This is a custom node for the ComfyUI project to support loading more vision models. It will fallback to the default loading if comfy supported models are detected. Meaning this node can be used as a drop-in replacement for the "Load Clip Vision" node.
The supported vision models can be found here at huggingface ostris/ComfyUI-Advanced-Vision. Put them in the models/clip_vision directory.
Clone this repo into the custom_nodes directory of the ComfyUI project.