Revert "Slight Performance Improvement"

This reverts commit 9a472e2435.
Revert "Update ui.py"
2024-11-07 14:58:03 +05:30 · 2024-11-07 14:57:47 +05:30 · 2024-10-29 14:53:19 +05:30 · 2024-10-29 14:07:47 +05:30 · 2024-10-28 16:53:55 +05:30 · 2024-10-28 13:50:44 +05:30
36 changed files with 1913 additions and 1237 deletions
@@ -1,26 +1,38 @@
-***[Remove this]The issue would be closed without notice and be considered spam if the template is not followed.***
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---

 **Describe the bug**
 A clear and concise description of what the bug is.

+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
 **Screenshots**
 If applicable, add screenshots to help explain your problem.

-**Error Message**
-
-`<The error message in terminal>`
-
 **Desktop (please complete the following information):**
- - OS: [e.g. Windows]
+ - OS: [e.g. iOS]
+ - Browser [e.g. chrome, safari]
+ - Version [e.g. 22]
+
+**Smartphone (please complete the following information):**
+ - Device: [e.g. iPhone6]
+ - OS: [e.g. iOS8.1]
+ - Browser [e.g. stock browser, safari]
 - Version [e.g. 22]
- - GPU
- - CPU

 **Additional context**
 Add any other context about the problem here.
-
-**Confirmation (Mandatory)**
- [ ] I have followed the template
- [ ] This is not a query about how to increase performance
- [ ] I have checked the issues page, and this is not a duplicate
-
@@ -24,4 +24,3 @@ models/GFPGANv1.4.pth
 models/DMDNet.pth
 faceswap/
 .vscode/
-switch_states.json
@@ -1,38 +1 @@
-# Collaboration Guidelines and Codebase Quality Standards
-
-To ensure smooth collaboration and maintain the high quality of our codebase, please adhere to the following guidelines:
-
-## Branching Strategy
-
-*   **`premain`**:
-    *   Always push your changes to the `premain` branch initially.
-    *   This safeguards the `main` branch from unintentional disruptions.
-    *   All tests will be performed on the `premain` branch.
-    *   Changes will only be merged into `main` after several hours or days of rigorous testing.
-*   **`experimental`**:
-    *   For large or potentially disruptive changes, use the `experimental` branch.
-    *   This allows for thorough discussion and review before considering a merge into `main`.
-
-## Pre-Pull Request Checklist
-
-Before creating a Pull Request (PR), ensure you have completed the following tests:
-
-### Functionality
-
-*   **Realtime Faceswap**:
-    *   Test with face enhancer **enabled** and **disabled**.
-*   **Map Faces**:
-    *   Test with both options (**enabled** and **disabled**).
-*   **Camera Listing**:
-    *   Verify that all cameras are listed accurately.
-
-### Stability
-
-*   **Realtime FPS**:
-    *   Confirm that there is no drop in real-time frames per second (FPS).
-*   **Boot Time**:
-    *   Changes should not negatively impact the boot time of either the application or the real-time faceswap feature.
-*   **GPU Overloading**:
-    *   Test for a minimum of 15 minutes to guarantee no GPU overloading, which could lead to crashes.
-*   **App Performance**:
-    *   The application should remain responsive and not exhibit any lag.
+Please always push on the experimental to ensure we don't mess with the main branch. All the test will be done on the experimental and will be pushed to the main branch after few days of testing.
@@ -5,120 +5,49 @@
 </p>

 <p align="center">
-<a href="https://trendshift.io/repositories/11395" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11395" alt="hacksider%2FDeep-Live-Cam | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+  <img src="media/demo.gif" alt="Demo GIF">
+  <img src="media/avgpcperformancedemo.gif" alt="Performance Demo GIF">
 </p>

-<p align="center">
-  <img src="media/demo.gif" alt="Demo GIF" width="800">
-</p>
+## Disclaimer

-##  Disclaimer
+This software is intended as a productive contribution to the AI-generated media industry. It aims to assist artists with tasks like animating custom characters or using them as models for clothing, etc.

-This deepfake software is designed to be a productive tool for the AI-generated media industry. It can assist artists in animating custom characters, creating engaging content, and even using models for clothing design.
-
-We are aware of the potential for unethical applications and are committed to preventative measures. A built-in check prevents the program from processing inappropriate media (nudity, graphic content, sensitive material like war footage, etc.). We will continue to develop this project responsibly, adhering to the law and ethics. We may shut down the project or add watermarks if legally required.
-
- Ethical Use: Users are expected to use this software responsibly and legally. If using a real person's face, obtain their consent and clearly label any output as a deepfake when sharing online.
-
- Content Restrictions: The software includes built-in checks to prevent processing inappropriate media, such as nudity, graphic content, or sensitive material.
-
- Legal Compliance: We adhere to all relevant laws and ethical guidelines. If legally required, we may shut down the project or add watermarks to the output.
-
- User Responsibility: We are not responsible for end-user actions. Users must ensure their use of the software aligns with ethical standards and legal requirements.
-
-By using this software, you agree to these terms and commit to using it in a manner that respects the rights and dignity of others.
+We are aware of the potential for unethical applications and are committed to preventative measures. A built-in check prevents the program from processing inappropriate media (nudity, graphic content, sensitive material like war footage, etc.). We will continue to develop this project responsibly, adhering to law and ethics. We may shut down the project or add watermarks if legally required.

 Users are expected to use this software responsibly and legally. If using a real person's face, obtain their consent and clearly label any output as a deepfake when sharing online. We are not responsible for end-user actions.


-## TLDR; Live Deepfake in just 3 Clicks
-![easysteps](https://github.com/user-attachments/assets/af825228-852c-411b-b787-ffd9aac72fc6)
-1. Select a face
-2. Select which camera to use
-3. Press live!
+## Quick Start (Windows / Nvidia)

-## Features & Uses - Everything is in real-time
+[![Download](media/download.png)](https://hacksider.gumroad.com/l/vccdmm) 

-### Mouth Mask
-
-**Retain your original mouth for accurate movement using Mouth Mask**
-
-<p align="center">
-  <img src="media/ludwig.gif" alt="resizable-gif">
-</p>
-
-### Face Mapping
-
-**Use different faces on multiple subjects simultaneously**
-
-<p align="center">
-  <img src="media/streamers.gif" alt="face_mapping_source">
-</p>
-
-### Your Movie, Your Face
-
-**Watch movies with any face in real-time**
-
-<p align="center">
-  <img src="media/movie.gif" alt="movie">
-</p>
-
-### Live Show
-
-**Run Live shows and performances**
-
-<p align="center">
-  <img src="media/live_show.gif" alt="show">
-</p>
-
-### Memes
-
-**Create Your Most Viral Meme Yet**
-
-<p align="center">
-  <img src="media/meme.gif" alt="show" width="450"> 
-  <br>
-  <sub>Created using Many Faces feature in Deep-Live-Cam</sub>
-</p>
-
-### Omegle
-
-**Surprise people on Omegle**
-
-<p align="center">
-  <video src="https://github.com/user-attachments/assets/2e9b9b82-fa04-4b70-9f56-b1f68e7672d0" width="450" controls></video>
-</p>
+[Download latest pre-built version with CUDA support](https://hacksider.gumroad.com/l/vccdmm) - No Manual Installation/Downloading required.

 ## Installation (Manual)
-
-**Please be aware that the installation requires technical skills and is not for beginners. Consider downloading the prebuilt version.**
-
-<details>
-<summary>Click to see the process</summary>
-
-### Installation
+**Please be aware that the installation needs technical skills and is NOT for beginners, consider downloading the prebuilt. Please do NOT open platform and installation related issues on GitHub before discussing it on the discord server.**
+### Basic Installation (CPU)

 This is more likely to work on your computer but will be slower as it utilizes the CPU.

-**1. Set up Your Platform**
+**1. Setup Your Platform**

-   Python (3.10 recommended)
-   pip
-   git
-   [ffmpeg](https://www.youtube.com/watch?v=OlNWCpFdVMA) - ```iex (irm ffmpeg.tc.ht)```
-   [Visual Studio 2022 Runtimes (Windows)](https://visualstudio.microsoft.com/visual-cpp-build-tools/)
+- Python (3.10 recommended)
+- pip
+- git
+- [ffmpeg](https://www.youtube.com/watch?v=OlNWCpFdVMA) 
+- [Visual Studio 2022 Runtimes (Windows)](https://visualstudio.microsoft.com/visual-cpp-build-tools/)

-**2. Clone the Repository**
+**2. Clone Repository**

 ```bash
-git clone https://github.com/hacksider/Deep-Live-Cam.git
-cd Deep-Live-Cam
+https://github.com/hacksider/Deep-Live-Cam.git
 ```

-**3. Download the Models**
+**3. Download Models**

 1. [GFPGANv1.4](https://huggingface.co/hacksider/deep-live-cam/resolve/main/GFPGANv1.4.pth)
-2. [inswapper\_128\_fp16.onnx](https://huggingface.co/hacksider/deep-live-cam/resolve/main/inswapper_128_fp16.onnx)
+2. [inswapper_128_fp16.onnx](https://huggingface.co/hacksider/deep-live-cam/resolve/main/inswapper_128.onnx) (Note: Use this [replacement version](https://github.com/facefusion/facefusion-assets/releases/download/models/inswapper_128.onnx) if you encounter issues)

 Place these files in the "**models**" folder.

@@ -126,112 +55,57 @@ Place these files in the "**models**" folder.

 We highly recommend using a `venv` to avoid issues.

-For Windows:
 ```bash
-python -m venv venv
-venv\Scripts\activate
 pip install -r requirements.txt
 ```

-**For macOS:**
-
-Apple Silicon (M1/M2/M3) requires specific setup:
+**For macOS:** Install or upgrade the `python-tk` package:

 ```bash
-# Install Python 3.10 (specific version is important)
-brew install python@3.10
-
-# Install tkinter package (required for the GUI)
 brew install python-tk@3.10
-
-# Create and activate virtual environment with Python 3.10
-python3.10 -m venv venv
-source venv/bin/activate
-
-# Install dependencies
-pip install -r requirements.txt
-```
-
-** In case something goes wrong and you need to reinstall the virtual environment **
-
-```bash
-# Deactivate the virtual environment
-rm -rf venv
-
-# Reinstall the virtual environment
-python -m venv venv
-source venv/bin/activate
-
-# install the dependencies again
-pip install -r requirements.txt
 ```

 **Run:** If you don't have a GPU, you can run Deep-Live-Cam using `python run.py`. Note that initial execution will download models (~300MB).

-### GPU Acceleration
+
+### GPU Acceleration (Optional)
+
+<details>
+<summary>Click to see the details</summary>

 **CUDA Execution Provider (Nvidia)**

-1. Install [CUDA Toolkit 11.8.0](https://developer.nvidia.com/cuda-11-8-0-download-archive)
+1. Install [CUDA Toolkit 11.8](https://developer.nvidia.com/cuda-11-8-0-download-archive)
 2. Install dependencies:
-
 ```bash
 pip uninstall onnxruntime onnxruntime-gpu
 pip install onnxruntime-gpu==1.16.3
 ```
-
 3. Usage:
-
 ```bash
 python run.py --execution-provider cuda
 ```

 **CoreML Execution Provider (Apple Silicon)**

-Apple Silicon (M1/M2/M3) specific installation:
-
-1. Make sure you've completed the macOS setup above using Python 3.10.
-2. Install dependencies:
-
+1. Install dependencies:
 ```bash
 pip uninstall onnxruntime onnxruntime-silicon
 pip install onnxruntime-silicon==1.13.1
 ```
-
-3. Usage (important: specify Python 3.10):
-
+2. Usage:
 ```bash
-python3.10 run.py --execution-provider coreml
+python run.py --execution-provider coreml
 ```

-**Important Notes for macOS:**
- You **must** use Python 3.10, not newer versions like 3.11 or 3.13
- Always run with `python3.10` command not just `python` if you have multiple Python versions installed
- If you get error about `_tkinter` missing, reinstall the tkinter package: `brew reinstall python-tk@3.10`
- If you get model loading errors, check that your models are in the correct folder
- If you encounter conflicts with other Python versions, consider uninstalling them:
-  ```bash
-  # List all installed Python versions
-  brew list | grep python
-  
-  # Uninstall conflicting versions if needed
-  brew uninstall --ignore-dependencies python@3.11 python@3.13
-  
-  # Keep only Python 3.10
-  brew cleanup
-  ```
-
 **CoreML Execution Provider (Apple Legacy)**

 1. Install dependencies:
-
 ```bash
 pip uninstall onnxruntime onnxruntime-coreml
 pip install onnxruntime-coreml==1.13.1
 ```
-
 2. Usage:
-
 ```bash
 python run.py --execution-provider coreml
 ```
@@ -239,14 +113,11 @@ python run.py --execution-provider coreml
 **DirectML Execution Provider (Windows)**

 1. Install dependencies:
-
 ```bash
 pip uninstall onnxruntime onnxruntime-directml
 pip install onnxruntime-directml==1.15.1
 ```
-
 2. Usage:
-
 ```bash
 python run.py --execution-provider directml
 ```
@@ -254,51 +125,75 @@ python run.py --execution-provider directml
 **OpenVINO™ Execution Provider (Intel)**

 1. Install dependencies:
-
 ```bash
 pip uninstall onnxruntime onnxruntime-openvino
 pip install onnxruntime-openvino==1.15.0
 ```
-
 2. Usage:
-
 ```bash
 python run.py --execution-provider openvino
 ```
+
 </details>

+
 ## Usage

 **1. Image/Video Mode**

-   Execute `python run.py`.
-   Choose a source face image and a target image/video.
-   Click "Start".
-   The output will be saved in a directory named after the target video.
+- Execute `python run.py`. 
+- Choose a source face image and a target image/video.
+- Click "Start".
+- The output will be saved in a directory named after the target video.

 **2. Webcam Mode**

-   Execute `python run.py`.
-   Select a source face image.
-   Click "Live".
-   Wait for the preview to appear (10-30 seconds).
-   Use a screen capture tool like OBS to stream.
-   To change the face, select a new source image.
+- Execute `python run.py`.
+- Select a source face image.
+- Click "Live".
+- Wait for the preview to appear (10-30 seconds).
+- Use a screen capture tool like OBS to stream.
+- To change the face, select a new source image.

-## Tips and Tricks
+![demo-gif](media/demo.gif)

-Check out these helpful guides to get the most out of Deep-Live-Cam:
+## Features

- [Unlocking the Secrets to the Perfect Deepfake Image](https://deeplivecam.net/index.php/blog/tips-and-tricks/unlocking-the-secrets-to-the-perfect-deepfake-image) - Learn how to create the best deepfake with full head coverage
- [Video Call with DeepLiveCam](https://deeplivecam.net/index.php/blog/tips-and-tricks/video-call-with-deeplivecam) - Make your meetings livelier by using DeepLiveCam with OBS and meeting software
- [Have a Special Guest!](https://deeplivecam.net/index.php/blog/tips-and-tricks/have-a-special-guest) - Tutorial on how to use face mapping to add special guests to your stream
- [Watch Deepfake Movies in Realtime](https://deeplivecam.net/index.php/blog/tips-and-tricks/watch-deepfake-movies-in-realtime) - See yourself star in any video without processing the video
- [Better Quality without Sacrificing Speed](https://deeplivecam.net/index.php/blog/tips-and-tricks/better-quality-without-sacrificing-speed) - Tips for achieving better results without impacting performance
- [Instant Vtuber!](https://deeplivecam.net/index.php/blog/tips-and-tricks/instant-vtuber) - Create a new persona/vtuber easily using Metahuman Creator
+### Resizable Preview Window

-Visit our [official blog](https://deeplivecam.net/index.php/blog/tips-and-tricks) for more tips and tutorials.
+Dynamically improve performance using the `--live-resizable` parameter.

-## Command Line Arguments (Unmaintained)
+![resizable-gif](media/resizable.gif)
+
+### Face Mapping
+
+Track and change faces on the fly.
+
+![face_mapping_source](media/face_mapping_source.gif)
+
+**Source Video:**
+
+![face-mapping](media/face_mapping.png)
+
+**Enable Face Mapping:**
+
+![face-mapping2](media/face_mapping2.png)
+
+**Map the Faces:**
+
+![face_mapping_result](media/face_mapping_result.gif)
+
+**See the Magic!**
+
+![movie](media/movie.gif)
+
+**Watch movies in realtime:**
+
+It's as simple as opening a movie on the screen, and selecting OBS as your camera!
+![image](media/movie_img.png)
+
+
+## Command Line Arguments

 ```
 options:
@@ -312,7 +207,7 @@ options:
  --keep-frames                                            keep temporary frames
  --many-faces                                             process every face
  --map-faces                                              map source target faces
-  --mouth-mask                                             mask the mouth region
+  --nsfw-filter                                            filter the NSFW image or video
  --video-encoder {libx264,libx265,libvpx-vp9}             adjust output video encoder
  --video-quality [0-51]                                   adjust output video quality
  --live-mirror                                            the live camera display as you see it in the front-facing camera frame
@@ -325,44 +220,188 @@ options:

 Looking for a CLI mode? Using the -s/--source argument will make the run program in cli mode.

-## Press

-**We are always open to criticism and are ready to improve, that's why we didn't cherry-pick anything.**
+## Webcam Mode on WSL2 Ubuntu (Optional)
+
+<details>
+<summary>Click to see the details</summary>
+
+If you want to use WSL2 on Windows 11 you will notice, that Ubuntu WSL2 doesn't come with USB-Webcam support in the Kernel. You need to do two things: Compile the Kernel with the right modules integrated and forward your USB Webcam from Windows to Ubuntu with the usbipd app. Here are detailed Steps:
+
+This tutorial will guide you through the process of setting up WSL2 Ubuntu with USB webcam support, rebuilding the kernel, and preparing the environment for the Deep-Live-Cam project.  
+  
+**1. Install WSL2 Ubuntu**  
+  
+Install WSL2 Ubuntu from the Microsoft Store or using PowerShell:  
+  
+**2. Enable USB Support in WSL2**  
+  
+1. Install the USB/IP tool for Windows:  
+[https://learn.microsoft.com/en-us/windows/wsl/connect-usb](https://learn.microsoft.com/en-us/windows/wsl/connect-usb)  
+  
+2. In Windows PowerShell (as Administrator), connect your webcam to WSL:  
+  
+```powershell  
+usbipd list  
+usbipd bind --busid x-x # Replace x-x with your webcam's bus ID  
+usbipd attach --wsl --busid x-x # Replace x-x with your webcam's bus ID  
+```  
+ You need to redo the above every time you reboot wsl or re-connect your webcam/usb device.
+ 
+**3. Rebuild WSL2 Ubuntu Kernel with USB and Webcam Modules**  
+  
+Follow these steps to rebuild the kernel:  
+  
+1. Start with this guide: [https://github.com/PINTO0309/wsl2_linux_kernel_usbcam_enable_conf](https://github.com/PINTO0309/wsl2_linux_kernel_usbcam_enable_conf)  
+  
+2. When you reach the `sudo wget [github.com](http://github.com/)...PINTO0309` step, which won't work for newer kernel versions, follow this video instead or alternatively follow the video tutorial from the beginning: 
+[https://www.youtube.com/watch?v=t_YnACEPmrM](https://www.youtube.com/watch?v=t_YnACEPmrM)  
+  
+Additional info: [https://askubuntu.com/questions/1413377/camera-not-working-in-cheese-in-wsl2](https://askubuntu.com/questions/1413377/camera-not-working-in-cheese-in-wsl2)  
+  
+3. After rebuilding, restart WSL with the new kernel. 
+  
+**4. Set Up Deep-Live-Cam Project**  
+ Within Ubuntu:
+1. Clone the repository:  
+  
+```bash  
+git clone [https://github.com/hacksider/Deep-Live-Cam](https://github.com/hacksider/Deep-Live-Cam)  
+```  
+  
+2. Follow the installation instructions in the repository, including cuda toolkit 11.8, make 100% sure it's not cuda toolkit 12.x.  
+   
+**5. Verify and Load Kernel Modules**  
+  
+1. Check if USB and webcam modules are built into the kernel:  
+  
+```bash  
+zcat /proc/config.gz | grep -i "CONFIG_USB_VIDEO_CLASS"  
+```  
+  
+2. If modules are loadable (m), not built-in (y), check if the file exists:  
+  
+```bash  
+ls /lib/modules/$(uname -r)/kernel/drivers/media/usb/uvc/  
+```  
+  
+3. Load the module and check for errors (optional if built-in):  
+  
+```bash  
+sudo modprobe uvcvideo  
+dmesg | tail  
+```  
+  
+4. Verify video devices:  
+  
+```bash  
+sudo ls -al /dev/video*  
+```  
+  
+**6. Set Up Permissions**  
+  
+1. Add user to video group and set permissions:  
+  
+```bash  
+sudo usermod -a -G video $USER  
+sudo chgrp video /dev/video0 /dev/video1  
+sudo chmod 660 /dev/video0 /dev/video1  
+```  
+  
+2. Create a udev rule for permanent permissions:  
+  
+```bash  
+sudo nano /etc/udev/rules.d/81-webcam.rules  
+```  
+  
+Add this content:  
+  
+```  
+KERNEL=="video[0-9]*", GROUP="video", MODE="0660"  
+```  
+  
+3. Reload udev rules:  
+  
+```bash  
+sudo udevadm control --reload-rules && sudo udevadm trigger  
+```  
+  
+4. Log out and log back into your WSL session.  
+  
+5. Start Deep-Live-Cam with `python run.py --execution-provider cuda --max-memory 8` where 8 can be changed to the number of GB VRAM of your GPU has, minus 1-2GB. If you have a RTX3080 with 10GB I suggest adding 8GB. Leave some left for Windows.
+
+**Final Notes**  
+  
+- Steps 6 and 7 may be optional if the modules are built into the kernel and permissions are already set correctly.  
+- Always ensure you're using compatible versions of CUDA, ONNX, and other dependencies.  
+- If issues persist, consider checking the Deep-Live-Cam project's specific requirements and troubleshooting steps.  
+  
+By following these steps, you should have a WSL2 Ubuntu environment with USB webcam support ready for the Deep-Live-Cam project. If you encounter any issues, refer back to the specific error messages and troubleshooting steps provided.
+
+**Troubleshooting CUDA Issues** 
+
+If you encounter this error:  
+  
+```  
+[ONNXRuntimeError] : 1 : FAIL : Failed to load library [libonnxruntime_providers_cuda.so](http://libonnxruntime_providers_cuda.so/) with error: libcufft.so.10: cannot open shared object file: No such file or directory  
+```  
+  
+Follow these steps:  
+  
+1. Install CUDA Toolkit 11.8 (ONNX 1.16.3 requires CUDA 11.x, not 12.x):  
+[https://developer.nvidia.com/cuda-11-8-0-download-archive](https://developer.nvidia.com/cuda-11-8-0-download-archive)  
+  select: Linux, x86_64, WSL-Ubuntu, 2.0, deb (local)
+2. Check CUDA version:  
+  
+```bash  
+/usr/local/cuda/bin/nvcc --version  
+```  
+  
+3. If the wrong version is installed, remove it completely:  
+[https://askubuntu.com/questions/530043/removing-nvidia-cuda-toolkit-and-installing-new-one](https://askubuntu.com/questions/530043/removing-nvidia-cuda-toolkit-and-installing-new-one)  
+  
+4. Install CUDA Toolkit 11.8 again [https://developer.nvidia.com/cuda-11-8-0-download-archive](https://developer.nvidia.com/cuda-11-8-0-download-archive), select: Linux, x86_64, WSL-Ubuntu, 2.0, deb (local)
+  
+```bash  
+sudo apt-get -y install cuda-toolkit-11-8  
+```
+</details>
+
+
+## Future Updates & Roadmap
+
+For the latest experimental builds and features, see the [experimental branch](https://github.com/hacksider/Deep-Live-Cam/tree/experimental).
+
+**TODO:**
+
+- [ ] Develop a version for web app/service
+- [ ] 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.
+
+**Tips and Links:**
+- [How to make the most of Deep-Live-Cam](https://hacksider.gumroad.com/p/how-to-make-the-most-on-deep-live-cam)
+- Face enhancer is good, but still very slow for any live streaming purpose.

- - [*"Deep-Live-Cam goes viral, allowing anyone to become a digital doppelganger"*](https://arstechnica.com/information-technology/2024/08/new-ai-tool-enables-real-time-face-swapping-on-webcams-raising-fraud-concerns/) - Ars Technica
- - [*"Thanks Deep Live Cam, shapeshifters are among us now"*](https://dataconomy.com/2024/08/15/what-is-deep-live-cam-github-deepfake/) - Dataconomy
- - [*"This free AI tool lets you become anyone during video-calls"*](https://www.newsbytesapp.com/news/science/deep-live-cam-ai-impersonation-tool-goes-viral/story) - NewsBytes
- - [*"OK, this viral AI live stream software is truly terrifying"*](https://www.creativebloq.com/ai/ok-this-viral-ai-live-stream-software-is-truly-terrifying) - Creative Bloq
- - [*"Deepfake AI Tool Lets You Become Anyone in a Video Call With Single Photo"*](https://petapixel.com/2024/08/14/deep-live-cam-deepfake-ai-tool-lets-you-become-anyone-in-a-video-call-with-single-photo-mark-zuckerberg-jd-vance-elon-musk/) - PetaPixel
- - [*"Deep-Live-Cam Uses AI to Transform Your Face in Real-Time, Celebrities Included"*](https://www.techeblog.com/deep-live-cam-ai-transform-face/) - TechEBlog
- - [*"An AI tool that "makes you look like anyone" during a video call is going viral online"*](https://telegrafi.com/en/a-tool-that-makes-you-look-like-anyone-during-a-video-call-is-going-viral-on-the-Internet/) - Telegrafi
- - [*"This Deepfake Tool Turning Images Into Livestreams is Topping the GitHub Charts"*](https://decrypt.co/244565/this-deepfake-tool-turning-images-into-livestreams-is-topping-the-github-charts) - Emerge
- - [*"New Real-Time Face-Swapping AI Allows Anyone to Mimic Famous Faces"*](https://www.digitalmusicnews.com/2024/08/15/face-swapping-ai-real-time-mimic/) - Digital Music News
- - [*"This real-time webcam deepfake tool raises alarms about the future of identity theft"*](https://www.diyphotography.net/this-real-time-webcam-deepfake-tool-raises-alarms-about-the-future-of-identity-theft/) - DIYPhotography
- - [*"That's Crazy, Oh God. That's Fucking Freaky Dude... That's So Wild Dude"*](https://www.youtube.com/watch?time_continue=1074&v=py4Tc-Y8BcY) - SomeOrdinaryGamers
- - [*"Alright look look look, now look chat, we can do any face we want to look like chat"*](https://www.youtube.com/live/mFsCe7AIxq8?feature=shared&t=2686) - IShowSpeed

 ## Credits

-   [ffmpeg](https://ffmpeg.org/): for making video-related operations easy
-   [deepinsight](https://github.com/deepinsight): for their [insightface](https://github.com/deepinsight/insightface) project which provided a well-made library and models. Please be reminded that the [use of the model is for non-commercial research purposes only](https://github.com/deepinsight/insightface?tab=readme-ov-file#license).
-   [havok2-htwo](https://github.com/havok2-htwo): for sharing the code for webcam
-   [GosuDRM](https://github.com/GosuDRM): for the open version of roop
-   [pereiraroland26](https://github.com/pereiraroland26): Multiple faces support
-   [vic4key](https://github.com/vic4key): For supporting/contributing to this project
-   [kier007](https://github.com/kier007): for improving the user experience
-   [qitianai](https://github.com/qitianai): for multi-lingual support
-   and [all developers](https://github.com/hacksider/Deep-Live-Cam/graphs/contributors) behind libraries used in this project.
-   Footnote: Please be informed that the base author of the code is [s0md3v](https://github.com/s0md3v/roop)
-   All the wonderful users who helped make this project go viral by starring the repo ❤️
-
-[![Stargazers](https://reporoster.com/stars/hacksider/Deep-Live-Cam)](https://github.com/hacksider/Deep-Live-Cam/stargazers)
+- [ffmpeg](https://ffmpeg.org/): for making video related operations easy
+- [deepinsight](https://github.com/deepinsight): for their [insightface](https://github.com/deepinsight/insightface) project which provided a well-made library and models. Please be reminded that the [use of the model is for non-commercial research purposes only](https://github.com/deepinsight/insightface?tab=readme-ov-file#license).
+- [havok2-htwo](https://github.com/havok2-htwo) : for sharing the code for webcam
+- [GosuDRM](https://github.com/GosuDRM) : for open version of roop
+- [pereiraroland26](https://github.com/pereiraroland26) : Multiple faces support
+- [vic4key](https://github.com/vic4key) : For supporting/contributing on this project
+- [KRSHH](https://github.com/KRSHH) : For updating the UI
+- and [all developers](https://github.com/hacksider/Deep-Live-Cam/graphs/contributors) behind libraries used in this project.
+- Foot Note: [This is originally roop-cam, see the full history of the code here.](https://github.com/hacksider/roop-cam) Please be informed that the base author of the code is [s0md3v](https://github.com/s0md3v/roop)

 ## Contributions
-
 ![Alt](https://repobeats.axiom.co/api/embed/fec8e29c45dfdb9c5916f3a7830e1249308d20e1.svg "Repobeats analytics image")
-
-## Stars to the Moon 🚀
+## Star History

 <a href="https://star-history.com/#hacksider/deep-live-cam&Date">
 <picture>
@@ -1,46 +0,0 @@
-{
-    "Source x Target Mapper": "Source x Target Mapper",
-    "select an source image": "选择一个源图像",
-    "Preview": "预览",
-    "select an target image or video": "选择一个目标图像或视频",
-    "save image output file": "保存图像输出文件",
-    "save video output file": "保存视频输出文件",
-    "select an target image": "选择一个目标图像",
-    "source": "源",
-    "Select a target": "选择一个目标",
-    "Select a face": "选择一张脸",
-    "Keep audio": "保留音频",
-    "Face Enhancer": "面纹增强器",
-    "Many faces": "多脸",
-    "Show FPS": "显示帧率",
-    "Keep fps": "保持帧率",
-    "Keep frames": "保持帧数",
-    "Fix Blueish Cam": "修复偏蓝的摄像头",
-    "Mouth Mask": "口罩",
-    "Show Mouth Mask Box": "显示口罩盒",
-    "Start": "开始",
-    "Live": "直播",
-    "Destroy": "结束",
-    "Map faces": "识别人脸",
-    "Processing...": "处理中...",
-    "Processing succeed!": "处理成功!",
-    "Processing ignored!": "处理被忽略!",
-    "Failed to start camera": "启动相机失败",
-    "Please complete pop-up or close it.": "请先完成弹出窗口或者关闭它",
-    "Getting unique faces": "获取独特面部",
-    "Please select a source image first": "请先选择一个源图像",
-    "No faces found in target": "目标图像中没有人脸",
-    "Add": "添加",
-    "Clear": "清除",
-    "Submit": "确认",
-    "Select source image": "请选取源图像",
-    "Select target image": "请选取目标图像",
-    "Please provide mapping!": "请提供映射",
-    "Atleast 1 source with target is required!": "至少需要一个来源图像与目标图像相关！",
-    "At least 1 source with target is required!": "至少需要一个来源图像与目标图像相关！",
-    "Face could not be detected in last upload!": "最近上传的图像中没有检测到人脸!",
-    "Select Camera:": "选择摄像头",
-    "All mappings cleared!": "所有映射均已清除!",
-    "Mappings successfully submitted!": "成功提交映射！",
-    "Source x Target Mapper is already open.": "源 x 目标映射器已打开。"
-}
@@ -1,4 +1,4 @@
 just put the models in this folder -

 https://huggingface.co/hacksider/deep-live-cam/resolve/main/inswapper_128_fp16.onnx?download=true
-https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth
+https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth
@@ -41,10 +41,8 @@ def parse_args() -> None:
    program.add_argument('--many-faces', help='process every face', dest='many_faces', action='store_true', default=False)
    program.add_argument('--nsfw-filter', help='filter the NSFW image or video', dest='nsfw_filter', action='store_true', default=False)
    program.add_argument('--map-faces', help='map source target faces', dest='map_faces', action='store_true', default=False)
-    program.add_argument('--mouth-mask', help='mask the mouth region', dest='mouth_mask', action='store_true', default=False)
    program.add_argument('--video-encoder', help='adjust output video encoder', dest='video_encoder', default='libx264', choices=['libx264', 'libx265', 'libvpx-vp9'])
    program.add_argument('--video-quality', help='adjust output video quality', dest='video_quality', type=int, default=18, choices=range(52), metavar='[0-51]')
-    program.add_argument('-l', '--lang', help='Ui language', default="en")
    program.add_argument('--live-mirror', help='The live camera display as you see it in the front-facing camera frame', dest='live_mirror', action='store_true', default=False)
    program.add_argument('--live-resizable', help='The live camera frame is resizable', dest='live_resizable', action='store_true', default=False)
    program.add_argument('--max-memory', help='maximum amount of RAM in GB', dest='max_memory', type=int, default=suggest_max_memory())
@@ -69,7 +67,6 @@ def parse_args() -> None:
    modules.globals.keep_audio = args.keep_audio
    modules.globals.keep_frames = args.keep_frames
    modules.globals.many_faces = args.many_faces
-    modules.globals.mouth_mask = args.mouth_mask
    modules.globals.nsfw_filter = args.nsfw_filter
    modules.globals.map_faces = args.map_faces
    modules.globals.video_encoder = args.video_encoder
@@ -79,7 +76,6 @@ def parse_args() -> None:
    modules.globals.max_memory = args.max_memory
    modules.globals.execution_providers = decode_execution_providers(args.execution_provider)
    modules.globals.execution_threads = args.execution_threads
-    modules.globals.lang = args.lang

    #for ENHANCER tumbler:
    if 'face_enhancer' in args.frame_processor:
@@ -255,5 +251,5 @@ def run() -> None:
    if modules.globals.headless:
        start()
    else:
-        window = ui.init(start, destroy, modules.globals.lang)
+        window = ui.init(start, destroy)
        window.mainloop()
@@ -39,13 +39,13 @@ def get_many_faces(frame: Frame) -> Any:
        return None

 def has_valid_map() -> bool:
-    for map in modules.globals.source_target_map:
+    for map in modules.globals.souce_target_map:
        if "source" in map and "target" in map:
            return True
    return False

 def default_source_face() -> Any:
-    for map in modules.globals.source_target_map:
+    for map in modules.globals.souce_target_map:
        if "source" in map:
            return map['source']['face']
    return None
@@ -53,7 +53,7 @@ def default_source_face() -> Any:
 def simplify_maps() -> Any:
    centroids = []
    faces = []
-    for map in modules.globals.source_target_map:
+    for map in modules.globals.souce_target_map:
        if "source" in map and "target" in map:
            centroids.append(map['target']['face'].normed_embedding)
            faces.append(map['source']['face'])
@@ -64,10 +64,10 @@ def simplify_maps() -> Any:
 def add_blank_map() -> Any:
    try:
        max_id = -1
-        if len(modules.globals.source_target_map) > 0:
-            max_id = max(modules.globals.source_target_map, key=lambda x: x['id'])['id']
+        if len(modules.globals.souce_target_map) > 0:
+            max_id = max(modules.globals.souce_target_map, key=lambda x: x['id'])['id']

-        modules.globals.source_target_map.append({
+        modules.globals.souce_target_map.append({
                'id' : max_id + 1
                })
    except ValueError:
@@ -75,14 +75,14 @@ def add_blank_map() -> Any:
    
 def get_unique_faces_from_target_image() -> Any:
    try:
-        modules.globals.source_target_map = []
+        modules.globals.souce_target_map = []
        target_frame = cv2.imread(modules.globals.target_path)
        many_faces = get_many_faces(target_frame)
        i = 0

        for face in many_faces:
            x_min, y_min, x_max, y_max = face['bbox']
-            modules.globals.source_target_map.append({
+            modules.globals.souce_target_map.append({
                'id' : i, 
                'target' : {
                            'cv2' : target_frame[int(y_min):int(y_max), int(x_min):int(x_max)],
@@ -96,7 +96,7 @@ def get_unique_faces_from_target_image() -> Any:
    
 def get_unique_faces_from_target_video() -> Any:
    try:
-        modules.globals.source_target_map = []
+        modules.globals.souce_target_map = []
        frame_face_embeddings = []
        face_embeddings = []
    
@@ -127,7 +127,7 @@ def get_unique_faces_from_target_video() -> Any:
                face['target_centroid'] = closest_centroid_index

        for i in range(len(centroids)):
-            modules.globals.source_target_map.append({
+            modules.globals.souce_target_map.append({
                'id' : i
            })

@@ -135,7 +135,7 @@ def get_unique_faces_from_target_video() -> Any:
            for frame in tqdm(frame_face_embeddings, desc=f"Mapping frame embeddings to centroids-{i}"):
                temp.append({'frame': frame['frame'], 'faces': [face for face in frame['faces'] if face['target_centroid'] == i], 'location': frame['location']})

-            modules.globals.source_target_map[i]['target_faces_in_frame'] = temp
+            modules.globals.souce_target_map[i]['target_faces_in_frame'] = temp

        # dump_faces(centroids, frame_face_embeddings)
        default_target_face()
@@ -144,7 +144,7 @@ def get_unique_faces_from_target_video() -> Any:
    

 def default_target_face():
-    for map in modules.globals.source_target_map:
+    for map in modules.globals.souce_target_map:
        best_face = None
        best_frame = None
        for frame in map['target_faces_in_frame']:
@@ -1,26 +0,0 @@
-import json
-from pathlib import Path
-
-class LanguageManager:
-    def __init__(self, default_language="en"):
-        self.current_language = default_language
-        self.translations = {}
-        self.load_language(default_language)
-
-    def load_language(self, language_code) -> bool:
-        """load language file"""
-        if language_code == "en":
-            return True
-        try:
-            file_path = Path(__file__).parent.parent / f"locales/{language_code}.json"
-            with open(file_path, "r", encoding="utf-8") as file:
-                self.translations = json.load(file)
-            self.current_language = language_code
-            return True
-        except FileNotFoundError:
-            print(f"Language file not found: {language_code}")
-            return False
-
-    def _(self, key, default=None) -> str:
-        """get translate text"""
-        return self.translations.get(key, default if default else key)
@@ -9,35 +9,38 @@ file_types = [
    ("Video", ("*.mp4", "*.mkv")),
 ]

-source_target_map = []
+souce_target_map = []
 simple_map = {}

 source_path = None
 target_path = None
 output_path = None
 frame_processors: List[str] = []
-keep_fps = True
-keep_audio = True
-keep_frames = False
-many_faces = False
-map_faces = False
-color_correction = False  # New global variable for color correction toggle
-nsfw_filter = False
+keep_fps = True  # Initialize with default value
+keep_audio = True  # Initialize with default value
+keep_frames = False  # Initialize with default value
+many_faces = False  # Initialize with default value
+map_faces = False  # Initialize with default value
+color_correction = False  # Initialize with default value
+nsfw_filter = False  # Initialize with default value
 video_encoder = None
 video_quality = None
-live_mirror = False
-live_resizable = True
+live_mirror = False  # Initialize with default value
+live_resizable = False  # Initialize with default value
 max_memory = None
 execution_providers: List[str] = []
 execution_threads = None
 headless = None
 log_level = "error"
-fp_ui: Dict[str, bool] = {"face_enhancer": False}
+fp_ui: Dict[str, bool] = {"face_enhancer": False}  # Initialize with default value
 camera_input_combobox = None
 webcam_preview_running = False
-show_fps = False
+show_fps = False  # Initialize with default value
 mouth_mask = False
 show_mouth_mask_box = False
+mask_down_size = 0.5
+mask_size = 1.0
 mask_feather_ratio = 8
-mask_down_size = 0.50
-mask_size = 1
+opacity_switch = False
+face_opacity = 100
+selected_camera = None
@@ -1,3 +1,3 @@
-name = 'Deep-Live-Cam'
-version = '1.9'
-edition = 'GitHub Edition'
+name = 'Deep Live Cam'
+version = '1.6.0'
+edition = 'Portable'
@@ -9,41 +9,23 @@ import modules.processors.frame.core
 from modules.core import update_status
 from modules.face_analyser import get_one_face
 from modules.typing import Frame, Face
-import platform
-import torch
-from modules.utilities import (
-    conditional_download,
-    is_image,
-    is_video,
-)
+from modules.utilities import conditional_download, resolve_relative_path, is_image, is_video

 FACE_ENHANCER = None
 THREAD_SEMAPHORE = threading.Semaphore()
 THREAD_LOCK = threading.Lock()
-NAME = "DLC.FACE-ENHANCER"
-
-abs_dir = os.path.dirname(os.path.abspath(__file__))
-models_dir = os.path.join(
-    os.path.dirname(os.path.dirname(os.path.dirname(abs_dir))), "models"
-)
+NAME = 'DLC.FACE-ENHANCER'


 def pre_check() -> bool:
-    download_directory_path = models_dir
-    conditional_download(
-        download_directory_path,
-        [
-            "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth"
-        ],
-    )
+    download_directory_path = resolve_relative_path('..\models')
+    conditional_download(download_directory_path, ['https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth'])
    return True


 def pre_start() -> bool:
-    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

@@ -53,24 +35,21 @@ def get_face_enhancer() -> Any:

    with THREAD_LOCK:
        if FACE_ENHANCER is None:
-            model_path = os.path.join(models_dir, "GFPGANv1.4.pth")
-            
-            match platform.system():
-                case "Darwin":  # Mac OS
-                    if torch.backends.mps.is_available():
-                        mps_device = torch.device("mps")
-                        FACE_ENHANCER = gfpgan.GFPGANer(model_path=model_path, upscale=1, device=mps_device)  # type: ignore[attr-defined]
-                    else:
-                        FACE_ENHANCER = gfpgan.GFPGANer(model_path=model_path, upscale=1)  # type: ignore[attr-defined]
-                case _:  # Other OS
-                    FACE_ENHANCER = gfpgan.GFPGANer(model_path=model_path, upscale=1)  # type: ignore[attr-defined]
-
+            if os.name == 'nt':
+                model_path = resolve_relative_path('..\models\GFPGANv1.4.pth')
+                # todo: set models path https://github.com/TencentARC/GFPGAN/issues/399
+            else:
+                model_path = resolve_relative_path('../models/GFPGANv1.4.pth')
+            FACE_ENHANCER = gfpgan.GFPGANer(model_path=model_path, upscale=1) # type: ignore[attr-defined]
    return FACE_ENHANCER


 def enhance_face(temp_frame: Frame) -> Frame:
    with THREAD_SEMAPHORE:
-        _, _, temp_frame = get_face_enhancer().enhance(temp_frame, paste_back=True)
+        _, _, temp_frame = get_face_enhancer().enhance(
+            temp_frame,
+            paste_back=True
+        )
    return temp_frame


@@ -81,9 +60,7 @@ def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
    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:
    for temp_frame_path in temp_frame_paths:
        temp_frame = cv2.imread(temp_frame_path)
        result = process_frame(None, temp_frame)
@@ -100,10 +77,3 @@ 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:
    modules.processors.frame.core.process_video(None, temp_frame_paths, process_frames)
-
-
-def process_frame_v2(temp_frame: Frame) -> Frame:
-    target_face = get_one_face(temp_frame)
-    if target_face:
-        temp_frame = enhance_face(temp_frame)
-    return temp_frame
@@ -1,44 +1,50 @@
-import os # <-- Added for os.path.exists
 from typing import Any, List
 import cv2
 import insightface
 import threading
-
+import numpy as np
 import modules.globals
 import modules.processors.frame.core
-# Ensure update_status is imported if not already globally accessible
-# If it's part of modules.core, it might already be accessible via modules.core.update_status
 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')
-    # Ensure both models are mentioned or downloaded if necessary
-    # Conditional download might need adjustment if you want it to fetch FP32 too
-    conditional_download(download_directory_path, ['https://huggingface.co/hacksider/deep-live-cam/blob/main/inswapper_128_fp16.onnx'])
-    # Add a check or download for the FP32 model if you have a URL
-    # conditional_download(download_directory_path, ['URL_TO_FP32_MODEL_HERE'])
+    download_directory_path = resolve_relative_path("../models")
+    conditional_download(
+        download_directory_path,
+        [
+            "https://huggingface.co/hacksider/deep-live-cam/blob/main/inswapper_128_fp16.onnx"
+        ],
+    )
    return True


 def pre_start() -> bool:
-    # --- No changes needed in pre_start ---
    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

@@ -48,57 +54,48 @@ def get_face_swapper() -> Any:

    with THREAD_LOCK:
        if FACE_SWAPPER is None:
-            # --- MODIFICATION START ---
-            # Define paths for both FP32 and FP16 models
-            model_dir = resolve_relative_path('../models')
-            model_path_fp32 = os.path.join(model_dir, 'inswapper_128.onnx')
-            model_path_fp16 = os.path.join(model_dir, 'inswapper_128_fp16.onnx')
-            chosen_model_path = None
-
-            # Prioritize FP32 model
-            if os.path.exists(model_path_fp32):
-                chosen_model_path = model_path_fp32
-                update_status(f"Loading FP32 model: {os.path.basename(chosen_model_path)}", NAME)
-            # Fallback to FP16 model
-            elif os.path.exists(model_path_fp16):
-                chosen_model_path = model_path_fp16
-                update_status(f"FP32 model not found. Loading FP16 model: {os.path.basename(chosen_model_path)}", NAME)
-            # Error if neither model is found
-            else:
-                error_message = f"Face Swapper model not found. Please ensure 'inswapper_128.onnx' (recommended) or 'inswapper_128_fp16.onnx' exists in the '{model_dir}' directory."
-                update_status(error_message, NAME)
-                raise FileNotFoundError(error_message)
-
-            # Load the chosen model
-            try:
-                FACE_SWAPPER = insightface.model_zoo.get_model(chosen_model_path, providers=modules.globals.execution_providers)
-            except Exception as e:
-                update_status(f"Error loading Face Swapper model {os.path.basename(chosen_model_path)}: {e}", NAME)
-                # Optionally, re-raise the exception or handle it more gracefully
-                raise e
-            # --- MODIFICATION END ---
+            model_path = resolve_relative_path("../models/inswapper_128_fp16.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:
-    # --- No changes needed in swap_face ---
-    swapper = get_face_swapper()
-    if swapper is None:
-         # Handle case where model failed to load
-         update_status("Face swapper model not loaded, skipping swap.", NAME)
-         return temp_frame
-    return swapper.get(temp_frame, target_face, source_face, paste_back=True)
+    swapped_frame = get_face_swapper().get(
+        temp_frame, target_face, source_face, paste_back=True
+    )
+
+    # Apply opacity if enabled
+    if modules.globals.opacity_switch:
+        opacity = modules.globals.face_opacity / 100
+        swapped_frame = cv2.addWeighted(
+            swapped_frame, opacity, temp_frame, 1 - opacity, 0
+        )
+
+    # Apply mouth mask if enabled
+    if modules.globals.mouth_mask:
+        face_mask = create_face_mask(target_face, temp_frame)
+        mouth_mask_data = create_lower_mouth_mask(target_face, temp_frame)
+        mouth_mask, mouth_cutout, mouth_box, lower_lip_polygon = mouth_mask_data
+
+        if mouth_box is not None:
+            swapped_frame = apply_mouth_area(
+                swapped_frame, mouth_cutout, mouth_box, face_mask, lower_lip_polygon
+            )
+
+            if modules.globals.show_mouth_mask_box:
+                swapped_frame = draw_mouth_mask_visualization(
+                    swapped_frame, target_face, mouth_mask_data
+                )
+
+    return swapped_frame


 def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
-    # --- No changes needed in process_frame ---
    # Ensure the frame is in RGB format if color correction is enabled
-    # Note: InsightFace swapper often expects BGR by default. Double-check if color issues appear.
-    # If color correction is needed *before* swapping and insightface needs BGR:
-    # original_was_bgr = True # Assume input is BGR
-    # if modules.globals.color_correction:
-    #     temp_frame = cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB)
-    #     original_was_bgr = False # Now it's RGB
+    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)
@@ -109,51 +106,52 @@ def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
        target_face = get_one_face(temp_frame)
        if target_face:
            temp_frame = swap_face(source_face, target_face, temp_frame)
-
-    # Convert back if necessary (example, might not be needed depending on workflow)
-    # if modules.globals.color_correction and not original_was_bgr:
-    #      temp_frame = cv2.cvtColor(temp_frame, cv2.COLOR_RGB2BGR)
-
    return temp_frame


 def process_frame_v2(temp_frame: Frame, temp_frame_path: str = "") -> Frame:
-    # --- No changes needed in process_frame_v2 ---
-    # (Assuming swap_face handles the potential None return from get_face_swapper)
    if is_image(modules.globals.target_path):
        if modules.globals.many_faces:
            source_face = default_source_face()
-            for map_entry in modules.globals.souce_target_map: # Renamed 'map' to 'map_entry'
-                target_face = map_entry['target']['face']
+            for map in modules.globals.souce_target_map:
+                target_face = map["target"]["face"]
                temp_frame = swap_face(source_face, target_face, temp_frame)

        elif not modules.globals.many_faces:
-            for map_entry in modules.globals.souce_target_map: # Renamed 'map' to 'map_entry'
-                if "source" in map_entry:
-                    source_face = map_entry['source']['face']
-                    target_face = map_entry['target']['face']
+            for map in modules.globals.souce_target_map:
+                if "source" in map:
+                    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_entry in modules.globals.souce_target_map: # Renamed 'map' to 'map_entry'
-                target_frame = [f for f in map_entry['target_faces_in_frame'] if f['location'] == temp_frame_path]
+            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
+                ]

                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_entry in modules.globals.souce_target_map: # Renamed 'map' to 'map_entry'
-                if "source" in map_entry:
-                    target_frame = [f for f in map_entry['target_faces_in_frame'] if f['location'] == temp_frame_path]
-                    source_face = map_entry['source']['face']
+            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"]

                    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: # Fallback for neither image nor video (e.g., live feed?)
+    else:
        detected_faces = get_many_faces(temp_frame)
        if modules.globals.many_faces:
            if detected_faces:
@@ -162,97 +160,334 @@ def process_frame_v2(temp_frame: Frame, temp_frame_path: str = "") -> Frame:
                    temp_frame = swap_face(source_face, target_face, temp_frame)

        elif not modules.globals.many_faces:
-            if detected_faces and hasattr(modules.globals, 'simple_map') and modules.globals.simple_map: # Check simple_map exists
-                if len(detected_faces) <= len(modules.globals.simple_map['target_embeddings']):
+            if detected_faces:
+                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)
-                        temp_frame = swap_face(modules.globals.simple_map['source_faces'][closest_centroid_index], detected_face, temp_frame)
+                        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,
+                        )
                else:
-                    detected_faces_centroids = [face.normed_embedding for face in detected_faces]
+                    detected_faces_centroids = []
+                    for face in detected_faces:
+                        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)
-                        # Ensure index is valid before accessing detected_faces
-                        if closest_centroid_index < len(detected_faces):
-                            temp_frame = swap_face(modules.globals.simple_map['source_faces'][i], detected_faces[closest_centroid_index], temp_frame)
+                    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,
+                        )
                        i += 1
    return temp_frame


-def process_frames(source_path: str, temp_frame_paths: List[str], progress: Any = None) -> None:
-    # --- No changes needed in process_frames ---
-    # Note: Ensure get_one_face is called only once if possible for efficiency if !map_faces
-    source_face = None
+def process_frames(
+    source_path: str, temp_frame_paths: List[str], progress: Any = None
+) -> None:
    if not modules.globals.map_faces:
-        source_img = cv2.imread(source_path)
-        if source_img is not None:
-            source_face = get_one_face(source_img)
-        if source_face is None:
-             update_status(f"Could not find face in source image: {source_path}, skipping swap.", NAME)
-             # If no source face, maybe skip processing? Or handle differently.
-             # For now, it will proceed but swap_face might fail later.
-
-    for temp_frame_path in temp_frame_paths:
-        temp_frame = cv2.imread(temp_frame_path)
-        if temp_frame is None:
-            update_status(f"Warning: Could not read frame {temp_frame_path}", NAME)
-            if progress: progress.update(1) # Still update progress even if frame fails
-            continue # Skip to next frame
-
-        try:
-            if not modules.globals.map_faces:
-                if source_face: # Only process if source face was found
-                    result = process_frame(source_face, temp_frame)
-                else:
-                    result = temp_frame # No source face, return original frame
-            else:
-                 result = process_frame_v2(temp_frame, temp_frame_path)
-
-            cv2.imwrite(temp_frame_path, result)
-        except Exception as exception:
-            update_status(f"Error processing frame {os.path.basename(temp_frame_path)}: {exception}", NAME)
-            # Decide whether to 'pass' (continue processing other frames) or raise
-            pass # Continue processing other frames
-        finally:
+        source_face = get_one_face(cv2.imread(source_path))
+        for temp_frame_path in temp_frame_paths:
+            temp_frame = cv2.imread(temp_frame_path)
+            try:
+                result = process_frame(source_face, temp_frame)
+                cv2.imwrite(temp_frame_path, result)
+            except Exception as exception:
+                print(exception)
+                pass
+            if progress:
+                progress.update(1)
+    else:
+        for temp_frame_path in temp_frame_paths:
+            temp_frame = cv2.imread(temp_frame_path)
+            try:
+                result = process_frame_v2(temp_frame, temp_frame_path)
+                cv2.imwrite(temp_frame_path, result)
+            except Exception as exception:
+                print(exception)
+                pass
            if progress:
                progress.update(1)


 def process_image(source_path: str, target_path: str, output_path: str) -> None:
-    # --- No changes needed in process_image ---
-    # Note: Added checks for successful image reads and face detection
-    target_frame = cv2.imread(target_path) # Read original target for processing
-    if target_frame is None:
-        update_status(f"Error: Could not read target image: {target_path}", NAME)
-        return
-
    if not modules.globals.map_faces:
-        source_img = cv2.imread(source_path)
-        if source_img is None:
-             update_status(f"Error: Could not read source image: {source_path}", NAME)
-             return
-        source_face = get_one_face(source_img)
-        if source_face is None:
-            update_status(f"Error: No face found in source image: {source_path}", NAME)
-            return
-
+        source_face = get_one_face(cv2.imread(source_path))
+        target_frame = cv2.imread(target_path)
        result = process_frame(source_face, target_frame)
+        cv2.imwrite(output_path, result)
    else:
        if modules.globals.many_faces:
-            update_status('Many faces enabled. Using first source image (if applicable in v2). Processing...', NAME)
-        # For process_frame_v2 on single image, it reads the 'output_path' which should be a copy
-        # Let's process the 'target_frame' we read instead.
-        result = process_frame_v2(target_frame) # Process the frame directly
-
-    # Write the final result to the output path
-    success = cv2.imwrite(output_path, result)
-    if not success:
-        update_status(f"Error: Failed to write output image to: {output_path}", 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)


 def process_video(source_path: str, temp_frame_paths: List[str]) -> None:
-    # --- No changes needed in process_video ---
    if modules.globals.map_faces and modules.globals.many_faces:
-        update_status('Many faces enabled. Using first source image (if applicable in v2). Processing...', NAME)
-    # The core processing logic is delegated, which is good.
-    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
+    )
+
+
+def create_face_mask(face: Face, frame: Frame) -> np.ndarray:
+    mask = np.zeros(frame.shape[:2], dtype=np.uint8)
+    landmarks = face.landmark_2d_106
+    if landmarks is not None:
+        landmarks = landmarks.astype(np.int32)
+
+        right_side_face = landmarks[0:16]
+        left_side_face = landmarks[17:32]
+        right_eye = landmarks[33:42]
+        right_eye_brow = landmarks[43:51]
+        left_eye = landmarks[87:96]
+        left_eye_brow = landmarks[97:105]
+
+        right_eyebrow_top = np.min(right_eye_brow[:, 1])
+        left_eyebrow_top = np.min(left_eye_brow[:, 1])
+        eyebrow_top = min(right_eyebrow_top, left_eyebrow_top)
+
+        face_top = np.min([right_side_face[0, 1], left_side_face[-1, 1]])
+        forehead_height = face_top - eyebrow_top
+        extended_forehead_height = int(forehead_height * 5.0)
+
+        forehead_left = right_side_face[0].copy()
+        forehead_right = left_side_face[-1].copy()
+        forehead_left[1] -= extended_forehead_height
+        forehead_right[1] -= extended_forehead_height
+
+        face_outline = np.vstack(
+            [
+                [forehead_left],
+                right_side_face,
+                left_side_face[::-1],
+                [forehead_right],
+            ]
+        )
+
+        padding = int(np.linalg.norm(right_side_face[0] - left_side_face[-1]) * 0.05)
+
+        hull = cv2.convexHull(face_outline)
+        hull_padded = []
+        for point in hull:
+            x, y = point[0]
+            center = np.mean(face_outline, axis=0)
+            direction = np.array([x, y]) - center
+            direction = direction / np.linalg.norm(direction)
+            padded_point = np.array([x, y]) + direction * padding
+            hull_padded.append(padded_point)
+
+        hull_padded = np.array(hull_padded, dtype=np.int32)
+        cv2.fillConvexPoly(mask, hull_padded, 255)
+        mask = cv2.GaussianBlur(mask, (5, 5), 3)
+
+    return mask
+
+
+def create_lower_mouth_mask(face: Face, frame: Frame) -> tuple:
+    mask = np.zeros(frame.shape[:2], dtype=np.uint8)
+    mouth_cutout = None
+    landmarks = face.landmark_2d_106
+    if landmarks is not None:
+        lower_lip_order = [
+            65,
+            66,
+            62,
+            70,
+            69,
+            18,
+            19,
+            20,
+            21,
+            22,
+            23,
+            24,
+            0,
+            8,
+            7,
+            6,
+            5,
+            4,
+            3,
+            2,
+            65,
+        ]
+        lower_lip_landmarks = landmarks[lower_lip_order].astype(np.float32)
+
+        center = np.mean(lower_lip_landmarks, axis=0)
+        expansion_factor = 1 + modules.globals.mask_down_size
+        expanded_landmarks = (lower_lip_landmarks - center) * expansion_factor + center
+
+        toplip_indices = [20, 0, 1, 2, 3, 4, 5]
+        toplip_extension = modules.globals.mask_size * 0.5
+        for idx in toplip_indices:
+            direction = expanded_landmarks[idx] - center
+            direction = direction / np.linalg.norm(direction)
+            expanded_landmarks[idx] += direction * toplip_extension
+
+        chin_indices = [11, 12, 13, 14, 15, 16]
+        chin_extension = 2 * 0.2
+        for idx in chin_indices:
+            expanded_landmarks[idx][1] += (
+                expanded_landmarks[idx][1] - center[1]
+            ) * chin_extension
+
+        expanded_landmarks = expanded_landmarks.astype(np.int32)
+
+        min_x, min_y = np.min(expanded_landmarks, axis=0)
+        max_x, max_y = np.max(expanded_landmarks, axis=0)
+
+        padding = int((max_x - min_x) * 0.1)
+        min_x = max(0, min_x - padding)
+        min_y = max(0, min_y - padding)
+        max_x = min(frame.shape[1], max_x + padding)
+        max_y = min(frame.shape[0], max_y + padding)
+
+        if max_x <= min_x or max_y <= min_y:
+            if (max_x - min_x) <= 1:
+                max_x = min_x + 1
+            if (max_y - min_y) <= 1:
+                max_y = min_y + 1
+
+        mask_roi = np.zeros((max_y - min_y, max_x - min_x), dtype=np.uint8)
+        cv2.fillPoly(mask_roi, [expanded_landmarks - [min_x, min_y]], 255)
+        mask_roi = cv2.GaussianBlur(mask_roi, (15, 15), 5)
+        mask[min_y:max_y, min_x:max_x] = mask_roi
+        mouth_cutout = frame[min_y:max_y, min_x:max_x].copy()
+
+        return mask, mouth_cutout, (min_x, min_y, max_x, max_y), expanded_landmarks
+
+    return mask, mouth_cutout, None, None
+
+
+def apply_mouth_area(
+    frame: Frame,
+    mouth_cutout: np.ndarray,
+    mouth_box: tuple,
+    face_mask: np.ndarray,
+    mouth_polygon: np.ndarray,
+) -> Frame:
+    min_x, min_y, max_x, max_y = mouth_box
+    box_width = max_x - min_x
+    box_height = max_y - min_y
+
+    if (
+        mouth_cutout is None
+        or box_width is None
+        or box_height is None
+        or face_mask is None
+        or mouth_polygon is None
+    ):
+        return frame
+
+    try:
+        resized_mouth_cutout = cv2.resize(mouth_cutout, (box_width, box_height))
+        roi = frame[min_y:max_y, min_x:max_x]
+
+        if roi.shape != resized_mouth_cutout.shape:
+            resized_mouth_cutout = cv2.resize(
+                resized_mouth_cutout, (roi.shape[1], roi.shape[0])
+            )
+
+        color_corrected_mouth = apply_color_transfer(resized_mouth_cutout, roi)
+
+        polygon_mask = np.zeros(roi.shape[:2], dtype=np.uint8)
+        adjusted_polygon = mouth_polygon - [min_x, min_y]
+        cv2.fillPoly(polygon_mask, [adjusted_polygon], 255)
+
+        feather_amount = min(
+            30,
+            box_width // modules.globals.mask_feather_ratio,
+            box_height // modules.globals.mask_feather_ratio,
+        )
+        feathered_mask = cv2.GaussianBlur(
+            polygon_mask.astype(float), (0, 0), feather_amount
+        )
+        feathered_mask = feathered_mask / feathered_mask.max()
+
+        face_mask_roi = face_mask[min_y:max_y, min_x:max_x]
+        combined_mask = feathered_mask * (face_mask_roi / 255.0)
+
+        combined_mask = combined_mask[:, :, np.newaxis]
+        blended = (
+            color_corrected_mouth * combined_mask + roi * (1 - combined_mask)
+        ).astype(np.uint8)
+
+        face_mask_3channel = (
+            np.repeat(face_mask_roi[:, :, np.newaxis], 3, axis=2) / 255.0
+        )
+        final_blend = blended * face_mask_3channel + roi * (1 - face_mask_3channel)
+
+        frame[min_y:max_y, min_x:max_x] = final_blend.astype(np.uint8)
+    except Exception as e:
+        pass
+
+    return frame
+
+
+def apply_color_transfer(source: np.ndarray, target: np.ndarray) -> np.ndarray:
+    source = cv2.cvtColor(source, cv2.COLOR_BGR2LAB).astype("float32")
+    target = cv2.cvtColor(target, cv2.COLOR_BGR2LAB).astype("float32")
+
+    source_mean, source_std = cv2.meanStdDev(source)
+    target_mean, target_std = cv2.meanStdDev(target)
+
+    source_mean = source_mean.reshape(1, 1, 3)
+    source_std = source_std.reshape(1, 1, 3)
+    target_mean = target_mean.reshape(1, 1, 3)
+    target_std = target_std.reshape(1, 1, 3)
+
+    source = (source - source_mean) * (target_std / source_std) + target_mean
+
+    return cv2.cvtColor(np.clip(source, 0, 255).astype("uint8"), cv2.COLOR_LAB2BGR)
+
+
+def draw_mouth_mask_visualization(
+    frame: Frame, face: Face, mouth_mask_data: tuple
+) -> Frame:
+    landmarks = face.landmark_2d_106
+    if landmarks is not None and mouth_mask_data is not None:
+        mask, mouth_cutout, (min_x, min_y, max_x, max_y), lower_lip_polygon = (
+            mouth_mask_data
+        )
+
+        vis_frame = frame.copy()
+
+        # Draw the lower lip polygon
+        cv2.polylines(vis_frame, [lower_lip_polygon], True, (0, 255, 0), 2)
+
+        # Add labels
+        cv2.putText(
+            vis_frame,
+            "Mouth Mask",
+            (min_x, min_y - 10),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.5,
+            (255, 255, 255),
+            1,
+        )
+
+        return vis_frame
+    return frame
@@ -12,23 +12,16 @@ from tqdm import tqdm

 import modules.globals

-TEMP_FILE = "temp.mp4"
-TEMP_DIRECTORY = "temp"
+TEMP_FILE = 'temp.mp4'
+TEMP_DIRECTORY = 'temp'

 # monkey patch ssl for mac
-if platform.system().lower() == "darwin":
+if platform.system().lower() == 'darwin':
    ssl._create_default_https_context = ssl._create_unverified_context


 def run_ffmpeg(args: List[str]) -> bool:
-    commands = [
-        "ffmpeg",
-        "-hide_banner",
-        "-hwaccel",
-        "auto",
-        "-loglevel",
-        modules.globals.log_level,
-    ]
+    commands = ['ffmpeg', '-hide_banner', '-hwaccel', 'auto', '-loglevel', modules.globals.log_level]
    commands.extend(args)
    try:
        subprocess.check_output(commands, stderr=subprocess.STDOUT)
@@ -39,19 +32,8 @@ def run_ffmpeg(args: List[str]) -> bool:


 def detect_fps(target_path: str) -> float:
-    command = [
-        "ffprobe",
-        "-v",
-        "error",
-        "-select_streams",
-        "v:0",
-        "-show_entries",
-        "stream=r_frame_rate",
-        "-of",
-        "default=noprint_wrappers=1:nokey=1",
-        target_path,
-    ]
-    output = subprocess.check_output(command).decode().strip().split("/")
+    command = ['ffprobe', '-v', 'error', '-select_streams', 'v:0', '-show_entries', 'stream=r_frame_rate', '-of', 'default=noprint_wrappers=1:nokey=1', target_path]
+    output = subprocess.check_output(command).decode().strip().split('/')
    try:
        numerator, denominator = map(int, output)
        return numerator / denominator
@@ -62,65 +44,25 @@ def detect_fps(target_path: str) -> float:

 def extract_frames(target_path: str) -> None:
    temp_directory_path = get_temp_directory_path(target_path)
-    run_ffmpeg(
-        [
-            "-i",
-            target_path,
-            "-pix_fmt",
-            "rgb24",
-            os.path.join(temp_directory_path, "%04d.png"),
-        ]
-    )
+    run_ffmpeg(['-i', target_path, '-pix_fmt', 'rgb24', os.path.join(temp_directory_path, '%04d.png')])


 def create_video(target_path: str, fps: float = 30.0) -> None:
    temp_output_path = get_temp_output_path(target_path)
    temp_directory_path = get_temp_directory_path(target_path)
-    run_ffmpeg(
-        [
-            "-r",
-            str(fps),
-            "-i",
-            os.path.join(temp_directory_path, "%04d.png"),
-            "-c:v",
-            modules.globals.video_encoder,
-            "-crf",
-            str(modules.globals.video_quality),
-            "-pix_fmt",
-            "yuv420p",
-            "-vf",
-            "colorspace=bt709:iall=bt601-6-625:fast=1",
-            "-y",
-            temp_output_path,
-        ]
-    )
+    run_ffmpeg(['-r', str(fps), '-i', os.path.join(temp_directory_path, '%04d.png'), '-c:v', modules.globals.video_encoder, '-crf', str(modules.globals.video_quality), '-pix_fmt', 'yuv420p', '-vf', 'colorspace=bt709:iall=bt601-6-625:fast=1', '-y', temp_output_path])


 def restore_audio(target_path: str, output_path: str) -> None:
    temp_output_path = get_temp_output_path(target_path)
-    done = run_ffmpeg(
-        [
-            "-i",
-            temp_output_path,
-            "-i",
-            target_path,
-            "-c:v",
-            "copy",
-            "-map",
-            "0:v:0",
-            "-map",
-            "1:a:0",
-            "-y",
-            output_path,
-        ]
-    )
+    done = run_ffmpeg(['-i', temp_output_path, '-i', target_path, '-c:v', 'copy', '-map', '0:v:0', '-map', '1:a:0', '-y', output_path])
    if not done:
        move_temp(target_path, output_path)


 def get_temp_frame_paths(target_path: str) -> List[str]:
    temp_directory_path = get_temp_directory_path(target_path)
-    return glob.glob((os.path.join(glob.escape(temp_directory_path), "*.png")))
+    return glob.glob((os.path.join(glob.escape(temp_directory_path), '*.png')))


 def get_temp_directory_path(target_path: str) -> str:
@@ -139,9 +81,7 @@ def normalize_output_path(source_path: str, target_path: str, output_path: str)
        source_name, _ = os.path.splitext(os.path.basename(source_path))
        target_name, target_extension = os.path.splitext(os.path.basename(target_path))
        if os.path.isdir(output_path):
-            return os.path.join(
-                output_path, source_name + "-" + target_name + target_extension
-            )
+            return os.path.join(output_path, source_name + '-' + target_name + target_extension)
    return output_path


@@ -168,20 +108,20 @@ def clean_temp(target_path: str) -> None:


 def has_image_extension(image_path: str) -> bool:
-    return image_path.lower().endswith(("png", "jpg", "jpeg"))
+    return image_path.lower().endswith(('png', 'jpg', 'jpeg'))


 def is_image(image_path: str) -> bool:
    if image_path and os.path.isfile(image_path):
        mimetype, _ = mimetypes.guess_type(image_path)
-        return bool(mimetype and mimetype.startswith("image/"))
+        return bool(mimetype and mimetype.startswith('image/'))
    return False


 def is_video(video_path: str) -> bool:
    if video_path and os.path.isfile(video_path):
        mimetype, _ = mimetypes.guess_type(video_path)
-        return bool(mimetype and mimetype.startswith("video/"))
+        return bool(mimetype and mimetype.startswith('video/'))
    return False


@@ -189,20 +129,12 @@ def conditional_download(download_directory_path: str, urls: List[str]) -> None:
    if not os.path.exists(download_directory_path):
        os.makedirs(download_directory_path)
    for url in urls:
-        download_file_path = os.path.join(
-            download_directory_path, os.path.basename(url)
-        )
+        download_file_path = os.path.join(download_directory_path, os.path.basename(url))
        if not os.path.exists(download_file_path):
-            request = urllib.request.urlopen(url)  # type: ignore[attr-defined]
-            total = int(request.headers.get("Content-Length", 0))
-            with tqdm(
-                total=total,
-                desc="Downloading",
-                unit="B",
-                unit_scale=True,
-                unit_divisor=1024,
-            ) as progress:
-                urllib.request.urlretrieve(url, download_file_path, reporthook=lambda count, block_size, total_size: progress.update(block_size))  # type: ignore[attr-defined]
+            request = urllib.request.urlopen(url) # type: ignore[attr-defined]
+            total = int(request.headers.get('Content-Length', 0))
+            with tqdm(total=total, desc='Downloading', unit='B', unit_scale=True, unit_divisor=1024) as progress:
+                urllib.request.urlretrieve(url, download_file_path, reporthook=lambda count, block_size, total_size: progress.update(block_size)) # type: ignore[attr-defined]


 def resolve_relative_path(path: str) -> str:
@@ -1,94 +0,0 @@
-import cv2
-import numpy as np
-from typing import Optional, Tuple, Callable
-import platform
-import threading
-
-# Only import Windows-specific library if on Windows
-if platform.system() == "Windows":
-    from pygrabber.dshow_graph import FilterGraph
-
-
-class VideoCapturer:
-    def __init__(self, device_index: int):
-        self.device_index = device_index
-        self.frame_callback = None
-        self._current_frame = None
-        self._frame_ready = threading.Event()
-        self.is_running = False
-        self.cap = None
-
-        # Initialize Windows-specific components if on Windows
-        if platform.system() == "Windows":
-            self.graph = FilterGraph()
-            # Verify device exists
-            devices = self.graph.get_input_devices()
-            if self.device_index >= len(devices):
-                raise ValueError(
-                    f"Invalid device index {device_index}. Available devices: {len(devices)}"
-                )
-
-    def start(self, width: int = 960, height: int = 540, fps: int = 60) -> bool:
-        """Initialize and start video capture"""
-        try:
-            if platform.system() == "Windows":
-                # Windows-specific capture methods
-                capture_methods = [
-                    (self.device_index, cv2.CAP_DSHOW),  # Try DirectShow first
-                    (self.device_index, cv2.CAP_ANY),  # Then try default backend
-                    (-1, cv2.CAP_ANY),  # Try -1 as fallback
-                    (0, cv2.CAP_ANY),  # Finally try 0 without specific backend
-                ]
-
-                for dev_id, backend in capture_methods:
-                    try:
-                        self.cap = cv2.VideoCapture(dev_id, backend)
-                        if self.cap.isOpened():
-                            break
-                        self.cap.release()
-                    except Exception:
-                        continue
-            else:
-                # Unix-like systems (Linux/Mac) capture method
-                self.cap = cv2.VideoCapture(self.device_index)
-
-            if not self.cap or not self.cap.isOpened():
-                raise RuntimeError("Failed to open camera")
-
-            # Configure format
-            self.cap.set(cv2.CAP_PROP_FRAME_WIDTH, width)
-            self.cap.set(cv2.CAP_PROP_FRAME_HEIGHT, height)
-            self.cap.set(cv2.CAP_PROP_FPS, fps)
-
-            self.is_running = True
-            return True
-
-        except Exception as e:
-            print(f"Failed to start capture: {str(e)}")
-            if self.cap:
-                self.cap.release()
-            return False
-
-    def read(self) -> Tuple[bool, Optional[np.ndarray]]:
-        """Read a frame from the camera"""
-        if not self.is_running or self.cap is None:
-            return False, None
-
-        ret, frame = self.cap.read()
-        if ret:
-            self._current_frame = frame
-            if self.frame_callback:
-                self.frame_callback(frame)
-            return True, frame
-        return False, None
-
-    def release(self) -> None:
-        """Stop capture and release resources"""
-        if self.is_running and self.cap is not None:
-            self.cap.release()
-            self.is_running = False
-            self.cap = None
-
-    def set_frame_callback(self, callback: Callable[[np.ndarray], None]) -> None:
-        """Set callback for frame processing"""
-        self.frame_callback = callback
@@ -1,23 +1,23 @@
+--extra-index-url https://download.pytorch.org/whl/cu118
+
 numpy>=1.23.5,<2
-typing-extensions>=4.8.0
-opencv-python==4.11.0.86
-onnx==1.17.0
-cv2_enumerate_cameras==1.1.18.3
+opencv-python==4.8.1.78
+cv2_enumerate_cameras==1.1.15
+onnx==1.16.0
 insightface==0.7.3
 psutil==5.9.8
 tk==0.1.0
-customtkinter==5.2.2
-pillow==11.1.0
-torch; sys_platform != 'darwin' --index-url https://download.pytorch.org/whl/cu126
-torch; sys_platform == 'darwin' --index-url https://download.pytorch.org/whl/cu126
-torchvision; sys_platform != 'darwin' --index-url https://download.pytorch.org/whl/cu126
-torchvision; sys_platform == 'darwin' --index-url https://download.pytorch.org/whl/cu126
+pillow==9.5.0
+torch==2.0.1+cu118; sys_platform != 'darwin'
+torch==2.0.1; sys_platform == 'darwin'
+torchvision==0.15.2+cu118; sys_platform != 'darwin'
+torchvision==0.15.2; sys_platform == 'darwin'
 onnxruntime-silicon==1.16.3; sys_platform == 'darwin' and platform_machine == 'arm64'
-onnxruntime-gpu==1.21; sys_platform != 'darwin'
-tensorflow; sys_platform != 'darwin'
+onnxruntime-gpu==1.16.3; sys_platform != 'darwin'
+tensorflow==2.12.1; sys_platform != 'darwin'
 opennsfw2==0.10.2
 protobuf==4.23.2
 tqdm==4.66.4
 gfpgan==1.3.8
 tkinterdnd2==0.4.2
-pygrabber==0.2
+customtkinter==5.2.2
@@ -1 +1 @@
-python run.py --execution-provider cuda
+python run.py --execution-provider cuda --execution-threads 60 --max-memory 60
@@ -1 +0,0 @@
-python run.py --execution-provider dml
@@ -0,0 +1 @@
+python run.py --execution-provider dml
@@ -0,0 +1,13 @@
+@echo off
+	:: Installing Microsoft Visual C++ Runtime - all versions 1.0.1 if it's not already installed
+	choco install vcredist-all
+	:: Installing CUDA if it's not already installed
+	choco install cuda
+	:: Inatalling ffmpeg if it's not already installed
+	choco install ffmpeg
+	:: Installing Python if it's not already installed
+	choco install python -y
+	:: Assuming successful installation, we ensure pip is upgraded
+	python -m ensurepip --upgrade
+	:: Use pip to install the packages listed in 'requirements.txt'
+	pip install -r requirements.txt
@@ -0,0 +1,122 @@
+@echo off
+setlocal EnableDelayedExpansion
+
+:: 1. Setup your platform
+echo Setting up your platform...
+
+:: Python
+where python >nul 2>&1
+if %ERRORLEVEL% neq 0 (
+    echo Python is not installed. Please install Python 3.10 or later.
+    pause
+    exit /b
+)
+
+:: Pip
+where pip >nul 2>&1
+if %ERRORLEVEL% neq 0 (
+    echo Pip is not installed. Please install Pip.
+    pause
+    exit /b
+)
+
+:: Git
+where git >nul 2>&1
+if %ERRORLEVEL% neq 0 (
+    echo Git is not installed. Installing Git...
+    winget install --id Git.Git -e --source winget
+)
+
+:: FFMPEG
+where ffmpeg >nul 2>&1
+if %ERRORLEVEL% neq 0 (
+    echo FFMPEG is not installed. Installing FFMPEG...
+    winget install --id Gyan.FFmpeg -e --source winget
+)
+
+:: Visual Studio 2022 Runtimes
+echo Installing Visual Studio 2022 Runtimes...
+winget install --id Microsoft.VC++2015-2022Redist-x64 -e --source winget
+
+:: 2. Clone Repository
+if exist Deep-Live-Cam (
+    echo Deep-Live-Cam directory already exists.
+    set /p overwrite="Do you want to overwrite? (Y/N): "
+    if /i "%overwrite%"=="Y" (
+        rmdir /s /q Deep-Live-Cam
+        git clone https://github.com/hacksider/Deep-Live-Cam.git
+    ) else (
+        echo Skipping clone, using existing directory.
+    )
+) else (
+    git clone https://github.com/hacksider/Deep-Live-Cam.git
+)
+cd Deep-Live-Cam
+
+:: 3. Download Models
+echo Downloading models...
+mkdir models
+curl -L -o models/GFPGANv1.4.pth https://path.to.model/GFPGANv1.4.pth
+curl -L -o models/inswapper_128_fp16.onnx https://path.to.model/inswapper_128_fp16.onnx
+
+:: 4. Install dependencies
+echo Creating a virtual environment...
+python -m venv venv
+call venv\Scripts\activate
+
+echo Installing required Python packages...
+pip install --upgrade pip
+pip install -r requirements.txt
+
+echo Setup complete. You can now run the application.
+
+:: GPU Acceleration Options
+echo.
+echo Choose the GPU Acceleration Option if applicable:
+echo 1. CUDA (Nvidia)
+echo 2. CoreML (Apple Silicon)
+echo 3. CoreML (Apple Legacy)
+echo 4. DirectML (Windows)
+echo 5. OpenVINO (Intel)
+echo 6. None
+set /p choice="Enter your choice (1-6): "
+
+if "%choice%"=="1" (
+    echo Installing CUDA dependencies...
+    pip uninstall -y onnxruntime onnxruntime-gpu
+    pip install onnxruntime-gpu==1.16.3
+    set exec_provider="cuda"
+) else if "%choice%"=="2" (
+    echo Installing CoreML (Apple Silicon) dependencies...
+    pip uninstall -y onnxruntime onnxruntime-silicon
+    pip install onnxruntime-silicon==1.13.1
+    set exec_provider="coreml"
+) else if "%choice%"=="3" (
+    echo Installing CoreML (Apple Legacy) dependencies...
+    pip uninstall -y onnxruntime onnxruntime-coreml
+    pip install onnxruntime-coreml==1.13.1
+    set exec_provider="coreml"
+) else if "%choice%"=="4" (
+    echo Installing DirectML dependencies...
+    pip uninstall -y onnxruntime onnxruntime-directml
+    pip install onnxruntime-directml==1.15.1
+    set exec_provider="directml"
+) else if "%choice%"=="5" (
+    echo Installing OpenVINO dependencies...
+    pip uninstall -y onnxruntime onnxruntime-openvino
+    pip install onnxruntime-openvino==1.15.0
+    set exec_provider="openvino"
+) else (
+    echo Skipping GPU acceleration setup.
+)
+
+:: Run the application
+if defined exec_provider (
+    echo Running the application with %exec_provider% execution provider...
+    python run.py --execution-provider %exec_provider%
+) else (
+    echo Running the application...
+    python run.py
+)
+
+pause
Author	SHA1	Message	Date
KRSHH	51b38fe253	Revert "Slight Performance Improvement" This reverts commit `9a472e2435`.	2024-11-07 14:58:03 +05:30
KRSHH	97a76c5e5b	Revert "Update ui.py" This reverts commit `df72a5431b`.	2024-11-07 14:57:47 +05:30
KRSHH	df72a5431b	Update ui.py	2024-10-29 14:53:19 +05:30
KRSHH	9a472e2435	Slight Performance Improvement avg 9.5 to avg 10	2024-10-29 14:07:47 +05:30
KRSHH	a581b81bd9	Change Switch/Slider positions	2024-10-28 16:53:55 +05:30
KRSHH	69b7970b87	Improved Camera Selection Menu	2024-10-28 13:50:44 +05:30
KRSHH	7fce1fd8b4	Update instructions.txt Links to Models in Instructions	2024-10-28 13:15:13 +05:30
KRSHH	c2918a52df	Minimum Windows Size	2024-10-28 13:12:02 +05:30
KRSHH	64c0f085b1	Change Switch positions	2024-10-28 12:20:54 +05:30
KRSHH	3c30ab8a5d	Opacity	2024-10-28 11:45:50 +05:30
KRSHH	acc8e778b6	Mouth Mask And UI	2024-10-28 10:56:01 +05:30
KRSHH	4b6f60f59b	Delete files from main	2024-10-21 19:15:21 +05:30
KRSHH	1178232268	Upload images to folder	2024-10-21 19:12:46 +05:30
KRSHH	ad918c5523	Shift Media to a folder	2024-10-21 19:10:21 +05:30
KRSHH	7b8d6171b7	Frame by Frame Navigation	2024-10-19 14:04:05 +05:30
KRSHH	6b86b0a72d	Preview Window Slider	2024-10-19 13:58:55 +05:30
KRSHH	936e78f93b	Fix Mapper for Live	2024-10-17 13:06:00 +05:30
KRSHH	aca0bcb7ce	Formatting Fix	2024-10-14 21:48:57 +05:30
KRSHH	966cb5a7df	Removed Package Repetition	2024-10-14 21:46:22 +05:30
KRSHH	1ab4bf06b1	Tips for DLC	2024-10-14 21:26:34 +05:30
KRSHH	6649e2a5df	remember/save switch states	2024-10-14 20:32:17 +05:30
KRSHH	72d4c9e9c4	Update metadata.py - 1.6	2024-10-14 19:50:09 +05:30
KRSHH	76d65247b7	improved performance enhancement	2024-10-14 19:49:51 +05:30
KRSHH	37f224cb47	FPS Counter	2024-10-14 19:46:48 +05:30
KRSHH	b58ffffd37	Fix the button position and bugs	2024-10-14 19:11:44 +05:30