ComfyUI Node: Qwen2-VL Model

Authored by gokayfem

Created

Updated

576 stars

Run Qwen2-VL Model without installing ComfyUI

This node already runs on ComfyICU. Open it in the browser, hit run, and you're billed for GPU seconds — not for setup, and not while you're idle.

Category

VLM Nodes/Qwen2-VL

Inputs

image IMAGE
text_input STRING
model_name
  • Qwen2-VL-2B
  • Qwen2-VL-7B
  • Qwen2-VL-72B
  • Qwen2-VL-2B-AWQ
  • Qwen2-VL-2B-GPTQ-Int4
  • Qwen2-VL-2B-GPTQ-Int8
  • Qwen2-VL-7B-AWQ
  • Qwen2-VL-7B-GPTQ-Int4
  • Qwen2-VL-7B-GPTQ-Int8
  • Qwen2-VL-72B-AWQ
  • Qwen2-VL-72B-GPTQ-Int4
  • Qwen2-VL-72B-GPTQ-Int8
memory_mode
  • Balanced (8-bit)
  • Maximum Savings (4-bit)
  • CPU Offload
  • Default
max_new_tokens INT
temperature FLOAT
top_p FLOAT
video_frames IMAGE
fps FLOAT

Outputs

STRING

Extension: VLM_nodes

Custom Nodes for Vision Language Models (VLM) , Large Language Models (LLM), Image Captioning, Automatic Prompt Generation, Creative and Consistent Prompt Suggestion, Keyword Extraction

Authored by gokayfem

Looking for a different node?

Run Qwen2-VL Model without installing ComfyUI

This node already runs on ComfyICU. Open it in the browser, hit run, and you're billed for GPU seconds — not for setup, and not while you're idle.

Learn more