Trained for 306 epochs and 7000 steps.

Trained with datasets ['makima-text-embeds', 'makima-512']
Learning rate 0.0002, batch size 32, 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 sha256:8facffef2ff949686ad70741028a56309e655e7049f439f1c612966a415dfb94
+oid sha256:394b8a855eddc833db7ba5f4532be12673b9411ba1525b3e22531292ed1870db
 size 194456044