ComfyUI Node
Vision-SLM: Model Selector
A ComfyUI node in Pilcothink/SLM-Vision with 4 inputs and 2 outputs.
Vision-SLM: Model Selector
- slm_model
- model_path
◄modeldeepseek-vl-1.3b-chat►
◄deviceauto►
◄dtypeauto►
◄download_if_missingtrue►
CategoryPilcothink/SLM-Vision
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | deepseek-vl-1.3b-chat | 8 options: deepseek-vl-1.3b-chat, Qwen2-VL-2B-Instruct, qwen2.5-vl-3b-instruct, Qwen3-VL-2B-Instruct, Qwen3-VL-2B-Thinking, Qwen3-VL-4B-Instruct, +2 |
| device | COMBO | auto | 3 options: auto, cuda, cpu |
| dtype | COMBO | auto | 4 options: auto, bfloat16, float16, float32 |
| download_if_missing | BOOLEAN | true | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| slm_model | SLM_MODEL | — |
| model_path | STRING | — |