Trained for 5 epochs and 800 steps.

Trained with datasets ['text-embed-cache', 'dreamgrain-512', 'dreamgrain-crop-512', 'dreamgrain-1024', 'dreamgrain-crop-1024']
Learning rate 0.001, 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: 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 sha256:233bc93f3859d7b2a5d7e1f5d93110b017e8643cc907aa26259345426362982c
+oid sha256:6a4c1a6ed89d43a49332d4b9bec5ec3666b5a9dace27c7b2737a72f21e580856
 size 109535132