Hugging Face's logo

ByteDance
/
LatentSync

Video-to-Video
Diffusers
Model card Files
xet
 Community
4
chunyu-li commited on
Commit
694fec2
·
1 Parent(s): a99b9dc

Uploaded checkpoints

Browse files
Files changed (13) hide show
  1. .gitignore +1 -0
  2. README.md +14 -3
  3. auxiliary/2DFAN4-cd938726ad.zip +3 -0
  4. auxiliary/i3d_torchscript.pt +3 -0
  5. auxiliary/koniq_pretrained.pkl +3 -0
  6. auxiliary/s3fd-619a316812.pth +3 -0
  7. auxiliary/sfd_face.pth +3 -0
  8. auxiliary/syncnet_v2.model +3 -0
  9. auxiliary/vgg16-397923af.pth +3 -0
  10. auxiliary/vit_g_hybrid_pt_1200e_ssv2_ft.pth +3 -0
  11. latentsync_syncnet.pt +3 -0
  12. latentsync_unet.pt +3 -0
  13. whisper/tiny.pt +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ .DS_Store
README.md CHANGED
@@ -1,3 +1,14 @@
1
- ---
2
- license: openrail
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: openrail
3
+ library_name: diffusers
4
+ tags:
5
+ - video-to-video
6
+ ---
7
+
8
+ # The checkpoints of LatentSync
9
+
10
+ This repo not only stores the pretrained U-Net and SyncNet checkpoints of LatentSync, but also stores the whisper checkpoints, auxiliary checkpoints for detecting face, calculating syncnet confidence score and so on. They have covered all you need for both inference and training of LatentSync
11
+
12
+ Paper: https://arxiv.org/abs/2412.09262
13
+
14
+ Code: https://github.com/bytedance/LatentSync
auxiliary/2DFAN4-cd938726ad.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd938726adb1f15f361263cce2db9cb820c42585fa8796ec72ce19107f369a46
3
+ size 96316515
auxiliary/i3d_torchscript.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec6519f66ea534e953026b4ae2c65553c17bf105611c746d904657e5860a5e2
3
+ size 51235320
auxiliary/koniq_pretrained.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff9277bcc68ecc10e77d88b6d0a32825ec3c85562095542734ec6212eaaf6d81
3
+ size 109768650
auxiliary/s3fd-619a316812.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619a31681264d3f7f7fc7a16a42cbbe8b23f31a256f75a366e5a1bcd59b33543
3
+ size 89843225
auxiliary/sfd_face.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d54a87c2b7543b64729c9a25eafd188da15fd3f6e02f0ecec76ae1b30d86c491
3
+ size 89844381
auxiliary/syncnet_v2.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:961e8696f888fce4f3f3a6c3d5b3267cf5b343100b238e79b2659bff2c605442
3
+ size 54573114
auxiliary/vgg16-397923af.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:397923af8e79cdbb6a7127f12361acd7a2f83e06b05044ddf496e83de57a5bf0
3
+ size 553433881
auxiliary/vit_g_hybrid_pt_1200e_ssv2_ft.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a210a92f035dff30c53b46157b612e7a1a5d3c99700e1b2d71da5c399ca7e70
3
+ size 2023804201
latentsync_syncnet.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38fa63bad3ed2332f647c40a5dc616cb0e233db8579f698f62af4c41965c4da5
3
+ size 1488019828
latentsync_unet.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63197c73d21ad55ddf2b6e5cc38d0a19a1e494317aefe2707c6b6c6fc952f3c7
3
+ size 3400080614
whisper/tiny.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9
3
+ size 75572083