Trained for 4 epochs and 3100 steps.

Trained with datasets ['text-embed-cache', 'cassatt-oil-512', 'cassatt-oil-768', 'cassatt-oil-1024', 'cassatt-oil-1536']
Learning rate 0.0002, 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 sha256:10e16626b7a145c6c6fdae231b8231a44bcc705d58baba0975dfa753e3d8bf3f
+oid sha256:96262c5b3561ed980bc6f64685a6e51e18a504df39610615a181e424cf20d55f
 size 109535132