storytold/FineTrainers-Conditioning
2
0
Fork 0
mirror of https://github.com/storytold/FineTrainers-Conditioning.git synced 2026-10-17 00:23:35 +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/args.py
+1
View File
@@ -78,6 +78,7 @@ def _get_dataset_args(parser: argparse.ArgumentParser) -> None:
nargs="+",
type=int,
default=[49],
help="CogVideoX1.5 need to guarantee that ((num_frames - 1) // self.vae_scale_factor_temporal + 1) % patch_size_t != 0, such as 53"
)
parser.add_argument(
"--load_tensors",