Compare commits

..

2 Commits

Author SHA1 Message Date
KRSHH b6d6cfa2ee
Update face_swapper.py 2024-10-03 18:33:57 +05:30
KRSHH 91d9f8a536
Update ui.py 2024-10-03 18:33:20 +05:30
4 changed files with 153 additions and 93 deletions

View File

@ -371,11 +371,11 @@ For the latest experimental builds and features, see the [experimental branch](h
**TODO:**
- [x] Support multiple faces
- [ ] Develop a version for web app/service
- [ ] UI/UX enhancements for desktop app
- [ ] Speed up model loading
- [ ] Speed up real-time face swapping
- [x] Support multiple faces
- [x] UI/UX enhancements for desktop app
This is an open-source project developed in our free time. Updates may be delayed.

View File

@ -8,29 +8,41 @@ 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.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 +52,28 @@ 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.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_face = get_face_swapper().get(
temp_frame, target_face, source_face, paste_back=True
)
# Apply opacity after swapping
opacity = modules.globals.face_opacity / 100
return cv2.addWeighted(swapped_face, opacity, temp_frame, 1 - opacity, 0)
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 +91,42 @@ 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 +138,46 @@ 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 +211,9 @@ 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 +221,9 @@ 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
)

View File

@ -3,7 +3,6 @@ import webbrowser
import customtkinter as ctk
from typing import Callable, Tuple
import cv2
from cv2_enumerate_cameras import enumerate_cameras
from PIL import Image, ImageOps
import tkinterdnd2 as tkdnd
import time
@ -404,33 +403,11 @@ def create_root(
)
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())
],
),
command=lambda: webcam_preview(root),
)
live_button.pack(side="left", padx=10, expand=True)
@ -478,6 +455,29 @@ def create_root(
)
remove_donate_button.pack(side="right", padx=(10, 0))
# Add opacity slider
opacity_frame = ctk.CTkFrame(options_column, fg_color="#2a2d2e")
opacity_frame.pack(pady=5, anchor="w", fill="x")
opacity_label = ctk.CTkLabel(
opacity_frame, text="Face Opacity:", font=("Roboto", 14, "bold")
)
opacity_label.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)
main_frame.grid_columnconfigure((0, 2), weight=1)
main_frame.grid_rowconfigure((0, 1, 2), weight=1)
@ -706,6 +706,29 @@ def create_preview(parent: ctk.CTkToplevel) -> ctk.CTkToplevel:
)
preview_slider.pack(fill="x", padx=20, pady=10)
last_update_time = 0
debounce_delay = 0.1 # Adjust this delay as needed (in seconds)
def on_key_press(event):
nonlocal last_update_time
current_time = time.time()
if current_time - last_update_time > debounce_delay:
current_frame = int(preview_slider.get())
if event.keysym == "Left":
new_frame = max(0, current_frame - 1)
elif event.keysym == "Right":
new_frame = min(int(preview_slider.cget("to")), current_frame + 1)
else:
return # Ignore other key presses
preview_slider.set(new_frame)
update_preview(new_frame)
last_update_time = current_time
preview.bind("<Left>", on_key_press)
preview.bind("<Right>", on_key_press)
return preview
@ -903,6 +926,11 @@ def init_preview() -> None:
preview_slider.configure(to=video_frame_total)
preview_slider.pack(fill="x")
preview_slider.set(0)
# Disable slider if it's an image
if is_image(modules.globals.target_path):
preview_slider.configure(state="disabled")
else:
preview_slider.configure(state="normal")
def update_preview(frame_number: int = 0) -> None:
@ -955,44 +983,26 @@ def update_preview(frame_number: int = 0) -> None:
PREVIEW.deiconify()
def webcam_preview(root: ctk.CTk, camera_index: int):
def webcam_preview(root: ctk.CTk):
if not modules.globals.map_faces:
if modules.globals.source_path is None:
# No image selected
return
create_webcam_preview(camera_index)
create_webcam_preview()
else:
modules.globals.souce_target_map = []
create_source_target_popup_for_webcam(root, modules.globals.souce_target_map)
def get_available_cameras():
"""Returns a list of available camera names and indices."""
camera_indices = []
camera_names = []
for camera in enumerate_cameras():
cap = cv2.VideoCapture(camera.index)
if cap.isOpened():
camera_indices.append(camera.index)
camera_names.append(camera.name)
cap.release()
return (camera_indices, camera_names)
# Add this function to update the opacity value
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():
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 = cv2.VideoCapture(0)
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)
@ -1030,15 +1040,10 @@ def create_webcam_preview(camera_index):
if not ret:
break
temp_frame = frame.copy() # Create a copy of the frame
temp_frame = frame.copy()
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()
)
temp_frame = cv2.flip(temp_frame, 1)
if not modules.globals.map_faces:
if source_image is None and modules.globals.source_path:
@ -1046,18 +1051,19 @@ def create_webcam_preview(camera_index):
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
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
image,
(preview_frame.winfo_width(), preview_frame.winfo_height()),
Image.LANCZOS,
)
image = ctk.CTkImage(image, size=image.size)
preview_label.configure(image=image)
@ -1067,7 +1073,7 @@ def create_webcam_preview(camera_index):
break
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:

View File

@ -2,7 +2,6 @@
numpy>=1.23.5,<2
opencv-python==4.8.1.78
cv2_enumerate_cameras==1.1.15
onnx==1.16.0
insightface==0.7.3
psutil==5.9.8