Trained for 1 epochs and 3000 steps.

Trained with datasets ['text-embeds', 'qxxy style']
Learning rate 0.0003, 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: /mnt/data1/shared_data/FLUX.1-dev/
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6f4aad1a9dded829e2be9bc87cd248238138b014bc91d796026039558be22c
-size 359102760
+oid sha256:74854049d2f1b7822405c2cad51bdf96d3178297dc697bb0fa529b07258fccd2
+size 359103520