-
|
I used textual inversion with an older version of this repo with great success in training SD to render specific art styles. There has been some change to the textual inversion ... I can now put in steps for a single image and while running the training it shows me "epochs" in cmd. What does it all mean? Is it better now? Do epochs have to be completed or can I just abort the training and test the embedding like before? I searched the automatic wiki but the entries are unchanged. Google is notoriously unhelpful with searching image generation details, so I just ask here if someone can give me some information |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment 1 reply
-
|
An epoch is when a training AI goes through all of its training data. You should be able to stop at any point |
Beta Was this translation helpful? Give feedback.
-
|
How much epoch is safer for hypernetwork training? I got around 80 Images Dataset for Hypernetwork training. I don't want to over-fit it. |
Beta Was this translation helpful? Give feedback.
An epoch is when a training AI goes through all of its training data. You should be able to stop at any point