---
license: other
license_name: other
license_link: LICENSE
language:
- en
base_model:
- Lightricks/LTX-Video
pipeline_tag: text-to-video
tags:
- text-to-video
- image-to-video
- video-to-video
- ltx-video
- ltxv
- gguf-comfy
---

# GGUF quantized version of LTX-Video

![screenshot](https://raw.githubusercontent.com/calcuis/comfy/master/ltxv.gif)

## Setup (once)
- drag ltx-video-2b-v0.9.1-q4_0.gguf ([1.09GB](https://huggingface.co/calcuis/ltxv-gguf/blob/main/ltx-video-2b-v0.9.1-q4_0.gguf)) to > ./ComfyUI/models/unet
- drag t5xxl_fp8_e4m3fn.safetensors ([4.89GB](https://huggingface.co/calcuis/ltxv-gguf/blob/main/t5xxl_fp8_e4m3fn.safetensors)) to > ./ComfyUI/models/clip
- drag ltx-video-vae.safetensors ([838MB](https://huggingface.co/calcuis/ltxv-gguf/blob/main/ltx-video-vae.safetensors)) to > ./ComfyUI/models/vae

## Run it straight (no installation needed way)
- run the .bat file in the main directory (assuming you are using the gguf-comfy pack below)
- drag the workflow json file (below) to > your browser

### Workflows
- example workflow for [gguf](https://huggingface.co/calcuis/ltxv-gguf/blob/main/workflow-ltxv-gguf.json) (see demo above)
- example workflow for the original [safetensors](https://huggingface.co/calcuis/ltxv-gguf/blob/main/workflow-ltxv-safetensors.json)

### Review
- q2_k is super fast but not usable; keep it for testing only

### References
- base model from [lightricks](https://huggingface.co/Lightricks/LTX-Video)
- comfyui from [comfyanonymous](https://github.com/comfyanonymous/ComfyUI)
- gguf node from [city96](https://github.com/city96/ComfyUI-GGUF)
- gguf-comfy [pack](https://github.com/calcuis/gguf-comfy/releases)