Unified-detector_v1 for Unified Physical-Digital Face Attack&Forgery Detection, a vanilla ViT-B/16-224 (FSFM Pre-trained on VGG-Face2 for 800 epochs) that could identify Real&Bonafide, Deepfake, Diffduion&AIGC, Spooing&Presentation-attacks facial images or videos.
This model is fine-tuned on millions of images from many public datasets.