inswapper

One-click Face Swapper and Restoration powered by insightface.

Installation

# git clone this repository
git clone https://github.com/haofanwang/inswapper.git
cd inswapper

# install required packages
pip install -r requirements.txt

Download Checkpoints

First, you need to download face swap model and save it under ./checkpoints. To obtain better result, it is highly recommendated to improve image quality with face restoration model. Here, we use CodeFormer. You can finish all as following, required models will be downloaded automatically when you first run the inference.

mkdir checkpoints
wget -O ./checkpoints/inswapper_128.onnx https://huggingface.co/deepinsight/inswapper/resolve/main/inswapper_128.onnx 

cd ..
git lfs install
git clone https://huggingface.co/spaces/sczhou/CodeFormer

Quick Inference

from swapper import *

source_img = [Image.open("./data/man1.jpeg"),Image.open("./data/man2.jpeg")]
target_img = Image.open("./data/mans1.jpeg")

model = "./checkpoints/inswapper_128.onnx"
result_image = process(source_img,target_img, model)
result_image.save("result.png")

To improve to quality of face, we can further do face restoration as shown in the full script.

python swapper.py \
--source_img="./data/man1.jpeg;./data/man2.jpeg" \
--target_img "./data/mans1.jpeg" \
--face_restore \
--background_enhance \
--face_upsample \
--upscale=2 \
--codeformer_fidelity=0.5

You will obtain the exact result as above.

Acknowledgement

This project is inspired by inswapper, thanks insightface.ai for releasing their powful swap model that makes this happen. Our codebase is built on the top of sd-webui-roop and CodeFormer.

Contact

If you have any issue, feel free to contact me via [email protected].