CivArchive

    ltx23 - i2v 1.1

    Slower but better audio and hip movement , use at 0.8-1.0

    ltx23 - i2v 1.0

    Same as previous ones , use at 0.9 or less to have speech

    Audio doesn't always sync up

    ltx2 - i2v 1.1

    Higher rank and resolution , less jittering , with audio.

    Use : fast slow from below from behind held in arms missionary pov riding on top

    lying down side view

    ltx2 - i2v

    Use at 1.0 str , or 0.8-0.9 if you want video to follow the text prompt better

    Add scene description and script "like this"

    Wan2.2 - I2V bulge HIGH
    Use at 1.0 str , or 0.6-0.8 if you want video to follow the text prompt better

    If it's too slow sample more frames in High , speed up to lower count , sample Low.
    Example 81 high > 65 low

    1.1 - 720p version , I2V bulge , with no mixing
    Best at 0.7-0.8 str , add other loras for better effect
    Around 3100 steps
    Same prompt below


    1.0 - 480p version , I2V bulge , mix test
    https://civarchive.com/models/1331682/wan-pov-missionary?modelVersionId=1623136

    Mixed at different proportions to add motion that was lacking
    Also tried merging at higher proportion so this lora is too strong at 1.0 in most cases
    Doesn't always sync , try different prompts/settings
    Trained on 15 videos 48 frames each , 512x512 , around 3800 steps

    Settings used:

    lora str - 0.4 - 0.7
    frames - 49
    steps - 10
    cfg - 6.0
    shift - 5.0


    Promt:
    st0mach ,she is getting fucked , missionary position, pov , stomach is bulging with each thrust,with her legs spread having sex with a man.A man is thrusting his penis back and forth

    Description

    base

    FAQ

    Comments (5)

    melovewrestlingApr 7, 2025· 2 reactions
    CivitAI

    Great job! And the sample vids looks amazing, gonna do some testing and get back to you, thx for the work and upload!

    chrisbraeuer41172035Apr 10, 2025· 1 reaction
    CivitAI

    Looks promising from the examples. Can you post the workflow?

    blo01
    Author
    Apr 10, 2025· 2 reactions

    Just default i2v one with kijai nodes ,
    lower resolution - lower shift value
    higher resolution - higher shift value
    Just match input image for what you will be using it
    https://github.com/kijai/ComfyUI-WanVideoWrapper

    ItsThatTimeAgainApr 18, 2025· 1 reaction
    CivitAI

    Does this work on 720p model or only 480p? Somehow the insertion doesn't want to go deep, just moving slightly. Might also be affected from trying to use boob bounce lora and another missionary one that was suggested in description

    blo01
    Author
    Apr 23, 2025· 3 reactions

    The more loras you add the less each works I think (and slower the video becomes maybe),
    Try v1.1 as v1.0 was trained on 480p model (same training set, no mix but its 512x512 res still )
    Might work better with other loras now , also start with image that has a slight bulge maybe , its all random depends on prompt and seed

    LORA
    Wan Video 14B i2v 480p

    Details

    Downloads
    2,861
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/7/2025
    Updated
    5/20/2026
    Deleted
    -
    Trigger Words:
    st0mach

    Files

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.