ComfyUI Node
Qwen2.5-VL Inference (Image+Prompt→Text)
A ComfyUI node in Qwen2.5-VL with 5 inputs and 1 output.
Qwen2.5-VL Inference (Image+Prompt→Text)
- image
- STRING
◄promptCan you describe the image?►
◄max_new_tokens500►
◄model_pathhelenai/Qwen2.5-VL-7B-Instruct-ov-int4►
◄deviceCPU►
CategoryQwen2.5-VL
Inputs (5)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | — | |
| prompt | STRING | Can you describe the image? | — |
| max_new_tokens | INT | 5001–512 | — |
| model_path | STRING | helenai/Qwen2.5-VL-7B-Instruct-ov-int4 | — |
| device | COMBO | CPU | 2 options: CPU, GPU |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| STRING | STRING | — |