CivArchive

    DR34ML4Y by DR34MSC4PE

    This LoRA, incredibly, manages to handle ALL of our specialty LoRA concepts - Double/Single Blowjobs, Missionary, Reverse (and regular) Cowgirl, Doggy, wrapped in one model! It obeys very well and is largely extremely accurate to the given keyword/position! Don't be shy; give it a try! =)

    ===========================================================================

    Update - Due to civit making sure we do not get paid for the use of our model via generation any longer, on-site generation has been switched to 100 buzz per generation. Please voice any concern directly to Civit AI's support over their change effective 11/1.

    10/15 - H3 PREVIEW: we're so back.

    Note: this is an early preview - expect some T2V challenges. H3 is not WAN/LTX. Prompt accordingly.

    Turbo LoRa moves latent space away from NSFW concepts. Results, especially audio, will get worse the more turbo you combine into the mix.

    AS ALWAYS: Enjoy, generate responsibly and share what prompting tricks you learn along the way!

    ==========================================================================

    Note - Missionary and cowgirl can have some mix-up if you don't specify the woman is on her back in the prompt.

    ===========================================================================

    DR34MSC4PE is

    c0ur4ge (trainer/qa/inference code) /

    ERA5ER (trainer/captions/tooling code/data/qa)

    Please generate responsibly!

    Description

    We're trying something new for Wan 2.2 - so here's an early gift from we to you!

    FAQ

    Comments (42)

    2900735Jul 26, 2025· 6 reactions
    CivitAI

    Oh boy, the goat's back in town. Thanks for this, mate, will take it for a spin

    Update: yeah, as expected, this thing is a BEAST. To me, preserving likeness is always top priority, and this thing delivers. Huge thanks for your work - will post a few samples.

    c0ur4ge
    Author
    Jul 26, 2025· 1 reaction

    Cheers - we hope you enjoy! ;)

    ColorWolveJul 26, 2025· 7 reactions
    CivitAI

    This Lora is amazing, i use for i2v blowjob, without any nsfw fix lora help it can do deepthroat action perfectly!

    sirbazzrickkJul 26, 2025· 3 reactions
    CivitAI

    the motion is amazing! great work!.. im struggling to keep the original faces clean on i2v... any loras to combat this anyone?

    ERA5ERJul 26, 2025· 3 reactions

    Try mixing in one of our other WAN Loras!

    sirbazzrickkJul 26, 2025

    ERA5ER yeah ill have a play around, thanks :)

    c0ur4ge
    Author
    Jul 27, 2025· 5 reactions

    sirbazzrickk We MAY try an I2V version of the tech preview but it depends on our schedule and if we can spare a few days to train it before Wan 2.2 is out. We’ll see if we can get a 2.1 tech preview out but ultimately we want you to see “the real deal” soon.

    flo11ok874Jul 27, 2025

    c0ur4ge Wan 2.2 will be tomorrow. But take your time

    CubeyAIJul 27, 2025· 3 reactions
    CivitAI

    Very nice!

    f6825800990Jul 27, 2025· 5 reactions
    CivitAI

    The best! Absolutely goated motion loras. Looking forward to what the future will bring :)

    craftbin583Jul 27, 2025· 1 reaction
    CivitAI

    Any advice on running this with lightx or FusionX? especially the missionary and cowgirl scenes have almost 0 movent with the lora

    c0ur4ge
    Author
    Jul 27, 2025

    I’ve honestly never tried it as it’s not what we’re training on as a base - that said, I know that I2V variants we’ve done have been reported to work fine with them so it may be a matter of parameters.

    I’ll let others chime in if they’ve had success!

    AlberistJul 27, 2025· 1 reaction

    All of my generations have been using lightx, mostly at 4 steps. I also use the MPS reward lora.

    craftbin583Jul 29, 2025

    sharp3 Thank you, i will study your workflow now, thanks for leaving it in the generation. Do you work with 2 workflows, one that makes an image and one that uses i2v on that?

    AlberistJul 29, 2025

    craftbin583 Yes. I make my images in ForgeUI, mostly with various pony checkpoints.

    DocueiJul 27, 2025· 5 reactions
    CivitAI

    This lora improved my SFW human with human prompts by 1000%

    c0ur4ge
    Author
    Jul 27, 2025

    This is perhaps the most surprising comment so far lol! Please share! :)

    LatentDreamJul 28, 2025· 4 reactions
    CivitAI

    i'm surprised how good this lora works.

    thanks for sharing

    c0ur4ge
    Author
    Jul 28, 2025

    we were surprised too! More to come!

    zanebeJul 30, 2025· 2 reactions
    CivitAI

    Marvelous lora.
    Wish it had more diverse dataset and without these TRY_T0_R3M3M63R_TH3_T4G.

    c0ur4ge
    Author
    Jul 30, 2025

    That’s, I’m afraid, exactly what makes it work. :)

    A new version is cooking with some additional positions for WAN 2.2!

    AI_2_addictedJul 31, 2025· 4 reactions
    CivitAI

    FANTASTIC JOB! Congratulations and thank you very much! This is one of the best NSFW loras and the best blowjob for WAN 2.1. Please make a version of this for WAN 2.2??!! That would be amazing and revolutionary. Thank you very much in advance.

    fadog74502638Jul 31, 2025· 1 reaction

    it works for 2.2 already my friend

    c0ur4ge
    Author
    Jul 31, 2025

    fadog74502638 And there’s a version for WAN 2.2 5B in the oven as we speak.

    AI_2_addictedJul 31, 2025

    fadog74502638 Yes, my friend. I can get it to work on WAN 2.2 I2V, but my main interest is WAN 2.2 T2V. I can also get it to work on WAN 2.2 T2V, but it doesn't compare to the quality of LoRas trained exclusively for WAN 2.2 T2V. When using a T2V 2.1 LoRa on T2V 2.2, it loses all the incredible features of the "high noise" model; only the "low noise" model is practically used. I tested a single LoRa trained exclusively for WAN 2.2 T2V, and the quality is FANTASTIC! It looks like real life; the lighting, movement, resolution, and skin textures are impressive, something that doesn't happen when using LoRas from version 2.1 T2V. I think developers should now dedicate themselves to creating LoRas exclusively for 2.2 (I2V/T2V) to reach another level of excellence.

    c0ur4ge
    Author
    Jul 31, 2025· 1 reaction

    rafaaguiar990170 Yeah - those will come after! 5B first just because I’m very surprised with the quality and it’s the fastest to train. 14b(s) are next !

    AI_2_addictedAug 1, 2025

    c0ur4ge Great! Thank you so much for your effort and great work for the Wan community!

    aiv_creatorAug 1, 2025

    IMPORTANT: INFORM ALL WAN USERS! I DISCOVERED HOW TO USE LORAS 'NSFW/SFW' IN WAN 2.2 T2V, GETTING THE FULL POTENTIAL OF "HIGH NOISE" AND "LOW NOISE." THE RESULTS WERE IMPRESSIVE!! I ran it on an RTX 3060 6GB, 32MB RAM, 480x480, length: 41, generation time: 5 minutes to generate each video. The quality is fantastic! For those of you with more powerful computers, the results will be even more incredible. I used the models: WAN 2.2 - Q4_1.gguf FOLLOW THE STEPS BELOW: 1: Don't use acceleration/enhancement LoRas (such as Lightx2v or other) on "high noise"; use only on "low noise" with strength 1. (I'm using this version of Lightx2v LoRa): lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16 2: Use 'NSFW/SFW' LoRas on both "high noise" and "low noise" models. On "high noise," use strength 2, and on "low noise," use half the strength, with strength 1. You can vary the strengths as you like, but always keep the "low noise" strength at half the strength of the "high noise." 3: Use these settings in KSamplers: "high noise": steps: 9 / cfg: 3.5 / euler/simple / start_at_step: 0 / end_at_step: 1 "low noise": steps: 9 / cfg: 1.0 / euler/simple / start_at_step: 1 / end_at_step: 10000 Note: To improve speed, I set the Windows system to "best performance," disable unnecessary background programs and applications, and lower the desktop resolution. This significantly speeds up video generation. I hope this helps.

    natalies5567Jul 31, 2025· 1 reaction
    CivitAI

    What does your lora training settings and dataset look like?

    c0ur4ge
    Author
    Jul 31, 2025

    We don’t stray far from recommended settings on diffusion pipe - as for the dataset on this one, it’s evolving. As you can gather its most of our previous concepts in one configuration with some balancing.

    spacesquirrelAug 1, 2025· 4 reactions
    CivitAI

    ugh the loras are soo good. hopefully you can add some gay capabilities too (ie anal t2v or make a separate lora)

    c0ur4ge
    Author
    Aug 1, 2025· 1 reaction

    It’s interesting you mention this because we have a dataset that is mostly just male anatomy but I wonder if it would help flexibility there - we’ll consider it!

    spacesquirrelAug 3, 2025

    c0ur4ge cool! would be cool to see. thank you!

    sirbazzrickkAug 1, 2025· 4 reactions
    CivitAI

    this at strength 0.85 and using the Self-Forcing / CausVid / Accvid Lora, massive speed up for Wan2.1 made by Kijai lora on strength 0.7 is amazing! keeps the faces true, helps the lighting and movement... excellent work

    c0ur4ge
    Author
    Aug 1, 2025· 1 reaction

    Wild. Need to try this myself even. :)

    ezramAug 1, 2025· 2 reactions
    CivitAI

    If it helps anyone on 2.2 T2V, I think the core of 2.2 is in the High Noise model, especially the movement. The low noise model is pretty much 2.1. You want the high noise model to do the bulk of the video, and have the low noise one just do clean up duty. If you let the low noise model do too much work, it outputs a 2.1 style video, its hard to explain. And as someone else said, the high noise model is at its best without the acceleration LORAs, its needs CFG to be higher than 1 to shine.

    c0ur4ge
    Author
    Aug 1, 2025· 2 reactions

    We’re definitely still going to do specific trainings for the new stuff. 5Bs going on right now. Only so much GPU to go around!

    zanebeAug 2, 2025

    For I2V with acceleration lora I don't use High Noise model at all, it dampens the motion.

    dmmyhtmlacc633Aug 4, 2025· 3 reactions
    CivitAI

    cant wait for the final version

    c0ur4ge
    Author
    Aug 5, 2025

    I’ve got it trained but not I have to evaluate and interpolate of the best of the 5B options for v1. Shooting to have it out by this weekend sometime!

    sirbazzrickkAug 8, 2025· 2 reactions
    CivitAI

    I seem to get error ' not an mp4 file' at the end of generating and it scraps it.... is it loras not playing nicely with eachother or down to settings/files.... its infuriating and any help would be great!

    c0ur4ge
    Author
    Aug 10, 2025· 1 reaction

    This is definitely something in your workflow, m8.