Trained for 1 epochs and 5000 steps.

Trained with datasets ['text-embed-cache', 'tools_joy_v1-512', 'tools_joy_v1-1024', 'tools_joy_v1-512-crop', 'tools_joy_v1-1024-crop']
Learning rate 0.0001, batch size 1, 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: stabilityai/stable-diffusion-3-medium-diffusers
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef7bb6e820711f6aa8f185ba3980611ce668cfaacbf94fc0e18d59040ddfc827
-size 167619178
+oid sha256:c6c8652cd0e5c04d9b5e65fd1d3220780da90a97a7da8d78f15485babc07da01
+size 167619114