Trained for 20 epochs and 8000 steps.

Trained with datasets ['text-embed-cache-cha_2102', 'cha_2102_512', 'cha_2102_768']
Learning rate 0.0004, batch size 1, 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: black-forest-labs/FLUX.1-dev
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f90976ae3d37384d262bafcd7e45c5ba59451ecd4b7e56c2655f176afed03b1
-size 179521508
+oid sha256:e2d4874c5060cfa5ea29c37f5614dda3f30080a01a461684676246126305da16
+size 179521444