Sign In

Pool(for research)

1.7k

Updated: May 31, 2025

backgroundpool

Not recently loaded

Download

1 variant available

SafeTensor

27.58 MB

Verified:

Type
LoRA
Stats

75

70

13

Reviews
Published

May 20, 2025

Base Model
Training
Epochs: 191
Usage Tips
Strength: 0.8
Hash
AutoV2DAED0E04CA
Trigger Words
school pool
School_Pool_high_epoch_e000191_01_20250520082927.png

School Pool, This is to note the study, no download is required

Since the learning failed, I took revenge by lowering the LR and raising the epoch.

I'll report back below someday.

As a result, changing the LR does not improve learning.

https://civitai.com/articles/13094/optimal-design-for-background-loralora

Lowering the LR requires more steps to learn, but it doesn't dramatically improve background learning.⬇(In normal LR, learning is completed in 500steps.)

https://civitai.com/models/1618049?modelVersionId=1831526