ComfyUI Node
LlamaCPP Chat
Chat with llama.cpp. Use media_mode to select none / image / video / audio input. Set visualization=html to force HTML output and render it to html_image. Wire a LlamaCPP Visualizer HTML node to viz_settings to control render dimensions (optional, defaults to 800x600).
LlamaCPP Chat
- connectivity
- options
- images
- video
- audio
- viz_settings
- result
- thinking
- html_image
◄systemYou are an AI assistant.►
◄promptHello!►
◄thinkfalse►
◄format▾►
◄reset_sessiontrue►
◄media_modenone►
◄visualizationdisabled►
CategoryLlamaCPP API
Inputs (13)
| Name | Type | Default | Description |
|---|---|---|---|
| system | STRING | You are an AI assistant. | — |
| prompt | STRING | Hello! | — |
| think | BOOLEAN | false | — |
| format | COMBO | 2 options: text, json | |
| reset_session | BOOLEAN | true | — |
| media_mode | COMBO | none | Which optional media socket to process. none=text only (inputs ignored even if wired), image=still frames, video=temporal batch, audio=AUDIO input (Gemma4 E2B/E4B only) |
| visualization | COMBO | disabled | html: forces full HTML document output and renders the result to html_image via Playwright. |
| connectivityopt | LLAMACPP_CONNECTIVITY | — | |
| optionsopt | LLAMACPP_OPTIONS | — | |
| imagesopt | IMAGE | Active when media_mode=image | |
| videoopt | IMAGE | Active when media_mode=video. Batch treated as temporal frames. Max 60 frames. | |
| audioopt | AUDIO | Active when media_mode=audio. Gemma4 E2B/E4B only. Max 30 s. | |
| viz_settingsopt | LLAMACPP_VIZ_SETTINGS | Wire a LlamaCPP Visualizer HTML node to control render width/height/delay. Optional — defaults to 800x600. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| result | STRING | — |
| thinking | STRING | — |
| html_image | IMAGE | — |