Trained for 89 epochs and 1700 steps.

Trained with datasets ['text-embeds', 'josh']
Learning rate 8e-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 '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:df4c965492428ba7274325db2bf0f5e86efc1eaf3f523d5bd040c9110110f9c2
+oid sha256:9690d3d590d1c2b11463938e6e75278f8f787fca11691508f9242d70c3a48fec
 size 209263048