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

Update README.md

Browse Source
This commit is contained in:
Kohya S
2023-07-06 07:43:30 +09:00
committed by GitHub
parent 4a34e5804e
commit 288efddf2f
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -45,7 +45,7 @@ Summary of the feature:
- Use `--cache_text_encoder_outputs` option and caching latents. - Use `--cache_text_encoder_outputs` option and caching latents.
- Use Adafactor optimizer. RMSprop 8bit or Adagrad 8bit may work. AdamW 8bit doesn't seem to work. - Use Adafactor optimizer. RMSprop 8bit or Adagrad 8bit may work. AdamW 8bit doesn't seem to work.
- The LoRA training can be done with 12GB GPU memory. - The LoRA training can be done with 12GB GPU memory.
- `--train_unet_only` option is highly recommended for SDXL LoRA. Because SDXL has two text encoders, the result of the training will be unexpected. - `--network_train_unet_only` option is highly recommended for SDXL LoRA. Because SDXL has two text encoders, the result of the training will be unexpected.
- PyTorch 2 seems to use slightly less GPU memory than PyTorch 1. - PyTorch 2 seems to use slightly less GPU memory than PyTorch 1.
Example of the optimizer settings for Adafactor with the fixed learning rate: Example of the optimizer settings for Adafactor with the fixed learning rate: