Trained for 6 epochs and 8750 steps.

Trained with datasets ['text-embed-cache', 'marco-background-512', 'marco-background-768', 'marco-background-1024', 'marco-background-1536', 'marco-background-512-crop', 'marco-background-768-crop', 'marco-background-512-tight-crop', 'marco-background-768-tight-crop', 'marco-background-1024-crop']
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: black-forest-labs/FLUX.1-dev

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3927b429cc2a765bf8d93a93b9e14a1e15d92609b7a822962674726a35b2280b
+oid sha256:cf09d16235f908a3d63f9c45153053955243a8f980050fd8bd782ebf78873668
 size 109535132