Nodes/ComfyUI-QwenVL/QwenVL TryOn
ComfyUI Node

QwenVL TryOn

A ComfyUI node in 🧠aistudynow/QwenVL with 19 inputs and 1 output.

By aistudynow·Created 10 months ago·Updated 4 months ago· 15
QwenVL TryOn
  • image_person
  • image_top
  • image_bottom
  • RESPONSE
â—„model_nameQwen3-VL-4B-Instructâ–º
â—„quantization8-bit (Balanced)â–º
â—„person_descriptionDescribe short info of the person in this imageâ–º
â—„top_descriptionDescribe the top outfit in this imageâ–º
â—„bottom_descriptionDescribe the bottom outfit in this imageâ–º
â—„max_tokens1024â–º
â—„temperature0.6â–º
â—„top_p0.90â–º
â—„num_beams1â–º
â—„repetition_penalty1.20â–º
â—„frame_count16â–º
â—„deviceautoâ–º
â—„use_torch_compilefalseâ–º
â—„keep_model_loadedtrueâ–º
â—„seed1â–º
â—„attention_modeautoâ–º
Category🧠aistudynow/QwenVL

Inputs (19)

NameTypeDefaultDescription
model_nameCOMBOQwen3-VL-4B-Instruct18 options: Qwen3-VL-2B-Instruct, Qwen3-VL-2B-Thinking, Qwen3-VL-2B-Instruct-FP8, Qwen3-VL-2B-Thinking-FP8, Qwen3-VL-4B-Instruct, Qwen3-VL-4B-Thinking, +12
quantizationCOMBO8-bit (Balanced)3 options: 4-bit (VRAM-friendly), 8-bit (Balanced), None (FP16)
person_descriptionSTRINGDescribe short info of the person in this image—
top_descriptionSTRINGDescribe the top outfit in this image—
bottom_descriptionSTRINGDescribe the bottom outfit in this image—
max_tokensINT102464–2048—
temperatureFLOAT0.60.1–1—
top_pFLOAT0.900–1—
num_beamsINT11–10—
repetition_penaltyFLOAT1.200–2—
frame_countINT161–64—
deviceCOMBOauto4 options: auto, cuda, cpu, mps
use_torch_compileBOOLEANfalse—
keep_model_loadedBOOLEANtrue—
seedINT11–18446744073709550000—
attention_modeCOMBOauto4 options: auto, sage, flash_attention_2, sdpa
image_personoptIMAGE—
image_topoptIMAGE—
image_bottomoptIMAGE—

Outputs (1)

NameTypeDescription
RESPONSESTRING—