CivArchive
    SexGod's NaughtyTimes MM H3 Lora - v1.0 pruned
    NSFW

    NaughtyTimes MM H3 Lora

    Join our discord: https://discord.gg/GCrr4Cj3D

    Use the right lora for your base model (pruned or unpruned), you may get "something" but if its not trained against that model it won't work right. Im adding pruned v2 loras now since people were asking why "It doesnt do anything" yesterday (this is why)

    *** V2 = trained on unpruned model! ***

    *** V1 = trained on pruned model! ***

    V2.0 unpruned lora is rank 128, 256, and 512 extracted from PinkCherry base model. It retains about 24%, 34% and 48% respectively of the base knowledge in PinkCherry fine tune. It doesnt have the distilled issue of v1.0 so you can run it at full strength if you want. Try different ranks and strengths to see what works or doesnt for you.

    I dont know which v2.0 lora rank 128,256 or 512 works best. Ive been testing them at str 1.0. Sort of a try different ranks and strengths and see which might be the better combo.

    Don't mix it with PinkCherry base unless you want crazy, use the base model with this lora.


    Pink Cherry Base Model: If you want to try PinkCherry Base model its at https://civarchive.com/models/2838593/pinkcherry-mm-h3


    V2 Base Model: unpruned fl2va

    V1 Base Model: pruned fl2va

    (confusing I know, sorry!)

    Lora Strength: 1.0 for v2

    Lora Strength: 0.5 for v1

    Training terms: vulgur captions, not medical terms. cock, pussy, fucking, cum, doggystyle, blowjob etc

    Strength: 0.3 to 0.5 for V1

    Strength: 1.0 for V2

    my videos are just quick low step generations, which I used to test the lora with.

    I didnt use any image conditioning (text to video training only), but it works on I2V as well it seems. Again this was a fairly quick "does it work" training session before I started a real model fine tune

    Enhances wide variety of nsfw concepts was trained on about a large dataset of 4k videos, use at str 0.5 and on the pruned int8 model as that is what I trained it on. This version is alpha quality so temper expectations. Ill train this one up further after im done fine tuning the base model.

    Description

    it was trained on distilled version so dont go over 0.5 strength and use the pruned int8 mode (not the ref model) first frame last frame model

    FAQ

    Comments (51)

    lifaniaAug 5, 2026
    CivitAI

    I might as well ask here too since you didn't really clarify, is it still the 1500 step lora, or has it been changed since the first release?

    sexgod1979
    Author
    Aug 5, 2026· 1 reaction

    Its the exact same lora, I havent trained it further. Using the GPUs to do fine tuning now. will swing back to retrain this lora later after im done

    NUGGZ1616Aug 5, 2026
    CivitAI

    is this the same as "pinkfluffy" from your HF? just want to make sure I dont duplicate it... ;)

    azretion188Aug 5, 2026

    Yep, same SHA hash

    sexgod1979
    Author
    Aug 5, 2026

    yes

    KazuhiraAug 5, 2026· 6 reactions
    CivitAI

    What is this lora specifically do?

    KiraNuggetAug 5, 2026

    It looks like its a general NSFW helper.

    KazuhiraAug 5, 2026

    @KiraNugget Thanks.Have to try it.

    sexgod1979
    Author
    Aug 5, 2026· 1 reaction

    it was just trained on varied sex clips, nothing specific

    blackhumantg735Aug 5, 2026· 7 reactions
    CivitAI

    What's the point of this lora? If the initial image already contains everything you need, a simple, good prompt is enough.

    sexgod1979
    Author
    Aug 5, 2026· 3 reactions

    I didnt find it was enough, but I guess everyone's milage varies.

    sexgod1979
    Author
    Aug 5, 2026· 4 reactions

    also I mostly posted it because people were asking me on chat to post it as huggingface took it down. I wasnt really sure I was going to bother as im already working on a fine tune

    ForbiddenNexusAIAug 5, 2026

    It doesnt know how a penis interacts with a vagina very well or what blowjobs should sound like. Its thankfully very good out the box just needs a proper final lap to really unlock good nsfw imo

    RenegadeZebraAug 5, 2026

    I feel like we'll be saying that about a lot of loras for this mode. We finally have a model than can do just about anything if you write your prompt correctly. I'm gonna be waiting for some stuff to drop that can definitively be proven to generate something impossible for the base model to generate before I go download crazy. This model is freeing up a lot of my hard drive space lol.

    flo11ok874Aug 5, 2026· 19 reactions
    CivitAI

    Please change the name to just 'H3' without company name. Thay have problems with that.

    brnfd24434343dAug 5, 2026

    H3 is TRITIUM, and that should be the *"I don't know what you're talking about but this isn't porn trained off your model"* name.

    Error666Aug 5, 2026· 3 reactions
    CivitAI

    Thank you! But I get the feeling that this is a model that will be very difficult to uncensor.

    ultimo_intentoAug 5, 2026

    The vagina lora is decentish

    Lora_AddictAug 5, 2026· 11 reactions

    Uncensor?! This ist the most uncensored video model i know?!

    sexgod1979
    Author
    Aug 5, 2026

    @Lora_Addict it truly is, isnt it wonderful?

    Lora_AddictAug 5, 2026

    @sexgod1979 it's fulfilling almost all wishes, indeed wonderful!

    damiangAug 5, 2026

    LMAO, you know that this is the most uncensored model we've ever gained?

    sissdfgaAug 5, 2026
    CivitAI

    I want to ask if this lora can let me generate more sex positions, I want to generate 69 position, but it didn't work either way

    sexgod1979
    Author
    Aug 5, 2026

    it wouldnt be significant enough in the dataset, likely need a specific 69 lora for that

    ultimo_intentoAug 5, 2026· 4 reactions
    CivitAI

    The GOAT 🐐!!! 🔥

    delta45424155Aug 5, 2026
    CivitAI

    Thanks for this. Now that I know this does t2v good; im switching my 6000pro back to comfyui. ;)

    Apprehensive6311Aug 7, 2026

    Hi Bro how long 6000 pro take for 10s. Is it able to do 30s too?

    delta45424155Aug 7, 2026· 1 reaction

    @Apprehensive6311 I haven't pulled my 6000 from my llm box yet. But 5080 takes about 35s at 512x384 for 10s using the turbo lora with 6 steps.

    LuringSuccubusAug 5, 2026· 6 reactions
    CivitAI

    what about REFRENCE TO VIDEO?

    sexgod1979
    Author
    Aug 5, 2026

    nope, wasnt trained on it. That model is different, different weights.

    meeatsmeatAug 6, 2026

    I think you can try with a lower strength like 0.3

    fatberg_slimAug 7, 2026

    You can do it but expect the quality to take a hit.

    sexgod1979
    Author
    Aug 7, 2026· 3 reactions

    I did try reference to video with the model using two images like <Picture 1> etc and it did actually work even though this model isnt really designed for it. Was happy with the result

    solidframegaming301Aug 5, 2026· 9 reactions
    CivitAI

    are you guys just using "load lora" node and hooking it between the model and the 2 model inputs in the default comfyui workflow? i can't seem to get it to work, it always seems to make the video output and audio quality worse, and i can't get a normal looking penis at all. Is there a special "minimax h3 load lora" i'm missing?

    jervis314Aug 5, 2026

    I'm just using a normal load lora node between the pruned h3 model and the basic guider and basic scheduler nodes. Try using only at 0.3 strength

    sexgod1979
    Author
    Aug 5, 2026

    yeah try 0.3 it was trained on distilled base which wasnt a great idea, so youre getting overcooked outputs

    delta45424155Aug 5, 2026

    Or try 0.5 strength and 10-12 steps.

    Pat3dxAug 5, 2026· 8 reactions
    CivitAI

    Just test a simple doggy sex scene in R2V mode with my own custom nodes and H3 workflow.

    If my futanari with her big erect penis and physical consitency is perfect, the sex act itself is totally crap.

    The scene was very simple

    Ther futanari is on all four on her bed, and a man is behind her assfucking her.

    My duta is on all four, the bedroom is perfect, but the man and the sexual act, are totally crap.

    So, i think this will need more traningand maybe add triggerword for each positions.

    ytyuiu545Aug 5, 2026· 2 reactions
    CivitAI

    not bad at all, the penis is still odd looking, mostly the head/tip area, but better than the flat model, thanks for doing this, looking forward to V2!!

    nbts1216617Aug 6, 2026· 2 reactions
    CivitAI

    the result is not good enough as I expected. Can you share the workflow you use, please?

    DaddyWolfgangAug 6, 2026· 18 reactions
    CivitAI

    I get better results with the convrot models without loras. Natural and fluid and it doesn't alter the faces. I'm sure we'll get great stuff moving forward but LoRAs need more time as it just released. I'm sure we'll se some exceptional stuff in the future!

    alessandrowwwAug 6, 2026· 9 reactions
    CivitAI

    Hi Good lora so far, just wanna report, not working with turbo lora. ^^ keep the work up thanks for sharing

    VI6_D_DARK_KINGAug 8, 2026· 18 reactions
    CivitAI

    "Is there demand for a similar ref model lora?" Most defiantly.

    kudon44Aug 8, 2026· 27 reactions
    CivitAI

    Anyone tested this and confirmed if this lora is a troll and needs banned or legit?

    All his prompts are just troll prompts that have nothing to do with his example videos.

    sexgod1979
    Author
    Aug 8, 2026· 12 reactions

    It was late and I had to get to bed and just didnt have time, but just load the video into your comfyUI and the prompt is there in the meta data. Also it would be nice if civit could take the extra 10 seconds and code in a reader for meta data so I dont have to do the work for them 1000s of times a week when I post models :)

    @sexgod1979 I downloaded your workflow, thanks for sharing. The LoRA isnt actually in there? Is it buried in some weird node? I dont see it used

    sexgod1979
    Author
    Aug 8, 2026· 1 reaction

    @SurrepticiousFabric try this image for workflow, I think the lora is in there buried behind the subgraph (doubleclick subgraph to see it). This is plaguekind's workflow I got off civit but v1.0 didnt have a lora loader so I added one

    sexgod1979
    Author
    Aug 8, 2026· 8 reactions

    yeah sorry all ill try to make sure I give my prompts from now on, just tired lazy on my end

    diogodAug 8, 2026

    @sexgod1979 exactly... there is even an open pr on civitai thing on github... it's been years. They should have added video metadata years ago.

    SoyKafAug 8, 2026· 3 reactions

    civit can't find your prompts in the metadata 90% of the time and will happily slap you with a "can't verify if this is AI please provide a prompt" Which makes it really annoying to upload anything.

    90% of the time if you see a prompt that doesn't match, it's probably not done out of malice.

    makiaeveliAug 8, 2026· 1 reaction

    lmfao why don't you fucking test it.

    LORA
    MiniMax H3

    Details

    Downloads
    7,568
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/5/2026
    Updated
    8/13/2026
    Deleted
    -