storytold/FineTrainers-Conditioning
2
0
Fork 0
mirror of https://github.com/storytold/FineTrainers-Conditioning.git synced 2026-10-28 08:57:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

adaption for CogVideoX1.5 (#92)

Browse Source 
* adaption for CogVideoX1.5

* add patch_size_t in full finetuning of T2V and lora finetuning of I2V

* Update training/args.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
This commit is contained in:
jiashenggu
2024-11-23 08:58:20 +08:00
committed by GitHub
parent d63a826f37
commit 0b80dba1de
5 changed files with 26 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
training/cogvideox_image_to_video_lora.py
+1
View File
@@ -787,6 +787,7 @@ def main(args):
num_frames=num_frames,
vae_scale_factor_spatial=VAE_SCALE_FACTOR_SPATIAL,
patch_size=model_config.patch_size,
patch_size_t=model_config.patch_size_t if hasattr(model_config, "patch_size_t") else None,
attention_head_dim=model_config.attention_head_dim,
device=accelerator.device,
)