admin
Live Button with webcam live preview - code attached =) #591
Comments
This code is invalid in roop 1.2. How to solve it? |
roop 1.2 can not use this script,please fixed,thx |
My Mod uses most of the existing code functions that where implemented in 1.0.2. I had to look into the new code base if it is still possible to do this kind of mod here. At the moment I am on set for a bigger movie production. Maybe I have time next week. As far I can tell my mod will not benefit from 1.2.0 Updates in performance. Use 1.0.2 for now. Thanks! |
ok，我改了下。1.2版本的live。 many face来回切换，就是自己和换脸的对象。 请下载附件，敬情玩耍。 |
havok2-htwo commented on Jun 23 •
Hello,
I was able to add a live button that opens a webcam preview with your webcam image that is face swapped (nearly realtime on my 4090) - I just added a function called webcam_preview() and a new button to run this. Sadly I am so new to git that I dont know how I can suggest my code somehow. Here is the code for the ui.py
import os import webbrowser import customtkinter as ctk from typing import Callable, Tuple import cv2 from PIL import Image, ImageOps import roop.globals import roop.metadata from roop.face_analyser import get_one_face from roop.capturer import get_video_frame, get_video_frame_total from roop.predicter import predict_frame from roop.processors.frame.core import get_frame_processors_modules from roop.utilities import is_image, is_video, resolve_relative_path import cv2 ROOT = None ROOT_HEIGHT = 700 ROOT_WIDTH = 600 PREVIEW = None PREVIEW_MAX_HEIGHT = 700 PREVIEW_MAX_WIDTH = 1200 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 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'{roop.metadata.name} {roop.metadata.version}') 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) source_button = ctk.CTkButton(root, text='Select a face', cursor='hand2', command=lambda: select_source_path()) source_button.place(relx=0.1, rely=0.4, relwidth=0.3, relheight=0.1) target_button = ctk.CTkButton(root, text='Select a target', cursor='hand2', command=lambda: select_target_path()) target_button.place(relx=0.6, rely=0.4, relwidth=0.3, relheight=0.1) keep_fps_value = ctk.BooleanVar(value=roop.globals.keep_fps) keep_fps_checkbox = ctk.CTkSwitch(root, text='Keep fps', variable=keep_fps_value, cursor='hand2', command=lambda: setattr(roop.globals, 'keep_fps', not roop.globals.keep_fps)) keep_fps_checkbox.place(relx=0.1, rely=0.6) keep_frames_value = ctk.BooleanVar(value=roop.globals.keep_frames) keep_frames_switch = ctk.CTkSwitch(root, text='Keep frames', variable=keep_frames_value, cursor='hand2', command=lambda: setattr(roop.globals, 'keep_frames', keep_frames_value.get())) keep_frames_switch.place(relx=0.1, rely=0.65) keep_audio_value = ctk.BooleanVar(value=roop.globals.keep_audio) keep_audio_switch = ctk.CTkSwitch(root, text='Keep audio', variable=keep_audio_value, cursor='hand2', command=lambda: setattr(roop.globals, 'keep_audio', keep_audio_value.get())) keep_audio_switch.place(relx=0.6, rely=0.6) many_faces_value = ctk.BooleanVar(value=roop.globals.many_faces) many_faces_switch = ctk.CTkSwitch(root, text='Many faces', variable=many_faces_value, cursor='hand2', command=lambda: setattr(roop.globals, 'many_faces', many_faces_value.get())) many_faces_switch.place(relx=0.6, rely=0.65) start_button = ctk.CTkButton(root, text='Start', cursor='hand2', command=lambda: select_output_path(start)) start_button.place(relx=0.15, rely=0.75, 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=0.75, 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=0.75, 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=0.83, 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='Become a GitHub Sponsor', 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('RoopDonate').get('text_color')) donate_label.bind('<Button>', lambda event: webbrowser.open('https://github.com/sponsors/s0md3v')) 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=False, height=False) 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 select_source_path() -> None: global RECENT_DIRECTORY_SOURCE PREVIEW.withdraw() source_path = ctk.filedialog.askopenfilename(title='select an source image', initialdir=RECENT_DIRECTORY_SOURCE) if is_image(source_path): roop.globals.source_path = source_path RECENT_DIRECTORY_SOURCE = os.path.dirname(roop.globals.source_path) image = render_image_preview(roop.globals.source_path, (200, 200)) source_label.configure(image=image) else: roop.globals.source_path = None source_label.configure(image=None) def select_target_path() -> None: global RECENT_DIRECTORY_TARGET PREVIEW.withdraw() target_path = ctk.filedialog.askopenfilename(title='select an target image or video', initialdir=RECENT_DIRECTORY_TARGET) if is_image(target_path): roop.globals.target_path = target_path RECENT_DIRECTORY_TARGET = os.path.dirname(roop.globals.target_path) image = render_image_preview(roop.globals.target_path, (200, 200)) target_label.configure(image=image) elif is_video(target_path): roop.globals.target_path = target_path RECENT_DIRECTORY_TARGET = os.path.dirname(roop.globals.target_path) video_frame = render_video_preview(target_path, (200, 200)) target_label.configure(image=video_frame) else: roop.globals.target_path = None target_label.configure(image=None) def select_output_path(start: Callable[[], None]) -> None: global RECENT_DIRECTORY_OUTPUT if is_image(roop.globals.target_path): output_path = ctk.filedialog.asksaveasfilename(title='save image output file', defaultextension='.png', initialfile='output.png', initialdir=RECENT_DIRECTORY_OUTPUT) elif is_video(roop.globals.target_path): output_path = ctk.filedialog.asksaveasfilename(title='save video output file', defaultextension='.mp4', initialfile='output.mp4', initialdir=RECENT_DIRECTORY_OUTPUT) else: output_path = None if output_path: roop.globals.output_path = output_path RECENT_DIRECTORY_OUTPUT = os.path.dirname(roop.globals.output_path) start() 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 roop.globals.source_path and roop.globals.target_path: init_preview() update_preview() PREVIEW.deiconify() def init_preview() -> None: if is_image(roop.globals.target_path): preview_slider.pack_forget() if is_video(roop.globals.target_path): video_frame_total = get_video_frame_total(roop.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 roop.globals.source_path and roop.globals.target_path: temp_frame = get_video_frame(roop.globals.target_path, frame_number) if predict_frame(temp_frame): quit() for frame_processor in get_frame_processors_modules(roop.globals.frame_processors): temp_frame = frame_processor.process_frame( get_one_face(cv2.imread(roop.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) def webcam_preview(): if roop.globals.source_path is None: # No image selected return global preview_label, PREVIEW cap = cv2.VideoCapture(0) # Use index for the webcam (adjust the index accordingly if necessary) cap.set(cv2.CAP_PROP_FRAME_WIDTH, 960) # Set the width of the resolution cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 540) # Set the height of the resolution cap.set(cv2.CAP_PROP_FPS, 30) # Set the frame rate of the webcam PREVIEW_MAX_HEIGHT = 960 PREVIEW_MAX_WIDTH = 540 preview_label.configure(image=None) # Reset the preview image before startup PREVIEW.deiconify() # Open preview window frame_processors = get_frame_processors_modules(roop.globals.frame_processors) source_image = None # Initialize variable for the selected face image while True: ret, frame = cap.read() if not ret: break # Select and save face image only once if source_image is None and roop.globals.source_path: source_image = get_one_face(cv2.imread(roop.globals.source_path)) temp_frame = frame.copy() #Create a copy of the frame 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, (PREVIEW_MAX_WIDTH, PREVIEW_MAX_HEIGHT), Image.LANCZOS) image = ctk.CTkImage(image, size=image.size) preview_label.configure(image=image) ROOT.update() cap.release() PREVIEW.withdraw() # Close preview window when loop is finished