Trained for 5 epochs and 8800 steps.

Trained with datasets ['text-embeds-sdxl', 'celebrities-sd3']
Learning rate 0.0001, batch size 1, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with v_prediction prediction type and rescaled_betas_zero_snr=True
Using 'trailing' timestep spacing.
Base model: stabilityai/stable-diffusion-3-medium-diffusers
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae65439e5bc183d981f50b8bf64030688eaa0e4fe02c4da771f67f4b015d2ada
+oid sha256:222662d82260396eefae27a0e10d14acfca7633822728931ed6a0da2f3189f86
 size 9461864