CivArchive
    Lazy Wan 2.2 V2V video extension workflow - v1.0
    NSFW

    v1.2 finally out.

    all instructions + custom node info are included in the workflow readme section.

    v1.1 is out.

    Some minor improvement on face morphing/degradation issue.

    Minor improvements on scene transition.

    Please get: https://github.com/ltdrdata/was-node-suite-comfyui and https://github.com/wildminder/ComfyUI-KEEP for v1.1

    As requested by many of you, here is my video extension workflow.

    With this you can infinitely extend your videos to your liking.

    Have fun and join my discord to contact me directly.

    Custom Nodes:

    https://github.com/pythongosssss/ComfyUI-Custom-Scripts

    https://github.com/yolain/ComfyUI-Easy-Use

    https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite

    https://github.com/cubiq/ComfyUI_essentials

    https://github.com/banodoco/steerable-motion

    https://github.com/Fannovel16/ComfyUI-Frame-Interpolation

    https://github.com/willmiao/ComfyUI-Lora-Manager

    https://github.com/Smirnov75/ComfyUI-mxToolkit

    https://github.com/ltdrdata/was-node-suite-comfyui

    https://github.com/wildminder/ComfyUI-KEEP

    Description

    FAQ

    Comments (14)

    Melty1989Oct 11, 2025
    CivitAI

    Excellent work, although it'd be nice to have a starting image as the input instead of directly loading a video.

    jarlax215Oct 11, 2025· 1 reaction

    They're other one is for that! https://civitai.com/models/2005198?modelVersionId=2296424 Can recommend!

    ac2023Oct 12, 2025
    CivitAI

    You are absolutely amazing! Thank you! Do you have a trick when the video looks great, but it does not perfectly resemble what you had in mind? For example, the person looks great in the first frame, but in frame 30, the person opens the mouth and you notice that the teeth don't look like what you had in mind. However, if you choose an image for frame 1 which shows the teeth perfectly, then for example the person looks not what you had in mind when the mouth is closed. I hope you understand what I mean. I wish there was a way to feed 3 images instead of 1 for the first frame.

    Chriqro
    Author
    Oct 12, 2025

    @ac2023
    im working on an improments for the next version that would hopefully resolve the issue.

    angelfive036698Oct 12, 2025
    CivitAI
    Thank you, brother, for the helpful information. But why is the final video blurry and broken? Is the Laura setting wrong?

    @Chriqro lightning lora or lightspeed lora?

    I have the same problem. Blurry at the end.
    The only error message that I found:
    clip missing: ['encoder.block.0.layer.0.SelfAttention.q.scale_weight', 'encoder.block.0.layer.0.SelfAttention.k.scale_weight',
    Couldn't find the solution.

    Chriqro
    Author
    Oct 14, 2025

    @perfectboobcollector do you have the text encoder loaded correctly?

    airdrop2me907Oct 12, 2025· 5 reactions
    CivitAI

    Can you please add screenshots of which Loras and where I need to install them?

    maxtusrordey512Oct 13, 2025
    CivitAI

    How do you get your undressing generations to be so good?

    mickyIammickyOct 14, 2025

    It's not good. Just look at her face, it's completely changed. You call this good when it can't even maintain face consistency?

    onetwofourtOct 19, 2025

    @mickyIammicky Do you reccomend something else to achieve better consistency

    AnonnoyingOct 14, 2025· 8 reactions
    CivitAI

    THANK YOU FOR INCLUDING CUSTOM NODES HOLY FUCK I WISH PEOPLE DID THAT MORE.

    jbear2447Oct 19, 2025

    For realses.

    Workflows
    Wan Video 2.2 I2V-A14B

    Details

    Downloads
    1,062
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/11/2025
    Updated
    5/14/2026
    Deleted
    -

    Files

    lazyWan22V2VVideo_v10.zip