Trained for 4 epochs and 2100 steps.

Trained with datasets ['texts', 'reg-512', 'reg-1024', 'furkan-uncut-512', 'furkan-cropped-512', 'furkan-uncut-1024', 'furkan-cropped-1024']
Learning rate 0.0001, batch size 1, 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 sha256:588818964f489036a165ae46921672d7de5f61e2409b30b486942c5ed8e39e1a
-size 224135886
+oid sha256:6c2a9651e5f010bafe5565c1a6a64b62e4826fa147d847da552a14aea4480a54
+size 224135958