ComfyUI-LLaVA-OneVision
★ 101
视觉-语言LLaVAComfyUI插件模型集成
在ComfyUI中调用 OneVision LLaVA(LLaVA-NeXT)视觉语言模型,便捷实现图像与文本的联合推理与生成,依赖精简,仍在开发中。
💡 在ComfyUI中快速调用 OneVision LLaVA 进行图文理解与生成
🍴 9 Forks💻 Python🔄 2026-01-12
https://pan.quark.cn/s/b45acaa3411d
📦 requirements.txt
huggingface_hub
pillow
transformers>=4.57.0
📄 README
WORK IN PROGRESS
Unsure of the dependencies, the original was a huge list, but I didn’t install single new one to my environment and it worked.
Original repo:
https://github.com/LLaVA-VL/LLaVA-NeXT