CivArchive

    Wan 2.2!

    Re-trained the dataset on Wan 2.2, make sure to grab BOTH Loras (High and Low)!
    Getting great results with K3NK's workflow - https://civarchive.com/models/1824027/wan-22-t2v-i2v4-stepskijais-wrapper-workflowk3nk


    Update 6.17

    I realized while trying to improve this LoRA that I never uploaded a T2V version, so... here it is. Enjoy!

    -- -- --

    My second LoRA... I've made some drastic changes to my captioning approach, and the results show some nice improvement.

    Please share anything you make with this, I'd love to see some better prompts!

    This was trained on WAN 14B I2V, on 45 videos normalized to 480P / 24FPS and trimmed to 3 seconds using diffusion-pipe. However, it works okay with the T2V model, and I've included some examples from that.

    My captioning approach:

    1. 45 videos, resized to 480P, 3 seconds, 24FPS.

    2. Ran each one through ComfyUI_Qwen2-VL-Instruct to generate a base video description, but this unfortunately doesn't pick up on any NSFW bits. This usually took a few tries on the same image, since the LLM almost seemed "disgusted" by the suggestion. :D

    3. Grabbed my "favorite" frame and ran that through Joy Caption 2, then I manually combined the Qwen description and the Joy Caption Two caption to make the final .txt file.

    Description

    Trained with Wan I2V 14B.

    FAQ

    Comments (36)

    AI_2_addictedApr 10, 2025· 4 reactions
    CivitAI
    WOW! this is perfect!!! Congrats! Please make a T2V version! Thanks!
    DennyDan84Apr 10, 2025· 2 reactions

    Yes - we need a T2V version!

    dngstn32
    Author
    Apr 10, 2025· 2 reactions

    Gotta clear some HD space for my linux partition so I can clone the T2V repo, but I'll try and get to that ASAP.

    AI_2_addictedApr 10, 2025

    @dngstn32 That's great! Thank you very much for your kindness! Your work is amazing!

    dngstn32
    Author
    Apr 10, 2025· 1 reaction

    @rafaaguiar990170 Sure thing. Just FYI, both the bride and black fishnets in my examples were done with the T2V model / workflow, they are NOT I2V. So I'd say grab it and give it a try... there's definitely room for improvement but it still works. :)

    AI_2_addictedApr 10, 2025

    @dngstn32 That's great to know, the results are very good! I'll try it, thanks!

    AI_2_addictedApr 10, 2025
    CivitAI
    What is the trigger word?
    dngstn32
    Author
    Apr 10, 2025· 2 reactions

    None needed by design, and it seems to have worked. I didn't put any in the training data. Just roll with the prompts in my examples and you should be good to go.

    AI_2_addictedApr 10, 2025

    @dngstn32 Ok, thanks! And congratulations once again for the excellent work!

    chestholeApr 10, 2025
    CivitAI

    This one is powerful, I accidentally said reverse cowgirl in a cowgirl i2v and she went through a warp zone, but by the end she was beautiful reverse cowgirl.

    dngstn32
    Author
    Apr 10, 2025

    Lol, nice... I haven't played with the weight much, just kept it at 1.0 after trying to lower it and ending up with lovely Stretch Armstrong dicks. Face consistency on I2V could be better too, I'm not sure how to accomplish that.

    swanApr 10, 2025
    CivitAI

    Very nice!
    Please make a mating press next time :)

    dngstn32
    Author
    Apr 10, 2025· 2 reactions

    WIP actually! Not at all happy with the results so far, but I'm trying.

    swanApr 10, 2025

    @dngstn32 Oh wow! I hope for some good news :D

    BBBAAA2Apr 10, 2025

    @dngstn32 your efforts are greatly appreciated

    tajimatenshinai837Apr 10, 2025
    CivitAI

    "My second LoRA... I've made some drastic changes to my captioning approach, and the results show some nice improvement."

    Would love to know your approach?

    dngstn32
    Author
    Apr 10, 2025· 1 reaction

    Sure... let me update the description of the LoRA so I can include hyperlinks.

    whitespider9999Apr 10, 2025· 3 reactions
    CivitAI

    Not sure if this also works with BWC. I'll have to test it. If not, could you consider adding one in the future? Thanks.

    dngstn32
    Author
    Apr 10, 2025· 2 reactions

    Just tried a few times I2V... it's not perfect. The dataset focused primarily on dark ones, for... size reasons. I haven't tried adding images to the training data, but I'd imagine that could help.

    whitespider9999Apr 12, 2025

    @dngstn32 bwc is very possible with wan and xp checkpoints/loras (flux is still in limbo) but i can see how it's much harder in terms of fining real content to train off (which is how i imagine you made this) since real data creates far better loras than AI data. That being said, if you ever find a way to create convincing bwc at these kind of sizes that would be awesome since that's definitely a missing segment right now in terms of loras. Thanks for the effort if you ever decide to take on the challenge. Either way i appreciate your efforts/talent in loras in this space.

    evilschizo999Jun 1, 2025· 1 reaction

    Are you using I2V? If so, it'll work with literally any skin colour; i've used it on white, black, and green with no issues. You can see this in most of the top-rated videos on this page.

    CyberAImaniaApr 13, 2025
    CivitAI

    How do you train? Locally on a PC? What software do you use?

    dngstn32
    Author
    Apr 13, 2025

    Yep, locally... I have a 4090. I use diffusion-pipe running via WSL, in Ubuntu.

    CyberAImaniaApr 13, 2025

    Yes, same as me – same graphics card and also WSL. I’m wondering how you managed to train on video? Every time I try, I get some errors.
    I prepare video clips of 3 seconds, 16 fps, and it still doesn’t work.
    Could you please send me an example of a config.toml file from your video training?

    i described my issue here:
    https://github.com/tdrussell/diffusion-pipe/issues/207

    dngstn32
    Author
    Apr 13, 2025· 1 reaction

    @CyberAImania I used the training data .tomls that @dtwr434 provided here: Wan POV Missionary - T2V v1.0 | Wan Video LoRA | Civitai. I don't think I modified any of the settings, except to point at my checkoued out Wan directories etc.

    BuffaloSymphonyApr 15, 2025

    @dngstn32 Do you blur the faces in the training videos?

    dngstn32
    Author
    Apr 15, 2025

    @BuffaloSymphony I didn't, no. This particular dataset doesn't exactly show a lot of faces, though. ;)

    Devilday666Apr 19, 2025
    CivitAI

    You might want to change the loras name, I feel alot of people have been using your lora just for how good it is even with the intention for it only being BBC

    logenninefingers888May 2, 2025
    CivitAI

    Nice work. Check out Joycaption if you want something that can do NSFW. It still needs fixing up manually though. I've also heard there's an uncensored version of Gemma.

    dngstn32
    Author
    May 5, 2025

    Thanks, I've been using Joy Caption on single frames from the video and then adding manually, which is pretty time consuming. If only there were something like Joy Caption for porn videos...

    evilschizo999May 25, 2025
    CivitAI

    good stuff. Very versatile too, moreso than you would think based on the title.

    SAY_AIJun 2, 2025· 1 reaction
    CivitAI

    Your LoRA works very well! 👍

    One issue is that in the second half of the video, a hand suddenly appears to touch the butt. How can I avoid this sudden extra hand?

    lebu0009203Jun 12, 2025

    Did you figure out something that mitigates this problem?

    SAY_AIJun 13, 2025· 2 reactions

    @lebu0009203 I haven’t found a one-size-fits-all solution yet, but adding "hand" and "hands" to the negative prompt words can sometimes work.

    evilschizo999Jun 15, 2025· 1 reaction

    @SAY_AI yeah same. I put stuff like "ass grab, hands, hands appearing from offscreen" in the negative and that also helps mitigate the issue

    KiefstormAug 12, 2025· 3 reactions

    Sorry that was my hand

    LORA
    Wan Video 14B i2v 480p

    Details

    Downloads
    5,151
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/9/2025
    Updated
    6/5/2026
    Deleted
    -

    Available On (1 platform)

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