Trained for 4 epochs and 10000 steps.

Trained with datasets ['text-embeds', 'natural-booru-caption-flux', 'natural-full-caption-flux']
Learning rate 0.0001, 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 sha256:5a4a0329cf77301f43cdd22200f1a062432bf742e281570989786db3a6d929f2
+oid sha256:803691a109226ecfce5a531e4560ccacf1bc5c78891ebc709b45057cb054ba96
 size 109535132