ComfyUI Node: 🦙 Llama.cpp Router Client (Chat + Vision + Audio + Video + Stream)

Authored by ai-joe-git

Created

Updated

3 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

LLM / Simple llama.cpp

Inputs

server_url STRING
model STRING
system_prompt STRING
prompt STRING
stream BOOLEAN
max_tokens INT
temperature FLOAT
seed INT
json_mode BOOLEAN
unload_after_generate BOOLEAN
text_postprocess
  • fix_mojibake
  • none
  • ascii_quotes
  • fix_mojibake+ascii_quotes
image IMAGE
audio_path STRING
video_path STRING
api_key STRING
json_schema_hint STRING
stop_custom STRING

Outputs

STRING

STRING

STRING

STRING

STRING

Extension: Simple LlamaCPP Client

A lightweight custom node for ComfyUI that connects to a local llama.cpp OpenAI-compatible server with support for chat, vision, streaming, JSON mode, and clean answer/thinking separation.

Authored by ai-joe-git

Looking for a different node?

More nodes in Simple LlamaCPP Client

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more