diaojiaolou
/
Deep-Live-Cam
mirror of https://github.com/hacksider/Deep-Live-Cam.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update some instruction

pull/6/head
Kenneth Estanislao 2023-09-24 21:59:24 +08:00
parent 2b2aa74644
commit 2293c54523
5 changed files with 11 additions and 307 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
README.md
View File

@ -1,9 +1,3 @@
Take a video and replace the face in it with a face of your choice. You only need one image of the desired face. No dataset, no training.
You can watch some demos [here](https://drive.google.com/drive/folders/1KHv8n_rd3Lcr2v7jBq1yPSTWM554Gq8e?usp=sharing). A StableDiffusion extension is also available, [here](https://github.com/s0md3v/sd-webui-roop).
![demo-gif](demo.gif) ![demo-gif](demo.gif)
## Disclaimer ## Disclaimer
@ -15,29 +9,22 @@ Users of this software are expected to use this software responsibly while abidi
## How do I install it? ## How do I install it?
### Single command install
For windows, [download this file](https://github.com/hacksider/roop-cam/files/12358726/1_click_install.zip), extract to a folder without space, then run (double click)
```
windows_run.bat
```
Then proceed to the folder of roop-cam and just double click
```
run-cuda-windows.bat
```
### Basic: It is more likely to work on your computer but it will also be very slow. You can follow instructions for the basic install (This usually runs via **CPU**) ### Basic: It is more likely to work on your computer but it will also be very slow. You can follow instructions for the basic install (This usually runs via **CPU**)
#### 1.Setup your platform #### 1.Setup your platform
- python (3.10 recommended) - python (3.10 recommended)
- pip - pip
- git - git
- ffmpeg - [ffmpeg](https://www.youtube.com/watch?v=OlNWCpFdVMA)
- visual studio 2022 runtimes (windows) - [visual studio 2022 runtimes (windows)](https://learn.microsoft.com/en-us/visualstudio/releases/2022/redistribution#vs2022-download)
#### 2. Clone Repository #### 2. Clone Repository
https://github.com/hacksider/roop-cam.git https://github.com/hacksider/Deep-Live-Cam.git
#### 3. Install dependency #### 3. Download Models
[GFPGANv1.4](https://huggingface.co/hacksider/deep-live-cam/resolve/main/GFPGANv1.4.pth)
[inswapper_128.onnx](https://huggingface.co/hacksider/deep-live-cam/resolve/main/inswapper_128.onnx)
#### 4. Install dependency
We highly recommend to work with a `venv` to avoid issues. We highly recommend to work with a `venv` to avoid issues.
``` ```
pip install -r requirements.txt pip install -r requirements.txt
@ -146,7 +133,7 @@ Just follow the clicks on the screenshot
2. Click live 2. Click live
3. Wait for a few second (it takes a longer time, usually 10 to 30 seconds before the preview shows up) 3. Wait for a few second (it takes a longer time, usually 10 to 30 seconds before the preview shows up)
![roop-cam](roop-cam.gif) ![demo-gif](demo.gif)
Just use your favorite screencapture to stream like OBS Just use your favorite screencapture to stream like OBS
> Note: In case you want to change your face, just select another picture, the preview mode will then restart (so just wait a bit). > Note: In case you want to change your face, just select another picture, the preview mode will then restart (so just wait a bit).

BIN
demo.gif
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 6.2 MiB

After

Width:  |  Height:  |  Size: 1.1 MiB

283
modules/ui (2).py
View File

@ -1,283 +0,0 @@
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='Send some love!', 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://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=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, 1280) # Set the width of the resolution
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 720) # Set the height of the resolution
cap.set(cv2.CAP_PROP_FPS, 60) # Set the frame rate of the webcam
PREVIEW_MAX_HEIGHT = 720
PREVIEW_MAX_WIDTH = 1280
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

4
modules/ui.py
View File

@ -107,10 +107,10 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
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) status_label.place(relx=0.1, rely=0.9, relwidth=0.8)
donate_label = ctk.CTkLabel(root, text='Gourieff GitHub', 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.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.configure(text_color=ctk.ThemeManager.theme.get('URL').get('text_color'))
donate_label.bind('<Button>', lambda event: webbrowser.open('https://github.com/Gourieff')) donate_label.bind('<Button>', lambda event: webbrowser.open('https://paypal.me/hacksider'))
return root return root

BIN
roop-cam.gif
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 1.1 MiB