Skip to content
Aikage edited this page Dec 7, 2024 · 7 revisions

Aspect Ratio Bucketing makes it possible to train the model on images with different aspect ratios at the same time. All images are resized to roughly match the same total pixel count.

Latent caching will speed up the training by saving intermediate data. If this setting is enabled, some data will be calculated based on your training images and saved to disc.

Clear cache before training - Clears the cache directory before starting to train. Only disable this if you want to continue using the same cached data. Disabling this can lead to errors, if other settings are changed during a restart.

Back to Tabs