CivArchive
    ← All articles
    Published March 10, 2025by driftjohnson

    LTXV Video Generation Supported in ComfyUI - Another Day one support release ! 2025 UPDATE!

    3.6K views14 reactions7 comments on CivitAI38 collected
    videosupportcomfyuitext2videoimage2videogentool guideday oneltxv

    LTXV is a new Video Generation model, which is enjoying Day one release support in ComfyUI

    2025 Update: LTXV 2B v095 was released! marked (NEW) links!

    Xoda-LTXV-Video-Pack

    Github Link: https://github.com/MushroomFleet/DJZ-Workflows/tree/main/XODA-LTXV-Video-Pack
    CivitAI Link: https://civitai.com/models/974859
    VIDEO:

    full details are below!

    Prompt Example:
    "The turquoise waves crash against the dark, jagged rocks of the shore, sending white foam spraying into the air. The scene is dominated by the stark contrast between the bright blue water and the dark, almost black rocks. The water is a clear, turquoise color, and the waves are capped with white foam. The rocks are dark and jagged, and they are covered in patches of green moss. The shore is lined with lush green vegetation, including trees and bushes. In the background, there are rolling hills covered in dense forest. The sky is cloudy, and the light is dim."

    I collected all the full length video prompt examples and added that list here.
    I will add new video prompt lists to that Repo, using the prefix "LTXV-video" for each.
    I have also built a dedicated promptGen module for ACE-HOLOFS here.
    - update: added 110 video prompts as lists of ten prompts per category.
    - update: LightTricks saw my post on the PromptGen and release their own version which is much easier to use, and is more portable too, you can use it here:
    https://huggingface.co/spaces/Lightricks/LTX-Video-Playground

    You Will Need:


    Main Checkpoint model:
    https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.safetensors

    https://huggingface.co/Lightricks/LTX-Video/resolve/main/ltx-video-2b-v0.9.5.safetensors (NEW)
    Place inside: ComfyUI\models\checkpoints

    GGUF weights:
    https://huggingface.co/city96/LTX-Video-0.9.5-gguf/tree/main
    Place inside: ComfyUI\models\unet

    CLIP model:
    https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors
    Place inside: ComfyUI\models\clip

    https://huggingface.co/Comfy-Org/mochi_preview_repackaged/blob/main/split_files/text_encoders/t5xxl_fp16.safetensors (NEW)

    Place inside: ComfyUI\models\text_encoders\

    Text Encoder model:
    https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
    Place inside: ComfyUI\models\text_encoders

    *this is held in two parts, so, follow these instructions to successfully get them into the correct folder; Clone the text encoder model to models/text_encoders:

    (run command line / terminal from your "ComfyUI" folder)

    cd models/text_encoders && git clone https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS

    More Information

    LTXV Website (LightTricks): https://www.lightricks.com/ltxv

    LTXV Huggingface: https://huggingface.co/Lightricks/LTX-Video
    LTXV Author Main Model Github: https://github.com/Lightricks/LTX-Video

    LTXV Author ComfyUI Github: https://github.com/Lightricks/ComfyUI-LTXVideo

    ComfyOrg Blog Post: https://blog.comfy.org/ltxv-day-1-comfyui/

    ~

    Default/Example Workflows:

    • ComfyUI Example

    https://comfyanonymous.github.io/ComfyUI_examples/ltxv/ltxv_text_to_video.json

    • LTXV Author text2video

    https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/assets/ltxvideo-v2v.json

    • LTXV Author image2video

    https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/assets/ltxvideo-i2v.json