https://www.youtube.com/watch?v=1NWJz_rFMq0
- download anaconda3 from link
- download simswap project from link, extract and place it somewhere
- download antelope from link or link
- create folder
models
inSimSwap-main\insightface_func\
extract antelope inside - download pretrained files (
checkpoints.zip
andarcface_checkpoint.tar
) from link - create folder
arcface_model
underSimSwap-main\
, placearcface_checkpoint.tar
inside - unzip
checkpoints.zip
insideSimSwap-main\
- open
anaconda prompt
and cd toSimSwap-main\
folder location - run command
conda create -n simswap python=3.6
to create environment - run command
conda activate simswap
to activate env - run command
conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=10.2 -c pytorch
- run command
pip install --ignore-installed imageio
- run command
pip install insightface==0.2.1 onnxruntime moviepy
- launch swap
python test_video_swapsingle.py --isTrain false --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path ./demo_file/Iron_man.jpg --video_path ./demo_file/mutil_people_1080p.mp4 --output_path ./output/mutil_test_swapsingle.mp4 --temp_path ./temp_results
or more command on https://github.com/neuralchen/SimSwap/blob/main/docs/guidance/usage.md
- optional: remove watermark
open
util/add_watermark.py
change line 80 to
def apply_frames(self, frame):
return frame