https://github.com/Constannnnnt/Video_FaceSwap

Given a user profile, a video clip and an actor(actress) profile in the video, Swap the actor's face with the user's face
https://github.com/Constannnnnt/Video_FaceSwap

face-detection face-landmarks face-recognition face-swap image-processing video-processing

Last synced: 8 days ago
JSON representation

Given a user profile, a video clip and an actor(actress) profile in the video, Swap the actor's face with the user's face

• Host: GitHub
• URL: https://github.com/Constannnnnt/Video_FaceSwap
• Owner: Constannnnnt
• License: mit
• Created: 2018-06-17T12:07:02.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2018-07-02T10:28:13.000Z (over 6 years ago)
• Last Synced: 2024-08-01T13:25:32.023Z (3 months ago)
• Topics: face-detection, face-landmarks, face-recognition, face-swap, image-processing, video-processing
• Language: Python
• Size: 16.6 KB
• Stars: 15
• Watchers: 3
• Forks: 6
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Video FaceSwap

Given a video clip, a user profile and an actor(actress) profile in the video, Swap the actor's face with the user's face. In a word, just replace the face of an actor with the input image for fun.

## Prerequisite

Install the prerequisites before using this module

1. Install *Cmake*

2. Install GCC(version>=4.8)

3. Install ffmpeg

4. ```shell

    pip3.5 install -r requirements.txt

    ```

**Note**: You will also need the *facial landmark detector*. The trained model can be downloaded from the [source](http://sourceforge.net/projects/dclib/files/dlib/v18.10/shape_predictor_68_face_landmarks.dat.bz2). Then, you can place it in the same directory where `main.py` is placed.

## Usage

```python3

python main.py $video_address $user_face_address $selected_actor_address $temp_address $output_video

```

E.g. `python main.py ./data/videos/video.mp4 ./data/images/user.jpeg ./data/images/actor.jpeg ./output/ ./output/output.mp4`

## Issue

1. To accelerate the program, *multiprocessing* is used, but it will comsume all your memory. If you are not interested in the computation time, you can comment this part out in `faceswap.py` and use sequential procedures.

    ```python

    cores = multiprocessing.cpu_count()

    pool = multiprocessing.Pool(processes=cores)

    pool.map(faceswapper, actors)

    pool.close()

    pool.join()

    ```

## Credits

Thanks to [face_recognition](https://github.com/ageitgey/face_recognition) by [Adam Geitgey](https://github.com/ageitgey) and [faceswap](https://github.com/matthewearl/faceswap) by [Matthew Earl](https://github.com/matthewearl).