ComfyUI Node
LMStudio - Connect
Creates a reusable LMStudio connection for downstream nodes. Set the Server URL, then click 'Refresh Models' to load and pick a model. 'Test Connection' verifies the server is reachable.
LMStudio - Connect
- Connection
- Status
◄server_urlhttp://127.0.0.1:1234►
◄model<refresh models>►
◄thinkingauto►
◄api_token-►
◄use_tooling_mcpfalse►
◄max_tokens1024►
◄temperature0.70►
◄timeout_seconds600►
◄test_connectivitytrue►
CategoryLMStudio
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| server_url | STRING | http://127.0.0.1:1234 | LMStudio server address, e.g. http://127.0.0.1:1234 (no /v1). |
| model | COMBO | <refresh models> | Loaded model to use. Click 'Refresh Models' to populate this dropdown from the server, then pick one. |
| thinking | COMBO | auto | Controls the model's reasoning phase. • auto — let the model decide; Gemma-family models are nudged on (they stay silent otherwise). • on — force reasoning on (enable_thinking:true). • off — suppress reasoning so the model answers directly, saving tokens. |
| api_token | STRING | - | Bearer token for the LMStudio OpenAI-compatible API. Leave '-' for local servers. |
| use_tooling_mcp | BOOLEAN | false | Signal intent to use MCP tooling. Only useful when the target model/session is configured for tool-enabled responses. |
| max_tokens | INT | 10241–1000000 | Max output tokens for downstream generation nodes. |
| temperature | FLOAT | 0.700–2 | Sampling temperature for downstream generation nodes. |
| timeout_seconds | INT | 6001–3600 | HTTP request timeout for all LMStudio calls. |
| test_connectivity | BOOLEAN | true | When enabled, validate server reachability and model availability during execution. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| Connection | LMSTUDIO_CONNECTION | Reusable LMStudio connection payload for text/image nodes. |
| Status | STRING | Connection status summary. |