Trained for 85 epochs and 600 steps.

Trained with datasets ['text-embeds', 'guimiv3']
Learning rate 0.0002, batch size 8, 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 sha256:4d722220b15e309ee39e00a97bdbb02cb555750b516fc1ba7d119aa5298d001e
+oid sha256:3d2a121e08783450e8a55c89d59b94ecbac131f73c29fdc75ddfe4eb22c8b400
 size 209263048