ComfyUI Node
Get LLM Response
Get response from the provided llama.cpp model
Get LLM Response
- model
- response_message
- full_response
◄prompt►
◄system_promptYou are a helpful assistant.►
◄temperature0.6►
◄max_tokens2048►
◄top_p0.95►
◄seed42►
◄image_path►
◄image_base64►
CategorySagado-Nodes
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| prompt | STRING | — | |
| system_prompt | STRING | You are a helpful assistant. | — |
| temperature | FLOAT | 0.60–1 | — |
| max_tokens | INT | 2048-1–32000 | — |
| top_p | FLOAT | 0.950–1 | — |
| seed | INT | 42 | — |
| image_pathopt | STRING | — | |
| image_base64opt | STRING | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| response_message | STRING | — |
| full_response | STRING | — |