---
base_model:
- Lightricks/LTX-Video
---
https://huggingface.co/Lightricks/LTX-Video To quantify, just put the model in your ComfyUI\models\checkpoints

Official support for ComfyUI: https://comfyanonymous.github.io/ComfyUI_examples/ltxv/    

The quantify model file sizes are:
- ltx-video-2b-v0.9-fp8_e4m3fn.safetensors 2.18G takes up about 10g of video memory when running
- ltx-video-2b-v0.9-mixed.safetensors 4.36G Mixed-precision model. It seems that there is not much change in effect, but the size is smaller.