ComfyUI-MimicMotionWrapper
Optimized wrapper nodes for MimicMotion: a/https://github.com/tencent/MimicMotion
Nodes (5)
The tiny switch that takes MimicMotion from 25 steps down to single digits
The node that drags down 7GB of model files so you don't have to
The short walk from latent video back to pixels you can actually save
Turn any video into the skeleton map MimicMotion dances to — sized to your character
The node that turns a photo and a dance clip into video — a 2024 classic still worth knowing
WORK IN PROGRESS
MimicMotion wrapper for ComfyUI
Installation
Clone this repo into custom_nodes folder.
Install dependencies: pip install -r requirements.txt
or if you use the portable install, run this in ComfyUI_windows_portable -folder:
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-MimicMotionWrapper\requirements.txt
Models are auto downloaded to their respective folders.
SVD XT:
\ComfyUI\models\diffusers\stable-video-diffusion-img2vid-xt-1-1
│ model_index.json
│
├───feature_extractor
│ preprocessor_config.json
│
├───image_encoder
│ config.json
│ model.fp16.safetensors
│
├───scheduler
│ scheduler_config.json
│
├───unet
│ config.json
│ diffusion_pytorch_model.fp16.safetensors
│
└───vae
config.json
diffusion_pytorch_model.fp16.safetensors
MimicMotion -model (3.05 GB), to ComfyUI\models\mimicmotion:
https://huggingface.co/Kijai/MimicMotion_pruned/tree/main
This needs Fp16 version (4.19 GB) diffusers version of SVD XT 1.1 to ComfyUI/models/diffusers:
https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1/tree/main
https://github.com/kijai/ComfyUI-MimicMotionWrapper/assets/40791699/c1517e20-8537-4ab0-b6fb-2d4aefa618d2
Original repo: https://github.com/tencent/MimicMotion