Trained for 3 epochs and 1800 steps.

Trained with datasets ['text-embeds', 'baahubaliflux']
Learning rate 0.0003, batch size 1, 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 sha256:5a3763772d7babba4467e84d2aa13df2bee257c750186f1f006cd4929c574145
+oid sha256:98569f12f8bd99645f20c27d5aebb6cdd4d54e1070f3249da904b49e433e292b
 size 37406344