ltxv-13b-0.9.7-dev-GGUF Open Source Model - Easily Generate Videos from Text and Images

Ltxv 13b 0.9.7 Dev GGUF

Developed by wsbagnsv1

GGUF quantized version of the 13b-0.9.7-dev variant based on Lightricks/LTX-Video, supporting text-to-video and image-to-video generation tasks.

Text-to-Video EnglishOpen Source License:Other #Text-to-Video Generation #GGUF Quantization #ComfyUI Compatibility

Downloads 25.99k

Release Time : 5/6/2025

Model Overview

This is a text-to-video and image-to-video generation model optimized in GGUF quantization format, suitable for ComfyUI workflows.

Model Features

GGUF Quantization

The model has undergone GGUF quantization, optimizing storage and computational efficiency while maintaining good generation quality.

ComfyUI Integration

Supports usage in ComfyUI via ComfyUI-GGUF custom nodes, facilitating integration into existing workflows.

Multi-Component Support

Compatible with T5 text encoders and specific VAE models, offering flexible configuration options.

Model Capabilities

Text-to-Video Generation

Image-to-Video Generation

Use Cases

Creative Content Generation

Short Video Generation

Automatically generates short video content based on text descriptions.

Produces video clips that match the text description.

Image-to-Video Conversion

Transforms static images into dynamic video content.

Generates dynamic effects based on input images.

🚀 LTX-Video GGUF Conversion

This project provides a direct GGUF conversion of the 13b - 0.9.7 - dev variant from Lightricks/LTX - Video. It enables users to utilize the model in ComfyUI, facilitating text - to - video and image - to - video tasks.

🚀 Quick Start

The model files can be used in ComfyUI with the ComfyUI - GGUF custom node. Place the required model(s) in the following folders:

Property	Details
Base Model	Lightricks/LTX - Video
Library Name	gguf
Quantized By	wsbagnsv1
Tags	ltx - video, text - to - video, image - to - video
Language	en
License	other
License Link	LICENSE.md

Type	Name	Location	Download
Main Model	ltxv - 13b - 0.9.7 - dev	`ComfyUI/models/diffusion_models`	GGUF (this repo)
Text Encoder	T5 - V1.1 - XXL - Encoder	`ComfyUI/models/text_encoders`	Safetensors / [GGUF](https://huggingface.co/city96/t5 - v1_1 - xxl - encoder - gguf)
VAE	ltxv - 13b - 0.9.7 - vae	`ComfyUI/models/vae`	[Safetensors](https://huggingface.co/wsbagnsv1/ltxv - 13b - 0.9.7 - dev - GGUF/blob/main/ltxv - 13b - 0.9.7 - vae - BF16.safetensors)

[Example workflow](https://huggingface.co/wsbagnsv1/ltxv - 13b - 0.9.7 - dev - GGUF/blob/main/exampleworkflow.json) - based on the [official example workflow](https://github.com/Lightricks/ComfyUI - LTXVideo/tree/master/example_workflows/)

📄 License

This is a direct GGUF conversion of the 13b - 0.9.7 - dev variant from [Lightricks/LTX - Video](https://huggingface.co/Lightricks/LTX - Video). As this is a quantized model not a finetune, all the same restrictions/original license terms still apply. The license information can be found here.

🔧 Technical Details

Notes

⚠️ Important Note

As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.

💡 Usage Tip

Comfyui now supports the ggufs natively, so you just need to update comfyui to the latest version and if some issues persist update all the nodes in the workflow.

Other T5 clips will probably work as well, just use one that you like, you can get them as safetensors or ggufs. The best I tried was the t5 v1.1 xxl one.

Loras do work, but you need to follow the steps in the example workflow and don't use torchcompile with loras!

Teacache works with ltx but atm not really good. The rel_l1_thresh only seems to work at 0.01 in my testing and even that causes some noticeable quality drops, best leave it disabled.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご