Deep-Live-Cam/modules/ui.py

370 lines
15 KiB
Python

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)
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)
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)
# Add color correction toggle button
color_correction_value = ctk.BooleanVar(value=modules.globals.color_correction)
color_correction_switch = ctk.CTkSwitch(root, text='Fix Blueish Cam\n(force cv2 to use RGB instead of BGR)', variable=color_correction_value, cursor='hand2', command=lambda: setattr(modules.globals, 'color_correction', color_correction_value.get()))
color_correction_switch.place(relx=0.6, rely=0.70)
# 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 swap_faces_paths() -> None:
global RECENT_DIRECTORY_SOURCE, RECENT_DIRECTORY_TARGET
source_path = modules.globals.source_path
target_path = modules.globals.target_path
if not is_image(source_path) or not is_image(target_path):
return
modules.globals.source_path = target_path
modules.globals.target_path = source_path
RECENT_DIRECTORY_SOURCE = os.path.dirname(modules.globals.source_path)
RECENT_DIRECTORY_TARGET = os.path.dirname(modules.globals.target_path)
PREVIEW.withdraw()
source_image = render_image_preview(modules.globals.source_path, (200, 200))
source_label.configure(image=source_image)
target_image = render_image_preview(modules.globals.target_path, (200, 200))
target_label.configure(image=target_image)
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