Request support for loading GGUF-quantized models

[Amazon90]

I hope you can perform GGUF quantization on the JoyCaption model and add a new node in ComfyUI for direct loading and usage of GGUF-quantized models, making it accessible to more consumer-grade GPUs.

[judian17]

I created a GGUF version of this node by using Gemini. Although installing llama-cpp-python is a bit tricky, you can give it a try.https://github.com/judian17/ComfyUI-joycaption-beta-one-GGUF

[Amazon90]

I created a GGUF version of this node by using Gemini. Although installing llama-cpp-python is a bit tricky, you can give it a try.https://github.com/judian17/ComfyUI-joycaption-beta-one-GGUF

Awesome! Your node has saved GPU starved users.