CivArchive
    LTX-2.3 TTS (Distilled GGUF) workflows - v1.0.2
    Preview 124739072

    Important Notice

    Optimized to work with the latest version of ComfyUI (v0.18.1 + Frontend 1.42.8).

    Overview

    An experimental TTS (Text-to-Speech) workflow using the LTX-2.3 model.
    It does not generate video. Since LTX-2.3 has strong audio generation capabilities, this workflow focuses solely on TTS for convenience.

    How to Use

    Write the language and script in the prompt.
    Providing an optional reference image may help generate audio closer to your intended result.

    Description

    v1.0.2 : Change to hybrid generate. (cfg3.0 3step+cfg1.0 5step)

    FAQ

    Workflows
    LTXV 2.3

    Details

    Downloads
    225
    Platform
    CivitAI
    Platform Status
    Available
    Created
    3/20/2026
    Updated
    5/13/2026
    Deleted
    -

    Files

    ltx23TTSDistilledGGUF_v102.zip

    Mirrors

    ltx23TTSDistilledGGUF_v101.zip

    Mirrors

    HuggingFace (1 mirrors)

    ltx23TTSDistilledGGUF_v10.zip

    Mirrors

    HuggingFace (1 mirrors)