Comfyui-MusePose

Comfyui-MusePose
★ 426

视频生成姿态控制虚拟人图像到视频
将静态人物图像在姿态等控制信号下生成可控动作视频的ComfyUI节点,便于制作端到端虚拟人动画。
💡 用姿态驱动将人物图片生成连续动作视频。
🍴 48 Forks💻 Python🔄 2024-07-31
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/79aaff81621b
📦 requirements.txt
einops==0.4.1
imageio==2.33.0
imageio-ffmpeg==0.4.9
omegaconf==2.2.3
opencv-contrib-python==4.8.1.78
opencv-python==4.8.1.78
scikit-image==0.21.0
scikit-learn==1.3.2
transformers==4.33.1
moviepy==1.0.3
urllib3==1.26.9
torch
torchdiffeq
torchmetrics
torchsde
torchvision
accelerate==0.29.3
av==11.0.0
clip
@
https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip#sha256=b5842c25da441d6c581b53a5c60e0c2127ebafe0f746f8e15561a006c6c3be6a
decord==0.6.0;
sys_platform
!=
'darwin'
and
platform_machine
!=
'arm64'
eva-decord==0.6.1;
sys_platform
==
'darwin'
and
platform_machine
==
'arm64'
diffusers>=0.24.0,<=0.27.2
open-clip-torch==2.20.0
xformers
📄 README

MusePose

MusePose is an image-to-video generation framework for virtual human under control signal such as pose.

MusePose is the last building block of the Muse opensource serie. Together with MuseV and MuseTalk, we hope the community can join us and march towards the vision where a virtual human can be generated end2end with native ability of full body movement and interaction. Please stay tuned for our next milestone!

Comfyui-MusePose

If you’re running on Linux, or non-admin account on windows you’ll want to ensure /ComfyUI/custom_nodes and Comfyui-MusePose has write permissions.

Followed ComfyUI’s manual installation steps and do the following:

  • Navigate to your /ComfyUI/custom_nodes/ folder
  • Run git clone https://github.com/TMElyralab/Comfyui-MusePose.git
  • Navigate to your /ComfyUI/custom_nodes/Comfyui-MusePose folder and run
  • “`shell

    pip install -r requirements.txt

    pip install –no-cache-dir -U openmim

    mim install mmengine

    mim install “mmcv>=2.0.1”

    mim install “mmdet>=3.1.0”

    mim install “mmpose>=1.1.0”

    “`

  • Start ComfyUI
  • Updates

  • requirements.txt: diffusers 0.27.2 is now supported
  • Download weights

    You can download weights manually as follows:

  • Download our trained weights.
  • Download the weights of other components:
  • sd-image-variations-diffusers
  • sd-vae-ft-mse
  • dwpose
  • yolox – Make sure to rename to yolox_l_8x8_300e_coco.pth
  • image_encoder
  • Finally, these weights should be organized in pretrained_weights as follows:

    ./pretrained_weights/
    |-- MusePose
    |   |-- denoising_unet.pth
    |   |-- motion_module.pth
    |   |-- pose_guider.pth
    |   └── reference_unet.pth
    |-- dwpose
    |   |-- dw-ll_ucoco_384.pth
    |   └── yolox_l_8x8_300e_coco.pth
    |-- sd-image-variations-diffusers
    |   └── unet
    |       |-- config.json
    |       └── diffusion_pytorch_model.bin
    |-- image_encoder
    |   |-- config.json
    |   └── pytorch_model.bin
    └── sd-vae-ft-mse
        |-- config.json
        └── diffusion_pytorch_model.bin
    

    workflow demo

    https://github.com/TMElyralab/Comfyui-MusePose/blob/main/musepose-workflow-demo.json

    https://github.com/TMElyralab/Comfyui-MusePose/assets/114042542/9cd8b9b8-6876-4281-b7a0-a7fbcb2de7e1