LTX-Video Open-Source Text-to-Video Model - Support Free Video Content Generation from Text or Image

Ltxv 13b 0.9.7 Distilled GGUF

Developed by wsbagnsv1

LTX-Video is a text-to-video generation model that supports creating video content from text or images.

Text-to-Video EnglishOpen Source License:Other #Text-to-Video Generation #ComfyUI Adaptation #T5 Encoder Compatibility

Downloads 6,208

Release Time : 5/14/2025

Model Overview

This model, developed by Lightricks, is a text-to-video generation model capable of producing corresponding video content based on text descriptions or input images. It is suitable for creative content generation, video editing assistance, and similar scenarios.

Model Features

GGUF Quantization Format

The model has been converted to GGUF format for easy use in frameworks like ComfyUI.

Multimodal Input Support

Supports both text and images as input sources for video generation.

LoRA Adapter Compatibility

Supports fine-tuning the model using LoRA adapters.

Model Capabilities

Text-to-Video Generation

Image-to-Video Generation

Creative Content Generation

Use Cases

Creative Content Production

Short Video Generation

Automatically generates short video content based on text descriptions.

Produces coherent video clips that match the description.

Image Animation

Converts static images into dynamic videos.

Adds reasonable motion effects to images.

🚀 LTX-Video GGUF Conversion

This project offers a direct GGUF conversion of the 13b - 0.9.7 - distilled variant from Lightricks/LTX-Video. It enables seamless integration with ComfyUI for text - to - video and image - to - video tasks.

🚀 Quick Start

The model files can be used in ComfyUI with the [ComfyUI - GGUF](https://github.com/city96/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 - distilled	`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 - distilled - GGUF/blob/main/exampleworkflow.json) - based on the [official example workflow](https://github.com/Lightricks/ComfyUI - LTXVideo/tree/master/example_workflows/)

📄 License

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