ComfyUI Node
LM Studio 988
LM Studio 988 — a node for integrating with LM Studio's local LLM/VLM capabilities.
LM Studio 988
- image1
- image2
- image3
- image4
- response
- reasoning
- troubleshooting
◄system_messageYou are a helpful assistant.►
◄default_system_message🚫OFF►
◄prompt►
◄model_selection-- Custom (enter below) --►
◄custom_model_name►
◄max_tokens1024►
◄temperature0.70►
◄seed0►
◄image_resizeMedium (768px)►
◄draft_model_selection-- Custom (enter below) --►
◄custom_draft_model►
◄top_p1.00►
◄top_k0►
◄repeat_penalty1.00►
◄reasoning_modeAuto-detect (recommended)►
◄custom_open_tag<think>►
◄custom_close_tag</think>►
◄unload_all_modelsfalse►
◄empty_cuda_cachefalse►
◄refresh_modelsfalse►
Category🦇988/LM Studio
Inputs (24)
| Name | Type | Default | Description |
|---|---|---|---|
| system_message | STRING | You are a helpful assistant. | System prompt that defines the LLM's role and behavior. |
| default_system_message | COMBO | 🚫OFF | Select a predefined system message template to append after your custom system message. |
| prompt | STRING | The user prompt to send to the LLM. | |
| model_selection | COMBO | -- Custom (enter below) -- | Select a model from LM Studio. Select 'Custom' to manually enter a model identifier. |
| custom_model_name | STRING | Manual model identifier. Only used when 'Custom' is selected above. | |
| max_tokens | INT | 10241–131072 | Maximum OUTPUT tokens for the response. |
| temperature | FLOAT | 0.700–2 | Controls randomness. Lower = focused, Higher = creative. |
| seed | INT | 00–18446744073709550000 | Seed for reproducibility. |
| image_resizeopt | COMBO | Medium (768px) | Resize images before processing. Smaller = faster inference. |
| image1opt | IMAGE | First image input for vision models (VLMs). | |
| image2opt | IMAGE | Second image input for multi-image VLMs. | |
| image3opt | IMAGE | Third image input for multi-image VLMs. | |
| image4opt | IMAGE | Fourth image input for multi-image VLMs. | |
| draft_model_selectionopt | COMBO | -- Custom (enter below) -- | Optional draft model for speculative decoding. |
| custom_draft_modelopt | STRING | Manual draft model identifier. Leave empty to disable. | |
| top_popt | FLOAT | 1.000–1 | Nucleus sampling threshold. 1.0 = disabled. |
| top_kopt | INT | 00–500 | Top-K sampling. 0 = disabled. Recommended: 20-40 for thinking models. |
| repeat_penaltyopt | FLOAT | 1.000–2 | Penalizes repeated tokens. 1.0 = disabled. |
| reasoning_modeopt | COMBO | Auto-detect (recommended) | How to extract reasoning/thinking from model output. |
| custom_open_tagopt | STRING | <think> | Custom opening tag for reasoning extraction. |
| custom_close_tagopt | STRING | </think> | Custom closing tag for reasoning extraction. |
| unload_all_modelsopt | BOOLEAN | false | Unloads ComfyUI models (SD, VAE, etc.) from VRAM. |
| empty_cuda_cacheopt | BOOLEAN | false | Clears the CUDA cache. |
| refresh_modelsopt | BOOLEAN | false | Toggle ON to re-fetch the model list from LM Studio. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| response | STRING | — |
| reasoning | STRING | — |
| troubleshooting | STRING | — |