ComfyUI-UNO

ComfyUI-UNO
★ 10

图像生成模型集成ComfyUI插件Python节点
为ComfyUI提供UNO模型节点，便于在工作流中集成并调用UNO进行图像生成与处理，简化部署与依赖管理。
💡 在ComfyUI工作流中调用UNO模型生成或处理图像
🍴 3 Forks💻 Python🔄 2025-04-11
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/a9fb3a59e10c
📦 requirements.txt
accelerate==1.1.1
deepspeed==0.14.4
einops==0.8.0
transformers==4.43.3
huggingface-hub
diffusers==0.30.1
sentencepiece==0.2.0
gradio==5.22.0
--extra-index-url
https://download.pytorch.org/whl/cu124
torch==2.4.0
torchvision==0.19.0
📄 README

ComfyUI-UNO

Make UNO avialbe in ComfyUI.

🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning. The arXiv paper of UNO is released. Less-to-More Generalization: Unlocking More Controllability by In-Context Generation.

Installation

  • Make sure you have ComfyUI installed

  • Clone this repository into your ComfyUI’s custom_nodes directory:
    • cd ComfyUI/custom_nodes
git clone https://github.com/Yuan-ManX/ComfyUI-UNO.git

  • Install dependencies:
    • cd ComfyUI-UNO
pip install -r requirements.txt

    Models

    Download model

    Download checkpoints in one of the three ways:

  • Directly run the inference scripts, the checkpoints will be downloaded automatically by the hf_hub_download function in the code to your $HF_HOME(the default value is ~/.cache/huggingface).

  • use huggingface-cli download to download black-forest-labs/FLUX.1-dev, xlabs-ai/xflux_text_encoders, openai/clip-vit-large-patch14, bytedance-research/UNO, then run the inference scripts.

  • use huggingface-cli download --local-dir to download all the checkpoints menthioned in 2. to the directories your want. Then set the environment variable AE, FLUX, T5, CLIP, LORA to the corresponding paths. Finally, run the inference scripts.