ComfyUI MiniCPM-V (Unofficial Support)

Unofficial MiniCPM-V support for ComfyUI.

Important Updates

2024/08/09: Added support for MiniCPM-V 2.6 (16GB+ video memory required)
2024/05/22: Added support for MiniCPM-Llama3-V 2.5 (16GB+ video memory required)
2024/04/18: Added ComfyUI nodes and workflow examples

This workflow shows the basic usage on querying an image with Chinese and English.

This workflow shows the Verson 2.6's usage on querying multiple images and a video.

Install from ComfyUI Manager (search for minicpm)
Download or git clone this repository into the ComfyUI/custom_nodes/ directory and run:

pip install -r requirements.txt

All the models will be downloaded automatically, no worries.

Name		Name	Last commit message	Last commit date
Latest commit History 421 Commits
.github		.github
.vscode		.vscode
assets		assets
docs		docs
eval_mm		eval_mm
examples		examples
finetune		finetune
omnilmm		omnilmm
quantize		quantize
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
README.md.bak		README.md.bak
README_en.md		README_en.md
README_zh.md		README_zh.md
__init__.py		__init__.py
chat.py		chat.py
minicpm_v1.md		minicpm_v1.md
nodes.py		nodes.py
omnilmm.md		omnilmm.md
omnilmm_en.md		omnilmm_en.md
pyproject.toml		pyproject.toml
requirements.txt		requirements.txt
requirements.txt.bak		requirements.txt.bak
web_demo.py		web_demo.py
web_demo_2.5.py		web_demo_2.5.py
web_demo_2.6.py		web_demo_2.6.py
web_demo_streamlit-2_5.py		web_demo_streamlit-2_5.py
web_demo_streamlit.py		web_demo_streamlit.py