VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-09 06:45:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: update README to include recent improvements in validation loss calculation

Browse Source
This commit is contained in:
Kohya S
2025-02-26 21:21:04 +09:00
parent ec350c83eb
commit 3d79239be4
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@@ -14,6 +14,11 @@ The command to install PyTorch is as follows:
### Recent Updates ### Recent Updates
Feb 26, 2025:
- Improve the validation loss calculation in `train_network.py`, `sdxl_train_network.py`, `flux_train_network.py`, and `sd3_train_network.py`. PR [#1903](https://github.com/kohya-ss/sd-scripts/pull/1903)
- The validation loss uses the fixed timestep sampling and the fixed random seed. This is to ensure that the validation loss is not fluctuated by the random values.
Jan 25, 2025: Jan 25, 2025:
- `train_network.py`, `sdxl_train_network.py`, `flux_train_network.py`, and `sd3_train_network.py` now support validation loss. PR [#1864](https://github.com/kohya-ss/sd-scripts/pull/1864) Thank you to rockerBOO! - `train_network.py`, `sdxl_train_network.py`, `flux_train_network.py`, and `sd3_train_network.py` now support validation loss. PR [#1864](https://github.com/kohya-ss/sd-scripts/pull/1864) Thank you to rockerBOO!