JLNTV_IPD/CogVideo
4
0
Fork 0
mirror of https://github.com/THUDM/CogVideo.git synced 2026-05-06 22:58:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge 7bc152ff350eed9967206a681032abe38b7b8ca7 into 7a1af7154511e0ce4e4be8d62faa8c5e5a3532d2

Browse Source
This commit is contained in:
Harikrishna KP 2026-02-11 19:36:15 +05:30 committed by GitHub
commit 256e7cfd91
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
finetune/models/cogvideox_i2v/lora_trainer.py
View File

@ -115,7 +115,7 @@ class CogVideoXI2VLoraTrainer(Trainer):
patch_size_t = self.state.transformer_config.patch_size_t
if patch_size_t is not None:
ncopy = latent.shape[2] % patch_size_t
ncopy = (patch_size_t - latent.shape[2] % patch_size_t) % patch_size_t
# Copy the first frame ncopy times to match patch_size_t
first_frame = latent[:, :, :1, :, :] # Get first frame [B, C, 1, H, W]
latent = torch.cat([first_frame.repeat(1, 1, ncopy, 1, 1), latent], dim=2)

2
finetune/models/cogvideox_t2v/lora_trainer.py
View File

@ -109,7 +109,7 @@ class CogVideoXT2VLoraTrainer(Trainer):
patch_size_t = self.state.transformer_config.patch_size_t
if patch_size_t is not None:
ncopy = latent.shape[2] % patch_size_t
ncopy = (patch_size_t - latent.shape[2] % patch_size_t) % patch_size_t
# Copy the first frame ncopy times to match patch_size_t
first_frame = latent[:, :, :1, :, :] # Get first frame [B, C, 1, H, W]
latent = torch.cat([first_frame.repeat(1, 1, ncopy, 1, 1), latent], dim=2)