ComfyUI LLaVA Captioner

by ceruleandeep0 starsfailed

A ComfyUI extension for chatting with your images. Runs on your own system, no external services used, no filter. Uses the [a/LLaVA multimodal LLM](https://llava-vl.github.io/) so you can give instructions or ask questions in natural language. It's maybe as smart as GPT3.5, and it can see.

View on GitHub

Nodes (0)

No node definitions found for this pack.

ComfyUI LLaVA Captioner | TealPug Node Explorer