Nodes/ComfyUI-Qwen2.5-VL-7B-OPENVINO/Qwen2_5_VL_ImageToTextpose
ComfyUI Node

Qwen2_5_VL_ImageToTextpose

A ComfyUI node in Qwen2.5-VL with 7 inputs and 2 outputs.

By blackmeat1225·Created 4 months ago·Updated 4 months ago· 2
Qwen2_5_VL_ImageToTextpose
  • image1
  • image2
  • raw_description
  • cleaned_description
max_new_tokens2048
max_description_length1002
model_pathhelenai/Qwen2.5-VL-7B-Instruct-ov-int4
deviceCPU
styleNone
CategoryQwen2.5-VL

Inputs (7)

NameTypeDefaultDescription
image1IMAGE
max_new_tokensINT20481–2048
max_description_lengthINT100250–2048
model_pathSTRINGhelenai/Qwen2.5-VL-7B-Instruct-ov-int4
deviceCOMBOCPU2 options: CPU, GPU
styleCOMBONone7 options: Standing, sitting, walking, t_pose, running, squatting, +1
image2optIMAGE

Outputs (2)

NameTypeDescription
raw_descriptionSTRING
cleaned_descriptionSTRING