CivArchive

    Welcome to DR34MSC4PE's latest WAN LoRA: C0WG1RL + REV3RSE C0WG1RL

    9/6/2025: It's finally ready to share - Our WAN 2.2 Reverse Cowgirl Text-to-Video LoRa.

    This thing is actually pretty crazy. The usual prompts/triggers still apply: Use r3v3rs3_c0wg1rl for when she's in the reverse cowgirl position. Use c0wg1rl when she's in the c0wg1rl position.

    You can also use different camera angles, such as: Close-up detailed view, wide angle view, side angle view from the left/right, low/high angle view looking up/down, etc.

    Try adding camera movements as well - "The camera slides slowly to the left, creating a parallax effect", etc.

    This lora also works GREAT with a Text-to-Image workflow. Create reverse cowgirl images and add motion with our I2V Lora.

    Have fun! It should work with other 2.1/2.2 LoRas.

    Please share workflows that work great for you!

    Please generate responsibly!

    8/27/2025: At long last, v1 of our Cowgirl/Reverse Cowgirl Wan2.2 14b lora is LIVE!

    Be sure to use some variation of 'she's positioned in the reverse cowgirl position'.

    Sample prompts:

    r3v3rs3_c0wg1rl, a nude woman with light brown hair small breasts and a navel piercing straddling a nude man with a visible erect penis penetrating her vagina. The man's hands grip her hips from below as she rides him in the reverse cowgirl position facing forward with a slight devilish smile. His penis is thrusting into her and his testicles are visible below. They are in an urban street setting at night with neon signs in the background including a prominent red and blue "NEON" sign. Cars are parked along the street and buildings with lit windows line the background. The perspective is from a low angle looking up at the woman. The lighting is bright highlighting their bodies against the dimly lit street. The woman's legs are spread wide and the man is lying on his back beneath her.
    c0wg1rl, a nude woman with light skin long blonde hair and small breasts straddling a man who is lying on his back. The woman's legs are spread wide and she is sitting on top of the man in the cowgirl position with his erect penis penetrating her vagina. She has a navel piercing and a focused expression on her face. The man's lower body and erect penis are visible while his upper body is out of frame. They are in a dimly lit room with a fireplace in the background casting warm light and shadows. Logs are stacked in the fireplace and there is a wooden shelf with various items on the right side of the frame. The perspective is from a slightly low angle looking up at the woman. The lighting emphasizes the contours of their bodies and the texture of their skin.

    REMEMBER: You can use both r3v3rs3_c0wgirl, or c0wg1rl, depending on her positioning. r3v3rs3 works best and can work for both positions.

    This LoRa works GREAT with Kijai's WAN2.2 I2V 14B finetunes found here: https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main/I2V

    8/18/2025: WAN 2.2 TI2V v2 is READY!

    After a few weeks in the smoker, she's ready to be served. Introducing v2 of our Cowgirl/Reverse Cowgirl Wan2.2 ti2v LoRa.

    This LoRa works BEST with Kijai's WAN2.2 TI2V 5B finetune found here: Wan2_2-TI2V-5B-FastWanFullAttn_bf16

    T2V and I2V Workflow's have been included - Sage-Attention and Triton are strongly recommended. An install guide for ComfyUI can be found here.

    Sample prompts from the dataset have also been included. Feel free to use these as a base for your prompts.

    Yes, penises can be a bit... long. We'll hopefully get that improved in a future iteration.

    08/12/25: Introducing our Wan 2.2 TI2V 5B Cowgirl Lora.

    This Lora is a work in progress. Epoch 280 seems to have the best overall performance during testing, but updates will be made as we get our training & dataset settings dialed in.

    For WAN2.2 The trigger has changed, c0wg1rl now denotes the traditional cowgirl position. r3v3rs3_c0wgirl for, you guessed it, reverse cowgirl positions, which this Lora excels at. The WAN2.1 Loras remain unchanged, c0wg1rl is still the trigger.

    Use the same types of prompts:

    r3v3rs3_c0wg1rl, A nude woman with light skin small breasts and long blonde hair straddling a nude man with a muscular build and light skin in the reverse cowgirl position. The man is lying on his back on a beige couch with the woman facing forward with her eyes closed and mouth slightly open in an expression of pleasure. His erect penis is visibly thrusting in and out of her vagina. The woman is leaning backward and her hands rest on his chest and her legs are spread apart. 
    The background includes beige curtains and a white flower-shaped floor lamp. The lighting is bright highlighting their bodies and creating a clear view of their skin tones and textures. The perspective is slightly above and to the side focusing on their upper bodies and the action. 

    A selection of the training captions have been provided to give you more of an idea on prompt structure.

    Before you comment - yes, movement can be static, or positions can be wonky - please experiment with different phrases in your promts, and different tweaks to your settings.

    You may have to add language such as "She bounces up and down", "The man's penis thrusts in and out of her vagina."

    I've found the DPM++ Sampler family seems to work pretty well.

    Before you ask: Yes, a 14b version is in the works.

    Please experiment, and don't forget to share your findings and creations with the class!

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

    DR34MSC4PE is

    c0ur4ge (trainer/qa/inference code) /

    ERA5ER (captions/tooling code/data/qa)

    Check out other models by DR34MSC4PE

    Like our work? Consider donating for coffee: https://ko-fi.com/dr34msc4pe

    PLEASE GENERATE RESPONSIBLY!

    Description

    Trained on the High Noise model of Wan2.2 14b.

    FAQ

    Comments (23)

    LuxariaAug 28, 2025· 25 reactions
    CivitAI

    Love this, the wan2.2 14B is good. Thank you so much for training it.

    Lora_AddictAug 28, 2025· 25 reactions
    CivitAI

    So good, thank you!

    honryindianAug 28, 2025· 28 reactions
    CivitAI

    can we please get wan2.2 14B T2V?

    ERA5ER
    Author
    Aug 28, 2025· 1 reaction

    Okay, but only because you said please. It's definitely in the works.

    In the meantime, check out the T2V capabilities of the 5B model - you might be surprised.

    honryindianAug 29, 2025

    @ERA5ER Thank you! You're the best! I'll definitely check it out!

    BrAInB0tAug 28, 2025· 28 reactions
    CivitAI

    Good job but I will never understand why people use the l33tsp34k tags, just cumbersome to type when you're working quickly.

    c0ur4geAug 28, 2025· 1 reaction

    You should probably do some more reading about class tokens and concepts then. We hear a lot of complaints but trust us when we say they serve a purpose and it’s important they are deliberately unique from normal speech or words.

    BrAInB0tAug 28, 2025

    @c0ur4ge Got any suggestions where to read up? I'm starting out training my own loras at the moment, it's a struggle. Thanks for the reply. I didn't know that they served a purpose, could help me in the future.

    WangnanJahardSep 1, 2025· 1 reaction

    @m0no1 the short answer: it's to prevent overlap with common trigger words. "cute girl" is going to give you a thousand and one variations regardless how well trained your LORA is, whereas if you use "cut3 grrl" as your trigger, you can be sure it will focus on your LORA.

    BrAInB0tSep 1, 2025

    @WangnanJahard Would you mind sharing your musubi-tuner config file with me? the toml? What gpu do you use?

    c0ur4geSep 1, 2025

    @m0no1 I'll save you the trouble - we use diffusion-pipe and more or less stay pretty close to the base WAN settings you'd find therein. The only thing we spend a fair bit of time with is the captions, the dataset, and the tradeoff how how many FPS/Resolution at which we can get training to start given our VRAM limitations. We do not use cloud training services and do all this training on 48gb boxes. Start with WAN 2.2 5b - the repo itself has all the information you should need to succeed.

    BrAInB0tSep 1, 2025

    @c0ur4ge Awesome thanks

    1601658Aug 28, 2025· 24 reactions
    CivitAI

    Would you be able to do a variation with the girl's legs together? @ERA5ER

    dravodir504Aug 28, 2025· 24 reactions
    CivitAI

    The third trigger phrase differs between the high- and low-noise models for I2V 14B. Is that accurate?

    ERA5ER
    Author
    Aug 28, 2025· 1 reaction

    Fixed. But either works, as long as 'reverse cowgirl position' is included somewhere.

    jj43797771Aug 29, 2025· 24 reactions
    CivitAI

    aww man everything but 2.2 t2v 14b :(

    ERA5ER
    Author
    Aug 29, 2025

    Shhhhhh, it's still cooking.
    Try out the 5B t2v capabilities in the meantime. You might be surprised!

    kofic28991624Sep 14, 2025· 1 reaction

    @ERA5ER Sorry but what's the diff between 5B and 14B?

    23423daAug 31, 2025· 29 reactions
    CivitAI

    14b is a game changer. I graduated to AV with this.

    yefan022Sep 1, 2025· 24 reactions
    CivitAI

    In my workflow the high model uses the high LoRA and the low model uses the low LoRA. Do I need to download just one LoRA, or do I need both wan2.2 I2V 14B-high and wan2.2 I2V 14B-low?

    ERA5ER
    Author
    Sep 1, 2025

    yes, you will want both.

    yefan022Sep 1, 2025

    @ERA5ER Thanks , for 720×1280, are 7–8 steps fine? Will a higher step count make a big difference? Any suggestions?

    LORA
    Wan Video 2.2 I2V-A14B

    Details

    Downloads
    50,549
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/28/2025
    Updated
    4/28/2026
    Deleted
    -
    Trigger Words:
    r3v3rs3_c0wg1rl
    c0wg1rl
    straddling him in the reverse cowgirl position

    Files