CivArchive
    LTX 2.5 - Unlimited Video Length - Sing or Talk (Alternating Shots) - v3.1
    NSFW

    cant seem to put my PG videos up here.Check Red for video.

    LTX 2.5 is here... the LIP SYNC is much better in 2.5.

    This workflow is for people who want long videos of someone talking/singing.

    Final demo (not allowed by civit and some edits with Davinci)

    I suggest updating to 2.5 if you use LIP SYNC frequently

    Please note this workflow requires my custom nodes : "TK Handy Nodes"

    This video was built for LTX 2.3, but most of this still applies, might add a new video, if there is any interest.

    Description

    3.1

    Had to fix a bug (oops). Now splitting audio when there is silence for better transition. You will need the latest TKNodes

    go to custom_nodes folder

    git clone https://github.com/trashkollector/TKNodes

    FAQ

    Comments (8)

    skyrimer3dMar 26, 2026
    CivitAI

    This worked brilliantly, feels so natural and movie like, amazing job. Only two things i don't like, if you use a close up shot and a wide shot, and the camera zooms out with the close up shot, it completely reinvents the clothing. Secondly, i'm not conviced about the fade out effect, that is barely used in movie dialogues, feels rather out of place. However the tech itself is very impressive, i hope you can interate with this for maybe a third shot / two character dialogues etc. , maybe add the recent id-lora that clones voices inside the LTX 2,3 workflow? can't wait to see what you come up with, great job!

    trashkollector175
    Author
    Mar 27, 2026· 1 reaction

    ID lora is a VRAM hog.. waiting for Kijai to maybe provide some solutions and then will try to implement.

    trashkollector175
    Author
    Mar 27, 2026

    if the video is zooming too much try this: the subject is talking. the camera is locked. If you add too many details it will start to zoom out to fill in details.

    skyrimer3dApr 4, 2026

    @trashkollector175 Interesting, i'll try that thanks, i'll check the new version later today and see how it works, thanks for keep on supporting this.

    OTAKKxMar 27, 2026
    CivitAI

    I switched the GGUF model for the regular diffusion one, and I keep gettting VAE errors, saying "no vae", even though all the proper Vaes are set in the proper nodes... does this not work with the regular ltx2.3 dev diffusion model?

    trashkollector175
    Author
    Mar 27, 2026

    can you send me the exact error message. Also, you are going to need a lot of VRAM for regular diffusion model

    OTAKKxMar 27, 2026

    @trashkollector175 I see, I wonder if that could be, even though I have a 5090, i rarely see OOM errors.. I'll test more and will come back if I keep getting errors.

    mushegvip737Mar 29, 2026
    CivitAI

    HI, thank's for your workflow!

    Can i use fp8 model (ltx-2.3-22b-dev_transformer_only_fp8_scaled.safetensors) with this workflow or it's only for low vram ? (my config : rtx 4080 16gb, ram64gb, ssd)

    Workflows
    LTXV 2.3

    Details

    Downloads
    383
    Platform
    CivitAI
    Platform Status
    Available
    Created
    3/25/2026
    Updated
    9/26/2026
    Deleted
    -

    Files

    ltx25UnlimitedVideoLength_v31.zip

    Mirrors