Trained for 16 epochs and 4000 steps.

Trained with datasets ['text-embed-cache', 'raphael-512', 'raphael-768', 'raphael-1024']
Learning rate 0.001, batch size 2, 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 sha256:223fa229f94add67262d2c54920a7b8206d7cd3318a17d06f9d4b2b5ea49296f
-size 109535132
+oid sha256:2ea22e5ae8f33070baba8e20201b1a3d16fc79997533a021ada54b5af74aef45
+size 109535068