Trained for 147 epochs and 2500 steps.

Trained with datasets ['text-embeds', 'image-embeds', 'julia']
Learning rate 1e-05, batch size 1, and 2 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'linspace' 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:cd27462869fffaeda973699915c13a3f337cb32750d69f3d7da126e1e25bcf03
-size 97190240
+oid sha256:3b136dfc81919bd2c26de98ab11f5cbacd71519fe6c2ac8b736c220b9ebd00d0
+size 37406344