Trained for 103 epochs and 15000 steps.

Trained with datasets ['text-embed-cache', 'crrllcrrllxovrtn_subjects_flat-512', 'crrllcrrllxovrtn_subjects_flat-768', 'crrllcrrllxovrtn_subjects_flat-1024']
Learning rate 0.0001, 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: FLUX.1-dev
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8561a6a4734e4a6f9358e28877c18350eb097c49970b4285f2de7af07449cfd
-size 284210572
+oid sha256:0b4e223fb830adad221c6a7b6ecfb28be3023d3c1ebc993bdb9d6e54cb3a0739
+size 284210508