CivArchive
    XODA LTXV Video Pack - v4
    NSFW

    XODA-LTXV-Video-Pack

    0.9.5 base model update:
    TBA version 8 workflows released!

    0.9.1 base model update:

    Initial Release video:

    click show more, full details are below!

    Consistent Video Variations can be provided by using my String Painter Node!

    A comprehensive workflow pack for ComfyUI implementing the LightTricks LTXV video generation model, complete with example workflows, prompts, and custom tools for streamlined video generation.

    Overview

    This pack brings together essential workflows, tools, and resources for working with the groundbreaking LTXV real-time video generation AI model from LightTricks. It includes official example workflows, custom prompt generation tools, and extensive prompt lists to help users get started quickly.

    Contents

    Example Workflows

    The pack includes the official ComfyUI maintainer and LTXV author-provided workflows:

    • AUTHOR-ltxvideo-i2v.json

    • AUTHOR-ltxvideo-v2v.json

    • COMFY-ltxv_image_to_video.json

    • COMFY-ltxv_text_to_video.json

    Resources and Tools

    1. Getting Started Guide

    2. LTXV PromptGen LLM Module

    3. Curated Prompt Lists

    4. Integration with DJZ-Nodes

      • Custom nodes for workflow automation

      • Includes Zenkai-Prompt nodes for automated prompt handling

      • Seamless integration with provided prompt lists

      • Located at: DJZ-Nodes/Prompts

    Getting Started

    1. Clone this repository

    2. Follow the setup guide at CivitAI Article #9115

    3. Install required models and dependencies

    4. Load example workflows in ComfyUI

    Features

    • Official LTXV example workflows

    • Custom prompt generation tools

    • Extensive prompt library

    • Automation capabilities

    • Integration with existing tools

    Requirements

    Please refer to the Getting Started Guide for a complete list of required models and dependencies.

    Description

    FAQ

    Comments (4)

    iseedeadpeople88Dec 5, 2024· 1 reaction
    CivitAI

    Thanks for all this great research. Have you tried getting the Detail Daemon and STG working with i2v? I've tried just using LTXVImgToVideo rather than the EmptyLTXVLatentVideo and as far as I can tell it's not following the provided image latent very closely, if at all. It produces a different output from the empty latent but definitely not what I would expect from i2v.

    I would say similarly even STG i2v without the Detail Daemon / Lying Sigma mods is not behaving in the i2v fashion I'd expect.

    Would be great to take advantage of these mods with solid i2v.

    john2staiDec 6, 2024· 1 reaction

    To use STG for i2v, you need the add LTX latent guide node from LTXTricks in the workflow. I have got STG working for i2v. It can produce better quality video with reduced number of steps. However, detail daemon in STG workflow, doesn't provide any improvements/increased motions as in the usual workflow.

    driftjohnson
    Author
    Dec 6, 2024

    yep exactly as we discussed in the videos on this pack STG improved the video quality far more than detailer daemon - that was a community experiment completed before STG nodes were published. my examples are just that, so i do expect people learn how to use the nodes and create their own workflows - it's like making a burger, you want extra cheese and bacon, just add that!
    have fun

    driftjohnson
    Author
    Dec 6, 2024

    also the github pack is faster to update than the civit pack version, this stops there from being 100 versions every week.

    Workflows
    LTXV

    Details

    Downloads
    251
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/29/2024
    Updated
    5/12/2026
    Deleted
    -

    Files

    xodaLTXVVideoPack_v4.zip

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)