Trained for 0 epochs and 50 steps.

Trained with datasets ['texts', 'domokun-cropped-512-NonReg', 'domokun-cropped-512']
Learning rate 0.0001, batch size 1, and 1 gradient accumulation steps.
Trained with None prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: fal/AuraFlow
VAE: fal/AuraFlow

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:927a7dcf687fa8f793dd91ef00bca6196e0c51be0f210c3b394afc43bd8624d5
-size 28350968
+oid sha256:8434ae22943e10452379d3ecdc32c59c475dbe15fecda56d7252fe0364448af5
+size 14195248