Create FF++_o_c23_ViT-B/README.md
Browse files
pretrained_models/FF++_o_c23_ViT-B/README.md
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
fsfm-3c_vit_base_patch16 pre-trained on FF++_o (~43W facial image from train and val videos of the original/YouTube subset in FaceForensics++ c23/HQ version, extract all frames) for 400 epochs.
|