Trained for 1 epochs and 1750 steps.

Trained with datasets ['text-embed-cache', 'codex-mendoza-itso-512', 'codex-mendoza-itso-1024', 'codex-mendoza-itso-512-crop', 'codex-mendoza-itso-1024-crop']
Learning rate 0.0008, batch size 2, 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 sha256:223c1b17c34494cf10c1370aaa7b7308e617155c0d37e7586dadb60ec100a190
+oid sha256:31021d9b380a475b57d380cd699f20ea9b4c29b0a4f956da52fed2ad6d2cf40d
 size 109535132