CivArchive

    For on-site generation, I recommend only using models designed for WAN2.1 or earlier. It does not appear that Civitai can get 2.2 models to work. You can use the Universal model with both high and low noise steps, but if you want the best quality, I included both versions as well.

    This LoRA is trained on conversational language. You can describe your scene in plain English or Chinese, and it should adhere to your prompt well. Below are some inspirations for you if you need it.

    Positions:

    • On her back

    • Kneeling

    Perspectives:

    • POV

    Enhancement phrases:

    • She bounces her body up and down

    • She bounces her breasts up and down with her hands

    All showcase videos have the workflow metadata embedded. You can download the video and drag it into ComfyUI to replicate them with their prompts, seeds, and settings.

    Description

    This model will work for T2V, I2V, and FunControl. I recommend using the I2V optimized model for any I2V, though, as it was trained using the I2V base.

    FAQ

    Comments (3)

    ComfyTinker
    Author
    Apr 22, 2025
    CivitAI

    Just a heads up!

    The WAN on-site txt2vid generation uses WAN1.3B. The on-site img2vid generation uses WAN14B. Please check the information on the post above for updates.

    I'll update HunYuan as well.

    aimaliasApr 23, 2025

    hi, thanks for all your models! do you have any idea if wan video lora training on-site uses 14b or 1.3b?

    ComfyTinker
    Author
    Apr 23, 2025

    @aimaliasart I don't know for sure. You may have to ask their support team in discord. I train on my own hardware.

    LORA
    Wan Video 14B t2v

    Details

    Downloads
    6,999
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/21/2025
    Updated
    6/14/2026
    Deleted
    -
    Trigger Words:
    Titfucks
    Fucks her tits

    Files

    Available On (1 platform)

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