I've created a RunPod template for the new LTX 13B model.
It has both T2V and I2V workflows for both the full and quantized models.
Deploy here: https://get.runpod.io/ltx13b-template
Please make sure to change the environment variables before deploying to download the required model.
I recommend 5090/4090 for the quantized model and L40/H100 for the full model.
For more workflows, LoRAs and RunPod templates, join my Discord:
https://discord.gg/ZVWVhT43GW
10,000+ members. New drops land there first, and that is where I answer questions.
Follow me here so you see the next one.
.jpeg)

