Trained for 6 epochs and 3400 steps.

Trained with datasets ['text-embeds', 'q1sV22-1024-crop', 'q1sV22-512-crop', 'gen-and-inpaint-q1s-1024-reg']
Learning rate 0.001, batch size 1, and 3 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: terminusresearch/FluxBooru-v0.3
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e16daa62245557cf9b47aa21fde1500e726572897494265d04c187d8e664713a
+oid sha256:546beefe4365a3ed1ff34e72cb1b170fe36cb4bc5ff35fa504a296a1c80d227f
 size 194456044