MINTIME-Multi-Identity-size-iNvariant-TIMEsformer-for-Video-Deepfake-Detection

Deepfakes Software For All

DeepFaceLab is the leading software for creating deepfakes.

Google Brain AutoML

NanoDet-Plus?Super fast and lightweight anchor-free object detection model. ?Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone?

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

An arbitrary face-swapping framework on images and videos with one single trained model!

Implementation of EfficientNet model. Keras and TensorFlow Keras.

A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights

Everything Deepfakes

Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS