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.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for Symphone/ltx-video-2b-v0.9-fp8
Base model
Lightricks/LTX-Video