Trained for 2666 epochs and 8000 steps.

Trained with datasets ['text-embeds', 'disney-black-and-white']
Learning rate 5e-05, batch size 8, 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: Lightricks/LTX-Video
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0995d55050044e3e9ce048a5d7b1c0e414c488e7071e0ae55461abcb05a5f0
+oid sha256:2ca2645bcec95036ff259211e8cd486a6467efe1cfc49824b70a210dafbac49b
 size 587307360