ComfyUI-SkyworkUniPic

ComfyUI-SkyworkUniPic
★ 13

多模态文本到图像图像编辑ComfyUI节点
在ComfyUI中接入Skywork-UniPic（15亿参数统一自回归多模态模型），在单节点内实现图像理解、文本到图像生成与图像编辑的一体化调用与流程整合。
💡 在ComfyUI流程中统一调用生成、理解与编辑功能。
🍴 3 Forks💻 Python🔄 2025-07-30
📦
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
torch==2.6.0
deepspeed
peft
xtuner
mmengine
transformers==4.45.2
timm==0.9.12
#
flash_attn==2.3.4
📄 README

ComfyUI-SkyworkUniPic

ComfyUI-SkyworkUniPic is now available in ComfyUI, Skywork-UniPic is a unified autoregressive multimodal model with 1.5 billion parameters that natively integrates image understanding, text-to-image generation, and image editing capabilities within a single architecture.

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-SkyworkUniPic.git

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

    Model

    Download Pretrained Models

    Download the model checkpoints from [🤗 SkyworkUniPic],

    It is recommended to use the following command to download the checkpoints

    # pip install -U "huggingface_hub[cli]"
huggingface-cli download Skywork/Skywork-UniPic-1.5B  --local-dir checkpoint --repo-type model