ComfyUI Node
[llama.cpp] Generate
Runs one request on a local or server-backed llama.cpp session and carries it forward.
[llama.cpp] Generate
- session
- images
- audio
- video
- model_profile
- response
- thinking
- raw_json
- metrics
- media_diagnostics
◄system►
◄prompt►
◄max_tokens512►
◄seed-1►
◄stop►
◄video_with_audiofalse►
◄session_unloadfalse►
Categoryllama_cpp/generate
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| session | OLLAMA_IMAGE_LIST_LLAMA_CPP_SESSION | — | |
| system | STRING | — | |
| prompt | STRING | — | |
| max_tokens | INT | 5121–131072 | — |
| seed | INT | -1-1–4294967295 | — |
| stop | STRING | — | |
| video_with_audio | BOOLEAN | false | — |
| session_unload | BOOLEAN | false | Unload the session after generation completes. |
| imagesopt | IMAGE | — | |
| audioopt | AUDIO | — | |
| videoopt | VIDEO | — | |
| model_profileopt | OLLAMA_IMAGE_LIST_LLAMA_CPP_MODEL_PROFILE | Optional per-request sampling and reasoning override. The session handler is selected at creation and is not changed. |
Outputs (5)
| Name | Type | Description |
|---|---|---|
| response | STRING | — |
| thinking | STRING | — |
| raw_json | STRING | — |
| metrics | STRING | — |
| media_diagnostics | OLLAMA_IMAGE_LIST_LLAMA_CPP_MEDIA_DIAGNOSTICS | — |