Trained for 10 epochs and 118000 steps.

Trained with datasets ['texts', 'image-embeds-local', 'signs', 'moviecollection', 'bookcovers', 'shutterstock', 'cinemamix-1mp', 'anatomy']
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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddd9629c1f23978fddf1aad5437b43bd694e820aa88a6c246b7b7bf8b386540e
+oid sha256:91c105f441da37ce289f63ea17d6ba7021c1c9ad7f067ec4e54776c76983d8f0
 size 778714106