Name		Name	Last commit message	Last commit date
.github/ISSUE_TEMPLATE		.github/ISSUE_TEMPLATE
.vscode		.vscode
assets		assets
docs		docs
eval_mm		eval_mm
examples		examples
finetune		finetune
omnilmm		omnilmm
.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
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_streamlit-2_5.py		web_demo_streamlit-2_5.py
web_demo_streamlit.py		web_demo_streamlit.py

Repository files navigation

ComfyUI MiniCPM-V (Unofficial Support)

Unofficial MiniCPM-V support for ComfyUI.

Important Updates

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

Basic Workflow

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

Installation

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

Download Checkpoints

All the models will be downloaded automatically, no worries.

About

Unofficial implementation of MiniCPM-V and MiniCPM-V-2 in ComfyUI

0 stars

0 watching

Report repository

Releases

Packages

Contributors

Languages