Trained for 2 epochs and 321000 steps.

Trained with datasets ['texts', 'image-embeds-local', 'image-embeds-local-512', 'image-embeds-local-1440', 'image-embeds-local-2048', 'text-1mp', 'signs', 'moviecollection', 'bookcovers', 'shutterstock', 'cinemamix-1mp', 'anatomy', 'signs-512', 'moviecollection-512', 'bookcovers-512', 'shutterstock-512', 'cinemamix-1mp-512', 'anatomy-512', 'signs-1440', 'moviecollection-1440', 'bookcovers-1440', 'shutterstock-1440', 'cinemamix-1mp-1440', 'anatomy-1440']
Learning rate 5e-05, 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-medium
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:826ab5e8a28695da9990475337d396a5f4419c2788b3f40d8302c4f8bba4203a
+oid sha256:7d75af7633c6056365fa9c9392c196181cb790bdc6d2057e2ab07a8160496aa8
 size 397669178