Trained for 0 epochs and 21 steps.

Trained with datasets ['text-embed-cache', 'image-dataset-480-wan', 'video-dataset-480-wan']
Learning rate 8e-05, 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: Wan-AI/Wan2.1-T2V-1.3B-Diffusers
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91cc0d483f2ecdc9a75065f1c7d48ebe90bc0cca296e58e67cdeee4318db3894
+oid sha256:0c662a23326398bed817f48543cad6f88b3bf86cc3158c04d14290f388e4afb1
 size 30454216