ltxv0.9.7 - gguf Open-Source Model: Effortlessly Convert Images to Videos with Plug-and-Play Functionality

Ltxv0.9.7 Gguf

Developed by calcuis

GGUF quantized version based on Lightricks/LTX-Video, focusing on image-to-video tasks, providing a complete plug-and-play workflow.

Text-to-Video EnglishOpen Source License:Other #Text-driven video generation #High dynamic scene rendering #Plug-and-play workflow

Downloads 3,443

Release Time : 5/7/2025

Model Overview

This model is an image-to-video generation model capable of producing high-quality video content based on text descriptions. Suitable for creative content generation, film previews, and other scenarios.

Model Features

Plug-and-play

Provides a complete GGUF kit (model + encoder + VAE), simplifying the installation process.

Automatic tensor size detection

Applied automatic tensor size detection logic to enhance model adaptability.

High-quality video generation

Capable of generating high-quality video content based on text prompts, supporting negative prompt filtering.

Model Capabilities

Text-to-video generation

High-quality video rendering

Negative prompt filtering

Use Cases

Creative content generation

Natural landscape video generation

Generate videos of natural landscapes such as alpine lakes and snow mountains based on text descriptions.

Produces high-quality video content showcasing realistic natural landscapes.

Architectural scene generation

Generate videos of architectural scenes like a solitary wooden house.

Generates detailed architectural scene videos, including dynamic effects like smoke.

Film preview

Camera movement simulation

Simulate film camera movements such as drone flights and camera pushes.

Generates cinematic camera movement videos.

🚀 gguf quantized ltxv0.9.7

This project focuses on the gguf quantization of ltxv0.9.7, enabling efficient image - to - video conversion. It provides a straightforward installation process and a clear workflow for users to generate high - quality video outputs from images.

🚀 Quick Start

Installation Steps

Drag the model to ./ComfyUI/models/diffusion_models.
Drag t5xxl to ./ComfyUI/models/text_encoders.
Drag pig to ./ComfyUI/models/vae.

Workflow

The full set of gguf (model + encoder + vae) can work right away.
Drag the json file or the demo video above to the browser for the workflow.

screenshot

Remark

The auto tensor size detection logic has just been applied.
Update your ComfyUI code to the recent git version, and then it should work.

screenshot

Reference

Base model from lightricks.
ComfyUI from comfyanonymous.
Pig architecture from connector.
gguf - node ([pypi](https://pypi.org/project/gguf - node)|repo|pack)

📄 License

License: other
License Name: other
License Link: LICENSE

📋 Model Information

Property	Details
Model Type	gguf quantized ltxv0.9.7
Base Model	Lightricks/LTX - Video
Pipeline Tag	image - to - video

🎨 Widget Examples

Example 1

Text Prompt: A drone quickly rises through a bank of morning fog, revealing a pristine alpine lake surrounded by snow - capped mountains. The camera glides forward over the glassy water, capturing perfect reflections of the peaks. As it continues, the perspective shifts to reveal a lone wooden cabin with a curl of smoke from its chimney, nestled among tall pines at the lake's edge. The final shot tracks upward rapidly, transitioning from intimate to epic as the full mountain range comes into view, bathed in the golden light of sunrise breaking through scattered clouds.
Negative Prompt: low quality, worst quality, deformed, distorted, disfigured, motion smear, motion artifacts, fused fingers, bad anatomy, weird hand, ugly
Output: samples\ComfyUI_00001_.webp

Example 2

Text Prompt: 0.9.7 - dev (same prompt as 1st)
Output: samples\ComfyUI_00002_.webp

Example 3

Text Prompt: 0.9.7 - distilled (same prompt)
Output: samples\ComfyUI_00003_.webp

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