Adding Drag and Drop feature to Face Mapper and Source and Target

This commit is contained in:
CH. Krish 2024-09-15 23:00:28 +05:30 committed by GitHub
parent 621c3f035e
commit 523d80550d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -4,13 +4,26 @@ import customtkinter as ctk
from typing import Callable, Tuple
import cv2
from PIL import Image, ImageOps
import tkinterdnd2 as tkdnd
import modules.globals
import modules.metadata
from modules.face_analyser import get_one_face, get_unique_faces_from_target_image, get_unique_faces_from_target_video, add_blank_map, has_valid_map, simplify_maps
from modules.face_analyser import (
get_one_face,
get_unique_faces_from_target_image,
get_unique_faces_from_target_video,
add_blank_map,
has_valid_map,
simplify_maps,
)
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
from modules.utilities import (
is_image,
is_video,
resolve_relative_path,
has_image_extension,
)
ROOT = None
POPUP = None
@ -20,18 +33,18 @@ ROOT_WIDTH = 600
PREVIEW = None
PREVIEW_MAX_HEIGHT = 700
PREVIEW_MAX_WIDTH = 1200
PREVIEW_DEFAULT_WIDTH = 960
PREVIEW_MAX_WIDTH = 1200
PREVIEW_DEFAULT_WIDTH = 960
PREVIEW_DEFAULT_HEIGHT = 540
POPUP_WIDTH = 750
POPUP_HEIGHT = 810
POPUP_SCROLL_WIDTH = 740,
POPUP_SCROLL_WIDTH = 740
POPUP_SCROLL_HEIGHT = 700
POPUP_LIVE_WIDTH = 900
POPUP_LIVE_HEIGHT = 820
POPUP_LIVE_SCROLL_WIDTH = 890,
POPUP_LIVE_SCROLL_WIDTH = 890
POPUP_LIVE_SCROLL_HEIGHT = 700
MAPPER_PREVIEW_MAX_HEIGHT = 100
@ -58,7 +71,58 @@ target_label_dict_live = {}
img_ft, vid_ft = modules.globals.file_types
def init(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.CTk:
class DragDropButton(ctk.CTkButton):
def __init__(self, master, **kwargs):
super().__init__(master, **kwargs)
self.drop_target_register(tkdnd.DND_FILES)
self.dnd_bind("<<Drop>>", self.drop)
def drop(self, event):
file_path = event.data
if file_path.startswith("{"):
file_path = file_path[1:-1]
self.handle_drop(file_path)
def handle_drop(self, file_path):
pass
class SourceButton(DragDropButton):
def handle_drop(self, file_path):
if is_image(file_path):
modules.globals.source_path = file_path
global RECENT_DIRECTORY_SOURCE
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)
class SourceMapperButton(DragDropButton):
def __init__(self, master, map, button_num, **kwargs):
super().__init__(master, **kwargs)
self.map = map
self.button_num = button_num
def handle_drop(self, file_path):
if is_image(file_path):
update_popup_source(self.master, self.map, self.button_num, file_path)
class TargetButton(DragDropButton):
def handle_drop(self, file_path):
global RECENT_DIRECTORY_TARGET
if is_image(file_path) or is_video(file_path):
modules.globals.target_path = file_path
RECENT_DIRECTORY_TARGET = os.path.dirname(modules.globals.target_path)
if is_image(file_path):
image = render_image_preview(modules.globals.target_path, (200, 200))
target_label.configure(image=image)
elif is_video(file_path):
video_frame = render_video_preview(file_path, (200, 200))
target_label.configure(image=video_frame)
def init(start: Callable[[], None], destroy: Callable[[], None]) -> tkdnd.TkinterDnD.Tk:
global ROOT, PREVIEW
ROOT = create_root(start, destroy)
@ -67,18 +131,22 @@ def init(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.CTk:
return ROOT
def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.CTk:
def create_root(
start: Callable[[], None], destroy: Callable[[], None]
) -> tkdnd.TkinterDnD.Tk:
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'))
ctk.set_appearance_mode("dark") # Re-add this line
ctk.set_default_color_theme(resolve_relative_path("ui.json"))
root = ctk.CTk()
root = tkdnd.TkinterDnD.Tk()
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())
root.title(
f"{modules.metadata.name} {modules.metadata.version} {modules.metadata.edition}"
)
root.configure(bg="gray12")
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)
@ -86,71 +154,137 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
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 = SourceButton(
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 = 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 = TargetButton(
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 = 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 = 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_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 = 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 = 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 = 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)
map_faces = ctk.BooleanVar(value=modules.globals.map_faces)
map_faces_switch = ctk.CTkSwitch(root, text='Map faces', variable=map_faces, cursor='hand2', command=lambda: setattr(modules.globals, 'map_faces', map_faces.get()))
map_faces_switch = ctk.CTkSwitch(
root,
text="Map faces",
variable=map_faces,
cursor="hand2",
command=lambda: setattr(modules.globals, "map_faces", map_faces.get()),
)
map_faces_switch.place(relx=0.1, rely=0.75)
start_button = ctk.CTkButton(root, text='Start', cursor='hand2', command=lambda: analyze_target(start, root))
start_button = ctk.CTkButton(
root, text="Start", cursor="hand2", command=lambda: analyze_target(start, root)
)
start_button.place(relx=0.15, rely=0.80, relwidth=0.2, relheight=0.05)
stop_button = ctk.CTkButton(root, text='Destroy', cursor='hand2', command=lambda: destroy())
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 = 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(root))
live_button = ctk.CTkButton(
root, text="Live", cursor="hand2", command=lambda: webcam_preview(root)
)
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 = 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 = 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'))
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 analyze_target(start: Callable[[], None], root: ctk.CTk):
if POPUP != None and POPUP.winfo_exists():
update_status("Please complete pop-up or close it.")
@ -160,10 +294,10 @@ def analyze_target(start: Callable[[], None], root: ctk.CTk):
modules.globals.souce_target_map = []
if is_image(modules.globals.target_path):
update_status('Getting unique faces')
update_status("Getting unique faces")
get_unique_faces_from_target_image()
elif is_video(modules.globals.target_path):
update_status('Getting unique faces')
update_status("Getting unique faces")
get_unique_faces_from_target_video()
if len(modules.globals.souce_target_map) > 0:
@ -173,7 +307,10 @@ def analyze_target(start: Callable[[], None], root: ctk.CTk):
else:
select_output_path(start)
def create_source_target_popup(start: Callable[[], None], root: ctk.CTk, map: list) -> None:
def create_source_target_popup(
start: Callable[[], None], root: ctk.CTk, map: list
) -> None:
global POPUP, popup_status_label
POPUP = ctk.CTkToplevel(root)
@ -188,65 +325,109 @@ def create_source_target_popup(start: Callable[[], None], root: ctk.CTk, map: li
else:
update_pop_status("Atleast 1 source with target is required!")
scrollable_frame = ctk.CTkScrollableFrame(POPUP, width=POPUP_SCROLL_WIDTH, height=POPUP_SCROLL_HEIGHT)
scrollable_frame.grid(row=0, column=0, padx=0, pady=0, sticky='nsew')
scrollable_frame = ctk.CTkScrollableFrame(
POPUP, width=POPUP_SCROLL_WIDTH, height=POPUP_SCROLL_HEIGHT
)
scrollable_frame.grid(row=0, column=0, padx=0, pady=0, sticky="nsew")
def on_button_click(map, button_num):
map = update_popup_source(scrollable_frame, map, button_num)
update_popup_source(scrollable_frame, map, button_num)
for item in map:
id = item['id']
id = item["id"]
button = ctk.CTkButton(scrollable_frame, text="Select source image", command=lambda id=id: on_button_click(map, id), width=DEFAULT_BUTTON_WIDTH, height=DEFAULT_BUTTON_HEIGHT)
button = SourceMapperButton(
scrollable_frame,
map,
id,
text="Select source image",
command=lambda id=id: on_button_click(map, id),
width=DEFAULT_BUTTON_WIDTH,
height=DEFAULT_BUTTON_HEIGHT,
)
button.grid(row=id, column=0, padx=50, pady=10)
x_label = ctk.CTkLabel(scrollable_frame, text=f"X", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT)
x_label = ctk.CTkLabel(
scrollable_frame,
text=f"X",
width=MAPPER_PREVIEW_MAX_WIDTH,
height=MAPPER_PREVIEW_MAX_HEIGHT,
)
x_label.grid(row=id, column=2, padx=10, pady=10)
image = Image.fromarray(cv2.cvtColor(item['target']['cv2'], cv2.COLOR_BGR2RGB))
image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS)
image = Image.fromarray(cv2.cvtColor(item["target"]["cv2"], cv2.COLOR_BGR2RGB))
image = image.resize(
(MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
)
tk_image = ctk.CTkImage(image, size=image.size)
target_image = ctk.CTkLabel(scrollable_frame, text=f"T-{id}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT)
target_image = ctk.CTkLabel(
scrollable_frame,
text=f"T-{id}",
width=MAPPER_PREVIEW_MAX_WIDTH,
height=MAPPER_PREVIEW_MAX_HEIGHT,
)
target_image.grid(row=id, column=3, padx=10, pady=10)
target_image.configure(image=tk_image)
popup_status_label = ctk.CTkLabel(POPUP, text=None, justify='center')
popup_status_label = ctk.CTkLabel(POPUP, text=None, justify="center")
popup_status_label.grid(row=1, column=0, pady=15)
close_button = ctk.CTkButton(POPUP, text="Submit", command=lambda: on_submit_click(start))
close_button = ctk.CTkButton(
POPUP, text="Submit", command=lambda: on_submit_click(start)
)
close_button.grid(row=2, column=0, pady=10)
def update_popup_source(scrollable_frame: ctk.CTkScrollableFrame, map: list, button_num: int) -> list:
global source_label_dict
def update_popup_source(
scrollable_frame: ctk.CTkScrollableFrame,
map: list,
button_num: int,
source_path: str = None,
) -> list:
global source_label_dict, RECENT_DIRECTORY_SOURCE
source_path = ctk.filedialog.askopenfilename(title='select an source image', initialdir=RECENT_DIRECTORY_SOURCE, filetypes=[img_ft])
if source_path is None:
source_path = ctk.filedialog.askopenfilename(
title="select an source image",
initialdir=RECENT_DIRECTORY_SOURCE,
filetypes=[img_ft],
)
if "source" in map[button_num]:
map[button_num].pop("source")
source_label_dict[button_num].destroy()
del source_label_dict[button_num]
if source_path == "":
return map
else:
RECENT_DIRECTORY_SOURCE = os.path.dirname(source_path)
cv2_img = cv2.imread(source_path)
face = get_one_face(cv2_img)
if face:
x_min, y_min, x_max, y_max = face['bbox']
x_min, y_min, x_max, y_max = face["bbox"]
map[button_num]['source'] = {
'cv2' : cv2_img[int(y_min):int(y_max), int(x_min):int(x_max)],
'face' : face
}
image = Image.fromarray(cv2.cvtColor(map[button_num]['source']['cv2'], cv2.COLOR_BGR2RGB))
image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS)
map[button_num]["source"] = {
"cv2": cv2_img[int(y_min) : int(y_max), int(x_min) : int(x_max)],
"face": face,
}
image = Image.fromarray(
cv2.cvtColor(map[button_num]["source"]["cv2"], cv2.COLOR_BGR2RGB)
)
image = image.resize(
(MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
)
tk_image = ctk.CTkImage(image, size=image.size)
source_image = ctk.CTkLabel(scrollable_frame, text=f"S-{button_num}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT)
source_image = ctk.CTkLabel(
scrollable_frame,
text=f"S-{button_num}",
width=MAPPER_PREVIEW_MAX_WIDTH,
height=MAPPER_PREVIEW_MAX_HEIGHT,
)
source_image.grid(row=button_num, column=1, padx=10, pady=10)
source_image.configure(image=tk_image)
source_label_dict[button_num] = source_image
@ -260,15 +441,17 @@ def create_preview(parent: ctk.CTkToplevel) -> ctk.CTkToplevel:
preview = ctk.CTkToplevel(parent)
preview.withdraw()
preview.title('Preview')
preview.title("Preview")
preview.configure()
preview.protocol('WM_DELETE_WINDOW', lambda: toggle_preview())
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_label.pack(fill="both", expand=True)
preview_slider = ctk.CTkSlider(preview, from_=0, to=0, command=lambda frame_value: update_preview(frame_value))
preview_slider = ctk.CTkSlider(
preview, from_=0, to=0, command=lambda frame_value: update_preview(frame_value)
)
return preview
@ -277,12 +460,15 @@ def update_status(text: str) -> None:
status_label.configure(text=text)
ROOT.update()
def update_pop_status(text: str) -> None:
popup_status_label.configure(text=text)
def update_pop_live_status(text: str) -> None:
popup_status_label_live.configure(text=text)
def update_tumbler(var: str, value: bool) -> None:
modules.globals.fp_ui[var] = value
@ -291,7 +477,11 @@ 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])
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)
@ -330,7 +520,11 @@ 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])
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)
@ -350,9 +544,21 @@ 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)
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)
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:
@ -362,32 +568,37 @@ def select_output_path(start: Callable[[], None]) -> None:
def check_and_ignore_nsfw(target, destroy: Callable = None) -> bool:
''' Check if the target is NSFW.
"""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
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
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!')
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
else:
return False
def fit_image_to_size(image, width: int, height: int):
if width is None and height is None:
return image
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_w = width / w
ratio = max(ratio_w, ratio_h)
new_size = (int(ratio * w), int(ratio * h))
return cv2.resize(image, dsize=new_size)
@ -400,7 +611,9 @@ def render_image_preview(image_path: str, size: Tuple[int, int]) -> ctk.CTkImage
return ctk.CTkImage(image, size=image.size)
def render_video_preview(video_path: str, size: Tuple[int, int], frame_number: int = 0) -> ctk.CTkImage:
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)
@ -415,7 +628,7 @@ def render_video_preview(video_path: str, size: Tuple[int, int], frame_number: i
def toggle_preview() -> None:
if PREVIEW.state() == 'normal':
if PREVIEW.state() == "normal":
PREVIEW.withdraw()
elif modules.globals.source_path and modules.globals.target_path:
init_preview()
@ -428,28 +641,32 @@ def init_preview() -> None:
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.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...')
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):
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
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 = 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!')
update_status("Processing succeed!")
PREVIEW.deiconify()
def webcam_preview(root: ctk.CTk):
if not modules.globals.map_faces:
if modules.globals.source_path is None:
@ -460,15 +677,24 @@ def webcam_preview(root: ctk.CTk):
modules.globals.souce_target_map = []
create_source_target_popup_for_webcam(root, modules.globals.souce_target_map)
def create_webcam_preview():
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
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_label.configure(
width=PREVIEW_DEFAULT_WIDTH, height=PREVIEW_DEFAULT_HEIGHT
) # Reset the preview image before startup
PREVIEW.deiconify() # Open preview window
@ -481,13 +707,15 @@ def create_webcam_preview():
if not ret:
break
temp_frame = frame.copy() #Create a copy of the frame
temp_frame = frame.copy() # Create a copy of the frame
if modules.globals.live_mirror:
temp_frame = cv2.flip(temp_frame, 1) # horizontal flipping
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())
temp_frame = fit_image_to_size(
temp_frame, PREVIEW.winfo_width(), PREVIEW.winfo_height()
)
if not modules.globals.map_faces:
# Select and save face image only once
@ -495,21 +723,25 @@ def create_webcam_preview():
source_image = get_one_face(cv2.imread(modules.globals.source_path))
for frame_processor in frame_processors:
temp_frame = frame_processor.process_frame(source_image, temp_frame)
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
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 = 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':
if PREVIEW.state() == "withdrawn":
break
camera.release()
@ -537,21 +769,25 @@ 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')
popup_status_label_live = ctk.CTkLabel(POPUP_LIVE, text=None, justify="center")
popup_status_label_live.grid(row=1, column=0, pady=15)
add_button = ctk.CTkButton(POPUP_LIVE, text="Add", command=lambda: on_add_click())
add_button.place(relx=0.2, rely=0.92, relwidth=0.2, relheight=0.05)
close_button = ctk.CTkButton(POPUP_LIVE, text="Submit", command=lambda: on_submit_click())
close_button = ctk.CTkButton(
POPUP_LIVE, text="Submit", command=lambda: on_submit_click()
)
close_button.place(relx=0.6, rely=0.92, relwidth=0.2, relheight=0.05)
def refresh_data(map: list):
global POPUP_LIVE
scrollable_frame = ctk.CTkScrollableFrame(POPUP_LIVE, width=POPUP_LIVE_SCROLL_WIDTH, height=POPUP_LIVE_SCROLL_HEIGHT)
scrollable_frame.grid(row=0, column=0, padx=0, pady=0, sticky='nsew')
scrollable_frame = ctk.CTkScrollableFrame(
POPUP_LIVE, width=POPUP_LIVE_SCROLL_WIDTH, height=POPUP_LIVE_SCROLL_HEIGHT
)
scrollable_frame.grid(row=0, column=0, padx=0, pady=0, sticky="nsew")
def on_sbutton_click(map, button_num):
map = update_webcam_source(scrollable_frame, map, button_num)
@ -560,46 +796,87 @@ def refresh_data(map: list):
map = update_webcam_target(scrollable_frame, map, button_num)
for item in map:
id = item['id']
id = item["id"]
button = ctk.CTkButton(scrollable_frame, text="Select source image", command=lambda id=id: on_sbutton_click(map, id), width=DEFAULT_BUTTON_WIDTH, height=DEFAULT_BUTTON_HEIGHT)
button = ctk.CTkButton(
scrollable_frame,
text="Select source image",
command=lambda id=id: on_sbutton_click(map, id),
width=DEFAULT_BUTTON_WIDTH,
height=DEFAULT_BUTTON_HEIGHT,
)
button.grid(row=id, column=0, padx=30, pady=10)
x_label = ctk.CTkLabel(scrollable_frame, text=f"X", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT)
x_label = ctk.CTkLabel(
scrollable_frame,
text=f"X",
width=MAPPER_PREVIEW_MAX_WIDTH,
height=MAPPER_PREVIEW_MAX_HEIGHT,
)
x_label.grid(row=id, column=2, padx=10, pady=10)
button = ctk.CTkButton(scrollable_frame, text="Select target image", command=lambda id=id: on_tbutton_click(map, id), width=DEFAULT_BUTTON_WIDTH, height=DEFAULT_BUTTON_HEIGHT)
button = ctk.CTkButton(
scrollable_frame,
text="Select target image",
command=lambda id=id: on_tbutton_click(map, id),
width=DEFAULT_BUTTON_WIDTH,
height=DEFAULT_BUTTON_HEIGHT,
)
button.grid(row=id, column=3, padx=20, pady=10)
if "source" in item:
image = Image.fromarray(cv2.cvtColor(item['source']['cv2'], cv2.COLOR_BGR2RGB))
image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS)
image = Image.fromarray(
cv2.cvtColor(item["source"]["cv2"], cv2.COLOR_BGR2RGB)
)
image = image.resize(
(MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
)
tk_image = ctk.CTkImage(image, size=image.size)
source_image = ctk.CTkLabel(scrollable_frame, text=f"S-{id}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT)
source_image = ctk.CTkLabel(
scrollable_frame,
text=f"S-{id}",
width=MAPPER_PREVIEW_MAX_WIDTH,
height=MAPPER_PREVIEW_MAX_HEIGHT,
)
source_image.grid(row=id, column=1, padx=10, pady=10)
source_image.configure(image=tk_image)
if "target" in item:
image = Image.fromarray(cv2.cvtColor(item['target']['cv2'], cv2.COLOR_BGR2RGB))
image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS)
image = Image.fromarray(
cv2.cvtColor(item["target"]["cv2"], cv2.COLOR_BGR2RGB)
)
image = image.resize(
(MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
)
tk_image = ctk.CTkImage(image, size=image.size)
target_image = ctk.CTkLabel(scrollable_frame, text=f"T-{id}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT)
target_image = ctk.CTkLabel(
scrollable_frame,
text=f"T-{id}",
width=MAPPER_PREVIEW_MAX_WIDTH,
height=MAPPER_PREVIEW_MAX_HEIGHT,
)
target_image.grid(row=id, column=4, padx=20, pady=10)
target_image.configure(image=tk_image)
def update_webcam_source(scrollable_frame: ctk.CTkScrollableFrame, map: list, button_num: int) -> list:
def update_webcam_source(
scrollable_frame: ctk.CTkScrollableFrame, map: list, button_num: int
) -> list:
global source_label_dict_live
source_path = ctk.filedialog.askopenfilename(title='select an source image', initialdir=RECENT_DIRECTORY_SOURCE, filetypes=[img_ft])
source_path = ctk.filedialog.askopenfilename(
title="select an source image",
initialdir=RECENT_DIRECTORY_SOURCE,
filetypes=[img_ft],
)
if "source" in map[button_num]:
map[button_num].pop("source")
source_label_dict_live[button_num].destroy()
del source_label_dict_live[button_num]
if source_path == "":
return map
else:
@ -607,35 +884,51 @@ def update_webcam_source(scrollable_frame: ctk.CTkScrollableFrame, map: list, bu
face = get_one_face(cv2_img)
if face:
x_min, y_min, x_max, y_max = face['bbox']
x_min, y_min, x_max, y_max = face["bbox"]
map[button_num]['source'] = {
'cv2' : cv2_img[int(y_min):int(y_max), int(x_min):int(x_max)],
'face' : face
}
image = Image.fromarray(cv2.cvtColor(map[button_num]['source']['cv2'], cv2.COLOR_BGR2RGB))
image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS)
map[button_num]["source"] = {
"cv2": cv2_img[int(y_min) : int(y_max), int(x_min) : int(x_max)],
"face": face,
}
image = Image.fromarray(
cv2.cvtColor(map[button_num]["source"]["cv2"], cv2.COLOR_BGR2RGB)
)
image = image.resize(
(MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
)
tk_image = ctk.CTkImage(image, size=image.size)
source_image = ctk.CTkLabel(scrollable_frame, text=f"S-{button_num}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT)
source_image = ctk.CTkLabel(
scrollable_frame,
text=f"S-{button_num}",
width=MAPPER_PREVIEW_MAX_WIDTH,
height=MAPPER_PREVIEW_MAX_HEIGHT,
)
source_image.grid(row=button_num, column=1, padx=10, pady=10)
source_image.configure(image=tk_image)
source_label_dict_live[button_num] = source_image
else:
update_pop_live_status("Face could not be detected in last upload!")
return map
def update_webcam_target(scrollable_frame: ctk.CTkScrollableFrame, map: list, button_num: int) -> list:
def update_webcam_target(
scrollable_frame: ctk.CTkScrollableFrame, map: list, button_num: int
) -> list:
global target_label_dict_live
target_path = ctk.filedialog.askopenfilename(title='select an target image', initialdir=RECENT_DIRECTORY_SOURCE, filetypes=[img_ft])
target_path = ctk.filedialog.askopenfilename(
title="select an target image",
initialdir=RECENT_DIRECTORY_SOURCE,
filetypes=[img_ft],
)
if "target" in map[button_num]:
map[button_num].pop("target")
target_label_dict_live[button_num].destroy()
del target_label_dict_live[button_num]
if target_path == "":
return map
else:
@ -643,22 +936,30 @@ def update_webcam_target(scrollable_frame: ctk.CTkScrollableFrame, map: list, bu
face = get_one_face(cv2_img)
if face:
x_min, y_min, x_max, y_max = face['bbox']
x_min, y_min, x_max, y_max = face["bbox"]
map[button_num]['target'] = {
'cv2' : cv2_img[int(y_min):int(y_max), int(x_min):int(x_max)],
'face' : face
}
image = Image.fromarray(cv2.cvtColor(map[button_num]['target']['cv2'], cv2.COLOR_BGR2RGB))
image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS)
map[button_num]["target"] = {
"cv2": cv2_img[int(y_min) : int(y_max), int(x_min) : int(x_max)],
"face": face,
}
image = Image.fromarray(
cv2.cvtColor(map[button_num]["target"]["cv2"], cv2.COLOR_BGR2RGB)
)
image = image.resize(
(MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
)
tk_image = ctk.CTkImage(image, size=image.size)
target_image = ctk.CTkLabel(scrollable_frame, text=f"T-{button_num}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT)
target_image = ctk.CTkLabel(
scrollable_frame,
text=f"T-{button_num}",
width=MAPPER_PREVIEW_MAX_WIDTH,
height=MAPPER_PREVIEW_MAX_HEIGHT,
)
target_image.grid(row=button_num, column=4, padx=20, pady=10)
target_image.configure(image=tk_image)
target_label_dict_live[button_num] = target_image
else:
update_pop_live_status("Face could not be detected in last upload!")
return map