Trained for 94 epochs and 1800 steps.

Trained with datasets ['text-embeds', 'zhijicarv7']
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: /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:c71649bac8eebc7e8eeb075d42d40fe6a8855297a6b2383476b5e830a99b839c
+oid sha256:30b841333138d200ce50865e8d2472b9fedccdd704d283df15a88c91946eec1d
 size 359102760