Trained for 4 epochs and 51000 steps.

Trained with datasets ['texts', 'image-embeds-local', 'image-embeds-local-512', 'image-embeds-local-1536', 'image-embeds-local-2048', 'signs', 'moviecollection', 'bookcovers', 'shutterstock', 'cinemamix-1mp', 'anatomy', 'signs-512', 'moviecollection-512', 'bookcovers-512', 'shutterstock-512', 'cinemamix-1mp-512', 'anatomy-512', 'signs-1536', 'moviecollection-1536', 'bookcovers-1536', 'shutterstock-1536', 'cinemamix-1mp-1536', 'anatomy-1536']
Learning rate 0.0001, 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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37dbe63651d6aa1f7bad46c763417b1d9b269ef8712e0e46a017c3ca91e94fe
+size 397669178