CivArchive
    Milking table | Wan 2.2 I2V - Live training
    NSFW

    I didn't know you could milk a bull 🀨

    Don't worry babe, just trust me πŸ˜‡


    Training

    • 360 steps on high noise

    • 3 edited videos (40 frames each video)

    • ZCD (These acronyms were created solely to confuse you)

    • Lots of confidence

    • $4 (βœ‹πŸ»πŸ€ πŸ€šπŸ»)


    Usage (Low noise)

    This LoRA was trained only on High Noise, so you should load a Low Noise LoRA that knows what a penis is (In this case I recommend DR34ML4Y v2)


    Uncensored prompts and examples

    You know that Civitai likes to remove some LoRAs, right? For that reason, I won't post the "Cut to action" prompt. To see all my LoRAs, visit my repository on HuggingFace.

    Or visit this LoRA on HuggingFace πŸ€—


    I2V:

    Ongoing:

    She moves her hand up and down repeatedly, stroking the hard penis.

    Prompt 1 (cut to action):

    Heeeey cowboy, not here... βœ‹πŸ»πŸ€ 

    Prompt 2 (cut to action):

    Heeeey cowboy, not here... βœ‹πŸ»πŸ€ 

    Prompt 3 (cut to action):

    Heeeey cowboy, not here... βœ‹πŸ»πŸ€ 

    High Noise LoRA Scale: 1

    Low Noise LoRA Scale: 1

    Shift: 4


    T2V:

    Theoretically it works, but I haven't tested it. If you want to test it, keep the same structure as I2V, and start with a low scale on High Noise (0.5).


    About ZCD (Zero Caption Dropout)

    Caption dropout is a technique that allows some steps to be learned without the prompt. When LoRA is used separately, this isn't a big problem, but it can cause LoRA to kick in even if you don't ask for it.

    This is bad when you try to incorporate LoRA into a checkpoint (you've probably already asked for a simple woman in an NSFW Flux checkpoint and ended up getting a woman with nipples showing through her shirt. That's what happens when you do caption dropout training πŸ€·πŸ»β€β™€οΈ)

    Negative effects:

    1. It will probably only work at the same camera angle

    2. High chance of not responding to different prompts

    3. High chance of forcing the original characters of the training video (reduced if you train only the high noise)


    Download

    Download High Noise LoRA (On HuggingFace πŸ€—)

    Download Low Noise LoRA (DR34ML4Y_I2V_14B_LOW_V2)


    Want to request a LoRA?!

    (Or help making a new one)

    Just visit LoRA Requests and see if what you want has already been requested, or start a new request for it.


    Help me creating more

    If you want to help me continue making LoRAs, or if you want me to make a LoRA for you, buy 5000 PlayCoins at Aisha-AI and transfer them to my account (account number 2).

    This helps Aisha-AI to stay alive and produce new LoRAs for you all πŸ’œ

    Description

    ## Live training

    The training is complete, check the newer version.

    LORA
    Wan Video 2.2 I2V-A14B

    Details

    Downloads
    186
    Platform
    CivitAI
    Platform Status
    Available
    Created
    3/30/2026
    Updated
    4/2/2026
    Deleted
    -

    Files

    milking_table_v1.zip

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)