Trained for 6 epochs and 8000 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-1024-crop']
Learning rate 0.0006, 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 sha256:948d267f1d0892cc4de726e22d36fd556ef9640d1c24bda69a63497cf882309e
-size 109535132
+oid sha256:0bcb5bca7074da313c17d4ea0563a313eb900d8760191a9a07358d8646d1fd76
+size 109535068