CivArchive
    Post Processing IMG/VIDEO Any - v1.055
    Preview 129406893

    simple workflow to do the post processing for mainly videos.

    since i get many OOM. in some parts of the video generations. i split the post processing to avoid this problem.

    any content of this workflows dont require checkpoint models. only his own models like rife49 for interpolation. etc.etc.etc.

    v1.05 - requires now my own custom nodes to solve some issues from now on

    shirosaki33/shiroaudio: custom nodes for comfy, related to audio

    v1.055 - experimental tools
    shirosaki33/shirotools: many utility tools made for different situations

    the image process is just a extra.

    you can do by single file or batch path in both.

    Description

    Added experimental field.

    *small issue detected*
    for some reason experimental nodes only work after first run of workflow with bypass on this nodes, run the first time with bypass in all experimental nodes. after conclude de run enable and run normally

    The contents of this version are still under testing.

    They may be removed or improved later, depending on the results.

    The focus of this update was to add a function to correct the "seamless" aspect of videos as best as possible.

    nodes were created to solve this.

    • autocrop by similarity = automatic removes initial frames based on similarity (color,bright,position,pose,etc)

    • de-stutter = This first one will clean frames between the end/beginning that are very similar (after interpolation)

    • The other two are the same, but work with/without an interpolation model.

    They will take an average of frames between the end and beginning, interpolate as if it were a new line, and take the middle frame between last/first and add it as a [bridge] to make the transition look more natural. For an automated mode, I've had good results so far. However, this is not a 100% functional fix for eveything. It's under testing. Therefore, it may be necessary to adjust the fields depending on the video you are adjusting.

    use only one of the bridge system.

    FAQ

    Workflows
    LTXV 2.3

    Details

    Downloads
    78
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/2/2026
    Updated
    5/8/2026
    Deleted
    -

    Files

    postProcessingIMG_v1055.zip

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    postProcessingIMG_v1055.zip

    Mirrors

    CivitAI (1 mirrors)

    postProcessingIMG_v1055.zip

    Mirrors

    CivitAI (1 mirrors)