Trained for 9 epochs and 12500 steps.

Trained with datasets ['text-embed-cache', 'drk-256', 'drk-crop-256', 'drk-512', 'drk-crop-512', 'drk-768', 'drk-crop-768', 'drk-1024', 'drk-crop-1024', 'drk-1440', 'drk-crop-1440']
Learning rate 8e-05, batch size 3, 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 sha256:1e3d56a5c980f335a9f75468e946efd62fbe3237b5a21abf9a0f698b4e4cb7a1
+oid sha256:79e4e126440f26bfbc4e5d8bb0f5a9222f829e19ebaae8899ef3874dbb66c15d
 size 109535132