CivArchive
    Wanvideo 14b MasterModel Workflow - Text2Video
    Preview 80638082

    This workflow is for use with Kijai's Wanwrapper nodes and the new Master Model Wan 14b checkpoint merge that allows for text to video in high quality in only 1.5 minutes on a 4090 before upscaling.

    Master model download:

    https://civarchive.com/models/1651125/wan2114bt2v-fusionx

    GGUFs of the above are available here:

    https://huggingface.co/lym00/Wan14BT2V_MoviiGen_AccVid_CausVid_MasterModel_GGUF

    Kijai's Wan Wrapper nodes:

    https://github.com/kijai/ComfyUI-WanVideoWrapper

    The upscale model I'm using in the workflow:

    https://openmodeldb.info/models/4x-NomosWebPhoto-RealPLKSR

    1280x720p: On a 3090/4090, I'd change these settings for 720p: Wanvideo Empty Embeds changed to 1280x720. Wanvideo Block Swap node changed from 0 to 20. Wanvideo Sampler Node to 15 steps, cfg 1, shift 8, with euler/beta scheduler. You can probably get rid of the upscale node, but you should set the CRF quality setting on the video combine node from 30 to 19 so you don't compress out the increase in resolution.

    Description

    This is for the text to video version.

    FAQ

    Workflows
    Wan Video 14B i2v 480p

    Details

    Downloads
    680
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/5/2025
    Updated
    4/30/2026
    Deleted
    -

    Files

    wanvideo14b_text2video.zip

    Mirrors

    CivitAI (1 mirrors)