ComfyUI Node: LLM Session Chat
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/Session
Inputs
user_text STRING
session_id STRING
model
- (No GGUF models found in models/LLM/)
mmproj
- (Auto-detect)
- (Not required)
system_prompt STRING
max_tokens INT
temperature FLOAT
top_p FLOAT
n_gpu_layers INT
n_ctx INT
media *
persistent_cache
- LlamaDiskCache
- off
runtime_cache
- KV_cache
- LlamaRAMCache
- LlamaTrieCache
- off
log_level
- minimal
- timing
- debug
suppress_backend_logs BOOLEAN
repeat_penalty FLOAT
repeat_last_n INT
rewrite_continue BOOLEAN
max_turns INT
summarize_old_history BOOLEAN
summary_chunk_turns INT
max_tokens_summary INT
summary_max_chars INT
dynamic_max_tokens BOOLEAN
min_generation_tokens INT
safety_margin_tokens INT
history_dir STRING
reset_session BOOLEAN
stream_to_console BOOLEAN
enable_thinking BOOLEAN
Outputs
STRING
Extension: ComfyUI-LLM-Session
Local LLM session nodes for ComfyUI using GGUF and llama.cpp, supporting Llama, Mistral, Qwen, DeepSeek, GLM, Gemma, Phi, LLaVA and gpt-oss, enabling both user–model chat and model-to-model dialogue without external runtimes like Ollama.
Authored by kantan-kanto
Looking for a different node?
More nodes in ComfyUI-LLM-Session
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.