Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

JSON config load does not load the "save trained model as" setting properly #71

Closed
alchemzy opened this issue Jan 25, 2023 · 2 comments
Closed

Comments

@alchemzy
Copy link

Save appears to update the JSON config, but it does not load the value which remains as "same as parent"

@alchemzy
Copy link
Author

alchemzy commented Jan 25, 2023

git diff master
diff --git a/lora_gui.py b/lora_gui.py
index 2a7421a..9645216 100644
--- a/lora_gui.py
+++ b/lora_gui.py
@@ -158,7 +158,7 @@ def open_configuration(
     stop_text_encoder_training,
     use_8bit_adam,
     xformers,
-    save_model_as_dropdown,
+    save_model_as,
     shuffle_caption,
     save_state,
     resume

@bmaltais
Copy link
Owner

Good catch. I will push a fix for it. If you "git checkout dev ; git pull" you will get the fix. I will release it in the master branch once I have a few of those lined up... but for now you can use the dev branch code to make use of it.

Thank you for reporting this!

Cauldrath pushed a commit to Cauldrath/kohya_ss that referenced this issue Apr 5, 2023
Fix negative prompt not working when token>75
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants