Trained for 2 epochs and 2000 steps.

Trained with datasets ['text-embed-cache', 'jazzy-512', 'jazzy-768', 'jazzy-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: 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 sha256:46ada63979e51ced347b23ef95a375025e97a329a5d6cb7f8da07c6bcb8f6489
+oid sha256:216857f7c8ecf3c3e7e681652019db3c16054ce73ec9eefc696abf751a77cf7d
 size 104667032