CivArchive
    Doggystyle from the side - Doggystyle from the side
    NSFW

    This is the Wan version, same dataset. You prompt the same. It works best at 0.5-1.0 strength. It's not that great at unnatural hair colors, and it occasionally shows a watermark so when I redo this I'll remove all the watermarks from the dataset first.

    This uses the 14b t2v, and I have a 14b i2v version I'm testing for extending these videos from the last frame.

    Any input on ways to improve it or things I should add would be appreciated.

    Description

    Version 1

    FAQ

    Comments (24)

    DomDomTomTomJan 7, 2025· 3 reactions
    CivitAI

    Looks like a great Lora but would be nice to have an example prompt.

    asdrabael
    Author
    Jan 7, 2025· 7 reactions

    I kept the metadata on the videos so I assumed that civitai would automatically put the prompts on the videos. Later when I get home from work I'll add a couple.

    DomDomTomTomJan 7, 2025

    @asdrabael Thanks bro!

    crombobularJan 7, 2025
    CivitAI

    pose is good, the motion is hit or miss tho

    makiaeveliJan 7, 2025

    so many bouncy loras :D

    asdrabael
    Author
    Jan 7, 2025

    Yeah, it was a first try. I think if I removed the images and used longer video clips I can get the motion better for v2.

    Rating_AgentJan 8, 2025· 3 reactions
    CivitAI

    Is model mode biased for african men? All examples are african guys

    asdrabael
    Author
    Jan 8, 2025

    A little bit. My training videos came from realbooru and I grabbed the first 10 that fit the poses and when I was prepping the files I realized 6 of the 10 had African men. You can get other colors but without prompting the mans race it leans towards that.

    Rating_AgentJan 8, 2025· 3 reactions

    @asdrabael can you please add more variety of man and women, having biased model by default is not cool imo

    asdrabael
    Author
    Jan 8, 2025· 3 reactions

    @Rating_Agent it's literally my first try. I know it has issues it needs work on like the motion is spotty too. I'm going to update it when I get the time. I just wasn't paying attention to races since it's not something I really look at and I was more focused on the correct pose and motion. Just prompt it with "white man" or whatever you wantin the meantime.

    playnproto266Jan 13, 2025· 1 reaction

    @asdrabael It's a great first try. I find that when I'm training describing everything but the motion is the way to go unless there is some sort of variety to the motion. People tend to forget to describe faces and ethnicities, which can lead to situations like this and same face syndrome.

    asdrabael
    Author
    Jan 13, 2025· 1 reaction

    @playnproto266 I corrected it with v2 I think. I mixed it up more and the motion came out better. It still needs a little work but I'll try not describing the motion

    playnproto266Jan 13, 2025

    @asdrabael We're all learning as we go! Thank you for your contribution to the community!

    kkkdsadasJan 8, 2025· 11 reactions
    CivitAI

    Your lora is great! , can I have a footjob with lora, thank you very much!

    YulexuanJan 11, 2025· 2 reactions
    CivitAI

    Is there an example workflow to run this? I tried to run it on Comfyui and it says "lora key not loaded: lora_unet_up_blocks_3_attentions_2_transformer_blocks_0_ff_net_2.lora_up.weight", the generations look nothing like the lora is supposed to do.

    asdrabael
    Author
    Jan 12, 2025

    I have no idea why it's doing that. Are you using the hunyuan wrapper nodes?

    lost_moonJan 12, 2025

    Same issue. Using Hunyuan FastVideo 720 fp8. Using comfyui native hunyuan nodes.
    What clip models do you load in the DualClipLoader?

    ColorWolveJan 13, 2025

    same...on fast hunyuan gguf...no idea how to solve it..

    asdrabael
    Author
    Jan 13, 2025

    @lost_moon I used clip_l because thats what Musubi Tuner species in the repo. I used the other one and it used a lot more vram.

    lost_moonJan 13, 2025

    Solution for this issue is the following, with musubi. This lora needs to be converted to work with comfyui properly. After doing so I get no error anymore and the lora is working:
    python convert_lora.py --input /pathto/lora.safetensors --output /pathto/lora_output/converted_lora.safetensors --target other

    Melty1989Jan 14, 2025

    @lost_moon I'm using the python_embedded within ComfyUI. When i run the command you mentioned i get this error:
    Traceback (most recent call last):

    File "D:\ComfyUI_windows_portable\musubi-tuner\convert_lora.py", line 6, in <module>

    from utils import model_utils

    ImportError: cannot import name 'model_utils' from 'utils' (D:\ComfyUI_windows_portable\ComfyUI\utils\__init__.py)

    Any idea what's wrong?

    lost_moonJan 14, 2025

    @Melty1989 i don't know what python_embedded in comfyui is. You got to download and install requirements of musubi. Then I open a cmd window, (maybe optional but I did then: active the venv), then run the two lines at once. Double check your paths and backslashes.

    Melty1989Jan 14, 2025

    @lost_moon So that's basically the bundled python version that comes in with it. I did install pip install all of the requirements.

    AimyiJan 16, 2025

    You need to convert lora to adapt to comfyui before you can use it.https://civitai.com/articles/10335

    LORA
    Hunyuan Video

    Details

    Downloads
    2,501
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/7/2025
    Updated
    6/28/2026
    Deleted
    -
    Trigger Words:
    Doggystyle from the side