kohya-ss enhanced text-to-image model trainer

Collection of PRs for kohya-ss text-to-image model trainer

rockerBOO/sd-scripts

Validation loss

Track a separate validation dataset for loss to compare with. Helps detect overfitting of the training dataset.

Preference optimization

Rank stabilized

Stablize the scaling component of alpha and rank for larger LoRA ranks.

LoRA+

Improve training performance by setting a higher LR for the B tensor in LoRA

Soft min SNR

Smooth out Min-SNR (signal-to-noise ratios) approach for minimum SNR.

Drop keys

Remove certain keys from being trained in the LoRA.

Momentum

Log and record momentum changes. In concert with CyclicLR and OneCycleLR PyTorch learning rates which modify the momentum.