13th of January 2026 update !!IMPORTANT!!

Turns out the video VAE in the initial distilled checkpoints has been wrong one all this time, which (of course) was the one I initially extracted. It has now been replaced with the correct one, which should provide much higher detail

at this moment this requires using updated KJNodes VAELoader to work correctly


Separated LTX2 checkpoint for alternative way to load the models in Comfy

image

LTX2 GGUFs that include the metadata also work with the setup, if your GGUF nodes are up to date.

Downloads last month
26,414
GGUF
Model size
19B params
Architecture
ltxv
Hardware compatibility
Log In to view the estimation

4-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support