Trained for 2 epochs and 5000 steps.

Trained with datasets ['text-embed-cache', 'dore-background-512', 'dore-background-768', 'dore-background-1024', 'dore-background-1536', 'dore-background-512-crop', 'dore-background-768-crop', 'dore-background-512-tight-crop', 'dore-background-768-tight-crop', 'dore-background-1024-crop']
Learning rate 0.0004, 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 sha256:3c585678cfd250ea3c39226309d8ec3192e19f58aad1c742771c34a9d3ad2716
+oid sha256:2471e55f9486b8708cf06de746796de68bc1bb9d2123f037589d4d6120c61401
 size 109535132