ComfyUI Node
LLM Studio - Options
Collects LM Studio connection details (URL, model, sampling rates, temperature, clothing-color toggle) into a single `llm_studio_options` dict that downstream describe nodes consume.
LLM Studio - Options
- llm_studio_options
◄base_urlhttp://192.168.50.41:1234►
◄model_nameqwen/qwen3-vl-30b►
◄prompt_styleText2Image►
◄temperature0.5►
◄sample_rate2.0►
◄max_duration5.0►
◄change_clothing_colorNo►
◄verbosefalse►
CategorySwiss Army Knife 🔪/Media Caption
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| base_url | STRING | http://192.168.50.41:1234 | LM Studio server URL (e.g. http://192.168.50.41:1234) |
| model_name | STRING | qwen/qwen3-vl-30b | Model name in LM Studio (e.g. qwen/qwen3-vl-30b) |
| prompt_style | COMBO | Text2Image | Text2Image: Generates descriptive prompts for models like FLUX Dev, SDXL, etc. ImageEdit: Generates instruction prompts with words like 'change to...', 'modify this...' for image editing models like FLUX Redux/Kontext, Nano Banana, Qwen Image Edit |
| temperature | FLOAT | 0.50–2 | Temperature for text generation |
| sample_rate | FLOAT | 2.00.1–30 | Frames per second to extract (e.g., 1.0 = 1 frame/sec, 2.0 = 2 frames/sec) |
| max_duration | FLOAT | 5.01–60 | Maximum duration in seconds to sample from video |
| change_clothing_color | COMBO | No | If enabled, adjust clothing color descriptions to new colors that harmonize with the scene and differ from the original colors |
| verbose | BOOLEAN | false | Show detailed processing information in console |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| llm_studio_options | LLM_STUDIO_OPTIONS | — |