Swap face between two photos for Python 3 with OpenCV and dlib.
python main.py --src imgs/test6.jpg --dst imgs/test7.jpg --out results/output6_7.jpg --correct_color
Source | Destination | Result |
---|---|---|
python main.py --src imgs/test6.jpg --dst imgs/test7.jpg --out results/output6_7_2d.jpg --correct_color --warp_2d
Source | Destination | Result |
---|---|---|
pip install -r requirements.txt
- OpenCV 3:
conda install opencv
(If you have conda/anaconda)
Note: See requirements.txt for more details.
git clone https://github.com/wuhuikai/FaceSwap.git
python main.py ...
Note: Run python main.py -h for more details.
python video_handler.py --src_img imgs/test7.jpg
python video_handler.py --src_img imgs/test7.jpg --video_path video/test.mov
Make sure the landmarks actually locate in the face. Then drag the left mouse to make a rectangle, it should surround the face. Finally, we handle our video. Note that the demo works best with good, even lighting. The demo also needs support for opencv TRACKER(see config).
From | To |
---|---|