Trained for 0 epochs and 100 steps.

Trained with datasets ['text-embeds-sdxl', 'celebrities']
Learning rate 1e-06, 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:ae02eb281cc99191465da36abf701e30bfb452dea5603232750843236c4ace68
+oid sha256:d21b444a16720dc753b0351e504034a10eaca4ff0344117283144e10a65f867e
 size 9461864