One-click Face Swapper and Restoration powered byinsightface.We don't use the name ROOP here, as the credit should be given to the group that develops this great face swap model.
🔥 We releaseInstantIDas a state-of-the-art ID preservering generation method.
#git clone this repository
git clone https://github /haofanwang/inswapper.git
cdinswapper
#create a Python venv
Python 3 -m venv venv
#activate the venv
sourcevenv/bin/activate
#install required packages
pip install -r requirements.txt
You have to installonnxruntime-gpu
manually to enable GPU inference, installonnxruntime
by default to use CPU only inference.
First, you need to downloadface swap modeland save it under./checkpoints
.To obtain better result, it is highly recommended to improve image quality with face restoration model. Here, we useCodeFormer.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://github /facefusion/facefusion-assets/releases/download/models/inswapper_128.onnx
cd..
git lfs install
git clone https://huggingface.co/spaces/sczhou/CodeFormer
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, -1, -1, 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.
This project is inspired byinswapper,thanksinsightface.aifor releasing their powerful face swap model that makes this happen. Our codebase is built on the top ofsd-webui-roopandCodeFormer.
If you have any issue, feel free to contact me viahaofanwang.ai@gmail.