Trained for 99 epochs and 1200 steps.

Trained with datasets ['text-embeds', 'Trunksv1']
Learning rate 0.0002, 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: /data/yihao/FLUX.1-dev
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45da3b329745c60dffe3462e451ea855b730641b8497a0a837d042d7e143cf9
+oid sha256:af86998ead953fc6a693c9bb1a47aa208df1db4855fd8015c4452d56138ba737
 size 523493168