CivArchive
    slop bounce MiniMax H3 LoRa - H3 slop bounce lora
    NSFW

    Put something like this in your prompt:

    breasts bounce, shake, jiggle and sway.

    Should work with I2VA. Idk about REF2VA, but feel free to try it out and share results! The first 2 video examples are T2VA with the lora strength set to 1, workflow and basic prompt included from video. I trained at 3000 steps and 10 epochs. This is epoch 5. Thanks to anonimoose for sharing the dataset.

    MiniMax H3 Prompt guide for you/LLM.
    https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md
    https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/VIDEO_PROMPT_WRITING_GUIDE_ref_en.md

    NEW* H3 SLOP TWERK: https://civarchive.com/models/2885070/slop-twerk-minimax-h3-lora

    If body is too big, try pairing with a breast/body type lora and slightly lower both strengths.

    If clothes are vanishing, you may have to prompt clothing.

    Description

    Put something like this in your prompt: shakes her hips side to side causing her breasts to bounce, shake, jiggle and sway.

    Should work with I2V but probably lower strength. I trained at 3000 steps and 10 epochs. This is epoch 5. Thanks to anonimoose for sharing the dataset.

    FAQ

    Comments (28)

    dshgfajshsksvv847Aug 22, 2026
    CivitAI

    Woohoo!!!!

    _Glint_Aug 22, 2026· 3 reactions
    CivitAI

    Who's the hero?! It's you!!

    AnonymousAAAAug 22, 2026
    CivitAI

    r2v works. But it seems to force the slow motion even if I prompt about speed and frequency

    AnonymousAAAAug 22, 2026

    And the tits are always out, the size is always huge.

    bhopping
    Author
    Aug 22, 2026

    @AnonymousAAA Try lowering the lora strength value to like 0.3

    bhopping
    Author
    Aug 29, 2026

    After some testing with a different lora having this issue as well, I think prompting clothing may stop the clothes from disappearing and you might be able to pair a breast/body type lora at like 0.8 STR with this lora at 0.8 to stop the body from enlarging

    meowmeow12345Aug 22, 2026
    CivitAI

    Just curious since I've tried something similar with mixed results/not very good, you use aitoolkit and train with videos? So you keep the i2v part unchecked? o.o;

    bhopping
    Author
    Aug 22, 2026

    I am unsure sorry. I trained it on civitai MiniMax H3 base model

    vdsvsdvsd3433Aug 22, 2026
    CivitAI

    its fantastic! But seems to give a lot of the time the same body shape/stomach.

    tested on different strengths

    bhopping
    Author
    Aug 26, 2026· 1 reaction

    Sorry I am a bit late. It sounds like I could've over trained it slightly but not sure exactly (I am noob), I am looking into it. Perhaps I will make a V2 to fix this. Ty for the feedback : )

    vdsvsdvsd3433Aug 26, 2026

    @bhopping No problem! You are doing amazing work :) I found turning the strength to around 0.45 and vis to around 0.70 gave a nice balance. Keep it up!

    bhopping
    Author
    Aug 27, 2026

    @vdsvsdvsd3433 Nice btw I guess the VIS knob is a multiplier for the strength, so I think your strength is technically set to 0.315, I totally thought it was something else

    SugarPixelArtAug 22, 2026· 1 reaction
    CivitAI

    A masterwork!

    bhopping
    Author
    Aug 22, 2026· 2 reactions

    thx for the buzz!

    SugarPixelArtAug 22, 2026

    @bhopping You’re welcome!

    RodumatriAug 23, 2026· 4 reactions
    CivitAI

    Nice work ♥️ You can do slop bounce for as s s? 👌👌

    bhopping
    Author
    Aug 23, 2026

    Currently baking in the oven as we speak. Stay tuned!

    KarsticlesAug 24, 2026· 3 reactions
    CivitAI

    Converts images to realism at high weights currently.

    bhopping
    Author
    Aug 26, 2026

    I might've over trained it slightly. I didn't know that was a thing, I am looking into it. Ty for the feedback!

    KarsticlesAug 26, 2026

    @bhopping You are most welcome, and thank you for the lora! Maybe you can use animated images at low weights as part of your training set if you are lacking data.

    REALMZEROFIVEAug 25, 2026· 1 reaction
    CivitAI

    Unfortunately does next to nothing that I can see, in R2V. You can prompt heavily for it, but the model already has good 'physics' baked in, so prompting it isn't really a feature of this LoRA. Definitely different than the W2.2 version, which was very much just "it just works"

    BretChampagneAug 26, 2026· 5 reactions
    CivitAI

    Dude, you are a boobies sorcerer...
    Your contribution to female sloppiness science is beyond all what could have done these crazy chinese searchers... Beijin should hire you... You just fixed the main problem with Minimax H3. Love you man

    ssfsd4624623523Aug 28, 2026
    CivitAI

    Hi, Can you tell me which checkpoints and models were used to generate the image (not the video)?

    bhopping
    Author
    Aug 29, 2026

    2B? That was just from T2V model, some of the training used 2B videos. Is that the one you are referring too?

    ssfsd4624623523Aug 29, 2026

    @bhopping  Thanks for getting back to me, I was under the impression that you generated the images using a separate checkpoint and then turned them into videos with MiniMax. I never thought it was possible to create work of this quality using just a T2V model. Could you tell me which T2V model you used? I'd like to give it a try, so it would be great if you could briefly point me in the right direction.

    bhopping
    Author
    Aug 30, 2026

    @ssfsd4624623523 I am using minimax_h3_fl2va_pruned_fp8_scaled but I think most ppl are using INT8 over FP8 for more speed if you are on CUDA 13.0+ from what I heard. I just haven't updated my stuff in a long time so I don't reap the benefit of INT8 yet

    LORA
    MiniMax H3

    Details

    Downloads
    2,624
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/22/2026
    Updated
    8/30/2026
    Deleted
    -

    Files

    H3_slop_bounce.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)