Trained for 25 epochs and 11000 steps.

Trained with datasets ['MALGOSIA-SD35-V01-text-embeds', 'MALGOSIA-SD35-V01-512', 'MALGOSIA-SD35-V01-768', 'MALGOSIA-SD35-V01-1024', 'MALGOSIA-RAFRAF-SD35-V01-512', 'MALGOSIA-RAFRAF-SD35-V01-768', 'MALGOSIA-RAFRAF-SD35-V01-1024', 'MALGOSIA-FRANCI-SD35-V01-512', 'MALGOSIA-FRANCI-SD35-V01-768']
Learning rate 3e-06, batch size 4, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: stabilityai/stable-diffusion-3.5-large
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cfab6b8de76992c39c8abfc3de969484872ab2a9066d0b87d50241d3f5fd150
-size 2817815782
+oid sha256:3960775cf855dbf00435fbada01997ec4170abc05dba6c8c9e5640f1e08cfa22
+size 2817815710