Update README.md

Update requirements.txt

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,26 @@
+***[Remove this]The issue would be closed without notice and be considered spam if the template is not followed.***
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**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]
+ - 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
+

.gitignore

@@ -6,17 +6,22 @@ __pycache__/
 .todo
 *.log
 *.backup
-
+tf_env/
 *.png
 *.mp4
 *.mkv
 
 .tmp/
 temp/
+.venv/
 venv/
+env/
 workflow/
 gfpgan/
 models/inswapper_128.onnx
 models/GFPGANv1.4.pth
 *.onnx
 models/DMDNet.pth
+faceswap/
+.vscode/
+switch_states.json

.python-version

@@ -1 +0,0 @@
-3.10.14

CONTRIBUTING.md

@@ -0,0 +1,38 @@
+# 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.

README.md

@@ -1,163 +1,267 @@
-![demo-gif](demo.gif)
+<h1 align="center">Deep-Live-Cam</h1>
+
+<p align="center">
+  Real-time face swap and video deepfake with a single click and only a single image.
+</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>
+</p>
+
+<p align="center">
+  <img src="media/demo.gif" alt="Demo GIF" width="800">
+</p>
+
+##  Disclaimer
+
+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.
+
+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.
 
 
-## Disclaimer
-This software is meant to be a productive contribution to the rapidly growing AI-generated media industry. It will help artists with tasks such as animating a custom character or using the character as a model for clothing etc.
+## Quick Start - Pre-built (Windows / Nvidia)
 
-The developers of this software are aware of its possible unethical applications and are committed to take preventative measures against them. It has a built-in check which prevents the program from working on inappropriate media including but not limited to nudity, graphic content, sensitive material such as war footage etc. We will continue to develop this project in the positive direction while adhering to law and ethics. This project may be shut down or include watermarks on the output if requested by law.
+  <a href="https://hacksider.gumroad.com/l/vccdmm"> <img src="https://github.com/user-attachments/assets/7d993b32-e3e8-4cd3-bbfb-a549152ebdd5" width="285" height="77" />
 
-Users of this software are expected to use this software responsibly while abiding the local law. If face of a real person is being used, users are suggested to get consent from the concerned person and clearly mention that it is a deepfake when posting content online. Developers of this software will not be responsible for actions of end-users.
+##### This is the fastest build you can get if you have a discrete NVIDIA GPU.
 
-## How do I install it?
+## Quick Start - Pre-built (Mac / Silicon)
+    
+  <a href="https://krshh.gumroad.com/l/Deep-Live-Cam-Mac"> <img src="https://github.com/user-attachments/assets/d5d913b5-a7de-4609-96b9-979a5749a703" width="285" height="77" />
+ 
+###### These Pre-builts are perfect for non-technical users or those who don’t have time to, or can't manually install all the requirements. Just a heads-up: this is an open-source project, so you can also install it manually.
 
+## 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!
 
-### 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
--   python (3.10 recommended)
+## Features & Uses - Everything is in real-time
+
+### 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>
+
+## 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
+
+This is more likely to work on your computer but will be slower as it utilizes the CPU.
+
+**1. Set up Your Platform**
+
+-   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 Repository
-    https://github.com/hacksider/Deep-Live-Cam.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/)
 
-#### 3. Download Models
+**2. Clone the Repository**
 
- 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.onnx)
-
-Then put those 2 files on the "**models**" folder
-
-#### 4. Install dependency
-We highly recommend to work with a  `venv`  to avoid issues.
+```bash
+https://github.com/hacksider/Deep-Live-Cam.git
 ```
+
+**3. Download the 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)
+
+Place these files in the "**models**" folder.
+
+**4. Install Dependencies**
+
+We highly recommend using a `venv` to avoid issues.
+
+```bash
 pip install -r requirements.txt
 ```
-##### DONE!!! If you dont have any GPU, You should be able to run roop using `python run.py` command. Keep in mind that while running the program for first time, it will download some models which can take time depending on your network connection.
 
-### *Proceed if you want to use GPU Acceleration
-### CUDA Execution Provider (Nvidia)*
-
-1.  Install  [CUDA Toolkit 11.8](https://developer.nvidia.com/cuda-11-8-0-download-archive)
-    
-2.  Install dependencies:
-    
+**For macOS:** Install or upgrade the `python-tk` package:
 
+```bash
+brew install python-tk@3.10
 ```
+
+**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
+
+**CUDA Execution Provider (Nvidia)**
+
+1. Install [CUDA Toolkit 11.8.0](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 in case the provider is available:
+3. Usage:
 
-```
+```bash
 python run.py --execution-provider cuda
-
 ```
 
-### [](https://github.com/s0md3v/roop/wiki/2.-Acceleration#coreml-execution-provider-apple-silicon)CoreML Execution Provider (Apple Silicon)
+**CoreML Execution Provider (Apple Silicon)**
 
-1.  Install dependencies:
+1. Install dependencies:
 
-```
+```bash
 pip uninstall onnxruntime onnxruntime-silicon
 pip install onnxruntime-silicon==1.13.1
-
 ```
 
-2.  Usage in case the provider is available:
+2. Usage:
 
-```
+```bash
 python run.py --execution-provider coreml
-
 ```
 
-### [](https://github.com/s0md3v/roop/wiki/2.-Acceleration#coreml-execution-provider-apple-legacy)CoreML Execution Provider (Apple Legacy)
+**CoreML Execution Provider (Apple Legacy)**
 
-1.  Install dependencies:
+1. Install dependencies:
 
-```
+```bash
 pip uninstall onnxruntime onnxruntime-coreml
 pip install onnxruntime-coreml==1.13.1
-
 ```
 
-2.  Usage in case the provider is available:
+2. Usage:
 
-```
+```bash
 python run.py --execution-provider coreml
-
 ```
 
-### [](https://github.com/s0md3v/roop/wiki/2.-Acceleration#directml-execution-provider-windows)DirectML Execution Provider (Windows)
+**DirectML Execution Provider (Windows)**
 
-1.  Install dependencies:
+1. Install dependencies:
 
-```
+```bash
 pip uninstall onnxruntime onnxruntime-directml
 pip install onnxruntime-directml==1.15.1
-
 ```
 
-2.  Usage in case the provider is available:
+2. Usage:
 
-```
+```bash
 python run.py --execution-provider directml
-
 ```
 
-### [](https://github.com/s0md3v/roop/wiki/2.-Acceleration#openvino-execution-provider-intel)OpenVINO™ Execution Provider (Intel)
+**OpenVINO™ Execution Provider (Intel)**
 
-1.  Install dependencies:
+1. Install dependencies:
 
-```
+```bash
 pip uninstall onnxruntime onnxruntime-openvino
 pip install onnxruntime-openvino==1.15.0
-
 ```
 
-2.  Usage in case the provider is available:
+2. Usage:
 
-```
+```bash
 python run.py --execution-provider openvino
 ```
 
-## How do I use it?
-> Note: When you run this program for the first time, it will download some models ~300MB in size.
+</details>
 
-Executing `python run.py` command will launch this window:
-![gui-demo](instruction.png)
+## Usage
 
-Choose a face (image with desired face) and the target image/video (image/video in which you want to replace the face) and click on `Start`. Open file explorer and navigate to the directory you select your output to be in. You will find a directory named `<video_title>` where you can see the frames being swapped in realtime. Once the processing is done, it will create the output file. That's it.
+**1. Image/Video Mode**
 
-## For the webcam mode
-Just follow the clicks on the screenshot
-1. Select a face
-2. Click live
-3. Wait for a few second (it takes a longer time, usually 10 to 30 seconds before the preview shows up)
+-   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.
 
-![demo-gif](demo.gif)
+**2. Webcam Mode**
 
-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).
-
-You can now use the virtual camera output (uses pyvirtualcam) by turning on the `Virtual Cam Output (OBS)` toggle which should output to the OBS Virtual Camera. Note: this may not work on macOS. You will get a preview as before, but now you will also have a virtual camera output which can be used in applications like Zoom.
-
-Additional command line arguments are given below. To learn out what they do, check [this guide](https://github.com/s0md3v/roop/wiki/Advanced-Options).
+-   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.
 
+## Command Line Arguments (Unmaintained)
 
 ```
 options:
   -h, --help                                               show this help message and exit
-  -s SOURCE_PATH, --source SOURCE_PATH                     select an source image
-  -t TARGET_PATH, --target TARGET_PATH                     select an target image or video
+  -s SOURCE_PATH, --source SOURCE_PATH                     select a source image
+  -t TARGET_PATH, --target TARGET_PATH                     select a target image or video
   -o OUTPUT_PATH, --output OUTPUT_PATH                     select output file or directory
-  --frame-processor FRAME_PROCESSOR [FRAME_PROCESSOR ...]  frame processors (choices: face_swapper, face_enhancer, super_resolution...)
+  --frame-processor FRAME_PROCESSOR [FRAME_PROCESSOR ...]  frame processors (choices: face_swapper, face_enhancer, ...)
   --keep-fps                                               keep original fps
   --keep-audio                                             keep original audio
   --keep-frames                                            keep temporary frames
   --many-faces                                             process every face
+  --map-faces                                              map source target faces
+  --mouth-mask                                             mask the mouth region
   --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
@@ -165,24 +269,56 @@ options:
   --max-memory MAX_MEMORY                                  maximum amount of RAM in GB
   --execution-provider {cpu} [{cpu} ...]                   available execution provider (choices: cpu, ...)
   --execution-threads EXECUTION_THREADS                    number of execution threads
-  --headless                                               run in headless mode
-  --enhancer-upscale-factor                                Sets the upscale factor for the enhancer. Only applies if `face_enhancer` is set as a frame-processor
-  --source-image-scaling-factor                            Set the upscale factor for source images. Only applies if `face_swapper` is set as a frame-processor
-  -r SCALE, --super-resolution-scale-factor SCALE          Super resolution scale factor, choices are 2, 3, 4
   -v, --version                                            show program's version number and exit
 ```
 
 Looking for a CLI mode? Using the -s/--source argument will make the run program in cli mode.
 
-To improve the video quality, you can use the `super_resolution` frame processor after swapping the faces. It will enhance the video quality by 2x, 3x or 4x. You can set the upscale factor using the `-r` or `--super-resolution-scale-factor` argument. 
-Processing time will increase with the upscale factor, but it's quite quick.
+## Press
 
-```
+**We are always open to criticism and are ready to improve, that's why we didn't cherry-pick anything.**
+
+ - [*"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
-- [henryruhs](https://github.com/henryruhs): for being an irreplaceable contributor to the project
-- [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.
-- [havok2-htwo](https://github.com/havok2-htwo) : for sharing the code for webcam
-- [GosuDRM](https://github.com/GosuDRM/nsfw-roop) : for uncensoring roop
-- and all developers behind libraries used in this project.
+
+-   [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)
+
+## Contributions
+
+![Alt](https://repobeats.axiom.co/api/embed/fec8e29c45dfdb9c5916f3a7830e1249308d20e1.svg "Repobeats analytics image")
+
+## Stars to the Moon 🚀
+
+<a href="https://star-history.com/#hacksider/deep-live-cam&Date">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=hacksider/deep-live-cam&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=hacksider/deep-live-cam&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=hacksider/deep-live-cam&type=Date" />
+ </picture>
+</a>
+
+

locales/zh.json

@@ -0,0 +1,46 @@
+{
+    "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。"
+}

models/instructions.txt

@@ -1 +1,4 @@
-just put the models in this folder
+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

modules/capturer.py

@@ -1,38 +1,32 @@
-from typing import Any, Optional
+from typing import Any
 import cv2
+import modules.globals  # Import the globals to check the color correction toggle
 
-def get_video_frame(video_path: str, frame_number: int = 0) -> Optional[Any]:
-    """Retrieve a specific frame from a video."""
+
+def get_video_frame(video_path: str, frame_number: int = 0) -> Any:
     capture = cv2.VideoCapture(video_path)
 
-    if not capture.isOpened():
-        print(f"Error: Cannot open video file {video_path}")
-        return None
-
-    frame_total = int(capture.get(cv2.CAP_PROP_FRAME_COUNT))
-
-    # Ensure frame_number is within the valid range
-    frame_number = max(0, min(frame_number, frame_total - 1))
-
-    capture.set(cv2.CAP_PROP_POS_FRAMES, frame_number)
-    has_frame, frame = capture.read()
-    capture.release()
-
-    if not has_frame:
-        print(f"Error: Cannot read frame {frame_number} from {video_path}")
-        return None
+    # Set MJPEG format to ensure correct color space handling
+    capture.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*'MJPG'))
     
-    return frame
+    # Only force RGB conversion if color correction is enabled
+    if modules.globals.color_correction:
+        capture.set(cv2.CAP_PROP_CONVERT_RGB, 1)
+    
+    frame_total = capture.get(cv2.CAP_PROP_FRAME_COUNT)
+    capture.set(cv2.CAP_PROP_POS_FRAMES, min(frame_total, frame_number - 1))
+    has_frame, frame = capture.read()
+
+    if has_frame and modules.globals.color_correction:
+        # Convert the frame color if necessary
+        frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+
+    capture.release()
+    return frame if has_frame else None
+
 
 def get_video_frame_total(video_path: str) -> int:
-    """Get the total number of frames in a video."""
     capture = cv2.VideoCapture(video_path)
-
-    if not capture.isOpened():
-        print(f"Error: Cannot open video file {video_path}")
-        return 0
-    
-    frame_total = int(capture.get(cv2.CAP_PROP_FRAME_COUNT))
+    video_frame_total = int(capture.get(cv2.CAP_PROP_FRAME_COUNT))
     capture.release()
-
-    return frame_total
+    return video_frame_total

modules/cluster_analysis.py

@@ -0,0 +1,32 @@
+import numpy as np
+from sklearn.cluster import KMeans
+from sklearn.metrics import silhouette_score
+from typing import Any
+
+
+def find_cluster_centroids(embeddings, max_k=10) -> Any:
+    inertia = []
+    cluster_centroids = []
+    K = range(1, max_k+1)
+
+    for k in K:
+        kmeans = KMeans(n_clusters=k, random_state=0)
+        kmeans.fit(embeddings)
+        inertia.append(kmeans.inertia_)
+        cluster_centroids.append({"k": k, "centroids": kmeans.cluster_centers_})
+
+    diffs = [inertia[i] - inertia[i+1] for i in range(len(inertia)-1)]
+    optimal_centroids = cluster_centroids[diffs.index(max(diffs)) + 1]['centroids']
+
+    return optimal_centroids
+
+def find_closest_centroid(centroids: list, normed_face_embedding) -> list:
+    try:
+        centroids = np.array(centroids)
+        normed_face_embedding = np.array(normed_face_embedding)
+        similarities = np.dot(centroids, normed_face_embedding)
+        closest_centroid_index = np.argmax(similarities)
+        
+        return closest_centroid_index, centroids[closest_centroid_index]
+    except ValueError:
+        return None

modules/core.py

@@ -1,17 +1,16 @@
 import os
 import sys
+# single thread doubles cuda performance - needs to be set before torch import
+if any(arg.startswith('--execution-provider') for arg in sys.argv):
+    os.environ['OMP_NUM_THREADS'] = '1'
+# reduce tensorflow log level
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
 import warnings
+from typing import List
 import platform
 import signal
 import shutil
 import argparse
-from typing import List
-
-# Set environment variables for CUDA performance and TensorFlow logging
-if any(arg.startswith('--execution-provider') for arg in sys.argv):
-    os.environ['OMP_NUM_THREADS'] = '1'
-os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
-
 import torch
 import onnxruntime
 import tensorflow
@@ -20,73 +19,40 @@ import modules.globals
 import modules.metadata
 import modules.ui as ui
 from modules.processors.frame.core import get_frame_processors_modules
-from modules.utilities import (
-    has_image_extension,
-    is_image,
-    is_video,
-    detect_fps,
-    create_video,
-    extract_frames,
-    get_temp_frame_paths,
-    restore_audio,
-    create_temp,
-    move_temp,
-    clean_temp,
-    normalize_output_path
-)
+from modules.utilities import has_image_extension, is_image, is_video, detect_fps, create_video, extract_frames, get_temp_frame_paths, restore_audio, create_temp, move_temp, clean_temp, normalize_output_path
+
+if 'ROCMExecutionProvider' in modules.globals.execution_providers:
+    del torch
 
-# Filter warnings
 warnings.filterwarnings('ignore', category=FutureWarning, module='insightface')
 warnings.filterwarnings('ignore', category=UserWarning, module='torchvision')
 
-# Cross-platform resource management
-if platform.system() == 'Darwin' and 'ROCMExecutionProvider' in modules.globals.execution_providers:
-    del torch
-
 
 def parse_args() -> None:
     signal.signal(signal.SIGINT, lambda signal_number, frame: destroy())
     program = argparse.ArgumentParser()
-    program.add_argument('-s', '--source', help='Select a source image', dest='source_path')
-    program.add_argument('-t', '--target', help='Select a target image or video', dest='target_path')
-    program.add_argument('-o', '--output', help='Select output file or directory', dest='output_path')
-    program.add_argument('--frame-processor', help='Pipeline of frame processors', dest='frame_processor',
-                         default=['face_swapper'], choices=['face_swapper', 'face_enhancer', 'super_resolution'],
-                         nargs='+')
-    program.add_argument('--keep-fps', help='Keep original fps', dest='keep_fps', action='store_true', default=False)
-    program.add_argument('--keep-audio', help='Keep original audio', dest='keep_audio', action='store_true',
-                         default=True)
-    program.add_argument('--keep-frames', help='Keep temporary frames', dest='keep_frames', action='store_true',
-                         default=False)
-    program.add_argument('--many-faces', help='Process every face', dest='many_faces', 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('--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())
-    program.add_argument('--execution-provider', help='Execution provider', dest='execution_provider', default=['cpu'],
-                         choices=suggest_execution_providers(), nargs='+')
-    program.add_argument('--execution-threads', help='Number of execution threads', dest='execution_threads', type=int,
-                         default=suggest_execution_threads())
-    program.add_argument('--headless', help='Run in headless mode', dest='headless', default=False, action='store_true')
-    program.add_argument('--enhancer-upscale-factor',
-                         help='Sets the upscale factor for the enhancer. Only applies if `face_enhancer` is set as a frame-processor',
-                         dest='enhancer_upscale_factor', type=int, default=1)
-    program.add_argument('--source-image-scaling-factor', help='Set the upscale factor for source images',
-                         dest='source_image_scaling_factor', default=2, type=int)
-    program.add_argument('-r', '--super-resolution-scale-factor', dest='super_resolution_scale_factor',
-                         help='Set the upscale factor for super resolution', default=4, choices=[2, 3, 4], type=int)
-    program.add_argument('-v', '--version', action='version',
-                         version=f'{modules.metadata.name} {modules.metadata.version}')
+    program.add_argument('-s', '--source', help='select an source image', dest='source_path')
+    program.add_argument('-t', '--target', help='select an target image or video', dest='target_path')
+    program.add_argument('-o', '--output', help='select output file or directory', dest='output_path')
+    program.add_argument('--frame-processor', help='pipeline of frame processors', dest='frame_processor', default=['face_swapper'], choices=['face_swapper', 'face_enhancer'], nargs='+')
+    program.add_argument('--keep-fps', help='keep original fps', dest='keep_fps', action='store_true', default=False)
+    program.add_argument('--keep-audio', help='keep original audio', dest='keep_audio', action='store_true', default=True)
+    program.add_argument('--keep-frames', help='keep temporary frames', dest='keep_frames', action='store_true', default=False)
+    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())
+    program.add_argument('--execution-provider', help='execution provider', dest='execution_provider', default=['cpu'], choices=suggest_execution_providers(), nargs='+')
+    program.add_argument('--execution-threads', help='number of execution threads', dest='execution_threads', type=int, default=suggest_execution_threads())
+    program.add_argument('-v', '--version', action='version', version=f'{modules.metadata.name} {modules.metadata.version}')
 
-    # Register deprecated args
+    # register deprecated args
     program.add_argument('-f', '--face', help=argparse.SUPPRESS, dest='source_path_deprecated')
     program.add_argument('--cpu-cores', help=argparse.SUPPRESS, dest='cpu_cores_deprecated', type=int)
     program.add_argument('--gpu-vendor', help=argparse.SUPPRESS, dest='gpu_vendor_deprecated')
@@ -96,14 +62,16 @@ def parse_args() -> None:
 
     modules.globals.source_path = args.source_path
     modules.globals.target_path = args.target_path
-    modules.globals.output_path = normalize_output_path(modules.globals.source_path, modules.globals.target_path,
-                                                        args.output_path)
+    modules.globals.output_path = normalize_output_path(modules.globals.source_path, modules.globals.target_path, args.output_path)
     modules.globals.frame_processors = args.frame_processor
     modules.globals.headless = args.source_path or args.target_path or args.output_path
     modules.globals.keep_fps = args.keep_fps
     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
     modules.globals.video_quality = args.video_quality
     modules.globals.live_mirror = args.live_mirror
@@ -111,26 +79,19 @@ 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.headless = args.headless
-    modules.globals.enhancer_upscale_factor = args.enhancer_upscale_factor
-    modules.globals.source_image_scaling_factor = args.source_image_scaling_factor
-    modules.globals.sr_scale_factor = args.super_resolution_scale_factor
-    # Handle face enhancer tumbler
-    modules.globals.fp_ui['face_enhancer'] = 'face_enhancer' in args.frame_processor
+    modules.globals.lang = args.lang
 
-    modules.globals.nsfw = False
+    #for ENHANCER tumbler:
+    if 'face_enhancer' in args.frame_processor:
+        modules.globals.fp_ui['face_enhancer'] = True
+    else:
+        modules.globals.fp_ui['face_enhancer'] = False
 
-    # Handle deprecated arguments
-    handle_deprecated_args(args)
-
-
-def handle_deprecated_args(args) -> None:
-    """Handle deprecated arguments by translating them to the new format."""
+    # translate deprecated args
     if args.source_path_deprecated:
         print('\033[33mArgument -f and --face are deprecated. Use -s and --source instead.\033[0m')
         modules.globals.source_path = args.source_path_deprecated
-        modules.globals.output_path = normalize_output_path(args.source_path_deprecated, modules.globals.target_path,
-                                                            args.output_path)
+        modules.globals.output_path = normalize_output_path(args.source_path_deprecated, modules.globals.target_path, args.output_path)
     if args.cpu_cores_deprecated:
         print('\033[33mArgument --cpu-cores is deprecated. Use --execution-threads instead.\033[0m')
         modules.globals.execution_threads = args.cpu_cores_deprecated
@@ -141,7 +102,7 @@ def handle_deprecated_args(args) -> None:
         print('\033[33mArgument --gpu-vendor nvidia is deprecated. Use --execution-provider cuda instead.\033[0m')
         modules.globals.execution_providers = decode_execution_providers(['cuda'])
     if args.gpu_vendor_deprecated == 'amd':
-        print('\033[33mArgument --gpu-vendor amd is deprecated. Use --execution-provider rocm instead.\033[0m')
+        print('\033[33mArgument --gpu-vendor amd is deprecated. Use --execution-provider cuda instead.\033[0m')
         modules.globals.execution_providers = decode_execution_providers(['rocm'])
     if args.gpu_threads_deprecated:
         print('\033[33mArgument --gpu-threads is deprecated. Use --execution-threads instead.\033[0m')
@@ -149,22 +110,18 @@ def handle_deprecated_args(args) -> None:
 
 
 def encode_execution_providers(execution_providers: List[str]) -> List[str]:
-    return [provider.replace('ExecutionProvider', '').lower() for provider in execution_providers]
+    return [execution_provider.replace('ExecutionProvider', '').lower() for execution_provider in execution_providers]
 
 
 def decode_execution_providers(execution_providers: List[str]) -> List[str]:
-    available_providers = onnxruntime.get_available_providers()
-    encoded_providers = encode_execution_providers(available_providers)
-
-    selected_providers = [available_providers[encoded_providers.index(req)] for req in execution_providers
-                          if req in encoded_providers]
-
-    # Default to CPU if no suitable providers are found
-    return selected_providers if selected_providers else ['CPUExecutionProvider']
+    return [provider for provider, encoded_execution_provider in zip(onnxruntime.get_available_providers(), encode_execution_providers(onnxruntime.get_available_providers()))
+            if any(execution_provider in encoded_execution_provider for execution_provider in execution_providers)]
 
 
 def suggest_max_memory() -> int:
-    return 4 if platform.system().lower() == 'darwin' else 16
+    if platform.system().lower() == 'darwin':
+        return 4
+    return 16
 
 
 def suggest_execution_providers() -> List[str]:
@@ -172,43 +129,34 @@ def suggest_execution_providers() -> List[str]:
 
 
 def suggest_execution_threads() -> int:
-    if 'dml' in modules.globals.execution_providers:
+    if 'DmlExecutionProvider' in modules.globals.execution_providers:
         return 1
-    if 'rocm' in modules.globals.execution_providers:
+    if 'ROCMExecutionProvider' in modules.globals.execution_providers:
         return 1
     return 8
 
 
 def limit_resources() -> None:
-    # Prevent TensorFlow memory leak
+    # prevent tensorflow memory leak
     gpus = tensorflow.config.experimental.list_physical_devices('GPU')
     for gpu in gpus:
         tensorflow.config.experimental.set_memory_growth(gpu, True)
-
-    # Limit memory usage
+    # limit memory usage
     if modules.globals.max_memory:
         memory = modules.globals.max_memory * 1024 ** 3
         if platform.system().lower() == 'darwin':
-            memory = modules.globals.max_memory * 1024 ** 3
-        elif platform.system().lower() == 'windows':
+            memory = modules.globals.max_memory * 1024 ** 6
+        if platform.system().lower() == 'windows':
             import ctypes
             kernel32 = ctypes.windll.kernel32
             kernel32.SetProcessWorkingSetSize(-1, ctypes.c_size_t(memory), ctypes.c_size_t(memory))
         else:
             import resource
-            try:
-                soft, hard = resource.getrlimit(resource.RLIMIT_DATA)
-                if memory > hard:
-                    print(
-                        f"Warning: Requested memory limit {memory / (1024 ** 3)} GB exceeds system's hard limit. Setting to maximum allowed {hard / (1024 ** 3)} GB.")
-                    memory = hard
-                resource.setrlimit(resource.RLIMIT_DATA, (memory, memory))
-            except ValueError as e:
-                print(f"Warning: Could not set memory limit: {e}. Continuing with default limits.")
+            resource.setrlimit(resource.RLIMIT_DATA, (memory, memory))
 
 
 def release_resources() -> None:
-    if 'cuda' in modules.globals.execution_providers:
+    if 'CUDAExecutionProvider' in modules.globals.execution_providers:
         torch.cuda.empty_cache()
 
 
@@ -219,86 +167,52 @@ def pre_check() -> bool:
     if not shutil.which('ffmpeg'):
         update_status('ffmpeg is not installed.')
         return False
-    if 'cuda' in modules.globals.execution_providers and not torch.cuda.is_available():
-        update_status('CUDA is not available. Please check your GPU or CUDA installation.')
-        return False
     return True
 
 
 def update_status(message: str, scope: str = 'DLC.CORE') -> None:
     print(f'[{scope}] {message}')
-    if not modules.globals.headless and ui.status_label:
+    if not modules.globals.headless:
         ui.update_status(message)
 
-
 def start() -> None:
     for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
         if not frame_processor.pre_start():
             return
-
-    # Process image to image
+    update_status('Processing...')
+    # process image to image
     if has_image_extension(modules.globals.target_path):
-        process_image_to_image()
+        if modules.globals.nsfw_filter and ui.check_and_ignore_nsfw(modules.globals.target_path, destroy):
+            return
+        try:
+            shutil.copy2(modules.globals.target_path, modules.globals.output_path)
+        except Exception as e:
+            print("Error copying file:", str(e))
+        for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
+            update_status('Progressing...', frame_processor.NAME)
+            frame_processor.process_image(modules.globals.source_path, modules.globals.output_path, modules.globals.output_path)
+            release_resources()
+        if is_image(modules.globals.target_path):
+            update_status('Processing to image succeed!')
+        else:
+            update_status('Processing to image failed!')
+        return
+    # process image to videos
+    if modules.globals.nsfw_filter and ui.check_and_ignore_nsfw(modules.globals.target_path, destroy):
         return
 
-    # Process image to video
-    process_image_to_video()
+    if not modules.globals.map_faces:
+        update_status('Creating temp resources...')
+        create_temp(modules.globals.target_path)
+        update_status('Extracting frames...')
+        extract_frames(modules.globals.target_path)
 
-
-def process_image_to_image() -> None:
-    if modules.globals.nsfw:
-        from modules.predicter import predict_image
-        if predict_image(modules.globals.target_path):
-            destroy(to_quit=False)
-            update_status('Processing to image ignored!')
-            return
-
-    try:
-        shutil.copy2(modules.globals.target_path, modules.globals.output_path)
-    except Exception as e:
-        print("Error copying file:", str(e))
-
-    for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
-        update_status('Processing...', frame_processor.NAME)
-        frame_processor.process_image(modules.globals.source_path, modules.globals.output_path,
-                                      modules.globals.output_path)
-        release_resources()
-
-    if is_image(modules.globals.target_path):
-        update_status('Processing to image succeeded!')
-    else:
-        update_status('Processing to image failed!')
-
-
-def process_image_to_video() -> None:
-    if modules.globals.nsfw:
-        from modules.predicter import predict_video
-        if predict_video(modules.globals.target_path):
-            destroy(to_quit=False)
-            update_status('Processing to video ignored!')
-            return
-
-    update_status('Creating temporary resources...')
-    create_temp(modules.globals.target_path)
-    update_status('Extracting frames...')
-    extract_frames(modules.globals.target_path)
     temp_frame_paths = get_temp_frame_paths(modules.globals.target_path)
     for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
-        update_status('Processing...', frame_processor.NAME)
+        update_status('Progressing...', frame_processor.NAME)
         frame_processor.process_video(modules.globals.source_path, temp_frame_paths)
         release_resources()
-
-    handle_video_fps()
-    handle_video_audio()
-    clean_temp(modules.globals.target_path)
-
-    if is_video(modules.globals.target_path):
-        update_status('Processing to video succeeded!')
-    else:
-        update_status('Processing to video failed!')
-
-
-def handle_video_fps() -> None:
+    # handles fps
     if modules.globals.keep_fps:
         update_status('Detecting fps...')
         fps = detect_fps(modules.globals.target_path)
@@ -307,9 +221,7 @@ def handle_video_fps() -> None:
     else:
         update_status('Creating video with 30.0 fps...')
         create_video(modules.globals.target_path)
-
-
-def handle_video_audio() -> None:
+    # handle audio
     if modules.globals.keep_audio:
         if modules.globals.keep_fps:
             update_status('Restoring audio...')
@@ -318,6 +230,12 @@ def handle_video_audio() -> None:
         restore_audio(modules.globals.target_path, modules.globals.output_path)
     else:
         move_temp(modules.globals.target_path, modules.globals.output_path)
+    # clean and validate
+    clean_temp(modules.globals.target_path)
+    if is_video(modules.globals.target_path):
+        update_status('Processing to video succeed!')
+    else:
+        update_status('Processing to video failed!')
 
 
 def destroy(to_quit=True) -> None:
@@ -327,20 +245,15 @@ def destroy(to_quit=True) -> None:
 
 
 def run() -> None:
-    try:
-        parse_args()
-        if not pre_check():
+    parse_args()
+    if not pre_check():
+        return
+    for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
+        if not frame_processor.pre_check():
             return
-        for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
-            if not frame_processor.pre_check():
-                return
-        limit_resources()
-        if modules.globals.headless:
-            start()
-        else:
-            window = ui.init(start, destroy)
-            window.mainloop()
-    except Exception as e:
-        print(f"UI initialization failed: {str(e)}")
-        update_status(f"UI initialization failed: {str(e)}")
-        destroy()  # Ensure any resources are cleaned up on failure
+    limit_resources()
+    if modules.globals.headless:
+        start()
+    else:
+        window = ui.init(start, destroy, modules.globals.lang)
+        window.mainloop()

modules/face_analyser.py

@@ -1,27 +1,189 @@
-from typing import Any, Optional
+import os
+import shutil
+from typing import Any
 import insightface
 
+import cv2
+import numpy as np
 import modules.globals
+from tqdm import tqdm
 from modules.typing import Frame
+from modules.cluster_analysis import find_cluster_centroids, find_closest_centroid
+from modules.utilities import get_temp_directory_path, create_temp, extract_frames, clean_temp, get_temp_frame_paths
+from pathlib import Path
 
-FACE_ANALYSER: Optional[insightface.app.FaceAnalysis] = None
+FACE_ANALYSER = None
 
-def get_face_analyser() -> insightface.app.FaceAnalysis:
+
+def get_face_analyser() -> Any:
     global FACE_ANALYSER
 
     if FACE_ANALYSER is None:
-        FACE_ANALYSER = insightface.app.FaceAnalysis(
-            name='buffalo_l', 
-            providers=modules.globals.execution_providers
-        )
+        FACE_ANALYSER = insightface.app.FaceAnalysis(name='buffalo_l', providers=modules.globals.execution_providers)
         FACE_ANALYSER.prepare(ctx_id=0, det_size=(640, 640))
-    
     return FACE_ANALYSER
 
-def get_one_face(frame: Frame) -> Optional[Any]:
-    faces = get_face_analyser().get(frame)
-    return min(faces, key=lambda x: x.bbox[0], default=None)
 
-def get_many_faces(frame: Frame) -> Optional[Any]:
-    faces = get_face_analyser().get(frame)
-    return faces if faces else None
+def get_one_face(frame: Frame) -> Any:
+    face = get_face_analyser().get(frame)
+    try:
+        return min(face, key=lambda x: x.bbox[0])
+    except ValueError:
+        return None
+
+
+def get_many_faces(frame: Frame) -> Any:
+    try:
+        return get_face_analyser().get(frame)
+    except IndexError:
+        return None
+
+def has_valid_map() -> bool:
+    for map in modules.globals.source_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:
+        if "source" in map:
+            return map['source']['face']
+    return None
+
+def simplify_maps() -> Any:
+    centroids = []
+    faces = []
+    for map in modules.globals.source_target_map:
+        if "source" in map and "target" in map:
+            centroids.append(map['target']['face'].normed_embedding)
+            faces.append(map['source']['face'])
+
+    modules.globals.simple_map = {'source_faces': faces, 'target_embeddings': centroids}
+    return None
+
+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']
+
+        modules.globals.source_target_map.append({
+                'id' : max_id + 1
+                })
+    except ValueError:
+        return None
+    
+def get_unique_faces_from_target_image() -> Any:
+    try:
+        modules.globals.source_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({
+                'id' : i, 
+                'target' : {
+                            'cv2' : target_frame[int(y_min):int(y_max), int(x_min):int(x_max)],
+                            'face' : face
+                            }
+                })
+            i = i + 1
+    except ValueError:
+        return None
+    
+    
+def get_unique_faces_from_target_video() -> Any:
+    try:
+        modules.globals.source_target_map = []
+        frame_face_embeddings = []
+        face_embeddings = []
+    
+        print('Creating temp resources...')
+        clean_temp(modules.globals.target_path)
+        create_temp(modules.globals.target_path)
+        print('Extracting frames...')
+        extract_frames(modules.globals.target_path)
+
+        temp_frame_paths = get_temp_frame_paths(modules.globals.target_path)
+
+        i = 0
+        for temp_frame_path in tqdm(temp_frame_paths, desc="Extracting face embeddings from frames"):
+            temp_frame = cv2.imread(temp_frame_path)
+            many_faces = get_many_faces(temp_frame)
+
+            for face in many_faces:
+                face_embeddings.append(face.normed_embedding)
+            
+            frame_face_embeddings.append({'frame': i, 'faces': many_faces, 'location': temp_frame_path})
+            i += 1
+
+        centroids = find_cluster_centroids(face_embeddings)
+
+        for frame in frame_face_embeddings:
+            for face in frame['faces']:
+                closest_centroid_index, _ = find_closest_centroid(centroids, face.normed_embedding)
+                face['target_centroid'] = closest_centroid_index
+
+        for i in range(len(centroids)):
+            modules.globals.source_target_map.append({
+                'id' : i
+            })
+
+            temp = []
+            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
+
+        # dump_faces(centroids, frame_face_embeddings)
+        default_target_face()
+    except ValueError:
+        return None
+    
+
+def default_target_face():
+    for map in modules.globals.source_target_map:
+        best_face = None
+        best_frame = None
+        for frame in map['target_faces_in_frame']:
+            if len(frame['faces']) > 0:
+                best_face = frame['faces'][0]
+                best_frame = frame
+                break
+
+        for frame in map['target_faces_in_frame']:
+            for face in frame['faces']:
+                if face['det_score'] > best_face['det_score']:
+                    best_face = face
+                    best_frame = frame
+
+        x_min, y_min, x_max, y_max = best_face['bbox']
+
+        target_frame = cv2.imread(best_frame['location'])
+        map['target'] = {
+                        'cv2' : target_frame[int(y_min):int(y_max), int(x_min):int(x_max)],
+                        'face' : best_face
+                        }
+
+
+def dump_faces(centroids: Any, frame_face_embeddings: list):
+    temp_directory_path = get_temp_directory_path(modules.globals.target_path)
+
+    for i in range(len(centroids)):
+        if os.path.exists(temp_directory_path + f"/{i}") and os.path.isdir(temp_directory_path + f"/{i}"):
+            shutil.rmtree(temp_directory_path + f"/{i}")
+        Path(temp_directory_path + f"/{i}").mkdir(parents=True, exist_ok=True)
+
+        for frame in tqdm(frame_face_embeddings, desc=f"Copying faces to temp/./{i}"):
+            temp_frame = cv2.imread(frame['location'])
+
+            j = 0
+            for face in frame['faces']:
+                if face['target_centroid'] == i:
+                    x_min, y_min, x_max, y_max = face['bbox']
+
+                    if temp_frame[int(y_min):int(y_max), int(x_min):int(x_max)].size > 0:
+                        cv2.imwrite(temp_directory_path + f"/{i}/{frame['frame']}_{j}.png", temp_frame[int(y_min):int(y_max), int(x_min):int(x_max)])
+                j += 1

modules/gettext.py

@@ -0,0 +1,26 @@
+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)

modules/globals.py

@@ -1,35 +1,43 @@
 import os
-from typing import List, Dict
+from typing import List, Dict, Any
 
 ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
-WORKFLOW_DIR = os.path.join(ROOT_DIR, 'workflow')
+WORKFLOW_DIR = os.path.join(ROOT_DIR, "workflow")
 
 file_types = [
-    ('Image', ('*.png','*.jpg','*.jpeg','*.gif','*.bmp')),
-    ('Video', ('*.mp4','*.mkv'))
+    ("Image", ("*.png", "*.jpg", "*.jpeg", "*.gif", "*.bmp")),
+    ("Video", ("*.mp4", "*.mkv")),
 ]
 
+source_target_map = []
+simple_map = {}
+
 source_path = None
 target_path = None
 output_path = None
 frame_processors: List[str] = []
-keep_fps = None
-keep_audio = None
-keep_frames = None
-many_faces = None
+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
 video_encoder = None
 video_quality = None
-live_mirror = None
-live_resizable = None
+live_mirror = False
+live_resizable = True
 max_memory = None
 execution_providers: List[str] = []
 execution_threads = None
 headless = None
-log_level = 'error'
-fp_ui: Dict[str, bool] = {}
-nsfw = None
+log_level = "error"
+fp_ui: Dict[str, bool] = {"face_enhancer": False}
 camera_input_combobox = None
 webcam_preview_running = False
-enhancer_upscale_factor = 1
-source_image_scaling_factor = 2
-sr_scale_factor = 4
+show_fps = False
+mouth_mask = False
+show_mouth_mask_box = False
+mask_feather_ratio = 8
+mask_down_size = 0.50
+mask_size = 1

modules/metadata.py

@@ -1,3 +1,3 @@
-name = 'Deep Live Cam'
-version = '1.3.0'
-edition = 'Portable'
+name = 'Deep-Live-Cam'
+version = '1.8'
+edition = 'GitHub Edition'

modules/predicter.py

@@ -1,6 +1,9 @@
-import numpy as np
+import numpy
 import opennsfw2
 from PIL import Image
+import cv2  # Add OpenCV import
+import modules.globals  # Import globals to access the color correction toggle
+
 from modules.typing import Frame
 
 MAX_PROBABILITY = 0.85
@@ -9,17 +12,24 @@ MAX_PROBABILITY = 0.85
 model = None
 
 def predict_frame(target_frame: Frame) -> bool:
-    global model
-    if model is None: model = opennsfw2.make_open_nsfw_model()
+    # Convert the frame to RGB before processing if color correction is enabled
+    if modules.globals.color_correction:
+        target_frame = cv2.cvtColor(target_frame, cv2.COLOR_BGR2RGB)
+        
     image = Image.fromarray(target_frame)
     image = opennsfw2.preprocess_image(image, opennsfw2.Preprocessing.YAHOO)
-    views = np.expand_dims(image, axis=0)
+    global model
+    if model is None: 
+        model = opennsfw2.make_open_nsfw_model()
+        
+    views = numpy.expand_dims(image, axis=0)
     _, probability = model.predict(views)[0]
     return probability > MAX_PROBABILITY
 
+
 def predict_image(target_path: str) -> bool:
-    probability = opennsfw2.predict_image(target_path)
-    return probability > MAX_PROBABILITY
+    return opennsfw2.predict_image(target_path) > MAX_PROBABILITY
+
 
 def predict_video(target_path: str) -> bool:
     _, probabilities = opennsfw2.predict_video_frames(video_path=target_path, frame_interval=100)

modules/processors/frame/core.py

@@ -17,56 +17,57 @@ FRAME_PROCESSORS_INTERFACE = [
     'process_video'
 ]
 
-def load_frame_processor_module(frame_processor: str) -> ModuleType:
+
+def load_frame_processor_module(frame_processor: str) -> Any:
     try:
         frame_processor_module = importlib.import_module(f'modules.processors.frame.{frame_processor}')
-        # Ensure all required methods are present
         for method_name in FRAME_PROCESSORS_INTERFACE:
             if not hasattr(frame_processor_module, method_name):
-                raise AttributeError(f"Missing required method {method_name} in {frame_processor} module.")
+                sys.exit()
     except ImportError:
-        print(f"Error: Frame processor '{frame_processor}' not found.")
-        sys.exit(1)
-    except AttributeError as e:
-        print(e)
-        sys.exit(1)
-    
+        print(f"Frame processor {frame_processor} not found")
+        sys.exit()
     return frame_processor_module
 
+
 def get_frame_processors_modules(frame_processors: List[str]) -> List[ModuleType]:
     global FRAME_PROCESSORS_MODULES
 
     if not FRAME_PROCESSORS_MODULES:
-        FRAME_PROCESSORS_MODULES = [load_frame_processor_module(fp) for fp in frame_processors]
-    
+        for frame_processor in frame_processors:
+            frame_processor_module = load_frame_processor_module(frame_processor)
+            FRAME_PROCESSORS_MODULES.append(frame_processor_module)
     set_frame_processors_modules_from_ui(frame_processors)
     return FRAME_PROCESSORS_MODULES
 
 def set_frame_processors_modules_from_ui(frame_processors: List[str]) -> None:
     global FRAME_PROCESSORS_MODULES
     for frame_processor, state in modules.globals.fp_ui.items():
-        if state and frame_processor not in frame_processors:
-            module = load_frame_processor_module(frame_processor)
-            FRAME_PROCESSORS_MODULES.append(module)
+        if state == True and frame_processor not in frame_processors:
+            frame_processor_module = load_frame_processor_module(frame_processor)
+            FRAME_PROCESSORS_MODULES.append(frame_processor_module)
             modules.globals.frame_processors.append(frame_processor)
-        elif not state and frame_processor in frame_processors:
-            module = load_frame_processor_module(frame_processor)
-            FRAME_PROCESSORS_MODULES.remove(module)
-            modules.globals.frame_processors.remove(frame_processor)
+        if state == False:
+            try:
+                frame_processor_module = load_frame_processor_module(frame_processor)
+                FRAME_PROCESSORS_MODULES.remove(frame_processor_module)
+                modules.globals.frame_processors.remove(frame_processor)
+            except:
+                pass
 
 def multi_process_frame(source_path: str, temp_frame_paths: List[str], process_frames: Callable[[str, List[str], Any], None], progress: Any = None) -> None:
     with ThreadPoolExecutor(max_workers=modules.globals.execution_threads) as executor:
-        futures = [executor.submit(process_frames, source_path, [path], progress) for path in temp_frame_paths]
+        futures = []
+        for path in temp_frame_paths:
+            future = executor.submit(process_frames, source_path, [path], progress)
+            futures.append(future)
         for future in futures:
             future.result()
 
-def process_video(source_path: str, frame_paths: List[str], process_frames: Callable[[str, List[str], Any], None]) -> None:
+
+def process_video(source_path: str, frame_paths: list[str], process_frames: Callable[[str, List[str], Any], None]) -> None:
     progress_bar_format = '{l_bar}{bar}| {n_fmt}/{total_fmt} [{elapsed}<{remaining}, {rate_fmt}{postfix}]'
     total = len(frame_paths)
     with tqdm(total=total, desc='Processing', unit='frame', dynamic_ncols=True, bar_format=progress_bar_format) as progress:
-        progress.set_postfix({
-            'execution_providers': modules.globals.execution_providers, 
-            'execution_threads': modules.globals.execution_threads, 
-            'max_memory': modules.globals.max_memory
-        })
+        progress.set_postfix({'execution_providers': modules.globals.execution_providers, 'execution_threads': modules.globals.execution_threads, 'max_memory': modules.globals.max_memory})
         multi_process_frame(source_path, frame_paths, process_frames, progress)

modules/processors/frame/face_enhancer.py

@@ -8,52 +8,82 @@ import modules.globals
 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  # Ensure these are imported
-from modules.utilities import conditional_download, resolve_relative_path, is_image, is_video
+from modules.typing import Frame, Face
+import platform
+import torch
+from modules.utilities import (
+    conditional_download,
+    is_image,
+    is_video,
+)
 
 FACE_ENHANCER = None
 THREAD_SEMAPHORE = threading.Semaphore()
 THREAD_LOCK = threading.Lock()
-NAME = 'DLC.FACE-ENHANCER'
+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"
+)
+
 
 def pre_check() -> bool:
-    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'])
+    download_directory_path = models_dir
+    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
 
+
 def get_face_enhancer() -> Any:
     global FACE_ENHANCER
 
     with THREAD_LOCK:
         if FACE_ENHANCER is None:
-            model_path = resolve_relative_path('../models/GFPGANv1.4.pth')
-            FACE_ENHANCER = gfpgan.GFPGANer(
-                model_path=model_path,
-                upscale=modules.globals.enhancer_upscale_factor
-            )  # type: ignore[attr-defined]
+            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]
+
     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
 
+
 def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
     target_face = get_one_face(temp_frame)
     if target_face:
         temp_frame = enhance_face(temp_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)
@@ -61,10 +91,19 @@ def process_frames(source_path: str, temp_frame_paths: List[str], progress: Any
         if progress:
             progress.update(1)
 
+
 def process_image(source_path: str, target_path: str, output_path: str) -> None:
     target_frame = cv2.imread(target_path)
     result = process_frame(None, target_frame)
     cv2.imwrite(output_path, result)
 
+
 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

modules/processors/frame/face_swapper.py

@@ -2,68 +2,105 @@ from typing import Any, List
 import cv2
 import insightface
 import threading
-import os
-
+import numpy as np
 import modules.globals
 import modules.processors.frame.core
 from modules.core import update_status
-from modules.face_analyser import get_one_face, get_many_faces
+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
-import numpy as np
+from modules.utilities import (
+    conditional_download,
+    is_image,
+    is_video,
+)
+from modules.cluster_analysis import find_closest_centroid
+import os
 
 FACE_SWAPPER = None
 THREAD_LOCK = threading.Lock()
-NAME = 'DLC.FACE-SWAPPER'
+NAME = "DLC.FACE-SWAPPER"
+
+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"
+)
+
 
 def pre_check() -> bool:
-    download_directory_path = resolve_relative_path('../models')
-    conditional_download(download_directory_path, [
-        'https://huggingface.co/hacksider/deep-live-cam/blob/main/inswapper_128.onnx'
-    ])
+    download_directory_path = abs_dir
+    conditional_download(
+        download_directory_path,
+        [
+            "https://huggingface.co/hacksider/deep-live-cam/blob/main/inswapper_128_fp16.onnx"
+        ],
+    )
     return True
 
+
 def pre_start() -> bool:
-    if not is_image(modules.globals.source_path):
-        update_status('Select an image for source path.', NAME)
+    if not modules.globals.map_faces and not is_image(modules.globals.source_path):
+        update_status("Select an image for source path.", NAME)
         return False
-    elif not get_one_face(cv2.imread(modules.globals.source_path)):
-        update_status('No face detected in the source path.', 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
 
+
 def get_face_swapper() -> Any:
     global FACE_SWAPPER
 
     with THREAD_LOCK:
         if FACE_SWAPPER is None:
-            model_path = resolve_relative_path('../models/inswapper_128.onnx')
-            FACE_SWAPPER = insightface.model_zoo.get_model(model_path, providers=modules.globals.execution_providers)
+            model_path = os.path.join(models_dir, "inswapper_128_fp16.onnx")
+            FACE_SWAPPER = insightface.model_zoo.get_model(
+                model_path, providers=modules.globals.execution_providers
+            )
     return FACE_SWAPPER
 
-def upscale_image(image: np.ndarray, scaling_factor: int = modules.globals.source_image_scaling_factor) -> np.ndarray:
-    """
-    Upscales the given image by the specified scaling factor.
-
-    Args:
-        image (np.ndarray): The input image to upscale.
-        scaling_factor (int): The factor by which to upscale the image.
-
-    Returns:
-        np.ndarray: The upscaled image.
-    """
-    height, width = image.shape[:2]
-    new_size = (width * scaling_factor, height * scaling_factor)
-    upscaled_image = cv2.resize(image, new_size, interpolation=cv2.INTER_CUBIC)
-    return upscaled_image
 
 def swap_face(source_face: Face, target_face: Face, temp_frame: Frame) -> Frame:
-    return get_face_swapper().get(temp_frame, target_face, source_face, paste_back=True)
+    face_swapper = get_face_swapper()
+
+    # Apply the face swap
+    swapped_frame = face_swapper.get(
+        temp_frame, target_face, source_face, paste_back=True
+    )
+
+    if modules.globals.mouth_mask:
+        # Create a mask for the target face
+        face_mask = create_face_mask(target_face, temp_frame)
+
+        # Create the mouth mask
+        mouth_mask, mouth_cutout, mouth_box, lower_lip_polygon = (
+            create_lower_mouth_mask(target_face, temp_frame)
+        )
+
+        # Apply the mouth area
+        swapped_frame = apply_mouth_area(
+            swapped_frame, mouth_cutout, mouth_box, face_mask, lower_lip_polygon
+        )
+
+        if modules.globals.show_mouth_mask_box:
+            mouth_mask_data = (mouth_mask, mouth_cutout, mouth_box, lower_lip_polygon)
+            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:
+    if modules.globals.color_correction:
+        temp_frame = cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB)
+
     if modules.globals.many_faces:
         many_faces = get_many_faces(temp_frame)
         if many_faces:
@@ -75,30 +112,504 @@ def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
             temp_frame = swap_face(source_face, target_face, temp_frame)
     return temp_frame
 
-def process_frames(source_path: str, temp_frame_paths: List[str], progress: Any = None) -> None:
-    source_image = cv2.imread(source_path)
-    if source_image is None:
-        print(f"Failed to load source image from {source_path}")
-        return
-    # Upscale the source image for better quality
-    source_image_upscaled = upscale_image(source_image, scaling_factor=2)
-    source_face = get_one_face(source_image_upscaled)
 
-    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(f"Error processing frame {temp_frame_path}: {exception}")
-        if progress:
-            progress.update(1)
+def process_frame_v2(temp_frame: Frame, temp_frame_path: str = "") -> Frame:
+    if is_image(modules.globals.target_path):
+        if modules.globals.many_faces:
+            source_face = default_source_face()
+            for map in modules.globals.source_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 in modules.globals.source_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 in modules.globals.source_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"]:
+                        temp_frame = swap_face(source_face, target_face, temp_frame)
+
+        elif not modules.globals.many_faces:
+            for map in modules.globals.source_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"]:
+                            temp_frame = swap_face(source_face, target_face, temp_frame)
+
+    else:
+        detected_faces = get_many_faces(temp_frame)
+        if modules.globals.many_faces:
+            if detected_faces:
+                source_face = default_source_face()
+                for target_face in detected_faces:
+                    temp_frame = swap_face(source_face, target_face, temp_frame)
+
+        elif not modules.globals.many_faces:
+            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,
+                        )
+                else:
+                    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
+                        )
+
+                        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:
+    if not modules.globals.map_faces:
+        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:
-    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)
+    if not modules.globals.map_faces:
+        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. 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:
-    modules.processors.frame.core.process_video(source_path, temp_frame_paths, process_frames)
+    if modules.globals.map_faces and modules.globals.many_faces:
+        update_status(
+            "Many faces enabled. Using first source image. Progressing...", NAME
+        )
+    modules.processors.frame.core.process_video(
+        source_path, temp_frame_paths, process_frames
+    )
+
+
+def create_lower_mouth_mask(
+    face: Face, frame: Frame
+) -> (np.ndarray, np.ndarray, tuple, np.ndarray):
+    mask = np.zeros(frame.shape[:2], dtype=np.uint8)
+    mouth_cutout = None
+    landmarks = face.landmark_2d_106
+    if landmarks is not None:
+        #                  0  1  2  3  4  5  6  7  8  9  10 11 12 13 14 15 16 17 18 19 20
+        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
+        )  # Use float for precise calculations
+
+        # Calculate the center of the landmarks
+        center = np.mean(lower_lip_landmarks, axis=0)
+
+        # Expand the landmarks outward
+        expansion_factor = (
+            1 + modules.globals.mask_down_size
+        )  # Adjust this for more or less expansion
+        expanded_landmarks = (lower_lip_landmarks - center) * expansion_factor + center
+
+        # Extend the top lip part
+        toplip_indices = [
+            20,
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+        ]  # Indices for landmarks 2, 65, 66, 62, 70, 69, 18
+        toplip_extension = (
+            modules.globals.mask_size * 0.5
+        )  # Adjust this factor to control the extension
+        for idx in toplip_indices:
+            direction = expanded_landmarks[idx] - center
+            direction = direction / np.linalg.norm(direction)
+            expanded_landmarks[idx] += direction * toplip_extension
+
+        # Extend the bottom part (chin area)
+        chin_indices = [
+            11,
+            12,
+            13,
+            14,
+            15,
+            16,
+        ]  # Indices for landmarks 21, 22, 23, 24, 0, 8
+        chin_extension = 2 * 0.2  # Adjust this factor to control the extension
+        for idx in chin_indices:
+            expanded_landmarks[idx][1] += (
+                expanded_landmarks[idx][1] - center[1]
+            ) * chin_extension
+
+        # Convert back to integer coordinates
+        expanded_landmarks = expanded_landmarks.astype(np.int32)
+
+        # Calculate bounding box for the expanded lower mouth
+        min_x, min_y = np.min(expanded_landmarks, axis=0)
+        max_x, max_y = np.max(expanded_landmarks, axis=0)
+
+        # Add some padding to the bounding box
+        padding = int((max_x - min_x) * 0.1)  # 10% padding
+        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)
+
+        # Ensure the bounding box dimensions are valid
+        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
+
+        # Create the mask
+        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)
+
+        # Apply Gaussian blur to soften the mask edges
+        mask_roi = cv2.GaussianBlur(mask_roi, (15, 15), 5)
+
+        # Place the mask ROI in the full-sized mask
+        mask[min_y:max_y, min_x:max_x] = mask_roi
+
+        # Extract the masked area from the frame
+        mouth_cutout = frame[min_y:max_y, min_x:max_x].copy()
+
+        # Return the expanded lower lip polygon in original frame coordinates
+        lower_lip_polygon = expanded_landmarks
+
+    return mask, mouth_cutout, (min_x, min_y, max_x, max_y), lower_lip_polygon
+
+
+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()
+
+        # Ensure coordinates are within frame bounds
+        height, width = vis_frame.shape[:2]
+        min_x, min_y = max(0, min_x), max(0, min_y)
+        max_x, max_y = min(width, max_x), min(height, max_y)
+
+        # Adjust mask to match the region size
+        mask_region = mask[0 : max_y - min_y, 0 : max_x - min_x]
+
+        # Remove the color mask overlay
+        # color_mask = cv2.applyColorMap((mask_region * 255).astype(np.uint8), cv2.COLORMAP_JET)
+
+        # Ensure shapes match before blending
+        vis_region = vis_frame[min_y:max_y, min_x:max_x]
+        # Remove blending with color_mask
+        # if vis_region.shape[:2] == color_mask.shape[:2]:
+        #     blended = cv2.addWeighted(vis_region, 0.7, color_mask, 0.3, 0)
+        #     vis_frame[min_y:max_y, min_x:max_x] = blended
+
+        # Draw the lower lip polygon
+        cv2.polylines(vis_frame, [lower_lip_polygon], True, (0, 255, 0), 2)
+
+        # Remove the red box
+        # cv2.rectangle(vis_frame, (min_x, min_y), (max_x, max_y), (0, 0, 255), 2)
+
+        # Visualize the feathered mask
+        feather_amount = max(
+            1,
+            min(
+                30,
+                (max_x - min_x) // modules.globals.mask_feather_ratio,
+                (max_y - min_y) // modules.globals.mask_feather_ratio,
+            ),
+        )
+        # Ensure kernel size is odd
+        kernel_size = 2 * feather_amount + 1
+        feathered_mask = cv2.GaussianBlur(
+            mask_region.astype(float), (kernel_size, kernel_size), 0
+        )
+        feathered_mask = (feathered_mask / feathered_mask.max() * 255).astype(np.uint8)
+        # Remove the feathered mask color overlay
+        # color_feathered_mask = cv2.applyColorMap(feathered_mask, cv2.COLORMAP_VIRIDIS)
+
+        # Ensure shapes match before blending feathered mask
+        # if vis_region.shape == color_feathered_mask.shape:
+        #     blended_feathered = cv2.addWeighted(vis_region, 0.7, color_feathered_mask, 0.3, 0)
+        #     vis_frame[min_y:max_y, min_x:max_x] = blended_feathered
+
+        # Add labels
+        cv2.putText(
+            vis_frame,
+            "Lower Mouth Mask",
+            (min_x, min_y - 10),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.5,
+            (255, 255, 255),
+            1,
+        )
+        cv2.putText(
+            vis_frame,
+            "Feathered Mask",
+            (min_x, max_y + 20),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.5,
+            (255, 255, 255),
+            1,
+        )
+
+        return vis_frame
+    return frame
+
+
+def apply_mouth_area(
+    frame: np.ndarray,
+    mouth_cutout: np.ndarray,
+    mouth_box: tuple,
+    face_mask: np.ndarray,
+    mouth_polygon: np.ndarray,
+) -> np.ndarray:
+    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)
+
+        # Use the provided mouth polygon to create the mask
+        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)
+
+        # Apply feathering to the polygon mask
+        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)
+
+        # Apply face mask to blended result
+        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 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:
+        # Convert landmarks to int32
+        landmarks = landmarks.astype(np.int32)
+
+        # Extract facial features
+        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]
+
+        # Calculate forehead extension
+        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)  # Extend by 50%
+
+        # Create forehead points
+        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
+
+        # Combine all points to create the face outline
+        face_outline = np.vstack(
+            [
+                [forehead_left],
+                right_side_face,
+                left_side_face[
+                    ::-1
+                ],  # Reverse left side to create a continuous outline
+                [forehead_right],
+            ]
+        )
+
+        # Calculate padding
+        padding = int(
+            np.linalg.norm(right_side_face[0] - left_side_face[-1]) * 0.05
+        )  # 5% of face width
+
+        # Create a slightly larger convex hull for padding
+        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)
+
+        # Fill the padded convex hull
+        cv2.fillConvexPoly(mask, hull_padded, 255)
+
+        # Smooth the mask edges
+        mask = cv2.GaussianBlur(mask, (5, 5), 3)
+
+    return mask
+
+
+def apply_color_transfer(source, target):
+    """
+    Apply color transfer from target to source image
+    """
+    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)
+
+    # Reshape mean and std to be broadcastable
+    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)
+
+    # Perform the color transfer
+    source = (source - source_mean) * (target_std / source_std) + target_mean
+
+    return cv2.cvtColor(np.clip(source, 0, 255).astype("uint8"), cv2.COLOR_LAB2BGR)

modules/processors/frame/super_resolution.py

@@ -1,197 +0,0 @@
-import threading
-import traceback
-from typing import Any, List
-import cv2
-
-import os
-
-import modules.globals
-import modules.processors.frame.core
-from modules.core import update_status
-from modules.face_analyser import get_one_face
-from modules.utilities import conditional_download, resolve_relative_path, is_image, is_video
-import numpy as np
-
-NAME = 'DLC.SUPER-RESOLUTION'
-THREAD_SEMAPHORE = threading.Semaphore()
-
-# Singleton class for Super-Resolution
-class SuperResolutionModel:
-    _instance = None
-    _lock = threading.Lock()
-
-    def __init__(self, sr_model_path: str = f'ESPCN_x{modules.globals.sr_scale_factor}.pb'):
-        if SuperResolutionModel._instance is not None:
-            raise Exception("This class is a singleton!")
-        self.sr = cv2.dnn_superres.DnnSuperResImpl_create()
-        self.model_path = os.path.join(resolve_relative_path('../models'), sr_model_path)
-        if not os.path.exists(self.model_path):
-            raise FileNotFoundError(f"Super-resolution model not found at {self.model_path}")
-        try:
-            self.sr.readModel(self.model_path)
-            self.sr.setModel("espcn", modules.globals.sr_scale_factor)  # Using ESPCN with 2,3 or 4x upscaling
-        except Exception as e:
-            print(f"Error during super-resolution model initialization: {e}")
-            raise e
-
-    @classmethod
-    def get_instance(cls, sr_model_path: str = f'ESPCN_x{modules.globals.sr_scale_factor}.pb'):
-        if cls._instance is None:
-            with cls._lock:
-                if cls._instance is None:
-                    try:
-                        cls._instance = cls(sr_model_path)
-                    except Exception as e:
-                        raise RuntimeError(f"Failed to initialize SuperResolution: {str(e)}")
-        return cls._instance
-
-
-def pre_check() -> bool:
-    """
-    Checks and downloads necessary models before starting the face swapper.
-    """
-    download_directory_path = resolve_relative_path('../models')
-    # Download the super-resolution model as well
-    conditional_download(download_directory_path, [
-        f'https://huggingface.co/spaces/PabloGabrielSch/AI_Resolution_Upscaler_And_Resizer/resolve/bcd13b766a9499196e8becbe453c4a848673b3b6/models/ESPCN_x{modules.globals.sr_scale_factor}.pb'
-    ])
-    return True
-
-def pre_start() -> bool:
-    if not is_image(modules.globals.source_path):
-        update_status('Select an image for source path.', NAME)
-        return False
-    elif not get_one_face(cv2.imread(modules.globals.source_path)):
-        update_status('No face detected in the source path.', 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)
-        return False
-    return True
-
-
-def apply_super_resolution(image: np.ndarray) -> np.ndarray:
-    """
-    Applies super-resolution to the given image using the provided super-resolver.
-
-    Args:
-        image (np.ndarray): The input image to enhance.
-        sr_model_path (str): ESPCN model path for super-resolution.
-
-    Returns:
-        np.ndarray: The super-resolved image.
-    """
-    with THREAD_SEMAPHORE:
-        sr_model = SuperResolutionModel.get_instance()
-
-        if sr_model is None:
-            print("Super-resolution model is not initialized.")
-            return image
-        try:
-            upscaled_image = sr_model.sr.upsample(image)
-            return upscaled_image
-        except Exception as e:
-            print(f"Error during super-resolution: {e}")
-            return image
-
-
-def process_frame(frame: np.ndarray) -> np.ndarray:
-    """
-    Processes a single frame by swapping the source face into detected target faces.
-
-    Args:
-
-        frame (np.ndarray): The target frame image.
-
-    Returns:
-        np.ndarray: The processed frame with swapped faces.
-    """
-
-    # Apply super-resolution to the entire frame
-    frame = apply_super_resolution(frame)
-
-    return frame
-
-def process_frames(source_path: str, temp_frame_paths: List[str], progress: Any = None) -> None:
-    """
-    Processes multiple frames by swapping the source face into each target frame.
-
-    Args:
-        source_path (str): Path to the source image.
-        temp_frame_paths (List[str]): List of paths to target frame images.
-        progress (Any, optional): Progress tracker. Defaults to None.
-    """
-    for idx, temp_frame_path in enumerate(temp_frame_paths):
-        frame = cv2.imread(temp_frame_path)
-        if frame is None:
-            print(f"Failed to load frame from {temp_frame_path}")
-            continue
-        try:
-            result = process_frame(frame)
-            cv2.imwrite(temp_frame_path, result)
-        except Exception as exception:
-            traceback.print_exc()
-            print(f"Error processing frame {temp_frame_path}: {exception}")
-        if progress:
-            progress.update(1)
-
-def upscale_image(image: np.ndarray, scaling_factor: int = 2) -> np.ndarray:
-    """
-    Upscales the given image by the specified scaling factor.
-
-    Args:
-        image (np.ndarray): The input image to upscale.
-        scaling_factor (int): The factor by which to upscale the image.
-
-    Returns:
-        np.ndarray: The upscaled image.
-    """
-    height, width = image.shape[:2]
-    new_size = (width * scaling_factor, height * scaling_factor)
-    upscaled_image = cv2.resize(image, new_size, interpolation=cv2.INTER_CUBIC)
-    return upscaled_image
-
-def process_image(source_path: str, target_path: str, output_path: str) -> None:
-    """
-    Processes a single image by swapping the source face into the target image.
-
-    Args:
-        source_path (str): Path to the source image.
-        target_path (str): Path to the target image.
-        output_path (str): Path to save the output image.
-    """
-    source_image = cv2.imread(source_path)
-    if source_image is None:
-        print(f"Failed to load source image from {source_path}")
-        return
-
-    # Upscale the source image for better quality before face detection
-    source_image_upscaled = upscale_image(source_image, scaling_factor=2)
-
-    # Detect source face from the upscaled image
-    source_face = get_one_face(source_image_upscaled)
-    if source_face is None:
-        print("No source face detected.")
-        return
-
-    target_frame = cv2.imread(target_path)
-    if target_frame is None:
-        print(f"Failed to load target image from {target_path}")
-        return
-
-    # Process the frame
-    result = process_frame(target_frame)
-
-    # Save the processed frame
-    cv2.imwrite(output_path, result)
-
-
-def process_video(source_path: str, temp_frame_paths: List[str]) -> None:
-    """
-    Processes a video by swapping the source face into each frame.
-
-    Args:
-        source_path (str): Path to the source image.
-        temp_frame_paths (List[str]): List of paths to video frame images.
-    """
-    modules.processors.frame.core.process_video(None, temp_frame_paths, process_frames)

modules/ui.json

@@ -1,57 +1,76 @@
 {
   "CTk": {
-    "fg_color": ["#FFFFFF", "#2D2D2D"]
+    "fg_color": ["gray95", "gray10"]
   },
   "CTkToplevel": {
-    "fg_color": ["#FFFFFF", "#2D2D2D"]
+    "fg_color": ["gray95", "gray10"]
   },
   "CTkFrame": {
     "corner_radius": 0,
     "border_width": 0,
-    "fg_color": ["#F0F0F0", "#3C3C3C"],
-    "top_fg_color": ["#E0E0E0", "#4B4B4B"],
-    "border_color": ["#B0B0B0", "#5A5A5A"]
+    "fg_color": ["gray90", "gray13"],
+    "top_fg_color": ["gray85", "gray16"],
+    "border_color": ["gray65", "gray28"]
   },
   "CTkButton": {
     "corner_radius": 0,
     "border_width": 0,
-    "fg_color": ["#007ACC", "#007ACC"],
-    "hover_color": ["#005EA3", "#005EA3"],
-    "border_color": ["#004C8A", "#004C8A"],
-    "text_color": ["#FFFFFF", "#FFFFFF"],
+    "fg_color": ["#2aa666", "#1f538d"],
+    "hover_color": ["#3cb666", "#14375e"],
+    "border_color": ["#3e4a40", "#949A9F"],
+    "text_color": ["#f3faf6", "#f3faf6"],
     "text_color_disabled": ["gray74", "gray60"]
   },
   "CTkLabel": {
     "corner_radius": 0,
     "fg_color": "transparent",
-    "text_color": ["#000000", "#FFFFFF"]
+    "text_color": ["gray14", "gray84"]
   },
   "CTkEntry": {
     "corner_radius": 0,
     "border_width": 2,
-    "fg_color": ["#FFFFFF", "#333333"],
-    "border_color": ["#A0A0A0", "#5A5A5A"],
-    "text_color": ["#000000", "#FFFFFF"],
+    "fg_color": ["#F9F9FA", "#343638"],
+    "border_color": ["#979DA2", "#565B5E"],
+    "text_color": ["gray14", "gray84"],
     "placeholder_text_color": ["gray52", "gray62"]
   },
+  "CTkCheckbox": {
+    "corner_radius": 0,
+    "border_width": 3,
+    "fg_color": ["#2aa666", "#1f538d"],
+    "border_color": ["#3e4a40", "#949A9F"],
+    "hover_color": ["#3cb666", "#14375e"],
+    "checkmark_color": ["#f3faf6", "gray90"],
+    "text_color": ["gray14", "gray84"],
+    "text_color_disabled": ["gray60", "gray45"]
+  },
   "CTkSwitch": {
     "corner_radius": 1000,
     "border_width": 3,
     "button_length": 0,
     "fg_color": ["#939BA2", "#4A4D50"],
     "progress_color": ["#2aa666", "#1f538d"],
-    "button_color": ["#444444", "#D5D9DE"],
-    "button_hover_color": ["#333333", "#FFFFFF"],
-    "text_color": ["#000000", "#FFFFFF"],
+    "button_color": ["gray36", "#D5D9DE"],
+    "button_hover_color": ["gray20", "gray100"],
+    "text_color": ["gray14", "gray84"],
     "text_color_disabled": ["gray60", "gray45"]
   },
-  "CTkOptionMenu": {
-    "corner_radius": 0,
+  "CTkRadiobutton": {
+    "corner_radius": 1000,
+    "border_width_checked": 6,
+    "border_width_unchecked": 3,
     "fg_color": ["#2aa666", "#1f538d"],
-    "button_color": ["#3cb666", "#14375e"],
-    "button_hover_color": ["#234567", "#1e2c40"],
-    "text_color": ["#FFFFFF", "#FFFFFF"],
-    "text_color_disabled": ["gray74", "gray60"]
+    "border_color": ["#3e4a40", "#949A9F"],
+    "hover_color": ["#3cb666", "#14375e"],
+    "text_color": ["gray14", "gray84"],
+    "text_color_disabled": ["gray60", "gray45"]
+  },
+  "CTkProgressBar": {
+    "corner_radius": 1000,
+    "border_width": 0,
+    "fg_color": ["#939BA2", "#4A4D50"],
+    "progress_color": ["#2aa666", "#1f538d"],
+    "border_color": ["gray", "gray"]
   },
   "CTkSlider": {
     "corner_radius": 1000,
@@ -63,6 +82,59 @@
     "button_color": ["#2aa666", "#1f538d"],
     "button_hover_color": ["#3cb666", "#14375e"]
   },
+  "CTkOptionMenu": {
+    "corner_radius": 0,
+    "fg_color": ["#2aa666", "#1f538d"],
+    "button_color": ["#3cb666", "#14375e"],
+    "button_hover_color": ["#234567", "#1e2c40"],
+    "text_color": ["#f3faf6", "#f3faf6"],
+    "text_color_disabled": ["gray74", "gray60"]
+  },
+  "CTkComboBox": {
+    "corner_radius": 0,
+    "border_width": 2,
+    "fg_color": ["#F9F9FA", "#343638"],
+    "border_color": ["#979DA2", "#565B5E"],
+    "button_color": ["#979DA2", "#565B5E"],
+    "button_hover_color": ["#6E7174", "#7A848D"],
+    "text_color": ["gray14", "gray84"],
+    "text_color_disabled": ["gray50", "gray45"]
+  },
+  "CTkScrollbar": {
+    "corner_radius": 1000,
+    "border_spacing": 4,
+    "fg_color": "transparent",
+    "button_color": ["gray55", "gray41"],
+    "button_hover_color": ["gray40", "gray53"]
+  },
+  "CTkSegmentedButton": {
+    "corner_radius": 0,
+    "border_width": 2,
+    "fg_color": ["#979DA2", "gray29"],
+    "selected_color": ["#2aa666", "#1f538d"],
+    "selected_hover_color": ["#3cb666", "#14375e"],
+    "unselected_color": ["#979DA2", "gray29"],
+    "unselected_hover_color": ["gray70", "gray41"],
+    "text_color": ["#f3faf6", "#f3faf6"],
+    "text_color_disabled": ["gray74", "gray60"]
+  },
+  "CTkTextbox": {
+    "corner_radius": 0,
+    "border_width": 0,
+    "fg_color": ["gray100", "gray20"],
+    "border_color": ["#979DA2", "#565B5E"],
+    "text_color": ["gray14", "gray84"],
+    "scrollbar_button_color": ["gray55", "gray41"],
+    "scrollbar_button_hover_color": ["gray40", "gray53"]
+  },
+  "CTkScrollableFrame": {
+    "label_fg_color": ["gray80", "gray21"]
+  },
+  "DropdownMenu": {
+    "fg_color": ["gray90", "gray20"],
+    "hover_color": ["gray75", "gray28"],
+    "text_color": ["gray14", "gray84"]
+  },
   "CTkFont": {
     "macOS": {
       "family": "Avenir",
@@ -80,12 +152,7 @@
       "weight": "normal"
     }
   },
-  "DropdownMenu": {
-    "fg_color": ["#FFFFFF", "#2D2D2D"],
-    "hover_color": ["#E0E0E0", "#4B4B4B"],
-    "text_color": ["#000000", "#FFFFFF"]
-  },
   "URL": {
-    "text_color": ["#007ACC", "#1E90FF"]
+    "text_color": ["gray74", "gray60"]
   }
 }

modules/utilities.py

@@ -5,133 +5,205 @@ import platform
 import shutil
 import ssl
 import subprocess
-import urllib.request
+import urllib
 from pathlib import Path
 from typing import List, Any
 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 macOS to handle issues with some HTTPS requests
-if platform.system().lower() == 'darwin':
+# monkey patch ssl for mac
+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)
         return True
-    except subprocess.CalledProcessError as e:
-        print(f"FFmpeg error: {e.output.decode()}")
+    except Exception:
+        pass
     return False
 
+
 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
+        "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:
-        output = subprocess.check_output(command).decode().strip().split('/')
         numerator, denominator = map(int, output)
         return numerator / denominator
-    except (subprocess.CalledProcessError, ValueError):
-        print("Failed to detect FPS, defaulting to 30.0 FPS.")
+    except Exception:
+        pass
     return 30.0
 
+
 def extract_frames(target_path: str) -> None:
     temp_directory_path = get_temp_directory_path(target_path)
-    create_temp(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:
-    target_name = Path(target_path).stem
-    target_directory_path = Path(target_path).parent
-    return str(target_directory_path / TEMP_DIRECTORY / target_name)
+    target_name, _ = os.path.splitext(os.path.basename(target_path))
+    target_directory_path = os.path.dirname(target_path)
+    return os.path.join(target_directory_path, TEMP_DIRECTORY, target_name)
+
 
 def get_temp_output_path(target_path: str) -> str:
     temp_directory_path = get_temp_directory_path(target_path)
-    return str(Path(temp_directory_path) / TEMP_FILE)
+    return os.path.join(temp_directory_path, TEMP_FILE)
 
-def normalize_output_path(source_path: str, target_path: str, output_path: str) -> str:
-    if source_path and target_path and os.path.isdir(output_path):
-        source_name = Path(source_path).stem
-        target_name = Path(target_path).stem
-        target_extension = Path(target_path).suffix
-        return str(Path(output_path) / f"{source_name}-{target_name}{target_extension}")
+
+def normalize_output_path(source_path: str, target_path: str, output_path: str) -> Any:
+    if source_path and target_path:
+        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 output_path
 
+
 def create_temp(target_path: str) -> None:
     temp_directory_path = get_temp_directory_path(target_path)
     Path(temp_directory_path).mkdir(parents=True, exist_ok=True)
 
+
 def move_temp(target_path: str, output_path: str) -> None:
     temp_output_path = get_temp_output_path(target_path)
     if os.path.isfile(temp_output_path):
+        if os.path.isfile(output_path):
+            os.remove(output_path)
         shutil.move(temp_output_path, output_path)
 
+
 def clean_temp(target_path: str) -> None:
     temp_directory_path = get_temp_directory_path(target_path)
-    parent_directory_path = Path(temp_directory_path).parent
+    parent_directory_path = os.path.dirname(temp_directory_path)
     if not modules.globals.keep_frames and os.path.isdir(temp_directory_path):
         shutil.rmtree(temp_directory_path)
-    if parent_directory_path.exists() and not list(parent_directory_path.iterdir()):
-        parent_directory_path.rmdir()
+    if os.path.exists(parent_directory_path) and not os.listdir(parent_directory_path):
+        os.rmdir(parent_directory_path)
+
 
 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 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 mimetype and mimetype.startswith('video/')
+        return bool(mimetype and mimetype.startswith("video/"))
     return False
 
+
 def conditional_download(download_directory_path: str, urls: List[str]) -> None:
-    download_directory = Path(download_directory_path)
-    download_directory.mkdir(parents=True, exist_ok=True)
+    if not os.path.exists(download_directory_path):
+        os.makedirs(download_directory_path)
     for url in urls:
-        download_file_path = download_directory / Path(url).name
-        if not download_file_path.exists():
-            with urllib.request.urlopen(url) as request:
-                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))
+        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]
+
 
 def resolve_relative_path(path: str) -> str:
-    return str(Path(__file__).parent / path)
+    return os.path.abspath(os.path.join(os.path.dirname(__file__), path))

modules/video_capture.py

@@ -0,0 +1,94 @@
+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

requirements.txt

@@ -1,27 +1,25 @@
 --extra-index-url https://download.pytorch.org/whl/cu118
 
-numpy==1.23.5
-opencv-contrib-python==4.10.0.84
+numpy>=1.23.5,<2
+typing-extensions>=4.8.0
+opencv-python==4.10.0.84
+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==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==1.18.0; sys_platform == 'darwin' and platform_machine != 'arm64'
+pillow==11.1.0
+torch==2.5.1+cu118; sys_platform != 'darwin'
+torch==2.5.1; sys_platform == 'darwin'
+torchvision==0.20.1; sys_platform != 'darwin'
+torchvision==0.20.1; sys_platform == 'darwin'
 onnxruntime-silicon==1.16.3; sys_platform == 'darwin' and platform_machine == 'arm64'
-onnxruntime-gpu==1.18.0; sys_platform != 'darwin'
-tensorflow==2.13.0rc1; sys_platform == 'darwin'
-tensorflow==2.12.1; sys_platform != 'darwin'
+onnxruntime-gpu==1.16.3; sys_platform != 'darwin'
+tensorflow; sys_platform != 'darwin'
 opennsfw2==0.10.2
 protobuf==4.23.2
 tqdm==4.66.4
 gfpgan==1.3.8
-pyobjc==9.1; sys_platform == 'darwin'
+tkinterdnd2==0.4.2
 pygrabber==0.2
-pyvirtualcam==0.12.0
-pyobjc-framework-AVFoundation==10.3.1; sys_platform == 'darwin'

run-cuda.bat

@@ -1 +1 @@
-python run.py --execution-provider cuda --execution-threads 60 --max-memory 60
+python run.py --execution-provider cuda

run-directml.bat

@@ -0,0 +1 @@
+python run.py --execution-provider dml

run-laptop-gpu.bat

@@ -1 +0,0 @@
-python run.py --execution-provider dml

run_with_chocolatey.bat

@@ -1,13 +0,0 @@
-@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

setup_deep_live_cam.bat

@@ -1,125 +0,0 @@
-@echo off
-setlocal EnableDelayedExpansion
-
-:: 1. Setup your platform
-echo Setting up your platform...
-call :check_installation python "Python 3.10 or later"
-call :check_installation pip "Pip"
-call :install_if_missing git "Git" "winget install --id Git.Git -e --source winget"
-call :install_if_missing ffmpeg "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
-call :clone_repository "https://github.com/iVideoGameBoss/iRoopDeepFaceCam.git" "iRoopDeepFaceCam"
-
-:: 3. Download Models
-echo Downloading models...
-if not exist models mkdir models
-curl -L -o models\GFPGANv1.4.pth https://huggingface.co/ivideogameboss/iroopdeepfacecam/resolve/main/GFPGANv1.4.pth
-curl -L -o models\inswapper_128_fp16.onnx https://huggingface.co/ivideogameboss/iroopdeepfacecam/resolve/main/inswapper_128_fp16.onnx
-
-:: 4. Install dependencies
-echo Creating a virtual environment...
-python -m venv venv
-call venv\Scripts\activate.bat
-
-echo Installing required Python packages...
-pip install --upgrade pip
-pip install -r requirements.txt
-echo Setup complete. You can now run the application.
-
-:menu
-:: 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): "
-
-set "exec_provider="
-call :set_execution_provider %choice%
-
-:end_choice
-echo.
-echo GPU Acceleration setup complete.
-echo Selected provider: !exec_provider!
-echo.
-
-:: 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
-)
-
-:: Deactivate the virtual environment
-call venv\Scripts\deactivate.bat
-
-echo.
-echo Script execution completed.
-pause
-exit /b
-
-:check_installation
-where %1 >nul 2>&1
-if %ERRORLEVEL% neq 0 (
-    echo %2 is not installed. Please install %2.
-    pause
-    exit /b
-)
-
-:install_if_missing
-where %1 >nul 2>&1
-if %ERRORLEVEL% neq 0 (
-    echo %2 is not installed. Installing %2...
-    %3
-)
-
-:clone_repository
-if exist %2 (
-    echo %2 directory already exists.
-    set /p overwrite="Do you want to overwrite? (Y/N): "
-    if /i "%overwrite%"=="Y" (
-        rmdir /s /q %2
-        git clone %1
-    ) else (
-        echo Skipping clone, using existing directory.
-    )
-) else (
-    git clone %1
-)
-
-:set_execution_provider
-if "%1"=="1" (
-    call :install_onnxruntime "onnxruntime-gpu" "1.16.3" "cuda"
-) else if "%1"=="2" (
-    call :install_onnxruntime "onnxruntime-silicon" "1.13.1" "coreml"
-) else if "%1"=="3" (
-    call :install_onnxruntime "onnxruntime-coreml" "1.13.1" "coreml"
-) else if "%1"=="4" (
-    call :install_onnxruntime "onnxruntime-directml" "1.15.1" "directml"
-) else if "%1"=="5" (
-    call :install_onnxruntime "onnxruntime-openvino" "1.15.0" "openvino"
-) else if "%1"=="6" (
-    echo Skipping GPU acceleration setup.
-    set "exec_provider=none"
-) else (
-    echo Invalid choice. Please try again.
-    goto menu
-)
-
-:install_onnxruntime
-echo Installing %1 dependencies...
-pip uninstall -y onnxruntime %1
-pip install %1==%2
-set "exec_provider=%3"
-goto end_choice