ComfyUI Node
🦙 Llama-Swap Client
A ComfyUI node in llama-swap with 6 inputs and 2 outputs.
🦙 Llama-Swap Client
- image
- response
- thinking
◄server_urlhttp://localhost:8080►
◄model►
◄system_promptYou are a helpful assistant.►
◄promptHello!►
◄unload_after_generatefalse►
Categoryllama-swap
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| server_url | STRING | http://localhost:8080 | llama-swap server base URL |
| model | STRING | Model name — click Fetch Models button to pick from the server | |
| system_prompt | STRING | You are a helpful assistant. | System prompt sent before the user message |
| prompt | STRING | Hello! | User message / question |
| unload_after_generate | BOOLEAN | false | Call /unload on the llama-swap server after generation |
| imageopt | IMAGE | Optional image for vision models (first frame used) |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| response | STRING | Clean response text with <think> blocks removed |
| thinking | STRING | Extracted thinking/reasoning content (empty if model produced none) |