ComfyUI Node
Download and Load Qwen2.5-VL Model
A ComfyUI node in Qwen2.5-VL with 4 inputs and 1 output.
Download and Load Qwen2.5-VL Model
- qwen_model
◄model_name▾►
◄device▾►
◄precision▾►
◄attention▾►
CategoryQwen2.5-VL
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| model_name | COMBO | 4 options: Qwen/Qwen2.5-VL-3B-Instruct, Qwen/Qwen2.5-VL-7B-Instruct, Qwen/Qwen2.5-VL-32B-Instruct, Qwen/Qwen2.5-VL-72B-Instruct | |
| device | COMBO | 4 options: auto, cuda:0, cuda:1, cpu | |
| precision | COMBO | 5 options: INT4, INT8, BF16, FP16, FP32 | |
| attention | COMBO | 2 options: flash_attention_2, sdpa |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| qwen_model | QWEN_MODEL | — |