CivArchive
    Dancing with breasts bouncing (hunyuan video) - v1.0
    NSFW

    trained on RTX 4016 ti (16GB).

    training setting:

    resolution 244, num frames 17

    It seems learning motion does not require so high resolutions.

    Description

    FAQ

    Comments (15)

    AbobazavrDec 20, 2024
    CivitAI

    How many videos in dataset?

    yanagi099
    Author
    Dec 20, 2024· 1 reaction

    17 videos sliced from 2 videos.

    screamlouderDec 21, 2024
    CivitAI

    How did you train this lora? Do you have a guide?

    yanagi099
    Author
    Dec 21, 2024· 13 reactions

    To train lora, I used diffusion-pipe (https://github.com/tdrussell/diffusion-pipe) on wsl2.

    some tips I have:

    I only have 16gb vram, so I had to set resolutions=244 and frame_buckets=[17] by changing ./examples/dataset.toml. The length of videos for train should be about 1 sec, so I sliced my videos before training.

    I found that, for training motion, you dont have to use so high resolution, and for training face, you have to train on higher resolution like 512. I trained that lora for about 4 hours, 2000steps.

    Too big dataset may cause overflow of vram. I trained on 17 videos.

    screamlouderDec 21, 2024

    @yanagi099 Thank you for the information! Is there a reason why the videos in the dataset need to be exactly 1 second?

    yanagi099
    Author
    Dec 21, 2024· 7 reactions

    @screamlouder Actually, you dont have to make the length of video to 1 second, because the video will automatically shorten into frame number you set in setting. However, If you want to choose exact moment in the videos, you should slice the video and choose them. Sorry for my poor English.

    asdrabaelDec 21, 2024

    @yanagi099 Did you resize the videos to the resolution you set, or just put the training to that resolution and keep the videos their original format?

    yanagi099
    Author
    Dec 22, 2024· 3 reactions

    @asdrabael I just put the training to that resolution.

    asdrabaelDec 22, 2024

    @yanagi099 so say I have a video that is 768x1280 resolution and I set it to 384. Will that warp the video or just resize it to 230x384? Just trying to understand how the function works.

    yanagi099
    Author
    Dec 23, 2024

    @asdrabael I dont know well, but it seems the video would resize to have 384x384 pixels keeping the aspect ratio.

    asdrabaelDec 30, 2024· 2 reactions

    @yanagi099 

    I'm still trying to figure out how you did this. My pc is linux. I got 12 video clips that are 1 second long each. I resized them all to 242x140. I tried 17 frames down to 10 frames. I have nothing using my gpu at all, and everything loads up and when it starts step 1, I get an OOM error.

    tomazxzas143Jan 30, 2025· 4 reactions
    CivitAI

    It only generates asian faces for me?

    3427221Feb 12, 2025· 3 reactions
    CivitAI

    I think this one still have one of the best bouncing/moving boobies of all loras,

    CyberfolkFeb 16, 2025· 1 reaction

    and the fact is training on RTX 4060 ti wtf

    3427221Feb 16, 2025· 1 reaction

    @Cyberfolk yeah but the number of frames and resolution he used is low so that part wasn't so surprising, the surprise is how good it turned despite that :)

    For example I went OOM and crashed on my RTX 3090 (24GB vram) when trying to train at 432 pixels resolution and 69 frames, but it worked at 350 resolution (or something like that) and 65 frames quite easy, so these two parameters really put the Vram in high use quickly

    LORA
    Hunyuan Video

    Details

    Downloads
    11,889
    Platform
    CivitAI
    Platform Status
    Available
    Created
    12/19/2024
    Updated
    5/13/2026
    Deleted
    -
    Trigger Words:
    high quality video of a dancing woman
    bouncing breasts

    Available On (1 platform)

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