Trained for 56 epochs and 8880 steps.

Trained with datasets ['LEIRIX-FLUX-V03-text-embeds', 'LEIRIX-FLUX-V03-512', 'LEIRIX-FLUX-V03-768', 'LEIRIX-FLUX-V03-1024', 'LEIRIX-FLUX-CROP-V03-512', 'LEIRIX-FLUX-CROP-V03-768', 'LEIRIX-FLUX-CROP-V03-1024']
Learning rate 1.5e-05, batch size 3, and 2 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: terminusresearch/FluxBooru-v0.3
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9960b5dc820fd040008eb1fed5f4938abb4ef8c9dda615e35b7d789e3b39012
-size 194456044
+oid sha256:34f681f5f5e2c58a59976ec12c05f802712d582fff6553d2aa411c9de7cfdff9
+size 194455980