filedialog.askopenfilename(title='select an target image or video', initialdir=RECENT_DIRECTORY_TARGET, filetypes=[img_ft, vid_ft]) if is_image(target_path): modules.globals.target_path = target_path RECENT_DIRECTORY_TARGET = os.path.dirname(modules.globals.target_path) image = render_image_preview(modules.globals.target_path, (200, 200)) target_label.configure(image=image) elif is_video(target_path): modules.globals.target_path = target_path RECENT_DIRECTORY_TARGET = os.path.dirname(modules.globals.target_path) video_frame = render_video_preview(target_path, (200, 200)) target_label.configure(image=video_frame) else: modules.globals.target_path = None target_label.configure(image=None) def select_output_path(start: Callable[[], None]) -> None: global RECENT_DIRECTORY_OUTPUT, img_ft, vid_ft if is_image(modules.globals.target_path): output_path = ctk.filedialog.asksaveasfilename(title='save image output file', filetypes=[img_ft], defaultextension='.png', initialfile='output.png', initialdir=RECENT_DIRECTORY_OUTPUT) elif is_video(modules.globals.target_path): output_path = ctk.filedialog.asksaveasfilename(title='save video output file', filetypes=[vid_ft], defaultextension='.mp4', initialfile='output.mp4', initialdir=RECENT_DIRECTORY_OUTPUT) else: output_path = None if output_path: modules.globals.output_path = output_path RECENT_DIRECTORY_OUTPUT = os.path.dirname(modules.globals.output_path) start() def check_and_ignore_nsfw(target, destroy: Callable = None) -> bool: ''' Check if the target is NSFW. TODO: Consider to make blur the target. ''' from numpy import ndarray from modules.predicter import predict_image, predict_video, predict_frame if type(target) is str: # image/video file path check_nsfw = predict_image if has_image_extension(target) else predict_video elif type(target) is ndarray: # frame object check_nsfw = predict_frame if check_nsfw and check_nsfw(target): if destroy: destroy(to_quit=False) # Do not need to destroy the window frame if the target is NSFW update_status('Processing ignored!') return True else: return False def fit_image_to_size(image, width: int, height: int): if width is None and height is None: return image h, w, _ = image.shape ratio_h = 0.0 ratio_w = 0.0 if width > height: ratio_h = height / h else: ratio_w = width / w ratio = max(ratio_w, ratio_h) new_size = (int(ratio * w), int(ratio * h)) return cv2.resize(image, dsize=new_size) def render_image_preview(image_path: str, size: Tuple[int, int]) -> ctk.CTkImage: image = Image.open(image_path) if size: image = ImageOps.fit(image, size, Image.LANCZOS) return ctk.CTkImage(image, size=image.size) def render_video_preview(video_path: str, size: Tuple[int, int], frame_number: int = 0) -> ctk.CTkImage: capture = cv2.VideoCapture(video_path) if frame_number: capture.set(cv2.CAP_PROP_POS_FRAMES, frame_number) has_frame, frame = capture.read() if has_frame: image = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)) if size: image = ImageOps.fit(image, size, Image.LANCZOS) return ctk.CTkImage(image, size=image.size) capture.release() cv2.destroyAllWindows() def toggle_preview() -> None: if PREVIEW.state() == 'normal': PREVIEW.withdraw() elif modules.globals.source_path and modules.globals.target_path: init_preview() update_preview() def init_preview() -> None: if is_image(modules.globals.target_path): preview_slider.pack_forget() if 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) def update_preview(frame_number: int = 0) -> None: if modules.globals.source_path and modules.globals.target_path: update_status('Processing...') temp_frame = get_video_frame(modules.globals.target_path, frame_number) if modules.globals.nsfw_filter and check_and_ignore_nsfw(temp_frame): return for frame_processor in get_frame_processors_modules(modules.globals.frame_processors): temp_frame = frame_processor.process_frame( get_one_face(cv2.imread(modules.globals.source_path)), temp_frame ) image = Image.fromarray(cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB)) image = ImageOps.contain(image, (PREVIEW_MAX_WIDTH, PREVIEW_MAX_HEIGHT), Image.LANCZOS) image = ctk.CTkImage(image, size=image.size) preview_label.configure(image=image) update_status('Processing succeed!') PREVIEW.deiconify() def webcam_preview(): if modules.globals.source_path is None: # No image selected return global preview_label, PREVIEW camera = cv2.VideoCapture(0) # Use index for the webcam (adjust the index accordingly if necessary) camera.set(cv2.CAP_PROP_FRAME_WIDTH, PREVIEW_DEFAULT_WIDTH) # Set the width of the resolution camera.set(cv2.CAP_PROP_FRAME_HEIGHT, PREVIEW_DEFAULT_HEIGHT) # Set the height of the resolution camera.set(cv2.CAP_PROP_FPS, 60) # Set the frame rate of the webcam preview_label.configure(width=PREVIEW_DEFAULT_WIDTH, height=PREVIEW_DEFAULT_HEIGHT) # Reset the preview image before startup PREVIEW.deiconify() # Open preview window frame_processors = get_frame_processors_modules(modules.globals.frame_processors) source_image = None # Initialize variable for the selected face image while camera: ret, frame = camera.read() if not ret: break # Select and save face image only once if source_image is None and modules.globals.source_path: source_image = get_one_face(cv2.imread(modules.globals.source_path)) temp_frame = frame.copy() #Create a copy of the frame if modules.globals.live_mirror: temp_frame = cv2.flip(temp_frame, 1) # horizontal flipping if modules.globals.live_resizable: temp_frame = fit_image_to_size(temp_frame, PREVIEW.winfo_width(), PREVIEW.winfo_height()) for frame_processor in frame_processors: temp_frame = frame_processor.process_frame(source_image, temp_frame) image = cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB) # Convert the image to RGB format to display it with Tkinter image = Image.fromarray(image) image = ImageOps.contain(image, (temp_frame.shape[1], temp_frame.shape[0]), Image.LANCZOS) image = ctk.CTkImage(image, size=image.size) preview_label.configure(image=image) ROOT.update() if PREVIEW.state() == 'withdrawn': break camera.release() PREVIEW.withdraw() # Close preview window when loop is finished