Trained for 4 epochs and 5000 steps.

Trained with datasets ['text-embed-cache', 'davinci-512', 'davinci-768', 'davinci-1024', 'davinci-1536', 'davinci-crops-512', 'davinci-1024-crop']
Learning rate 0.0003, batch size 3, 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 sha256:1fbfa180ea42fe8a6cb01bb24bd4f8b39a10e8bb1e15fe07cda98c5955b9c643
-size 109535132
+oid sha256:7156151f24fe119f62129493be6b402da4a7d11892e91c0a73cc85768c33aa7b
+size 109535068