Trained for 0 epochs and 7500 steps.

Trained with datasets ['text-embeds-flux', 'text-embeds-photocb-flux', 'celebrities', 'comicstrips', 'movieposters', 'normalnudes', 'propagandaposters', 'guys', 'pixel-art', 'signs', 'moviecollection', 'bookcovers', 'nijijourney', 'experimental', 'ethnic', 'sports', 'gay', 'architecture', 'shutterstock', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp', 'sfwbooru']
Learning rate 0.0001, batch size 4, 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: terminusresearch/flux-booru-v0.2
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1575bdaf36f449891431426e4a00eed170be07aec390997c3d49132a8d6d08f
+oid sha256:dc4730fca79647dacd465cce0a6b00b88c4de30c7a262c515187aceaddb097b9
 size 3235871604