ComfyUI Node: LLaVA Captioner 🌊
Category
image
Inputs
image IMAGE
model
mm_proj
prompt STRING
max_tokens INT
temperature FLOAT
Outputs
STRING
Extension: ComfyUI LLaVA Captioner
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 so you can give instructions or ask questions in natural language. It's maybe as smart as GPT3.5, and it can see.
Authored by ceruleandeep
Run ComfyUI workflows in the Cloud!
No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues
Learn more