Nodes/ComfyUI-Qwen2.5-VL-7B-OPENVINO/Qwen2.5-VL Inference (Image+Prompt→Text)
ComfyUI Node

Qwen2.5-VL Inference (Image+Prompt→Text)

A ComfyUI node in Qwen2.5-VL with 5 inputs and 1 output.

By blackmeat1225·Created 4 months ago·Updated 4 months ago· 2
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)

NameTypeDefaultDescription
imageIMAGE
promptSTRINGCan you describe the image?
max_new_tokensINT5001–512
model_pathSTRINGhelenai/Qwen2.5-VL-7B-Instruct-ov-int4
deviceCOMBOCPU2 options: CPU, GPU

Outputs (1)

NameTypeDescription
STRINGSTRING