CivArchive
    大摆锤 dance ——framepack - v1.5
    NSFW

    base on framepack

    The 1.5 version, trained exclusively on a single video, exhibits improved motion dynamics and more coherent action sequences compared to version 1.0. However, this approach has led to overfitting in certain areas, such as unnatural limb proportions, which I am currently addressing. For optimal results, I suggest generating content with a duration of 7.5 seconds and a resolution of 448x752.
    you can use cowboy shot,hands on hips to generate first img


    v1.0

    The FramePack LoRA training conducted using the Musubi tuner utilized 13 videos for the generation of big swing dance.

    you can download this video,then drag into comfyui to see the workflow and parameter

    The training took approximately 24 hours on 4090. I would highly recommend using a GPU with greater than 24GB of VRAM for training.

    I have only tested this on BF16 precision and have not conducted any evaluations under FP8 precision.

    thanks to 青龙圣者 , for addressing some questions regarding training parameters.

    It can be observed that FramePack, even without using F1, achieves a remarkably significant improvement in motion amplitude when employing LoRA.

    So I’m wondering if a single LoRA could simply amplify all motion amplitudes significantly.

    On the RTX 4080 32GB, it takes an average of 1 minute per second to generate.

    Description

    train on 1video

    FAQ

    Comments (7)

    iassc0866655Jun 19, 2025
    CivitAI

    What's happening to me here is that the 4090 explodes video memory as soon as lora is loaded in comfyUI, even if gpu_memory is set very high

    xianienie
    Author
    Jun 19, 2025

    Maybe your video resolution is too high.

    wqn999Jun 22, 2025
    CivitAI

    Great dance, Lora. May I ask if there will be the same content for the subsequent training of version Wan2.1? Currently, most players have moved on to use version Wan2.1.

    Pip444Jul 16, 2025
    CivitAI

    Please help aha

    Here's the error I get trying to use this specific LoRa:

    Model doesn't have any LoRA adapters or peft_config.[After unloading LoRAs] Transformer has no peft_config attribute[After unloading LoRAs] No LoRA components found in transformer
    xianienie
    Author
    Jul 16, 2025

    I mainly use ComfyUI for generation, and I’m not quite sure what you’re using.Maybe you need to check if your plugin installation is correct.

    jxyAug 5, 2025
    CivitAI

    Hi,guys . I can't use your lora to my f8 model , comfyui warning : only use bf16 , so sad.

    meikerAI3dAug 18, 2025
    CivitAI

    IndexError: list index out of range

    Unloading all LoRAs after error

    Unloading all LoRAs from Original model

    Model doesn't have any LoRA adapters or peft_config.

    [After unloading LoRAs] Transformer has no peft_config attribute

    [After unloading LoRAs] No LoRA components found in transformer

    LORA
    Hunyuan Video

    Details

    Downloads
    981
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/11/2025
    Updated
    4/30/2026
    Deleted
    -
    Trigger Words:
    One person is dancing to the dance dabaichui.The person performs a series of confident dance moves, arching her back, raising her arms behind her head, and swaying her long hair to the rhythm.

    Files

    dabaichui_2.safetensors

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)