Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
crj1998 8a3a633d04 | 4 days ago | |
---|---|---|
asset | 2 months ago | |
examples | 1 month ago | |
facex | 1 month ago | |
facex_torch | 3 weeks ago | |
.gitignore | 2 months ago | |
README.md | 1 month ago | |
demo.py | 1 month ago | |
download.sh | 2 months ago | |
face_swap.py | 4 days ago | |
fsv.py | 4 days ago | |
makeup_transfer.py | 2 months ago | |
requirements.txt | 2 months ago | |
setup.py | 1 month ago | |
video.py | 5 days ago |
Face toolkits for detection, recognition based on onnxruntime
face detection bbox kps5 landmark68 pose
face align parsing restoration
face makeup transfer & restoration
face swap
#
pip install git+https://openi.pcl.ac.cn/crj1998/face_toolkit.git
git clone https://openi.pcl.ac.cn/crj1998/face_toolkit.git && cd face_toolkit && pip install -e .
import cv2
import numpy as np
from facex import FaceX
from facex.model_zoo import get_model
from facex.face_align import norm_crop
app = FaceX(
providers=[
'CUDAExecutionProvider',
'CPUExecutionProvider',
],
tasks=[
"detection",
"landmark_3d_68",
"genderage",
"recognition",
"restoration",
"parsing"
]
)
app.prepare(ctx_id=0, det_size=(640, 640))
img = cv2.imread("image.jpg")
assert img is not None
faces = app.get(img)
result = app.draw_on(img, faces)
assert cv2.imwrite("result.jpg", result)
wget https://github.com/facefusion/facefusion-assets/releases/download/models/codeformer.onnx
wget https://github.com/facefusion/facefusion-assets/releases/download/models/face_parser.onnx
wget https://storage.googleapis.com/ailia-models/beauty_gan/G_ep300.onnx -O beautygan.onnx
pip install --upgrade huggingface_hub
huggingface-cli login
huggingface-cli upload maze/faceX det_10g.onnx det_10g.onnx
huggingface-cli upload maze/faceX 1k3d68.onnx 1k3d68.onnx
huggingface-cli upload maze/faceX genderage.onnx genderage.onnx
huggingface-cli upload maze/faceX w600k_r50.onnx w600k_r50.onnx
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》