JLNTV_IPD/CogVideo
4
0
Fork 0
mirror of https://github.com/THUDM/CogVideo.git synced 2025-04-05 19:41:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: clarify train_frames includes padding frame

Browse Source 
Add docstring to train_frames field in State schema to explicitly indicate
that it includes one image padding frame
This commit is contained in:
OleehyO 2025-01-04 06:20:25 +00:00
parent 7e1ac76847
commit 93b906b3fb
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
finetune/schemas/state.py
View File

@ -7,7 +7,7 @@ from pydantic import BaseModel, field_validator
class State(BaseModel):
model_config = {"arbitrary_types_allowed": True}
train_frames: int
train_frames: int # user-defined training frames, **containing one image padding frame**
train_height: int
train_width: int