LTX13B – FP8 Quantized
Hey guys! The new LTX13B is here and it is HOT — blazing fast video generation, sharp output, and now fully available as an FP8 quantized model for major VRAM savings and faster load times.
A GGUF version is also available through the Patreon post for those who prefer that format.
This setup is extremely easy to use. Place it outside your ComfyUI folder, extract, and run. It supports both manual and portable ComfyUI setups.
The setup downloads all required nodes and models automatically.
Important Notes
- This will upgrade your Torch version to 12.8.
- If you want to test without affecting your main setup, visit:
comfy.getgoingfast.pro and set up a clean ComfyUI environment.
How to Use
- Place folder outside your ComfyUI directory
- Extract the ZIP
- Run the setup
- Open ComfyUI
- Load the included workflow
Get Going Fast provides community setup guidance, documentation, tutorials, troubleshooting support, and member services. Get Going Fast does not sell, host, store, mirror, or redistribute AI model files, model weights, training datasets, or third-party project files.
When a setup guide references third-party dependencies, repositories, or model files, it points users to official upstream public sources such as GitHub, Hugging Face, package managers, or original project repositories, subject to those sources' own licenses, terms, and availability.
Get Going Fast is a general-audience AI education and workflow site, not an adult-content site or hosted AI generation service. Do not use Get Going Fast materials, support, guidance, or referenced third-party tools for unlawful, abusive, non-consensual, sexually explicit, exploitative, harassing, deceptive, or privacy-violating content, including misuse of another person's likeness, voice, identity, intellectual property, privacy, or publicity rights. See our Acceptable Use Policy.
If you are a rights holder, platform reviewer, payment processor, or hosting provider with a concern about a listed tool, guide reference, or upstream source, please contact us. We will review the concern promptly and remove or revise references when appropriate.
