This repository contains GGUF quantized weights for the LTX 2.3 video generation model. It is designed for local inference using diffuser-based GGUF loading logic and requires approximately 5GB VRAM for 81-frame generation. Note that it is not compatible with standard ComfyUI or certain other GGUF nodes.
LTX 2.3 Test is a Quantised & converted weights project. It focuses on running video generation models locally with reduced memory requirements using GGUF format. It is built as an open-source project for Local AI video generation enthusiasts. The project is open source (Open Source). LTX 2.3 Test is available on the web and API.
Behind LTX 2.3 Test is smthem.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do