Trained for 2 epochs and 9500 steps.

Trained with datasets ['text-embed-cache', 'mnmlsmo_architecture_photography_style-512', 'mnmlsmo_architecture_photography_style-768', 'mnmlsmo_architecture_photography_style-1024', 'mnmlsmo_art_photography_style-512', 'mnmlsmo_art_photography_style-768', 'mnmlsmo_art_photography_style-1024', 'mnmlsmo_furniture_photography_style-512', 'mnmlsmo_furniture_photography_style-768', 'mnmlsmo_furniture_photography_style-1024', 'mnmlsmo_homewares_photography_style-512', 'mnmlsmo_homewares_photography_style-768', 'mnmlsmo_homewares_photography_style-1024', 'mnmlsmo_interiors_photography_style-512', 'mnmlsmo_interiors_photography_style-768', 'mnmlsmo_interiors_photography_style-1024', 'mnmlsmo_lighting_photography_style-512', 'mnmlsmo_lighting_photography_style-768', 'mnmlsmo_lighting_photography_style-1024', 'mnmlsmo_moods_photography_style-512', 'mnmlsmo_moods_photography_style-768', 'mnmlsmo_moods_photography_style-1024', 'mnmlsmo_technology_photography_style-512', 'mnmlsmo_technology_photography_style-768', 'mnmlsmo_technology_photography_style-1024']
Learning rate 0.0001, batch size 2, 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: FLUX.1-dev
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf63f73a8af038646db0079b73b262f167c9a60bb4d13c122f02c455520dea8
+oid sha256:cc8d9aeb5491d5a2ac40e691f6efc02ad69aeef959386c26761fdcecf8659b83
 size 284210572