Trained for 55 epochs and 10000 steps.

Trained with datasets ['text-embed-cache', 'autotrain-512', 'autotrain-crop-512', 'autotrain-768', 'autotrain-crop-768', 'autotrain-1024', 'autotrain-crop-1024']
Learning rate 0.0004, 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: /workspace/models/FLUX.1-dev
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:233d9159bdb57097b20858c50ab15321278d5800386a73089de8787cc7873f36
+oid sha256:9a9c88e1cc9fc6c05957d820fb59e99d8802db84664a57ac8249c9482c347721
 size 52369144