Trained for 0 epochs and 3200 steps.

Trained with datasets ['text-embeds', 'image-embeds', 'sfwbooru', 'normalnudes', 'guys', 'signs', 'nsfw-1024', 'anatomy', 'yoga', 'photo-aesthetics', 'text-1mp', 'normalnudes-crop', 'guys-crop', 'signs-crop', 'nsfw-1024-crop', 'anatomy-crop', 'yoga-crop', 'photo-aesthetics-crop', 'text-1mp-crop']
Learning rate 0.0003, 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: 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:f0f5b0a3d1fe2ebadfa5f374a27bd2fdbb0c772773438eaa4f95768978413438
+oid sha256:9cc309ac4bd1672a4e97b98d02a5632d9b11979e2288b8c97bd539f137f57ccb
 size 498220804